diff --git a/llama2_13b_peft/elementary_math_qa/README.md b/llama2_13b_peft/elementary_math_qa/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31094d3ac5dcc9673826dea8a490931cfb19cfa1
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/README.md
@@ -0,0 +1,138 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: elementary_math_qa_no_sys
+ results: []
+---
+
+
+
+# elementary_math_qa_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the elementary_math_qa_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0705
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- total_train_batch_size: 24
+- total_eval_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3438 | 0.05 | 50 | 0.3364 |
+| 0.3021 | 0.09 | 100 | 0.3056 |
+| 0.2676 | 0.14 | 150 | 0.2710 |
+| 0.2679 | 0.18 | 200 | 0.2582 |
+| 0.2448 | 0.23 | 250 | 0.2475 |
+| 0.2355 | 0.28 | 300 | 0.2372 |
+| 0.2335 | 0.32 | 350 | 0.2282 |
+| 0.2226 | 0.37 | 400 | 0.2227 |
+| 0.2098 | 0.42 | 450 | 0.2109 |
+| 0.1839 | 0.46 | 500 | 0.2048 |
+| 0.2008 | 0.51 | 550 | 0.1992 |
+| 0.1945 | 0.55 | 600 | 0.2019 |
+| 0.1891 | 0.6 | 650 | 0.1859 |
+| 0.2015 | 0.65 | 700 | 0.1966 |
+| 0.174 | 0.69 | 750 | 0.1801 |
+| 0.1565 | 0.74 | 800 | 0.1762 |
+| 0.1825 | 0.79 | 850 | 0.1717 |
+| 0.1651 | 0.83 | 900 | 0.1682 |
+| 0.1598 | 0.88 | 950 | 0.1598 |
+| 0.1502 | 0.92 | 1000 | 0.1558 |
+| 0.1599 | 0.97 | 1050 | 0.1465 |
+| 0.0977 | 1.02 | 1100 | 0.1520 |
+| 0.1166 | 1.06 | 1150 | 0.1403 |
+| 0.0943 | 1.11 | 1200 | 0.1387 |
+| 0.1007 | 1.16 | 1250 | 0.1311 |
+| 0.1035 | 1.2 | 1300 | 0.1325 |
+| 0.0842 | 1.25 | 1350 | 0.1309 |
+| 0.1114 | 1.29 | 1400 | 0.1225 |
+| 0.1047 | 1.34 | 1450 | 0.1184 |
+| 0.0807 | 1.39 | 1500 | 0.1136 |
+| 0.0846 | 1.43 | 1550 | 0.1200 |
+| 0.0737 | 1.48 | 1600 | 0.1145 |
+| 0.0844 | 1.52 | 1650 | 0.1037 |
+| 0.0809 | 1.57 | 1700 | 0.0940 |
+| 0.0718 | 1.62 | 1750 | 0.0931 |
+| 0.0687 | 1.66 | 1800 | 0.0930 |
+| 0.0629 | 1.71 | 1850 | 0.0969 |
+| 0.0852 | 1.76 | 1900 | 0.0872 |
+| 0.0622 | 1.8 | 1950 | 0.0849 |
+| 0.0653 | 1.85 | 2000 | 0.0831 |
+| 0.0507 | 1.89 | 2050 | 0.0829 |
+| 0.0518 | 1.94 | 2100 | 0.0785 |
+| 0.0566 | 1.99 | 2150 | 0.0750 |
+| 0.0193 | 2.03 | 2200 | 0.0837 |
+| 0.0233 | 2.08 | 2250 | 0.0766 |
+| 0.0249 | 2.13 | 2300 | 0.0829 |
+| 0.0217 | 2.17 | 2350 | 0.0824 |
+| 0.0233 | 2.22 | 2400 | 0.0735 |
+| 0.0192 | 2.26 | 2450 | 0.0767 |
+| 0.0207 | 2.31 | 2500 | 0.0794 |
+| 0.0232 | 2.36 | 2550 | 0.0843 |
+| 0.0295 | 2.4 | 2600 | 0.0800 |
+| 0.0185 | 2.45 | 2650 | 0.0777 |
+| 0.0178 | 2.5 | 2700 | 0.0767 |
+| 0.0245 | 2.54 | 2750 | 0.0717 |
+| 0.0226 | 2.59 | 2800 | 0.0774 |
+| 0.0222 | 2.63 | 2850 | 0.0671 |
+| 0.0194 | 2.68 | 2900 | 0.0666 |
+| 0.0162 | 2.73 | 2950 | 0.0713 |
+| 0.0184 | 2.77 | 3000 | 0.0740 |
+| 0.0227 | 2.82 | 3050 | 0.0675 |
+| 0.0176 | 2.87 | 3100 | 0.0701 |
+| 0.034 | 2.91 | 3150 | 0.0675 |
+| 0.0148 | 2.96 | 3200 | 0.0688 |
+| 0.014 | 3.0 | 3250 | 0.0673 |
+| 0.0178 | 3.05 | 3300 | 0.0719 |
+| 0.0059 | 3.1 | 3350 | 0.0734 |
+| 0.0069 | 3.14 | 3400 | 0.0764 |
+| 0.0074 | 3.19 | 3450 | 0.0818 |
+| 0.009 | 3.23 | 3500 | 0.0705 |
+| 0.0048 | 3.28 | 3550 | 0.0735 |
+| 0.005 | 3.33 | 3600 | 0.0705 |
+| 0.0073 | 3.37 | 3650 | 0.0724 |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2
\ No newline at end of file
diff --git a/llama2_13b_peft/elementary_math_qa/adapter_config.json b/llama2_13b_peft/elementary_math_qa/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2f5609002295c6446ebd937056a049b162dca872
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/adapter_config.json
@@ -0,0 +1,33 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "o_proj",
+ "gate_proj",
+ "q_proj",
+ "k_proj",
+ "v_proj",
+ "down_proj",
+ "up_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/elementary_math_qa/adapter_model.safetensors b/llama2_13b_peft/elementary_math_qa/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..82de8981abc72a38554fc071f32b1f82bfc99dbf
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95310146c699416787331f0c95920283e55a47a6355cc22383f3c069b9929aa
+size 125248064
diff --git a/llama2_13b_peft/elementary_math_qa/all_results.json b/llama2_13b_peft/elementary_math_qa/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..3f07f91234446caea6b30c41a866b3c2d637f4c7
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/all_results.json
@@ -0,0 +1,11 @@
+{
+ "epoch": 3.37,
+ "eval_loss": 0.07047122716903687,
+ "eval_runtime": 36.1294,
+ "eval_samples_per_second": 126.766,
+ "eval_steps_per_second": 5.287,
+ "train_loss": 0.10634728888738645,
+ "train_runtime": 4965.2136,
+ "train_samples_per_second": 52.266,
+ "train_steps_per_second": 2.179
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/elementary_math_qa/eval_results.json b/llama2_13b_peft/elementary_math_qa/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..194dcb76c51caf46ba36c2119ced39d44b4bc1d5
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/eval_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 3.37,
+ "eval_loss": 0.07047122716903687,
+ "eval_runtime": 36.1294,
+ "eval_samples_per_second": 126.766,
+ "eval_steps_per_second": 5.287
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/elementary_math_qa/special_tokens_map.json b/llama2_13b_peft/elementary_math_qa/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/llama2_13b_peft/elementary_math_qa/tokenizer.model b/llama2_13b_peft/elementary_math_qa/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/llama2_13b_peft/elementary_math_qa/tokenizer_config.json b/llama2_13b_peft/elementary_math_qa/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a40266f39e5b5fed14de34710d35eb9e98d6bdad
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false
+}
diff --git a/llama2_13b_peft/elementary_math_qa/train_results.json b/llama2_13b_peft/elementary_math_qa/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..2ffe37d3ef36aea041a0c53c59972d72aa8ecc80
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/train_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 3.37,
+ "train_loss": 0.10634728888738645,
+ "train_runtime": 4965.2136,
+ "train_samples_per_second": 52.266,
+ "train_steps_per_second": 2.179
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/elementary_math_qa/trainer_log.jsonl b/llama2_13b_peft/elementary_math_qa/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..aa9dfdcec464d7b7773f0df3909f0a2a81f9cebe
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/trainer_log.jsonl
@@ -0,0 +1,440 @@
+{"current_steps": 10, "total_steps": 10820, "loss": 3.4664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.01, "percentage": 0.09, "elapsed_time": "0:00:07", "remaining_time": "2:16:37"}
+{"current_steps": 20, "total_steps": 10820, "loss": 1.2417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 0.02, "percentage": 0.18, "elapsed_time": "0:00:14", "remaining_time": "2:10:47"}
+{"current_steps": 30, "total_steps": 10820, "loss": 0.3726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999978846027431e-05, "epoch": 0.03, "percentage": 0.28, "elapsed_time": "0:00:20", "remaining_time": "2:05:01"}
+{"current_steps": 40, "total_steps": 10820, "loss": 0.3371, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999915384288722e-05, "epoch": 0.04, "percentage": 0.37, "elapsed_time": "0:00:27", "remaining_time": "2:01:46"}
+{"current_steps": 50, "total_steps": 10820, "loss": 0.3438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999809615320856e-05, "epoch": 0.05, "percentage": 0.46, "elapsed_time": "0:00:33", "remaining_time": "1:59:04"}
+{"current_steps": 50, "total_steps": 10820, "loss": null, "eval_loss": 0.3363588750362396, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.05, "percentage": 0.46, "elapsed_time": "0:00:33", "remaining_time": "1:59:04"}
+{"current_steps": 60, "total_steps": 10820, "loss": 0.3451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999661540018812e-05, "epoch": 0.06, "percentage": 0.55, "elapsed_time": "0:01:15", "remaining_time": "3:45:47"}
+{"current_steps": 70, "total_steps": 10820, "loss": 0.3227, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999471159635539e-05, "epoch": 0.06, "percentage": 0.65, "elapsed_time": "0:01:22", "remaining_time": "3:29:59"}
+{"current_steps": 80, "total_steps": 10820, "loss": 0.3368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999238475781957e-05, "epoch": 0.07, "percentage": 0.74, "elapsed_time": "0:01:28", "remaining_time": "3:17:56"}
+{"current_steps": 90, "total_steps": 10820, "loss": 0.3171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998963490426943e-05, "epoch": 0.08, "percentage": 0.83, "elapsed_time": "0:01:34", "remaining_time": "3:08:11"}
+{"current_steps": 100, "total_steps": 10820, "loss": 0.3021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998646205897309e-05, "epoch": 0.09, "percentage": 0.92, "elapsed_time": "0:01:40", "remaining_time": "3:00:26"}
+{"current_steps": 100, "total_steps": 10820, "loss": null, "eval_loss": 0.30562111735343933, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.09, "percentage": 0.92, "elapsed_time": "0:01:40", "remaining_time": "3:00:26"}
+{"current_steps": 110, "total_steps": 10820, "loss": 0.3053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998286624877786e-05, "epoch": 0.1, "percentage": 1.02, "elapsed_time": "0:02:22", "remaining_time": "3:51:54"}
+{"current_steps": 120, "total_steps": 10820, "loss": 0.2789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997884750411005e-05, "epoch": 0.11, "percentage": 1.11, "elapsed_time": "0:02:29", "remaining_time": "3:41:42"}
+{"current_steps": 130, "total_steps": 10820, "loss": 0.2854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997440585897455e-05, "epoch": 0.12, "percentage": 1.2, "elapsed_time": "0:02:35", "remaining_time": "3:33:14"}
+{"current_steps": 140, "total_steps": 10820, "loss": 0.2841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99695413509548e-05, "epoch": 0.13, "percentage": 1.29, "elapsed_time": "0:02:41", "remaining_time": "3:25:52"}
+{"current_steps": 150, "total_steps": 10820, "loss": 0.2676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996425402121223e-05, "epoch": 0.14, "percentage": 1.39, "elapsed_time": "0:02:48", "remaining_time": "3:19:23"}
+{"current_steps": 150, "total_steps": 10820, "loss": null, "eval_loss": 0.27099743485450745, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.14, "percentage": 1.39, "elapsed_time": "0:02:48", "remaining_time": "3:19:23"}
+{"current_steps": 160, "total_steps": 10820, "loss": 0.2841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995854391448606e-05, "epoch": 0.15, "percentage": 1.48, "elapsed_time": "0:03:30", "remaining_time": "3:53:43"}
+{"current_steps": 170, "total_steps": 10820, "loss": 0.2624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99524110790929e-05, "epoch": 0.16, "percentage": 1.57, "elapsed_time": "0:03:36", "remaining_time": "3:46:12"}
+{"current_steps": 180, "total_steps": 10820, "loss": 0.2398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994585556692624e-05, "epoch": 0.17, "percentage": 1.66, "elapsed_time": "0:03:42", "remaining_time": "3:39:18"}
+{"current_steps": 190, "total_steps": 10820, "loss": 0.2488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.993887743345614e-05, "epoch": 0.18, "percentage": 1.76, "elapsed_time": "0:03:48", "remaining_time": "3:33:26"}
+{"current_steps": 200, "total_steps": 10820, "loss": 0.2679, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99314767377287e-05, "epoch": 0.18, "percentage": 1.85, "elapsed_time": "0:03:55", "remaining_time": "3:28:17"}
+{"current_steps": 200, "total_steps": 10820, "loss": null, "eval_loss": 0.25818708539009094, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.18, "percentage": 1.85, "elapsed_time": "0:03:55", "remaining_time": "3:28:17"}
+{"current_steps": 210, "total_steps": 10820, "loss": 0.2595, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992365354236557e-05, "epoch": 0.19, "percentage": 1.94, "elapsed_time": "0:04:38", "remaining_time": "3:54:12"}
+{"current_steps": 220, "total_steps": 10820, "loss": 0.2625, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.991540791356342e-05, "epoch": 0.2, "percentage": 2.03, "elapsed_time": "0:04:44", "remaining_time": "3:48:47"}
+{"current_steps": 230, "total_steps": 10820, "loss": 0.2491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990673992109335e-05, "epoch": 0.21, "percentage": 2.13, "elapsed_time": "0:04:51", "remaining_time": "3:43:32"}
+{"current_steps": 240, "total_steps": 10820, "loss": 0.2272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.989764963830037e-05, "epoch": 0.22, "percentage": 2.22, "elapsed_time": "0:04:57", "remaining_time": "3:38:40"}
+{"current_steps": 250, "total_steps": 10820, "loss": 0.2448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.988813714210272e-05, "epoch": 0.23, "percentage": 2.31, "elapsed_time": "0:05:03", "remaining_time": "3:34:00"}
+{"current_steps": 250, "total_steps": 10820, "loss": null, "eval_loss": 0.2475069910287857, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.23, "percentage": 2.31, "elapsed_time": "0:05:03", "remaining_time": "3:34:00"}
+{"current_steps": 260, "total_steps": 10820, "loss": 0.2425, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987820251299122e-05, "epoch": 0.24, "percentage": 2.4, "elapsed_time": "0:05:46", "remaining_time": "3:54:20"}
+{"current_steps": 270, "total_steps": 10820, "loss": 0.2502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.986784583502862e-05, "epoch": 0.25, "percentage": 2.5, "elapsed_time": "0:05:52", "remaining_time": "3:49:28"}
+{"current_steps": 280, "total_steps": 10820, "loss": 0.2599, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.985706719584888e-05, "epoch": 0.26, "percentage": 2.59, "elapsed_time": "0:05:58", "remaining_time": "3:45:05"}
+{"current_steps": 290, "total_steps": 10820, "loss": 0.244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98458666866564e-05, "epoch": 0.27, "percentage": 2.68, "elapsed_time": "0:06:05", "remaining_time": "3:40:59"}
+{"current_steps": 300, "total_steps": 10820, "loss": 0.2355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.983424440222531e-05, "epoch": 0.28, "percentage": 2.77, "elapsed_time": "0:06:11", "remaining_time": "3:36:51"}
+{"current_steps": 300, "total_steps": 10820, "loss": null, "eval_loss": 0.23719529807567596, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.28, "percentage": 2.77, "elapsed_time": "0:06:11", "remaining_time": "3:36:51"}
+{"current_steps": 310, "total_steps": 10820, "loss": 0.2368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.982220044089859e-05, "epoch": 0.29, "percentage": 2.87, "elapsed_time": "0:06:53", "remaining_time": "3:53:50"}
+{"current_steps": 320, "total_steps": 10820, "loss": 0.2509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.980973490458728e-05, "epoch": 0.3, "percentage": 2.96, "elapsed_time": "0:06:59", "remaining_time": "3:49:38"}
+{"current_steps": 330, "total_steps": 10820, "loss": 0.2539, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.979684789876965e-05, "epoch": 0.3, "percentage": 3.05, "elapsed_time": "0:07:06", "remaining_time": "3:45:54"}
+{"current_steps": 340, "total_steps": 10820, "loss": 0.2308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.978353953249022e-05, "epoch": 0.31, "percentage": 3.14, "elapsed_time": "0:07:12", "remaining_time": "3:42:26"}
+{"current_steps": 350, "total_steps": 10820, "loss": 0.2335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.976980991835894e-05, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:07:19", "remaining_time": "3:38:58"}
+{"current_steps": 350, "total_steps": 10820, "loss": null, "eval_loss": 0.22817698121070862, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:07:19", "remaining_time": "3:38:58"}
+{"current_steps": 360, "total_steps": 10820, "loss": 0.2046, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.975565917255016e-05, "epoch": 0.33, "percentage": 3.33, "elapsed_time": "0:08:01", "remaining_time": "3:53:21"}
+{"current_steps": 370, "total_steps": 10820, "loss": 0.2174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.974108741480165e-05, "epoch": 0.34, "percentage": 3.42, "elapsed_time": "0:08:08", "remaining_time": "3:50:01"}
+{"current_steps": 380, "total_steps": 10820, "loss": 0.2346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.972609476841367e-05, "epoch": 0.35, "percentage": 3.51, "elapsed_time": "0:08:14", "remaining_time": "3:46:29"}
+{"current_steps": 390, "total_steps": 10820, "loss": 0.2291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.971068136024781e-05, "epoch": 0.36, "percentage": 3.6, "elapsed_time": "0:08:20", "remaining_time": "3:43:14"}
+{"current_steps": 400, "total_steps": 10820, "loss": 0.2226, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.9694847320726e-05, "epoch": 0.37, "percentage": 3.7, "elapsed_time": "0:08:27", "remaining_time": "3:40:16"}
+{"current_steps": 400, "total_steps": 10820, "loss": null, "eval_loss": 0.22269846498966217, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.37, "percentage": 3.7, "elapsed_time": "0:08:27", "remaining_time": "3:40:16"}
+{"current_steps": 410, "total_steps": 10820, "loss": 0.2235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.967859278382938e-05, "epoch": 0.38, "percentage": 3.79, "elapsed_time": "0:09:09", "remaining_time": "3:52:39"}
+{"current_steps": 420, "total_steps": 10820, "loss": 0.2308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.966191788709716e-05, "epoch": 0.39, "percentage": 3.88, "elapsed_time": "0:09:16", "remaining_time": "3:49:29"}
+{"current_steps": 430, "total_steps": 10820, "loss": 0.193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.964482277162546e-05, "epoch": 0.4, "percentage": 3.97, "elapsed_time": "0:09:22", "remaining_time": "3:46:29"}
+{"current_steps": 440, "total_steps": 10820, "loss": 0.2144, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.962730758206611e-05, "epoch": 0.41, "percentage": 4.07, "elapsed_time": "0:09:28", "remaining_time": "3:43:33"}
+{"current_steps": 450, "total_steps": 10820, "loss": 0.2098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.960937246662546e-05, "epoch": 0.42, "percentage": 4.16, "elapsed_time": "0:09:34", "remaining_time": "3:40:44"}
+{"current_steps": 450, "total_steps": 10820, "loss": null, "eval_loss": 0.2109217643737793, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42, "percentage": 4.16, "elapsed_time": "0:09:34", "remaining_time": "3:40:44"}
+{"current_steps": 460, "total_steps": 10820, "loss": 0.2355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.959101757706308e-05, "epoch": 0.43, "percentage": 4.25, "elapsed_time": "0:10:17", "remaining_time": "3:51:42"}
+{"current_steps": 470, "total_steps": 10820, "loss": 0.2108, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.957224306869053e-05, "epoch": 0.43, "percentage": 4.34, "elapsed_time": "0:10:23", "remaining_time": "3:48:52"}
+{"current_steps": 480, "total_steps": 10820, "loss": 0.2295, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.955304910036993e-05, "epoch": 0.44, "percentage": 4.44, "elapsed_time": "0:10:29", "remaining_time": "3:46:10"}
+{"current_steps": 490, "total_steps": 10820, "loss": 0.2129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.95334358345128e-05, "epoch": 0.45, "percentage": 4.53, "elapsed_time": "0:10:36", "remaining_time": "3:43:28"}
+{"current_steps": 500, "total_steps": 10820, "loss": 0.1839, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.951340343707852e-05, "epoch": 0.46, "percentage": 4.62, "elapsed_time": "0:10:42", "remaining_time": "3:41:00"}
+{"current_steps": 500, "total_steps": 10820, "loss": null, "eval_loss": 0.20476657152175903, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.46, "percentage": 4.62, "elapsed_time": "0:10:42", "remaining_time": "3:41:00"}
+{"current_steps": 510, "total_steps": 10820, "loss": 0.1975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.949295207757299e-05, "epoch": 0.47, "percentage": 4.71, "elapsed_time": "0:11:25", "remaining_time": "3:50:57"}
+{"current_steps": 520, "total_steps": 10820, "loss": 0.2055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.947208192904722e-05, "epoch": 0.48, "percentage": 4.81, "elapsed_time": "0:11:31", "remaining_time": "3:48:13"}
+{"current_steps": 530, "total_steps": 10820, "loss": 0.242, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.945079316809585e-05, "epoch": 0.49, "percentage": 4.9, "elapsed_time": "0:11:37", "remaining_time": "3:45:36"}
+{"current_steps": 540, "total_steps": 10820, "loss": 0.1907, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.942908597485558e-05, "epoch": 0.5, "percentage": 4.99, "elapsed_time": "0:11:43", "remaining_time": "3:43:13"}
+{"current_steps": 550, "total_steps": 10820, "loss": 0.2008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.94069605330038e-05, "epoch": 0.51, "percentage": 5.08, "elapsed_time": "0:11:49", "remaining_time": "3:40:50"}
+{"current_steps": 550, "total_steps": 10820, "loss": null, "eval_loss": 0.19918882846832275, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.51, "percentage": 5.08, "elapsed_time": "0:11:49", "remaining_time": "3:40:50"}
+{"current_steps": 560, "total_steps": 10820, "loss": 0.189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.938441702975689e-05, "epoch": 0.52, "percentage": 5.18, "elapsed_time": "0:12:31", "remaining_time": "3:49:34"}
+{"current_steps": 570, "total_steps": 10820, "loss": 0.2045, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.936145565586871e-05, "epoch": 0.53, "percentage": 5.27, "elapsed_time": "0:12:38", "remaining_time": "3:47:16"}
+{"current_steps": 580, "total_steps": 10820, "loss": 0.196, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.933807660562898e-05, "epoch": 0.54, "percentage": 5.36, "elapsed_time": "0:12:45", "remaining_time": "3:45:07"}
+{"current_steps": 590, "total_steps": 10820, "loss": 0.2054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.931428007686158e-05, "epoch": 0.55, "percentage": 5.45, "elapsed_time": "0:12:51", "remaining_time": "3:42:58"}
+{"current_steps": 600, "total_steps": 10820, "loss": 0.1945, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.929006627092299e-05, "epoch": 0.55, "percentage": 5.55, "elapsed_time": "0:12:57", "remaining_time": "3:40:46"}
+{"current_steps": 600, "total_steps": 10820, "loss": null, "eval_loss": 0.20194485783576965, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.55, "percentage": 5.55, "elapsed_time": "0:12:57", "remaining_time": "3:40:46"}
+{"current_steps": 610, "total_steps": 10820, "loss": 0.2278, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.926543539270048e-05, "epoch": 0.56, "percentage": 5.64, "elapsed_time": "0:13:40", "remaining_time": "3:48:52"}
+{"current_steps": 620, "total_steps": 10820, "loss": 0.1894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.924038765061042e-05, "epoch": 0.57, "percentage": 5.73, "elapsed_time": "0:13:46", "remaining_time": "3:46:44"}
+{"current_steps": 630, "total_steps": 10820, "loss": 0.1868, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.921492325659649e-05, "epoch": 0.58, "percentage": 5.82, "elapsed_time": "0:13:53", "remaining_time": "3:44:35"}
+{"current_steps": 640, "total_steps": 10820, "loss": 0.1927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.918904242612795e-05, "epoch": 0.59, "percentage": 5.91, "elapsed_time": "0:13:59", "remaining_time": "3:42:31"}
+{"current_steps": 650, "total_steps": 10820, "loss": 0.1891, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.916274537819775e-05, "epoch": 0.6, "percentage": 6.01, "elapsed_time": "0:14:05", "remaining_time": "3:40:29"}
+{"current_steps": 650, "total_steps": 10820, "loss": null, "eval_loss": 0.1859094649553299, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6, "percentage": 6.01, "elapsed_time": "0:14:05", "remaining_time": "3:40:29"}
+{"current_steps": 660, "total_steps": 10820, "loss": 0.1772, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.913603233532067e-05, "epoch": 0.61, "percentage": 6.1, "elapsed_time": "0:14:47", "remaining_time": "3:47:49"}
+{"current_steps": 670, "total_steps": 10820, "loss": 0.1787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.910890352353153e-05, "epoch": 0.62, "percentage": 6.19, "elapsed_time": "0:14:54", "remaining_time": "3:45:48"}
+{"current_steps": 680, "total_steps": 10820, "loss": 0.192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.908135917238321e-05, "epoch": 0.63, "percentage": 6.28, "elapsed_time": "0:15:00", "remaining_time": "3:43:50"}
+{"current_steps": 690, "total_steps": 10820, "loss": 0.1784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.905339951494463e-05, "epoch": 0.64, "percentage": 6.38, "elapsed_time": "0:15:06", "remaining_time": "3:41:55"}
+{"current_steps": 700, "total_steps": 10820, "loss": 0.2015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.902502478779896e-05, "epoch": 0.65, "percentage": 6.47, "elapsed_time": "0:15:13", "remaining_time": "3:40:04"}
+{"current_steps": 700, "total_steps": 10820, "loss": null, "eval_loss": 0.19662824273109436, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.65, "percentage": 6.47, "elapsed_time": "0:15:13", "remaining_time": "3:40:04"}
+{"current_steps": 710, "total_steps": 10820, "loss": 0.188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.899623523104149e-05, "epoch": 0.66, "percentage": 6.56, "elapsed_time": "0:15:55", "remaining_time": "3:46:48"}
+{"current_steps": 720, "total_steps": 10820, "loss": 0.172, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.896703108827759e-05, "epoch": 0.67, "percentage": 6.65, "elapsed_time": "0:16:01", "remaining_time": "3:44:52"}
+{"current_steps": 730, "total_steps": 10820, "loss": 0.1933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.893741260662071e-05, "epoch": 0.67, "percentage": 6.75, "elapsed_time": "0:16:08", "remaining_time": "3:43:01"}
+{"current_steps": 740, "total_steps": 10820, "loss": 0.1942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.890738003669029e-05, "epoch": 0.68, "percentage": 6.84, "elapsed_time": "0:16:14", "remaining_time": "3:41:15"}
+{"current_steps": 750, "total_steps": 10820, "loss": 0.174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.887693363260958e-05, "epoch": 0.69, "percentage": 6.93, "elapsed_time": "0:16:21", "remaining_time": "3:39:33"}
+{"current_steps": 750, "total_steps": 10820, "loss": null, "eval_loss": 0.18010230362415314, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.69, "percentage": 6.93, "elapsed_time": "0:16:21", "remaining_time": "3:39:33"}
+{"current_steps": 760, "total_steps": 10820, "loss": 0.1806, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.884607365200356e-05, "epoch": 0.7, "percentage": 7.02, "elapsed_time": "0:17:03", "remaining_time": "3:45:49"}
+{"current_steps": 770, "total_steps": 10820, "loss": 0.1784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.881480035599667e-05, "epoch": 0.71, "percentage": 7.12, "elapsed_time": "0:17:09", "remaining_time": "3:44:02"}
+{"current_steps": 780, "total_steps": 10820, "loss": 0.1707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.878311400921072e-05, "epoch": 0.72, "percentage": 7.21, "elapsed_time": "0:17:16", "remaining_time": "3:42:20"}
+{"current_steps": 790, "total_steps": 10820, "loss": 0.1732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.875101487976253e-05, "epoch": 0.73, "percentage": 7.3, "elapsed_time": "0:17:23", "remaining_time": "3:40:43"}
+{"current_steps": 800, "total_steps": 10820, "loss": 0.1565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.871850323926177e-05, "epoch": 0.74, "percentage": 7.39, "elapsed_time": "0:17:29", "remaining_time": "3:39:05"}
+{"current_steps": 800, "total_steps": 10820, "loss": null, "eval_loss": 0.17616184055805206, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.74, "percentage": 7.39, "elapsed_time": "0:17:29", "remaining_time": "3:39:05"}
+{"current_steps": 810, "total_steps": 10820, "loss": 0.1855, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.868557936280855e-05, "epoch": 0.75, "percentage": 7.49, "elapsed_time": "0:18:11", "remaining_time": "3:44:51"}
+{"current_steps": 820, "total_steps": 10820, "loss": 0.1763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.865224352899119e-05, "epoch": 0.76, "percentage": 7.58, "elapsed_time": "0:18:17", "remaining_time": "3:43:09"}
+{"current_steps": 830, "total_steps": 10820, "loss": 0.149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.861849601988383e-05, "epoch": 0.77, "percentage": 7.67, "elapsed_time": "0:18:24", "remaining_time": "3:41:33"}
+{"current_steps": 840, "total_steps": 10820, "loss": 0.1773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.858433712104403e-05, "epoch": 0.78, "percentage": 7.76, "elapsed_time": "0:18:31", "remaining_time": "3:40:02"}
+{"current_steps": 850, "total_steps": 10820, "loss": 0.1825, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.854976712151031e-05, "epoch": 0.79, "percentage": 7.86, "elapsed_time": "0:18:37", "remaining_time": "3:38:23"}
+{"current_steps": 850, "total_steps": 10820, "loss": null, "eval_loss": 0.1716548502445221, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.79, "percentage": 7.86, "elapsed_time": "0:18:37", "remaining_time": "3:38:23"}
+{"current_steps": 860, "total_steps": 10820, "loss": 0.1608, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.851478631379982e-05, "epoch": 0.79, "percentage": 7.95, "elapsed_time": "0:19:19", "remaining_time": "3:43:52"}
+{"current_steps": 870, "total_steps": 10820, "loss": 0.1723, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.84793949939058e-05, "epoch": 0.8, "percentage": 8.04, "elapsed_time": "0:19:26", "remaining_time": "3:42:18"}
+{"current_steps": 880, "total_steps": 10820, "loss": 0.1566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.844359346129503e-05, "epoch": 0.81, "percentage": 8.13, "elapsed_time": "0:19:32", "remaining_time": "3:40:46"}
+{"current_steps": 890, "total_steps": 10820, "loss": 0.1769, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.84073820189054e-05, "epoch": 0.82, "percentage": 8.23, "elapsed_time": "0:19:39", "remaining_time": "3:39:14"}
+{"current_steps": 900, "total_steps": 10820, "loss": 0.1651, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.837076097314319e-05, "epoch": 0.83, "percentage": 8.32, "elapsed_time": "0:19:45", "remaining_time": "3:37:44"}
+{"current_steps": 900, "total_steps": 10820, "loss": null, "eval_loss": 0.16817261278629303, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.83, "percentage": 8.32, "elapsed_time": "0:19:45", "remaining_time": "3:37:44"}
+{"current_steps": 910, "total_steps": 10820, "loss": 0.1472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.83337306338807e-05, "epoch": 0.84, "percentage": 8.41, "elapsed_time": "0:20:27", "remaining_time": "3:42:51"}
+{"current_steps": 920, "total_steps": 10820, "loss": 0.1683, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.829629131445342e-05, "epoch": 0.85, "percentage": 8.5, "elapsed_time": "0:20:34", "remaining_time": "3:41:20"}
+{"current_steps": 930, "total_steps": 10820, "loss": 0.151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.825844333165748e-05, "epoch": 0.86, "percentage": 8.6, "elapsed_time": "0:20:40", "remaining_time": "3:39:46"}
+{"current_steps": 940, "total_steps": 10820, "loss": 0.1641, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.822018700574695e-05, "epoch": 0.87, "percentage": 8.69, "elapsed_time": "0:20:46", "remaining_time": "3:38:17"}
+{"current_steps": 950, "total_steps": 10820, "loss": 0.1598, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.818152266043114e-05, "epoch": 0.88, "percentage": 8.78, "elapsed_time": "0:20:52", "remaining_time": "3:36:54"}
+{"current_steps": 950, "total_steps": 10820, "loss": null, "eval_loss": 0.15981163084506989, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.88, "percentage": 8.78, "elapsed_time": "0:20:52", "remaining_time": "3:36:54"}
+{"current_steps": 960, "total_steps": 10820, "loss": 0.156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.814245062287189e-05, "epoch": 0.89, "percentage": 8.87, "elapsed_time": "0:21:35", "remaining_time": "3:41:44"}
+{"current_steps": 970, "total_steps": 10820, "loss": 0.1646, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.810297122368067e-05, "epoch": 0.9, "percentage": 8.96, "elapsed_time": "0:21:41", "remaining_time": "3:40:16"}
+{"current_steps": 980, "total_steps": 10820, "loss": 0.1727, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.806308479691595e-05, "epoch": 0.91, "percentage": 9.06, "elapsed_time": "0:21:47", "remaining_time": "3:38:51"}
+{"current_steps": 990, "total_steps": 10820, "loss": 0.1566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.802279168008029e-05, "epoch": 0.91, "percentage": 9.15, "elapsed_time": "0:21:53", "remaining_time": "3:37:24"}
+{"current_steps": 1000, "total_steps": 10820, "loss": 0.1502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.798209221411747e-05, "epoch": 0.92, "percentage": 9.24, "elapsed_time": "0:22:00", "remaining_time": "3:36:04"}
+{"current_steps": 1000, "total_steps": 10820, "loss": null, "eval_loss": 0.15576273202896118, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.92, "percentage": 9.24, "elapsed_time": "0:22:00", "remaining_time": "3:36:04"}
+{"current_steps": 1010, "total_steps": 10820, "loss": 0.1634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.794098674340965e-05, "epoch": 0.93, "percentage": 9.33, "elapsed_time": "0:22:43", "remaining_time": "3:40:48"}
+{"current_steps": 1020, "total_steps": 10820, "loss": 0.1438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.789947561577445e-05, "epoch": 0.94, "percentage": 9.43, "elapsed_time": "0:22:49", "remaining_time": "3:39:21"}
+{"current_steps": 1030, "total_steps": 10820, "loss": 0.1297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.785755918246194e-05, "epoch": 0.95, "percentage": 9.52, "elapsed_time": "0:22:56", "remaining_time": "3:38:00"}
+{"current_steps": 1040, "total_steps": 10820, "loss": 0.1525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.781523779815179e-05, "epoch": 0.96, "percentage": 9.61, "elapsed_time": "0:23:02", "remaining_time": "3:36:38"}
+{"current_steps": 1050, "total_steps": 10820, "loss": 0.1599, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.777251182095011e-05, "epoch": 0.97, "percentage": 9.7, "elapsed_time": "0:23:08", "remaining_time": "3:35:21"}
+{"current_steps": 1050, "total_steps": 10820, "loss": null, "eval_loss": 0.1465296447277069, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.97, "percentage": 9.7, "elapsed_time": "0:23:08", "remaining_time": "3:35:21"}
+{"current_steps": 1060, "total_steps": 10820, "loss": 0.1601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.77293816123866e-05, "epoch": 0.98, "percentage": 9.8, "elapsed_time": "0:23:51", "remaining_time": "3:39:37"}
+{"current_steps": 1070, "total_steps": 10820, "loss": 0.159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.768584753741134e-05, "epoch": 0.99, "percentage": 9.89, "elapsed_time": "0:23:57", "remaining_time": "3:38:15"}
+{"current_steps": 1080, "total_steps": 10820, "loss": 0.1444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.764190996439181e-05, "epoch": 1.0, "percentage": 9.98, "elapsed_time": "0:24:03", "remaining_time": "3:36:56"}
+{"current_steps": 1090, "total_steps": 10820, "loss": 0.1205, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.759756926510965e-05, "epoch": 1.01, "percentage": 10.07, "elapsed_time": "0:24:09", "remaining_time": "3:35:39"}
+{"current_steps": 1100, "total_steps": 10820, "loss": 0.0977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.755282581475769e-05, "epoch": 1.02, "percentage": 10.17, "elapsed_time": "0:24:15", "remaining_time": "3:34:23"}
+{"current_steps": 1100, "total_steps": 10820, "loss": null, "eval_loss": 0.15202057361602783, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.02, "percentage": 10.17, "elapsed_time": "0:24:15", "remaining_time": "3:34:23"}
+{"current_steps": 1110, "total_steps": 10820, "loss": 0.1106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.750767999193656e-05, "epoch": 1.03, "percentage": 10.26, "elapsed_time": "0:24:58", "remaining_time": "3:38:27"}
+{"current_steps": 1120, "total_steps": 10820, "loss": 0.0907, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.74621321786517e-05, "epoch": 1.04, "percentage": 10.35, "elapsed_time": "0:25:04", "remaining_time": "3:37:11"}
+{"current_steps": 1130, "total_steps": 10820, "loss": 0.0832, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.741618276030997e-05, "epoch": 1.04, "percentage": 10.44, "elapsed_time": "0:25:10", "remaining_time": "3:35:56"}
+{"current_steps": 1140, "total_steps": 10820, "loss": 0.1197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.736983212571646e-05, "epoch": 1.05, "percentage": 10.54, "elapsed_time": "0:25:17", "remaining_time": "3:34:44"}
+{"current_steps": 1150, "total_steps": 10820, "loss": 0.1166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.732308066707122e-05, "epoch": 1.06, "percentage": 10.63, "elapsed_time": "0:25:23", "remaining_time": "3:33:28"}
+{"current_steps": 1150, "total_steps": 10820, "loss": null, "eval_loss": 0.1403137743473053, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.06, "percentage": 10.63, "elapsed_time": "0:25:23", "remaining_time": "3:33:28"}
+{"current_steps": 1160, "total_steps": 10820, "loss": 0.1138, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.727592877996585e-05, "epoch": 1.07, "percentage": 10.72, "elapsed_time": "0:26:06", "remaining_time": "3:37:21"}
+{"current_steps": 1170, "total_steps": 10820, "loss": 0.1159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.722837686338025e-05, "epoch": 1.08, "percentage": 10.81, "elapsed_time": "0:26:12", "remaining_time": "3:36:08"}
+{"current_steps": 1180, "total_steps": 10820, "loss": 0.0983, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.718042531967918e-05, "epoch": 1.09, "percentage": 10.91, "elapsed_time": "0:26:18", "remaining_time": "3:34:55"}
+{"current_steps": 1190, "total_steps": 10820, "loss": 0.0913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.713207455460894e-05, "epoch": 1.1, "percentage": 11.0, "elapsed_time": "0:26:24", "remaining_time": "3:33:44"}
+{"current_steps": 1200, "total_steps": 10820, "loss": 0.0943, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.708332497729378e-05, "epoch": 1.11, "percentage": 11.09, "elapsed_time": "0:26:31", "remaining_time": "3:32:35"}
+{"current_steps": 1200, "total_steps": 10820, "loss": null, "eval_loss": 0.13866838812828064, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.11, "percentage": 11.09, "elapsed_time": "0:26:31", "remaining_time": "3:32:35"}
+{"current_steps": 1210, "total_steps": 10820, "loss": 0.0999, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.70341770002326e-05, "epoch": 1.12, "percentage": 11.18, "elapsed_time": "0:27:13", "remaining_time": "3:36:15"}
+{"current_steps": 1220, "total_steps": 10820, "loss": 0.0914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.698463103929542e-05, "epoch": 1.13, "percentage": 11.28, "elapsed_time": "0:27:20", "remaining_time": "3:35:07"}
+{"current_steps": 1230, "total_steps": 10820, "loss": 0.0938, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.693468751371977e-05, "epoch": 1.14, "percentage": 11.37, "elapsed_time": "0:27:26", "remaining_time": "3:33:59"}
+{"current_steps": 1240, "total_steps": 10820, "loss": 0.1101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.688434684610726e-05, "epoch": 1.15, "percentage": 11.46, "elapsed_time": "0:27:32", "remaining_time": "3:32:49"}
+{"current_steps": 1250, "total_steps": 10820, "loss": 0.1007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.683360946241989e-05, "epoch": 1.16, "percentage": 11.55, "elapsed_time": "0:27:39", "remaining_time": "3:31:42"}
+{"current_steps": 1250, "total_steps": 10820, "loss": null, "eval_loss": 0.13109833002090454, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.16, "percentage": 11.55, "elapsed_time": "0:27:39", "remaining_time": "3:31:42"}
+{"current_steps": 1260, "total_steps": 10820, "loss": 0.1057, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.678247579197657e-05, "epoch": 1.16, "percentage": 11.65, "elapsed_time": "0:28:21", "remaining_time": "3:35:09"}
+{"current_steps": 1270, "total_steps": 10820, "loss": 0.0865, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.673094626744942e-05, "epoch": 1.17, "percentage": 11.74, "elapsed_time": "0:28:27", "remaining_time": "3:34:02"}
+{"current_steps": 1280, "total_steps": 10820, "loss": 0.1077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.667902132486009e-05, "epoch": 1.18, "percentage": 11.83, "elapsed_time": "0:28:34", "remaining_time": "3:32:57"}
+{"current_steps": 1290, "total_steps": 10820, "loss": 0.0923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.662670140357611e-05, "epoch": 1.19, "percentage": 11.92, "elapsed_time": "0:28:40", "remaining_time": "3:31:52"}
+{"current_steps": 1300, "total_steps": 10820, "loss": 0.1035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.657398694630712e-05, "epoch": 1.2, "percentage": 12.01, "elapsed_time": "0:28:47", "remaining_time": "3:30:49"}
+{"current_steps": 1300, "total_steps": 10820, "loss": null, "eval_loss": 0.13247531652450562, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2, "percentage": 12.01, "elapsed_time": "0:28:47", "remaining_time": "3:30:49"}
+{"current_steps": 1310, "total_steps": 10820, "loss": 0.0803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.652087839910124e-05, "epoch": 1.21, "percentage": 12.11, "elapsed_time": "0:29:30", "remaining_time": "3:34:11"}
+{"current_steps": 1320, "total_steps": 10820, "loss": 0.0814, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.646737621134112e-05, "epoch": 1.22, "percentage": 12.2, "elapsed_time": "0:29:36", "remaining_time": "3:33:05"}
+{"current_steps": 1330, "total_steps": 10820, "loss": 0.0976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.641348083574034e-05, "epoch": 1.23, "percentage": 12.29, "elapsed_time": "0:29:42", "remaining_time": "3:32:01"}
+{"current_steps": 1340, "total_steps": 10820, "loss": 0.1047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.635919272833938e-05, "epoch": 1.24, "percentage": 12.38, "elapsed_time": "0:29:49", "remaining_time": "3:30:58"}
+{"current_steps": 1350, "total_steps": 10820, "loss": 0.0842, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.63045123485019e-05, "epoch": 1.25, "percentage": 12.48, "elapsed_time": "0:29:55", "remaining_time": "3:29:55"}
+{"current_steps": 1350, "total_steps": 10820, "loss": null, "eval_loss": 0.13089965283870697, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.25, "percentage": 12.48, "elapsed_time": "0:29:55", "remaining_time": "3:29:55"}
+{"current_steps": 1360, "total_steps": 10820, "loss": 0.0631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.62494401589108e-05, "epoch": 1.26, "percentage": 12.57, "elapsed_time": "0:30:38", "remaining_time": "3:33:07"}
+{"current_steps": 1370, "total_steps": 10820, "loss": 0.0967, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.619397662556435e-05, "epoch": 1.27, "percentage": 12.66, "elapsed_time": "0:30:44", "remaining_time": "3:32:04"}
+{"current_steps": 1380, "total_steps": 10820, "loss": 0.0727, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.613812221777212e-05, "epoch": 1.28, "percentage": 12.75, "elapsed_time": "0:30:51", "remaining_time": "3:31:02"}
+{"current_steps": 1390, "total_steps": 10820, "loss": 0.0832, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.60818774081512e-05, "epoch": 1.28, "percentage": 12.85, "elapsed_time": "0:30:57", "remaining_time": "3:29:59"}
+{"current_steps": 1400, "total_steps": 10820, "loss": 0.1114, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.602524267262203e-05, "epoch": 1.29, "percentage": 12.94, "elapsed_time": "0:31:03", "remaining_time": "3:28:56"}
+{"current_steps": 1400, "total_steps": 10820, "loss": null, "eval_loss": 0.12248954176902771, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.29, "percentage": 12.94, "elapsed_time": "0:31:03", "remaining_time": "3:28:56"}
+{"current_steps": 1410, "total_steps": 10820, "loss": 0.0997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.596821849040447e-05, "epoch": 1.3, "percentage": 13.03, "elapsed_time": "0:31:45", "remaining_time": "3:31:57"}
+{"current_steps": 1420, "total_steps": 10820, "loss": 0.0917, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.591080534401371e-05, "epoch": 1.31, "percentage": 13.12, "elapsed_time": "0:31:52", "remaining_time": "3:30:57"}
+{"current_steps": 1430, "total_steps": 10820, "loss": 0.1039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.58530037192562e-05, "epoch": 1.32, "percentage": 13.22, "elapsed_time": "0:31:58", "remaining_time": "3:29:57"}
+{"current_steps": 1440, "total_steps": 10820, "loss": 0.0957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.579481410522556e-05, "epoch": 1.33, "percentage": 13.31, "elapsed_time": "0:32:04", "remaining_time": "3:28:58"}
+{"current_steps": 1450, "total_steps": 10820, "loss": 0.1047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.573623699429836e-05, "epoch": 1.34, "percentage": 13.4, "elapsed_time": "0:32:11", "remaining_time": "3:27:59"}
+{"current_steps": 1450, "total_steps": 10820, "loss": null, "eval_loss": 0.11836496740579605, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.34, "percentage": 13.4, "elapsed_time": "0:32:11", "remaining_time": "3:27:59"}
+{"current_steps": 1460, "total_steps": 10820, "loss": 0.0957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.567727288213005e-05, "epoch": 1.35, "percentage": 13.49, "elapsed_time": "0:32:53", "remaining_time": "3:30:53"}
+{"current_steps": 1470, "total_steps": 10820, "loss": 0.0973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.561792226765072e-05, "epoch": 1.36, "percentage": 13.59, "elapsed_time": "0:33:00", "remaining_time": "3:29:54"}
+{"current_steps": 1480, "total_steps": 10820, "loss": 0.0887, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.555818565306085e-05, "epoch": 1.37, "percentage": 13.68, "elapsed_time": "0:33:06", "remaining_time": "3:28:57"}
+{"current_steps": 1490, "total_steps": 10820, "loss": 0.094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.549806354382717e-05, "epoch": 1.38, "percentage": 13.77, "elapsed_time": "0:33:12", "remaining_time": "3:27:57"}
+{"current_steps": 1500, "total_steps": 10820, "loss": 0.0807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.543755644867822e-05, "epoch": 1.39, "percentage": 13.86, "elapsed_time": "0:33:18", "remaining_time": "3:26:59"}
+{"current_steps": 1500, "total_steps": 10820, "loss": null, "eval_loss": 0.11355672031641006, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.39, "percentage": 13.86, "elapsed_time": "0:33:18", "remaining_time": "3:26:59"}
+{"current_steps": 1510, "total_steps": 10820, "loss": 0.0829, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.537666487960019e-05, "epoch": 1.4, "percentage": 13.96, "elapsed_time": "0:34:01", "remaining_time": "3:29:49"}
+{"current_steps": 1520, "total_steps": 10820, "loss": 0.0749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.53153893518325e-05, "epoch": 1.4, "percentage": 14.05, "elapsed_time": "0:34:08", "remaining_time": "3:28:51"}
+{"current_steps": 1530, "total_steps": 10820, "loss": 0.0647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.52537303838635e-05, "epoch": 1.41, "percentage": 14.14, "elapsed_time": "0:34:14", "remaining_time": "3:27:54"}
+{"current_steps": 1540, "total_steps": 10820, "loss": 0.0713, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.519168849742604e-05, "epoch": 1.42, "percentage": 14.23, "elapsed_time": "0:34:21", "remaining_time": "3:26:59"}
+{"current_steps": 1550, "total_steps": 10820, "loss": 0.0846, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.512926421749304e-05, "epoch": 1.43, "percentage": 14.33, "elapsed_time": "0:34:27", "remaining_time": "3:26:03"}
+{"current_steps": 1550, "total_steps": 10820, "loss": null, "eval_loss": 0.12000197172164917, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.43, "percentage": 14.33, "elapsed_time": "0:34:27", "remaining_time": "3:26:03"}
+{"current_steps": 1560, "total_steps": 10820, "loss": 0.0724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.506645807227311e-05, "epoch": 1.44, "percentage": 14.42, "elapsed_time": "0:35:09", "remaining_time": "3:28:42"}
+{"current_steps": 1570, "total_steps": 10820, "loss": 0.0851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.500327059320606e-05, "epoch": 1.45, "percentage": 14.51, "elapsed_time": "0:35:15", "remaining_time": "3:27:45"}
+{"current_steps": 1580, "total_steps": 10820, "loss": 0.0984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.493970231495835e-05, "epoch": 1.46, "percentage": 14.6, "elapsed_time": "0:35:22", "remaining_time": "3:26:50"}
+{"current_steps": 1590, "total_steps": 10820, "loss": 0.0584, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.487575377541864e-05, "epoch": 1.47, "percentage": 14.7, "elapsed_time": "0:35:28", "remaining_time": "3:25:55"}
+{"current_steps": 1600, "total_steps": 10820, "loss": 0.0737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.481142551569318e-05, "epoch": 1.48, "percentage": 14.79, "elapsed_time": "0:35:34", "remaining_time": "3:25:01"}
+{"current_steps": 1600, "total_steps": 10820, "loss": null, "eval_loss": 0.11450409889221191, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.48, "percentage": 14.79, "elapsed_time": "0:35:34", "remaining_time": "3:25:01"}
+{"current_steps": 1610, "total_steps": 10820, "loss": 0.0962, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.474671808010126e-05, "epoch": 1.49, "percentage": 14.88, "elapsed_time": "0:36:17", "remaining_time": "3:27:33"}
+{"current_steps": 1620, "total_steps": 10820, "loss": 0.0739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.468163201617062e-05, "epoch": 1.5, "percentage": 14.97, "elapsed_time": "0:36:23", "remaining_time": "3:26:39"}
+{"current_steps": 1630, "total_steps": 10820, "loss": 0.089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.461616787463278e-05, "epoch": 1.51, "percentage": 15.06, "elapsed_time": "0:36:29", "remaining_time": "3:25:46"}
+{"current_steps": 1640, "total_steps": 10820, "loss": 0.0914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.45503262094184e-05, "epoch": 1.52, "percentage": 15.16, "elapsed_time": "0:36:36", "remaining_time": "3:24:53"}
+{"current_steps": 1650, "total_steps": 10820, "loss": 0.0844, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.44841075776526e-05, "epoch": 1.52, "percentage": 15.25, "elapsed_time": "0:36:42", "remaining_time": "3:24:03"}
+{"current_steps": 1650, "total_steps": 10820, "loss": null, "eval_loss": 0.1037188321352005, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.52, "percentage": 15.25, "elapsed_time": "0:36:42", "remaining_time": "3:24:03"}
+{"current_steps": 1660, "total_steps": 10820, "loss": 0.0968, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.441751253965021e-05, "epoch": 1.53, "percentage": 15.34, "elapsed_time": "0:37:25", "remaining_time": "3:26:31"}
+{"current_steps": 1670, "total_steps": 10820, "loss": 0.097, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.435054165891109e-05, "epoch": 1.54, "percentage": 15.43, "elapsed_time": "0:37:32", "remaining_time": "3:25:39"}
+{"current_steps": 1680, "total_steps": 10820, "loss": 0.0699, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.42831955021153e-05, "epoch": 1.55, "percentage": 15.53, "elapsed_time": "0:37:38", "remaining_time": "3:24:49"}
+{"current_steps": 1690, "total_steps": 10820, "loss": 0.0781, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.421547463911835e-05, "epoch": 1.56, "percentage": 15.62, "elapsed_time": "0:37:45", "remaining_time": "3:23:56"}
+{"current_steps": 1700, "total_steps": 10820, "loss": 0.0809, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.414737964294636e-05, "epoch": 1.57, "percentage": 15.71, "elapsed_time": "0:37:51", "remaining_time": "3:23:04"}
+{"current_steps": 1700, "total_steps": 10820, "loss": null, "eval_loss": 0.09402556717395782, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.57, "percentage": 15.71, "elapsed_time": "0:37:51", "remaining_time": "3:23:04"}
+{"current_steps": 1710, "total_steps": 10820, "loss": 0.0897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.407891108979117e-05, "epoch": 1.58, "percentage": 15.8, "elapsed_time": "0:38:33", "remaining_time": "3:25:27"}
+{"current_steps": 1720, "total_steps": 10820, "loss": 0.0629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.401006955900556e-05, "epoch": 1.59, "percentage": 15.9, "elapsed_time": "0:38:39", "remaining_time": "3:24:33"}
+{"current_steps": 1730, "total_steps": 10820, "loss": 0.0671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.394085563309827e-05, "epoch": 1.6, "percentage": 15.99, "elapsed_time": "0:38:46", "remaining_time": "3:23:42"}
+{"current_steps": 1740, "total_steps": 10820, "loss": 0.0736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.38712698977291e-05, "epoch": 1.61, "percentage": 16.08, "elapsed_time": "0:38:52", "remaining_time": "3:22:52"}
+{"current_steps": 1750, "total_steps": 10820, "loss": 0.0718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.380131294170393e-05, "epoch": 1.62, "percentage": 16.17, "elapsed_time": "0:38:58", "remaining_time": "3:22:02"}
+{"current_steps": 1750, "total_steps": 10820, "loss": null, "eval_loss": 0.093104287981987, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.62, "percentage": 16.17, "elapsed_time": "0:38:58", "remaining_time": "3:22:02"}
+{"current_steps": 1760, "total_steps": 10820, "loss": 0.0644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.373098535696979e-05, "epoch": 1.63, "percentage": 16.27, "elapsed_time": "0:39:41", "remaining_time": "3:24:19"}
+{"current_steps": 1770, "total_steps": 10820, "loss": 0.0798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.36602877386098e-05, "epoch": 1.64, "percentage": 16.36, "elapsed_time": "0:39:47", "remaining_time": "3:23:28"}
+{"current_steps": 1780, "total_steps": 10820, "loss": 0.0717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.358922068483812e-05, "epoch": 1.65, "percentage": 16.45, "elapsed_time": "0:39:54", "remaining_time": "3:22:39"}
+{"current_steps": 1790, "total_steps": 10820, "loss": 0.1072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.351778479699499e-05, "epoch": 1.65, "percentage": 16.54, "elapsed_time": "0:40:00", "remaining_time": "3:21:50"}
+{"current_steps": 1800, "total_steps": 10820, "loss": 0.0687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.344598067954152e-05, "epoch": 1.66, "percentage": 16.64, "elapsed_time": "0:40:06", "remaining_time": "3:20:59"}
+{"current_steps": 1800, "total_steps": 10820, "loss": null, "eval_loss": 0.09301283955574036, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.66, "percentage": 16.64, "elapsed_time": "0:40:06", "remaining_time": "3:20:59"}
+{"current_steps": 1810, "total_steps": 10820, "loss": 0.0611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.337380894005463e-05, "epoch": 1.67, "percentage": 16.73, "elapsed_time": "0:40:48", "remaining_time": "3:23:10"}
+{"current_steps": 1820, "total_steps": 10820, "loss": 0.0827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.330127018922194e-05, "epoch": 1.68, "percentage": 16.82, "elapsed_time": "0:40:55", "remaining_time": "3:22:20"}
+{"current_steps": 1830, "total_steps": 10820, "loss": 0.0693, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.322836504083654e-05, "epoch": 1.69, "percentage": 16.91, "elapsed_time": "0:41:01", "remaining_time": "3:21:31"}
+{"current_steps": 1840, "total_steps": 10820, "loss": 0.058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.315509411179182e-05, "epoch": 1.7, "percentage": 17.01, "elapsed_time": "0:41:08", "remaining_time": "3:20:45"}
+{"current_steps": 1850, "total_steps": 10820, "loss": 0.0629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.308145802207629e-05, "epoch": 1.71, "percentage": 17.1, "elapsed_time": "0:41:14", "remaining_time": "3:19:57"}
+{"current_steps": 1850, "total_steps": 10820, "loss": null, "eval_loss": 0.09685970097780228, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.71, "percentage": 17.1, "elapsed_time": "0:41:14", "remaining_time": "3:19:57"}
+{"current_steps": 1860, "total_steps": 10820, "loss": 0.0717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.300745739476829e-05, "epoch": 1.72, "percentage": 17.19, "elapsed_time": "0:41:57", "remaining_time": "3:22:06"}
+{"current_steps": 1870, "total_steps": 10820, "loss": 0.0679, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.293309285603067e-05, "epoch": 1.73, "percentage": 17.28, "elapsed_time": "0:42:03", "remaining_time": "3:21:17"}
+{"current_steps": 1880, "total_steps": 10820, "loss": 0.07, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.285836503510562e-05, "epoch": 1.74, "percentage": 17.38, "elapsed_time": "0:42:10", "remaining_time": "3:20:31"}
+{"current_steps": 1890, "total_steps": 10820, "loss": 0.0824, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.278327456430926e-05, "epoch": 1.75, "percentage": 17.47, "elapsed_time": "0:42:16", "remaining_time": "3:19:43"}
+{"current_steps": 1900, "total_steps": 10820, "loss": 0.0852, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.270782207902629e-05, "epoch": 1.76, "percentage": 17.56, "elapsed_time": "0:42:22", "remaining_time": "3:18:57"}
+{"current_steps": 1900, "total_steps": 10820, "loss": null, "eval_loss": 0.0872357115149498, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.76, "percentage": 17.56, "elapsed_time": "0:42:22", "remaining_time": "3:18:57"}
+{"current_steps": 1910, "total_steps": 10820, "loss": 0.0749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.263200821770461e-05, "epoch": 1.77, "percentage": 17.65, "elapsed_time": "0:43:05", "remaining_time": "3:21:00"}
+{"current_steps": 1920, "total_steps": 10820, "loss": 0.058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.255583362184999e-05, "epoch": 1.77, "percentage": 17.74, "elapsed_time": "0:43:11", "remaining_time": "3:20:12"}
+{"current_steps": 1930, "total_steps": 10820, "loss": 0.07, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.247929893602054e-05, "epoch": 1.78, "percentage": 17.84, "elapsed_time": "0:43:17", "remaining_time": "3:19:25"}
+{"current_steps": 1940, "total_steps": 10820, "loss": 0.0638, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.24024048078213e-05, "epoch": 1.79, "percentage": 17.93, "elapsed_time": "0:43:24", "remaining_time": "3:18:40"}
+{"current_steps": 1950, "total_steps": 10820, "loss": 0.0622, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.23251518878988e-05, "epoch": 1.8, "percentage": 18.02, "elapsed_time": "0:43:30", "remaining_time": "3:17:55"}
+{"current_steps": 1950, "total_steps": 10820, "loss": null, "eval_loss": 0.08488291501998901, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8, "percentage": 18.02, "elapsed_time": "0:43:30", "remaining_time": "3:17:55"}
+{"current_steps": 1960, "total_steps": 10820, "loss": 0.0592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.224754082993552e-05, "epoch": 1.81, "percentage": 18.11, "elapsed_time": "0:44:13", "remaining_time": "3:19:54"}
+{"current_steps": 1970, "total_steps": 10820, "loss": 0.0709, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.21695722906443e-05, "epoch": 1.82, "percentage": 18.21, "elapsed_time": "0:44:19", "remaining_time": "3:19:08"}
+{"current_steps": 1980, "total_steps": 10820, "loss": 0.0657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.209124692976287e-05, "epoch": 1.83, "percentage": 18.3, "elapsed_time": "0:44:25", "remaining_time": "3:18:22"}
+{"current_steps": 1990, "total_steps": 10820, "loss": 0.0644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.201256541004829e-05, "epoch": 1.84, "percentage": 18.39, "elapsed_time": "0:44:32", "remaining_time": "3:17:37"}
+{"current_steps": 2000, "total_steps": 10820, "loss": 0.0653, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.193352839727121e-05, "epoch": 1.85, "percentage": 18.48, "elapsed_time": "0:44:38", "remaining_time": "3:16:53"}
+{"current_steps": 2000, "total_steps": 10820, "loss": null, "eval_loss": 0.08305433392524719, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.85, "percentage": 18.48, "elapsed_time": "0:44:38", "remaining_time": "3:16:53"}
+{"current_steps": 2010, "total_steps": 10820, "loss": 0.0752, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.185413656021036e-05, "epoch": 1.86, "percentage": 18.58, "elapsed_time": "0:45:21", "remaining_time": "3:18:49"}
+{"current_steps": 2020, "total_steps": 10820, "loss": 0.0502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.177439057064683e-05, "epoch": 1.87, "percentage": 18.67, "elapsed_time": "0:45:28", "remaining_time": "3:18:04"}
+{"current_steps": 2030, "total_steps": 10820, "loss": 0.0717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.169429110335841e-05, "epoch": 1.88, "percentage": 18.76, "elapsed_time": "0:45:34", "remaining_time": "3:17:19"}
+{"current_steps": 2040, "total_steps": 10820, "loss": 0.0577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.16138388361139e-05, "epoch": 1.89, "percentage": 18.85, "elapsed_time": "0:45:40", "remaining_time": "3:16:36"}
+{"current_steps": 2050, "total_steps": 10820, "loss": 0.0507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.153303444966727e-05, "epoch": 1.89, "percentage": 18.95, "elapsed_time": "0:45:47", "remaining_time": "3:15:52"}
+{"current_steps": 2050, "total_steps": 10820, "loss": null, "eval_loss": 0.08292171359062195, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.89, "percentage": 18.95, "elapsed_time": "0:45:47", "remaining_time": "3:15:52"}
+{"current_steps": 2060, "total_steps": 10820, "loss": 0.0632, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.145187862775209e-05, "epoch": 1.9, "percentage": 19.04, "elapsed_time": "0:46:29", "remaining_time": "3:17:43"}
+{"current_steps": 2070, "total_steps": 10820, "loss": 0.0637, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.137037205707552e-05, "epoch": 1.91, "percentage": 19.13, "elapsed_time": "0:46:35", "remaining_time": "3:16:57"}
+{"current_steps": 2080, "total_steps": 10820, "loss": 0.0462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.128851542731271e-05, "epoch": 1.92, "percentage": 19.22, "elapsed_time": "0:46:41", "remaining_time": "3:16:13"}
+{"current_steps": 2090, "total_steps": 10820, "loss": 0.0665, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.120630943110077e-05, "epoch": 1.93, "percentage": 19.32, "elapsed_time": "0:46:48", "remaining_time": "3:15:29"}
+{"current_steps": 2100, "total_steps": 10820, "loss": 0.0518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.112375476403312e-05, "epoch": 1.94, "percentage": 19.41, "elapsed_time": "0:46:54", "remaining_time": "3:14:47"}
+{"current_steps": 2100, "total_steps": 10820, "loss": null, "eval_loss": 0.07847684621810913, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.94, "percentage": 19.41, "elapsed_time": "0:46:54", "remaining_time": "3:14:47"}
+{"current_steps": 2110, "total_steps": 10820, "loss": 0.0523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.104085212465336e-05, "epoch": 1.95, "percentage": 19.5, "elapsed_time": "0:47:37", "remaining_time": "3:16:34"}
+{"current_steps": 2120, "total_steps": 10820, "loss": 0.0485, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.09576022144496e-05, "epoch": 1.96, "percentage": 19.59, "elapsed_time": "0:47:43", "remaining_time": "3:15:51"}
+{"current_steps": 2130, "total_steps": 10820, "loss": 0.0613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.087400573784833e-05, "epoch": 1.97, "percentage": 19.69, "elapsed_time": "0:47:50", "remaining_time": "3:15:09"}
+{"current_steps": 2140, "total_steps": 10820, "loss": 0.0652, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.079006340220862e-05, "epoch": 1.98, "percentage": 19.78, "elapsed_time": "0:47:56", "remaining_time": "3:14:27"}
+{"current_steps": 2150, "total_steps": 10820, "loss": 0.0566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.070577591781597e-05, "epoch": 1.99, "percentage": 19.87, "elapsed_time": "0:48:02", "remaining_time": "3:13:44"}
+{"current_steps": 2150, "total_steps": 10820, "loss": null, "eval_loss": 0.07502878457307816, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.99, "percentage": 19.87, "elapsed_time": "0:48:02", "remaining_time": "3:13:44"}
+{"current_steps": 2160, "total_steps": 10820, "loss": 0.0703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.062114399787647e-05, "epoch": 2.0, "percentage": 19.96, "elapsed_time": "0:48:45", "remaining_time": "3:15:28"}
+{"current_steps": 2170, "total_steps": 10820, "loss": 0.0327, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.053616835851062e-05, "epoch": 2.01, "percentage": 20.06, "elapsed_time": "0:48:51", "remaining_time": "3:14:45"}
+{"current_steps": 2180, "total_steps": 10820, "loss": 0.0259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.045084971874738e-05, "epoch": 2.01, "percentage": 20.15, "elapsed_time": "0:48:57", "remaining_time": "3:14:01"}
+{"current_steps": 2190, "total_steps": 10820, "loss": 0.0167, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.0365188800518e-05, "epoch": 2.02, "percentage": 20.24, "elapsed_time": "0:49:03", "remaining_time": "3:13:21"}
+{"current_steps": 2200, "total_steps": 10820, "loss": 0.0193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.027918632864997e-05, "epoch": 2.03, "percentage": 20.33, "elapsed_time": "0:49:10", "remaining_time": "3:12:39"}
+{"current_steps": 2200, "total_steps": 10820, "loss": null, "eval_loss": 0.08374720066785812, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.03, "percentage": 20.33, "elapsed_time": "0:49:10", "remaining_time": "3:12:39"}
+{"current_steps": 2210, "total_steps": 10820, "loss": 0.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.019284303086087e-05, "epoch": 2.04, "percentage": 20.43, "elapsed_time": "0:49:52", "remaining_time": "3:14:18"}
+{"current_steps": 2220, "total_steps": 10820, "loss": 0.0235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.01061596377522e-05, "epoch": 2.05, "percentage": 20.52, "elapsed_time": "0:49:59", "remaining_time": "3:13:38"}
+{"current_steps": 2230, "total_steps": 10820, "loss": 0.0177, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.00191368828032e-05, "epoch": 2.06, "percentage": 20.61, "elapsed_time": "0:50:05", "remaining_time": "3:12:57"}
+{"current_steps": 2240, "total_steps": 10820, "loss": 0.0274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.993177550236464e-05, "epoch": 2.07, "percentage": 20.7, "elapsed_time": "0:50:11", "remaining_time": "3:12:16"}
+{"current_steps": 2250, "total_steps": 10820, "loss": 0.0233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.984407623565267e-05, "epoch": 2.08, "percentage": 20.79, "elapsed_time": "0:50:17", "remaining_time": "3:11:34"}
+{"current_steps": 2250, "total_steps": 10820, "loss": null, "eval_loss": 0.07661169022321701, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.08, "percentage": 20.79, "elapsed_time": "0:50:17", "remaining_time": "3:11:34"}
+{"current_steps": 2260, "total_steps": 10820, "loss": 0.016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.97560398247424e-05, "epoch": 2.09, "percentage": 20.89, "elapsed_time": "0:51:00", "remaining_time": "3:13:11"}
+{"current_steps": 2270, "total_steps": 10820, "loss": 0.0123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.966766701456177e-05, "epoch": 2.1, "percentage": 20.98, "elapsed_time": "0:51:06", "remaining_time": "3:12:29"}
+{"current_steps": 2280, "total_steps": 10820, "loss": 0.0235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.957895855288517e-05, "epoch": 2.11, "percentage": 21.07, "elapsed_time": "0:51:13", "remaining_time": "3:11:50"}
+{"current_steps": 2290, "total_steps": 10820, "loss": 0.0209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.948991519032716e-05, "epoch": 2.12, "percentage": 21.16, "elapsed_time": "0:51:19", "remaining_time": "3:11:10"}
+{"current_steps": 2300, "total_steps": 10820, "loss": 0.0249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.940053768033609e-05, "epoch": 2.13, "percentage": 21.26, "elapsed_time": "0:51:25", "remaining_time": "3:10:30"}
+{"current_steps": 2300, "total_steps": 10820, "loss": null, "eval_loss": 0.08285840600728989, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.13, "percentage": 21.26, "elapsed_time": "0:51:25", "remaining_time": "3:10:30"}
+{"current_steps": 2310, "total_steps": 10820, "loss": 0.0164, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.931082677918771e-05, "epoch": 2.13, "percentage": 21.35, "elapsed_time": "0:52:08", "remaining_time": "3:12:04"}
+{"current_steps": 2320, "total_steps": 10820, "loss": 0.0253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.922078324597879e-05, "epoch": 2.14, "percentage": 21.44, "elapsed_time": "0:52:14", "remaining_time": "3:11:22"}
+{"current_steps": 2330, "total_steps": 10820, "loss": 0.0266, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.91304078426207e-05, "epoch": 2.15, "percentage": 21.53, "elapsed_time": "0:52:20", "remaining_time": "3:10:43"}
+{"current_steps": 2340, "total_steps": 10820, "loss": 0.0191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.903970133383297e-05, "epoch": 2.16, "percentage": 21.63, "elapsed_time": "0:52:26", "remaining_time": "3:10:04"}
+{"current_steps": 2350, "total_steps": 10820, "loss": 0.0217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.894866448713679e-05, "epoch": 2.17, "percentage": 21.72, "elapsed_time": "0:52:33", "remaining_time": "3:09:25"}
+{"current_steps": 2350, "total_steps": 10820, "loss": null, "eval_loss": 0.0823688879609108, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.17, "percentage": 21.72, "elapsed_time": "0:52:33", "remaining_time": "3:09:25"}
+{"current_steps": 2360, "total_steps": 10820, "loss": 0.0408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.885729807284856e-05, "epoch": 2.18, "percentage": 21.81, "elapsed_time": "0:53:15", "remaining_time": "3:10:55"}
+{"current_steps": 2370, "total_steps": 10820, "loss": 0.0335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.87656028640733e-05, "epoch": 2.19, "percentage": 21.9, "elapsed_time": "0:53:21", "remaining_time": "3:10:15"}
+{"current_steps": 2380, "total_steps": 10820, "loss": 0.0189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.86735796366982e-05, "epoch": 2.2, "percentage": 22.0, "elapsed_time": "0:53:28", "remaining_time": "3:09:37"}
+{"current_steps": 2390, "total_steps": 10820, "loss": 0.0255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.858122916938601e-05, "epoch": 2.21, "percentage": 22.09, "elapsed_time": "0:53:34", "remaining_time": "3:08:58"}
+{"current_steps": 2400, "total_steps": 10820, "loss": 0.0233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.848855224356839e-05, "epoch": 2.22, "percentage": 22.18, "elapsed_time": "0:53:41", "remaining_time": "3:08:20"}
+{"current_steps": 2400, "total_steps": 10820, "loss": null, "eval_loss": 0.07353760302066803, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.22, "percentage": 22.18, "elapsed_time": "0:53:41", "remaining_time": "3:08:20"}
+{"current_steps": 2410, "total_steps": 10820, "loss": 0.0151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.839554964343943e-05, "epoch": 2.23, "percentage": 22.27, "elapsed_time": "0:54:23", "remaining_time": "3:09:48"}
+{"current_steps": 2420, "total_steps": 10820, "loss": 0.0178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.83022221559489e-05, "epoch": 2.24, "percentage": 22.37, "elapsed_time": "0:54:29", "remaining_time": "3:09:10"}
+{"current_steps": 2430, "total_steps": 10820, "loss": 0.0378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.820857057079565e-05, "epoch": 2.25, "percentage": 22.46, "elapsed_time": "0:54:36", "remaining_time": "3:08:33"}
+{"current_steps": 2440, "total_steps": 10820, "loss": 0.0273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.811459568042091e-05, "epoch": 2.26, "percentage": 22.55, "elapsed_time": "0:54:42", "remaining_time": "3:07:54"}
+{"current_steps": 2450, "total_steps": 10820, "loss": 0.0192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.802029828000156e-05, "epoch": 2.26, "percentage": 22.64, "elapsed_time": "0:54:49", "remaining_time": "3:07:17"}
+{"current_steps": 2450, "total_steps": 10820, "loss": null, "eval_loss": 0.07672559469938278, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.26, "percentage": 22.64, "elapsed_time": "0:54:49", "remaining_time": "3:07:17"}
+{"current_steps": 2460, "total_steps": 10820, "loss": 0.0218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.792567916744346e-05, "epoch": 2.27, "percentage": 22.74, "elapsed_time": "0:55:32", "remaining_time": "3:08:44"}
+{"current_steps": 2470, "total_steps": 10820, "loss": 0.025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.783073914337466e-05, "epoch": 2.28, "percentage": 22.83, "elapsed_time": "0:55:38", "remaining_time": "3:08:05"}
+{"current_steps": 2480, "total_steps": 10820, "loss": 0.0328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.773547901113862e-05, "epoch": 2.29, "percentage": 22.92, "elapsed_time": "0:55:44", "remaining_time": "3:07:27"}
+{"current_steps": 2490, "total_steps": 10820, "loss": 0.0135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.763989957678742e-05, "epoch": 2.3, "percentage": 23.01, "elapsed_time": "0:55:50", "remaining_time": "3:06:50"}
+{"current_steps": 2500, "total_steps": 10820, "loss": 0.0207, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.754400164907497e-05, "epoch": 2.31, "percentage": 23.11, "elapsed_time": "0:55:57", "remaining_time": "3:06:14"}
+{"current_steps": 2500, "total_steps": 10820, "loss": null, "eval_loss": 0.07941900193691254, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.31, "percentage": 23.11, "elapsed_time": "0:55:57", "remaining_time": "3:06:14"}
+{"current_steps": 2510, "total_steps": 10820, "loss": 0.0168, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.744778603945011e-05, "epoch": 2.32, "percentage": 23.2, "elapsed_time": "0:56:40", "remaining_time": "3:07:37"}
+{"current_steps": 2520, "total_steps": 10820, "loss": 0.0254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.73512535620498e-05, "epoch": 2.33, "percentage": 23.29, "elapsed_time": "0:56:46", "remaining_time": "3:07:00"}
+{"current_steps": 2530, "total_steps": 10820, "loss": 0.0244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.72544050336922e-05, "epoch": 2.34, "percentage": 23.38, "elapsed_time": "0:56:53", "remaining_time": "3:06:23"}
+{"current_steps": 2540, "total_steps": 10820, "loss": 0.0221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.715724127386972e-05, "epoch": 2.35, "percentage": 23.48, "elapsed_time": "0:56:59", "remaining_time": "3:05:47"}
+{"current_steps": 2550, "total_steps": 10820, "loss": 0.0232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.705976310474219e-05, "epoch": 2.36, "percentage": 23.57, "elapsed_time": "0:57:05", "remaining_time": "3:05:10"}
+{"current_steps": 2550, "total_steps": 10820, "loss": null, "eval_loss": 0.08428460359573364, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.36, "percentage": 23.57, "elapsed_time": "0:57:05", "remaining_time": "3:05:10"}
+{"current_steps": 2560, "total_steps": 10820, "loss": 0.0182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.69619713511298e-05, "epoch": 2.37, "percentage": 23.66, "elapsed_time": "0:57:48", "remaining_time": "3:06:30"}
+{"current_steps": 2570, "total_steps": 10820, "loss": 0.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.68638668405062e-05, "epoch": 2.38, "percentage": 23.75, "elapsed_time": "0:57:54", "remaining_time": "3:05:53"}
+{"current_steps": 2580, "total_steps": 10820, "loss": 0.0217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.676545040299145e-05, "epoch": 2.38, "percentage": 23.84, "elapsed_time": "0:58:00", "remaining_time": "3:05:15"}
+{"current_steps": 2590, "total_steps": 10820, "loss": 0.0178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.666672287134494e-05, "epoch": 2.39, "percentage": 23.94, "elapsed_time": "0:58:06", "remaining_time": "3:04:39"}
+{"current_steps": 2600, "total_steps": 10820, "loss": 0.0295, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.656768508095853e-05, "epoch": 2.4, "percentage": 24.03, "elapsed_time": "0:58:13", "remaining_time": "3:04:04"}
+{"current_steps": 2600, "total_steps": 10820, "loss": null, "eval_loss": 0.08000972867012024, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.4, "percentage": 24.03, "elapsed_time": "0:58:13", "remaining_time": "3:04:04"}
+{"current_steps": 2610, "total_steps": 10820, "loss": 0.0257, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.646833786984927e-05, "epoch": 2.41, "percentage": 24.12, "elapsed_time": "0:58:55", "remaining_time": "3:05:21"}
+{"current_steps": 2620, "total_steps": 10820, "loss": 0.0365, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.636868207865244e-05, "epoch": 2.42, "percentage": 24.21, "elapsed_time": "0:59:01", "remaining_time": "3:04:45"}
+{"current_steps": 2630, "total_steps": 10820, "loss": 0.0304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.626871855061438e-05, "epoch": 2.43, "percentage": 24.31, "elapsed_time": "0:59:08", "remaining_time": "3:04:10"}
+{"current_steps": 2640, "total_steps": 10820, "loss": 0.0266, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.61684481315854e-05, "epoch": 2.44, "percentage": 24.4, "elapsed_time": "0:59:14", "remaining_time": "3:03:34"}
+{"current_steps": 2650, "total_steps": 10820, "loss": 0.0185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.606787167001257e-05, "epoch": 2.45, "percentage": 24.49, "elapsed_time": "0:59:21", "remaining_time": "3:02:59"}
+{"current_steps": 2650, "total_steps": 10820, "loss": null, "eval_loss": 0.07773510366678238, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.45, "percentage": 24.49, "elapsed_time": "0:59:21", "remaining_time": "3:02:59"}
+{"current_steps": 2660, "total_steps": 10820, "loss": 0.0336, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.596699001693255e-05, "epoch": 2.46, "percentage": 24.58, "elapsed_time": "1:00:03", "remaining_time": "3:04:14"}
+{"current_steps": 2670, "total_steps": 10820, "loss": 0.0231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.586580402596446e-05, "epoch": 2.47, "percentage": 24.68, "elapsed_time": "1:00:09", "remaining_time": "3:03:38"}
+{"current_steps": 2680, "total_steps": 10820, "loss": 0.017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.576431455330258e-05, "epoch": 2.48, "percentage": 24.77, "elapsed_time": "1:00:16", "remaining_time": "3:03:03"}
+{"current_steps": 2690, "total_steps": 10820, "loss": 0.02, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.566252245770909e-05, "epoch": 2.49, "percentage": 24.86, "elapsed_time": "1:00:22", "remaining_time": "3:02:27"}
+{"current_steps": 2700, "total_steps": 10820, "loss": 0.0178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.556042860050687e-05, "epoch": 2.5, "percentage": 24.95, "elapsed_time": "1:00:28", "remaining_time": "3:01:52"}
+{"current_steps": 2700, "total_steps": 10820, "loss": null, "eval_loss": 0.07669008523225784, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 24.95, "elapsed_time": "1:00:28", "remaining_time": "3:01:52"}
+{"current_steps": 2710, "total_steps": 10820, "loss": 0.0171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.545803384557219e-05, "epoch": 2.5, "percentage": 25.05, "elapsed_time": "1:01:10", "remaining_time": "3:03:05"}
+{"current_steps": 2720, "total_steps": 10820, "loss": 0.0248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.535533905932738e-05, "epoch": 2.51, "percentage": 25.14, "elapsed_time": "1:01:16", "remaining_time": "3:02:29"}
+{"current_steps": 2730, "total_steps": 10820, "loss": 0.0318, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.525234511073352e-05, "epoch": 2.52, "percentage": 25.23, "elapsed_time": "1:01:23", "remaining_time": "3:01:55"}
+{"current_steps": 2740, "total_steps": 10820, "loss": 0.0123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.51490528712831e-05, "epoch": 2.53, "percentage": 25.32, "elapsed_time": "1:01:29", "remaining_time": "3:01:20"}
+{"current_steps": 2750, "total_steps": 10820, "loss": 0.0245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.504546321499255e-05, "epoch": 2.54, "percentage": 25.42, "elapsed_time": "1:01:35", "remaining_time": "3:00:45"}
+{"current_steps": 2750, "total_steps": 10820, "loss": null, "eval_loss": 0.07172290980815887, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.54, "percentage": 25.42, "elapsed_time": "1:01:35", "remaining_time": "3:00:45"}
+{"current_steps": 2760, "total_steps": 10820, "loss": 0.0093, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.4941577018395e-05, "epoch": 2.55, "percentage": 25.51, "elapsed_time": "1:02:18", "remaining_time": "3:01:57"}
+{"current_steps": 2770, "total_steps": 10820, "loss": 0.0177, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.483739516053276e-05, "epoch": 2.56, "percentage": 25.6, "elapsed_time": "1:02:25", "remaining_time": "3:01:23"}
+{"current_steps": 2780, "total_steps": 10820, "loss": 0.0238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.473291852294987e-05, "epoch": 2.57, "percentage": 25.69, "elapsed_time": "1:02:31", "remaining_time": "3:00:49"}
+{"current_steps": 2790, "total_steps": 10820, "loss": 0.0132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.462814798968472e-05, "epoch": 2.58, "percentage": 25.79, "elapsed_time": "1:02:37", "remaining_time": "3:00:15"}
+{"current_steps": 2800, "total_steps": 10820, "loss": 0.0226, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.452308444726249e-05, "epoch": 2.59, "percentage": 25.88, "elapsed_time": "1:02:43", "remaining_time": "2:59:40"}
+{"current_steps": 2800, "total_steps": 10820, "loss": null, "eval_loss": 0.0774235799908638, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.59, "percentage": 25.88, "elapsed_time": "1:02:43", "remaining_time": "2:59:40"}
+{"current_steps": 2810, "total_steps": 10820, "loss": 0.03, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.44177287846877e-05, "epoch": 2.6, "percentage": 25.97, "elapsed_time": "1:03:26", "remaining_time": "3:00:50"}
+{"current_steps": 2820, "total_steps": 10820, "loss": 0.0269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.43120818934367e-05, "epoch": 2.61, "percentage": 26.06, "elapsed_time": "1:03:32", "remaining_time": "3:00:16"}
+{"current_steps": 2830, "total_steps": 10820, "loss": 0.0178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.420614466745e-05, "epoch": 2.62, "percentage": 26.16, "elapsed_time": "1:03:39", "remaining_time": "2:59:42"}
+{"current_steps": 2840, "total_steps": 10820, "loss": 0.0189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.409991800312493e-05, "epoch": 2.62, "percentage": 26.25, "elapsed_time": "1:03:45", "remaining_time": "2:59:09"}
+{"current_steps": 2850, "total_steps": 10820, "loss": 0.0222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.399340279930786e-05, "epoch": 2.63, "percentage": 26.34, "elapsed_time": "1:03:51", "remaining_time": "2:58:35"}
+{"current_steps": 2850, "total_steps": 10820, "loss": null, "eval_loss": 0.0670793429017067, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.63, "percentage": 26.34, "elapsed_time": "1:03:51", "remaining_time": "2:58:35"}
+{"current_steps": 2860, "total_steps": 10820, "loss": 0.0187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.388659995728663e-05, "epoch": 2.64, "percentage": 26.43, "elapsed_time": "1:04:34", "remaining_time": "2:59:42"}
+{"current_steps": 2870, "total_steps": 10820, "loss": 0.0136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.377951038078302e-05, "epoch": 2.65, "percentage": 26.52, "elapsed_time": "1:04:40", "remaining_time": "2:59:08"}
+{"current_steps": 2880, "total_steps": 10820, "loss": 0.0318, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.367213497594502e-05, "epoch": 2.66, "percentage": 26.62, "elapsed_time": "1:04:46", "remaining_time": "2:58:35"}
+{"current_steps": 2890, "total_steps": 10820, "loss": 0.0228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.356447465133919e-05, "epoch": 2.67, "percentage": 26.71, "elapsed_time": "1:04:52", "remaining_time": "2:58:01"}
+{"current_steps": 2900, "total_steps": 10820, "loss": 0.0194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.345653031794292e-05, "epoch": 2.68, "percentage": 26.8, "elapsed_time": "1:04:59", "remaining_time": "2:57:28"}
+{"current_steps": 2900, "total_steps": 10820, "loss": null, "eval_loss": 0.0666012316942215, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.68, "percentage": 26.8, "elapsed_time": "1:04:59", "remaining_time": "2:57:28"}
+{"current_steps": 2910, "total_steps": 10820, "loss": 0.0155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.334830288913682e-05, "epoch": 2.69, "percentage": 26.89, "elapsed_time": "1:05:42", "remaining_time": "2:58:35"}
+{"current_steps": 2920, "total_steps": 10820, "loss": 0.0159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.323979328069689e-05, "epoch": 2.7, "percentage": 26.99, "elapsed_time": "1:05:48", "remaining_time": "2:58:02"}
+{"current_steps": 2930, "total_steps": 10820, "loss": 0.017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.313100241078689e-05, "epoch": 2.71, "percentage": 27.08, "elapsed_time": "1:05:54", "remaining_time": "2:57:28"}
+{"current_steps": 2940, "total_steps": 10820, "loss": 0.024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.302193119995039e-05, "epoch": 2.72, "percentage": 27.17, "elapsed_time": "1:06:00", "remaining_time": "2:56:54"}
+{"current_steps": 2950, "total_steps": 10820, "loss": 0.0162, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.291258057110319e-05, "epoch": 2.73, "percentage": 27.26, "elapsed_time": "1:06:06", "remaining_time": "2:56:22"}
+{"current_steps": 2950, "total_steps": 10820, "loss": null, "eval_loss": 0.07134513556957245, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.73, "percentage": 27.26, "elapsed_time": "1:06:06", "remaining_time": "2:56:22"}
+{"current_steps": 2960, "total_steps": 10820, "loss": 0.0221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.280295144952536e-05, "epoch": 2.74, "percentage": 27.36, "elapsed_time": "1:06:49", "remaining_time": "2:57:26"}
+{"current_steps": 2970, "total_steps": 10820, "loss": 0.0107, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.269304476285349e-05, "epoch": 2.74, "percentage": 27.45, "elapsed_time": "1:06:55", "remaining_time": "2:56:53"}
+{"current_steps": 2980, "total_steps": 10820, "loss": 0.0185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.258286144107276e-05, "epoch": 2.75, "percentage": 27.54, "elapsed_time": "1:07:02", "remaining_time": "2:56:21"}
+{"current_steps": 2990, "total_steps": 10820, "loss": 0.0185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.247240241650918e-05, "epoch": 2.76, "percentage": 27.63, "elapsed_time": "1:07:08", "remaining_time": "2:55:48"}
+{"current_steps": 3000, "total_steps": 10820, "loss": 0.0184, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.236166862382163e-05, "epoch": 2.77, "percentage": 27.73, "elapsed_time": "1:07:14", "remaining_time": "2:55:16"}
+{"current_steps": 3000, "total_steps": 10820, "loss": null, "eval_loss": 0.07399819046258926, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.77, "percentage": 27.73, "elapsed_time": "1:07:14", "remaining_time": "2:55:16"}
+{"current_steps": 3010, "total_steps": 10820, "loss": 0.0197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.225066099999392e-05, "epoch": 2.78, "percentage": 27.82, "elapsed_time": "1:07:57", "remaining_time": "2:56:19"}
+{"current_steps": 3020, "total_steps": 10820, "loss": 0.0231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.213938048432697e-05, "epoch": 2.79, "percentage": 27.91, "elapsed_time": "1:08:03", "remaining_time": "2:55:46"}
+{"current_steps": 3030, "total_steps": 10820, "loss": 0.013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.202782801843076e-05, "epoch": 2.8, "percentage": 28.0, "elapsed_time": "1:08:10", "remaining_time": "2:55:15"}
+{"current_steps": 3040, "total_steps": 10820, "loss": 0.0247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.191600454621642e-05, "epoch": 2.81, "percentage": 28.1, "elapsed_time": "1:08:16", "remaining_time": "2:54:44"}
+{"current_steps": 3050, "total_steps": 10820, "loss": 0.0227, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.18039110138882e-05, "epoch": 2.82, "percentage": 28.19, "elapsed_time": "1:08:23", "remaining_time": "2:54:12"}
+{"current_steps": 3050, "total_steps": 10820, "loss": null, "eval_loss": 0.06754355877637863, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.82, "percentage": 28.19, "elapsed_time": "1:08:23", "remaining_time": "2:54:12"}
+{"current_steps": 3060, "total_steps": 10820, "loss": 0.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.169154836993551e-05, "epoch": 2.83, "percentage": 28.28, "elapsed_time": "1:09:05", "remaining_time": "2:55:13"}
+{"current_steps": 3070, "total_steps": 10820, "loss": 0.0216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.157891756512488e-05, "epoch": 2.84, "percentage": 28.37, "elapsed_time": "1:09:11", "remaining_time": "2:54:41"}
+{"current_steps": 3080, "total_steps": 10820, "loss": 0.0405, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.146601955249188e-05, "epoch": 2.85, "percentage": 28.47, "elapsed_time": "1:09:18", "remaining_time": "2:54:10"}
+{"current_steps": 3090, "total_steps": 10820, "loss": 0.0319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.135285528733308e-05, "epoch": 2.86, "percentage": 28.56, "elapsed_time": "1:09:25", "remaining_time": "2:53:39"}
+{"current_steps": 3100, "total_steps": 10820, "loss": 0.0176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.1239425727198e-05, "epoch": 2.87, "percentage": 28.65, "elapsed_time": "1:09:31", "remaining_time": "2:53:07"}
+{"current_steps": 3100, "total_steps": 10820, "loss": null, "eval_loss": 0.07011596113443375, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.87, "percentage": 28.65, "elapsed_time": "1:09:31", "remaining_time": "2:53:07"}
+{"current_steps": 3110, "total_steps": 10820, "loss": 0.0285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.112573183188099e-05, "epoch": 2.87, "percentage": 28.74, "elapsed_time": "1:10:13", "remaining_time": "2:54:05"}
+{"current_steps": 3120, "total_steps": 10820, "loss": 0.0149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.1011774563413e-05, "epoch": 2.88, "percentage": 28.84, "elapsed_time": "1:10:19", "remaining_time": "2:53:34"}
+{"current_steps": 3130, "total_steps": 10820, "loss": 0.0223, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.089755488605366e-05, "epoch": 2.89, "percentage": 28.93, "elapsed_time": "1:10:26", "remaining_time": "2:53:04"}
+{"current_steps": 3140, "total_steps": 10820, "loss": 0.015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.07830737662829e-05, "epoch": 2.9, "percentage": 29.02, "elapsed_time": "1:10:32", "remaining_time": "2:52:32"}
+{"current_steps": 3150, "total_steps": 10820, "loss": 0.034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.066833217279297e-05, "epoch": 2.91, "percentage": 29.11, "elapsed_time": "1:10:38", "remaining_time": "2:52:00"}
+{"current_steps": 3150, "total_steps": 10820, "loss": null, "eval_loss": 0.06750660389661789, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.91, "percentage": 29.11, "elapsed_time": "1:10:38", "remaining_time": "2:52:00"}
+{"current_steps": 3160, "total_steps": 10820, "loss": 0.0187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.055333107647999e-05, "epoch": 2.92, "percentage": 29.21, "elapsed_time": "1:11:21", "remaining_time": "2:52:58"}
+{"current_steps": 3170, "total_steps": 10820, "loss": 0.0261, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.043807145043604e-05, "epoch": 2.93, "percentage": 29.3, "elapsed_time": "1:11:28", "remaining_time": "2:52:28"}
+{"current_steps": 3180, "total_steps": 10820, "loss": 0.0175, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.032255426994069e-05, "epoch": 2.94, "percentage": 29.39, "elapsed_time": "1:11:34", "remaining_time": "2:51:57"}
+{"current_steps": 3190, "total_steps": 10820, "loss": 0.0163, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.020678051245282e-05, "epoch": 2.95, "percentage": 29.48, "elapsed_time": "1:11:40", "remaining_time": "2:51:26"}
+{"current_steps": 3200, "total_steps": 10820, "loss": 0.0148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.009075115760243e-05, "epoch": 2.96, "percentage": 29.57, "elapsed_time": "1:11:46", "remaining_time": "2:50:55"}
+{"current_steps": 3200, "total_steps": 10820, "loss": null, "eval_loss": 0.06875752657651901, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.96, "percentage": 29.57, "elapsed_time": "1:11:46", "remaining_time": "2:50:55"}
+{"current_steps": 3210, "total_steps": 10820, "loss": 0.0445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.99744671871822e-05, "epoch": 2.97, "percentage": 29.67, "elapsed_time": "1:12:28", "remaining_time": "2:51:50"}
+{"current_steps": 3220, "total_steps": 10820, "loss": 0.0216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.985792958513931e-05, "epoch": 2.98, "percentage": 29.76, "elapsed_time": "1:12:35", "remaining_time": "2:51:20"}
+{"current_steps": 3230, "total_steps": 10820, "loss": 0.0173, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.974113933756707e-05, "epoch": 2.99, "percentage": 29.85, "elapsed_time": "1:12:42", "remaining_time": "2:50:50"}
+{"current_steps": 3240, "total_steps": 10820, "loss": 0.0185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.962409743269654e-05, "epoch": 2.99, "percentage": 29.94, "elapsed_time": "1:12:48", "remaining_time": "2:50:20"}
+{"current_steps": 3250, "total_steps": 10820, "loss": 0.014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.950680486088823e-05, "epoch": 3.0, "percentage": 30.04, "elapsed_time": "1:12:55", "remaining_time": "2:49:50"}
+{"current_steps": 3250, "total_steps": 10820, "loss": null, "eval_loss": 0.0672665610909462, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 30.04, "elapsed_time": "1:12:55", "remaining_time": "2:49:50"}
+{"current_steps": 3260, "total_steps": 10820, "loss": 0.0234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.938926261462366e-05, "epoch": 3.01, "percentage": 30.13, "elapsed_time": "1:13:37", "remaining_time": "2:50:44"}
+{"current_steps": 3270, "total_steps": 10820, "loss": 0.0094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.927147168849704e-05, "epoch": 3.02, "percentage": 30.22, "elapsed_time": "1:13:43", "remaining_time": "2:50:13"}
+{"current_steps": 3280, "total_steps": 10820, "loss": 0.007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.915343307920674e-05, "epoch": 3.03, "percentage": 30.31, "elapsed_time": "1:13:49", "remaining_time": "2:49:43"}
+{"current_steps": 3290, "total_steps": 10820, "loss": 0.0106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.903514778554699e-05, "epoch": 3.04, "percentage": 30.41, "elapsed_time": "1:13:56", "remaining_time": "2:49:14"}
+{"current_steps": 3300, "total_steps": 10820, "loss": 0.0178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.891661680839932e-05, "epoch": 3.05, "percentage": 30.5, "elapsed_time": "1:14:03", "remaining_time": "2:48:44"}
+{"current_steps": 3300, "total_steps": 10820, "loss": null, "eval_loss": 0.07193872332572937, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.05, "percentage": 30.5, "elapsed_time": "1:14:03", "remaining_time": "2:48:44"}
+{"current_steps": 3310, "total_steps": 10820, "loss": 0.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.879784115072417e-05, "epoch": 3.06, "percentage": 30.59, "elapsed_time": "1:14:45", "remaining_time": "2:49:36"}
+{"current_steps": 3320, "total_steps": 10820, "loss": 0.0035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.86788218175523e-05, "epoch": 3.07, "percentage": 30.68, "elapsed_time": "1:14:51", "remaining_time": "2:49:05"}
+{"current_steps": 3330, "total_steps": 10820, "loss": 0.0028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.855955981597643e-05, "epoch": 3.08, "percentage": 30.78, "elapsed_time": "1:14:57", "remaining_time": "2:48:36"}
+{"current_steps": 3340, "total_steps": 10820, "loss": 0.0092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.844005615514259e-05, "epoch": 3.09, "percentage": 30.87, "elapsed_time": "1:15:04", "remaining_time": "2:48:08"}
+{"current_steps": 3350, "total_steps": 10820, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.832031184624164e-05, "epoch": 3.1, "percentage": 30.96, "elapsed_time": "1:15:10", "remaining_time": "2:47:38"}
+{"current_steps": 3350, "total_steps": 10820, "loss": null, "eval_loss": 0.07338841259479523, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.1, "percentage": 30.96, "elapsed_time": "1:15:10", "remaining_time": "2:47:38"}
+{"current_steps": 3360, "total_steps": 10820, "loss": 0.0145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.820032790250074e-05, "epoch": 3.11, "percentage": 31.05, "elapsed_time": "1:15:54", "remaining_time": "2:48:31"}
+{"current_steps": 3370, "total_steps": 10820, "loss": 0.0043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.808010533917465e-05, "epoch": 3.11, "percentage": 31.15, "elapsed_time": "1:16:00", "remaining_time": "2:48:01"}
+{"current_steps": 3380, "total_steps": 10820, "loss": 0.0125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.795964517353735e-05, "epoch": 3.12, "percentage": 31.24, "elapsed_time": "1:16:06", "remaining_time": "2:47:32"}
+{"current_steps": 3390, "total_steps": 10820, "loss": 0.0023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.783894842487322e-05, "epoch": 3.13, "percentage": 31.33, "elapsed_time": "1:16:13", "remaining_time": "2:47:03"}
+{"current_steps": 3400, "total_steps": 10820, "loss": 0.0069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.771801611446858e-05, "epoch": 3.14, "percentage": 31.42, "elapsed_time": "1:16:19", "remaining_time": "2:46:34"}
+{"current_steps": 3400, "total_steps": 10820, "loss": null, "eval_loss": 0.07644446939229965, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.14, "percentage": 31.42, "elapsed_time": "1:16:19", "remaining_time": "2:46:34"}
+{"current_steps": 3410, "total_steps": 10820, "loss": 0.0118, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.75968492656029e-05, "epoch": 3.15, "percentage": 31.52, "elapsed_time": "1:17:02", "remaining_time": "2:47:24"}
+{"current_steps": 3420, "total_steps": 10820, "loss": 0.0066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.74754489035403e-05, "epoch": 3.16, "percentage": 31.61, "elapsed_time": "1:17:08", "remaining_time": "2:46:54"}
+{"current_steps": 3430, "total_steps": 10820, "loss": 0.0187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.735381605552073e-05, "epoch": 3.17, "percentage": 31.7, "elapsed_time": "1:17:14", "remaining_time": "2:46:25"}
+{"current_steps": 3440, "total_steps": 10820, "loss": 0.0094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.723195175075136e-05, "epoch": 3.18, "percentage": 31.79, "elapsed_time": "1:17:21", "remaining_time": "2:45:56"}
+{"current_steps": 3450, "total_steps": 10820, "loss": 0.0074, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.710985702039786e-05, "epoch": 3.19, "percentage": 31.89, "elapsed_time": "1:17:27", "remaining_time": "2:45:28"}
+{"current_steps": 3450, "total_steps": 10820, "loss": null, "eval_loss": 0.08178228884935379, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.19, "percentage": 31.89, "elapsed_time": "1:17:27", "remaining_time": "2:45:28"}
+{"current_steps": 3460, "total_steps": 10820, "loss": 0.0038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.698753289757565e-05, "epoch": 3.2, "percentage": 31.98, "elapsed_time": "1:18:10", "remaining_time": "2:46:17"}
+{"current_steps": 3470, "total_steps": 10820, "loss": 0.0113, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.68649804173412e-05, "epoch": 3.21, "percentage": 32.07, "elapsed_time": "1:18:16", "remaining_time": "2:45:47"}
+{"current_steps": 3480, "total_steps": 10820, "loss": 0.0099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.674220061668322e-05, "epoch": 3.22, "percentage": 32.16, "elapsed_time": "1:18:22", "remaining_time": "2:45:18"}
+{"current_steps": 3490, "total_steps": 10820, "loss": 0.0089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.661919453451394e-05, "epoch": 3.23, "percentage": 32.26, "elapsed_time": "1:18:28", "remaining_time": "2:44:49"}
+{"current_steps": 3500, "total_steps": 10820, "loss": 0.009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.649596321166024e-05, "epoch": 3.23, "percentage": 32.35, "elapsed_time": "1:18:34", "remaining_time": "2:44:20"}
+{"current_steps": 3500, "total_steps": 10820, "loss": null, "eval_loss": 0.07047122716903687, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.23, "percentage": 32.35, "elapsed_time": "1:18:34", "remaining_time": "2:44:20"}
+{"current_steps": 3510, "total_steps": 10820, "loss": 0.0084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.6372507690855e-05, "epoch": 3.24, "percentage": 32.44, "elapsed_time": "1:19:17", "remaining_time": "2:45:08"}
+{"current_steps": 3520, "total_steps": 10820, "loss": 0.0119, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.6248829016728e-05, "epoch": 3.25, "percentage": 32.53, "elapsed_time": "1:19:24", "remaining_time": "2:44:40"}
+{"current_steps": 3530, "total_steps": 10820, "loss": 0.0139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.612492823579745e-05, "epoch": 3.26, "percentage": 32.62, "elapsed_time": "1:19:30", "remaining_time": "2:44:12"}
+{"current_steps": 3540, "total_steps": 10820, "loss": 0.0092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.600080639646077e-05, "epoch": 3.27, "percentage": 32.72, "elapsed_time": "1:19:37", "remaining_time": "2:43:44"}
+{"current_steps": 3550, "total_steps": 10820, "loss": 0.0048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.5876464548986e-05, "epoch": 3.28, "percentage": 32.81, "elapsed_time": "1:19:43", "remaining_time": "2:43:15"}
+{"current_steps": 3550, "total_steps": 10820, "loss": null, "eval_loss": 0.07350648939609528, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.28, "percentage": 32.81, "elapsed_time": "1:19:43", "remaining_time": "2:43:15"}
+{"current_steps": 3560, "total_steps": 10820, "loss": 0.0095, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.575190374550272e-05, "epoch": 3.29, "percentage": 32.9, "elapsed_time": "1:20:25", "remaining_time": "2:44:00"}
+{"current_steps": 3570, "total_steps": 10820, "loss": 0.0052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.562712503999327e-05, "epoch": 3.3, "percentage": 32.99, "elapsed_time": "1:20:31", "remaining_time": "2:43:32"}
+{"current_steps": 3580, "total_steps": 10820, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.550212948828377e-05, "epoch": 3.31, "percentage": 33.09, "elapsed_time": "1:20:37", "remaining_time": "2:43:04"}
+{"current_steps": 3590, "total_steps": 10820, "loss": 0.0194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.537691814803521e-05, "epoch": 3.32, "percentage": 33.18, "elapsed_time": "1:20:44", "remaining_time": "2:42:35"}
+{"current_steps": 3600, "total_steps": 10820, "loss": 0.005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.52514920787345e-05, "epoch": 3.33, "percentage": 33.27, "elapsed_time": "1:20:50", "remaining_time": "2:42:08"}
+{"current_steps": 3600, "total_steps": 10820, "loss": null, "eval_loss": 0.07049556821584702, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.33, "percentage": 33.27, "elapsed_time": "1:20:50", "remaining_time": "2:42:08"}
+{"current_steps": 3610, "total_steps": 10820, "loss": 0.0162, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.51258523416855e-05, "epoch": 3.34, "percentage": 33.36, "elapsed_time": "1:21:33", "remaining_time": "2:42:52"}
+{"current_steps": 3620, "total_steps": 10820, "loss": 0.0108, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.500000000000001e-05, "epoch": 3.35, "percentage": 33.46, "elapsed_time": "1:21:39", "remaining_time": "2:42:24"}
+{"current_steps": 3630, "total_steps": 10820, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.487393611858883e-05, "epoch": 3.35, "percentage": 33.55, "elapsed_time": "1:21:45", "remaining_time": "2:41:57"}
+{"current_steps": 3640, "total_steps": 10820, "loss": 0.011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.474766176415271e-05, "epoch": 3.36, "percentage": 33.64, "elapsed_time": "1:21:52", "remaining_time": "2:41:29"}
+{"current_steps": 3650, "total_steps": 10820, "loss": 0.0073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.462117800517336e-05, "epoch": 3.37, "percentage": 33.73, "elapsed_time": "1:21:58", "remaining_time": "2:41:01"}
+{"current_steps": 3650, "total_steps": 10820, "loss": null, "eval_loss": 0.07236067205667496, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.37, "percentage": 33.73, "elapsed_time": "1:21:58", "remaining_time": "2:41:01"}
+{"current_steps": 3650, "total_steps": 10820, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.37, "percentage": 33.73, "elapsed_time": "1:21:58", "remaining_time": "2:41:01"}
+{"current_steps": 191, "total_steps": 191, "loss": null, "eval_loss": 0.07047122716903687, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.37, "percentage": 100.0, "elapsed_time": "1:23:24", "remaining_time": "0:00:00"}
diff --git a/llama2_13b_peft/elementary_math_qa/trainer_state.json b/llama2_13b_peft/elementary_math_qa/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3372a8df512a50f9c5f8ca9465fa088e6cb85c85
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/trainer_state.json
@@ -0,0 +1,3169 @@
+{
+ "best_metric": 0.07047122716903687,
+ "best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/elementary_math_qa_no_sys/checkpoint-3500",
+ "epoch": 3.3733826247689462,
+ "eval_steps": 50,
+ "global_step": 3650,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01,
+ "grad_norm": 4.040522575378418,
+ "learning_rate": 5e-05,
+ "loss": 3.4664,
+ "step": 10
+ },
+ {
+ "epoch": 0.02,
+ "grad_norm": 0.8851511478424072,
+ "learning_rate": 0.0001,
+ "loss": 1.2417,
+ "step": 20
+ },
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.6568808555603027,
+ "learning_rate": 9.999978846027431e-05,
+ "loss": 0.3726,
+ "step": 30
+ },
+ {
+ "epoch": 0.04,
+ "grad_norm": 0.29808229207992554,
+ "learning_rate": 9.999915384288722e-05,
+ "loss": 0.3371,
+ "step": 40
+ },
+ {
+ "epoch": 0.05,
+ "grad_norm": 0.2813255488872528,
+ "learning_rate": 9.999809615320856e-05,
+ "loss": 0.3438,
+ "step": 50
+ },
+ {
+ "epoch": 0.05,
+ "eval_loss": 0.3363588750362396,
+ "eval_runtime": 35.8964,
+ "eval_samples_per_second": 127.589,
+ "eval_steps_per_second": 5.321,
+ "step": 50
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.2735520899295807,
+ "learning_rate": 9.999661540018812e-05,
+ "loss": 0.3451,
+ "step": 60
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.2597522735595703,
+ "learning_rate": 9.999471159635539e-05,
+ "loss": 0.3227,
+ "step": 70
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 0.2065269947052002,
+ "learning_rate": 9.999238475781957e-05,
+ "loss": 0.3368,
+ "step": 80
+ },
+ {
+ "epoch": 0.08,
+ "grad_norm": 0.44564762711524963,
+ "learning_rate": 9.998963490426943e-05,
+ "loss": 0.3171,
+ "step": 90
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.29043757915496826,
+ "learning_rate": 9.998646205897309e-05,
+ "loss": 0.3021,
+ "step": 100
+ },
+ {
+ "epoch": 0.09,
+ "eval_loss": 0.30562111735343933,
+ "eval_runtime": 36.0314,
+ "eval_samples_per_second": 127.111,
+ "eval_steps_per_second": 5.301,
+ "step": 100
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 0.7949171662330627,
+ "learning_rate": 9.998286624877786e-05,
+ "loss": 0.3053,
+ "step": 110
+ },
+ {
+ "epoch": 0.11,
+ "grad_norm": 0.44385454058647156,
+ "learning_rate": 9.997884750411005e-05,
+ "loss": 0.2789,
+ "step": 120
+ },
+ {
+ "epoch": 0.12,
+ "grad_norm": 1.0356186628341675,
+ "learning_rate": 9.997440585897455e-05,
+ "loss": 0.2854,
+ "step": 130
+ },
+ {
+ "epoch": 0.13,
+ "grad_norm": 0.43352845311164856,
+ "learning_rate": 9.99695413509548e-05,
+ "loss": 0.2841,
+ "step": 140
+ },
+ {
+ "epoch": 0.14,
+ "grad_norm": 0.9958717823028564,
+ "learning_rate": 9.996425402121223e-05,
+ "loss": 0.2676,
+ "step": 150
+ },
+ {
+ "epoch": 0.14,
+ "eval_loss": 0.27099743485450745,
+ "eval_runtime": 36.2627,
+ "eval_samples_per_second": 126.301,
+ "eval_steps_per_second": 5.267,
+ "step": 150
+ },
+ {
+ "epoch": 0.15,
+ "grad_norm": 0.5326156616210938,
+ "learning_rate": 9.995854391448606e-05,
+ "loss": 0.2841,
+ "step": 160
+ },
+ {
+ "epoch": 0.16,
+ "grad_norm": 0.49322521686553955,
+ "learning_rate": 9.99524110790929e-05,
+ "loss": 0.2624,
+ "step": 170
+ },
+ {
+ "epoch": 0.17,
+ "grad_norm": 0.777406632900238,
+ "learning_rate": 9.994585556692624e-05,
+ "loss": 0.2398,
+ "step": 180
+ },
+ {
+ "epoch": 0.18,
+ "grad_norm": 0.509154200553894,
+ "learning_rate": 9.993887743345614e-05,
+ "loss": 0.2488,
+ "step": 190
+ },
+ {
+ "epoch": 0.18,
+ "grad_norm": 0.6434066891670227,
+ "learning_rate": 9.99314767377287e-05,
+ "loss": 0.2679,
+ "step": 200
+ },
+ {
+ "epoch": 0.18,
+ "eval_loss": 0.25818708539009094,
+ "eval_runtime": 36.3199,
+ "eval_samples_per_second": 126.102,
+ "eval_steps_per_second": 5.259,
+ "step": 200
+ },
+ {
+ "epoch": 0.19,
+ "grad_norm": 0.460243821144104,
+ "learning_rate": 9.992365354236557e-05,
+ "loss": 0.2595,
+ "step": 210
+ },
+ {
+ "epoch": 0.2,
+ "grad_norm": 0.5987964868545532,
+ "learning_rate": 9.991540791356342e-05,
+ "loss": 0.2625,
+ "step": 220
+ },
+ {
+ "epoch": 0.21,
+ "grad_norm": 0.9906507134437561,
+ "learning_rate": 9.990673992109335e-05,
+ "loss": 0.2491,
+ "step": 230
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 0.7199179530143738,
+ "learning_rate": 9.989764963830037e-05,
+ "loss": 0.2272,
+ "step": 240
+ },
+ {
+ "epoch": 0.23,
+ "grad_norm": 0.5103895664215088,
+ "learning_rate": 9.988813714210272e-05,
+ "loss": 0.2448,
+ "step": 250
+ },
+ {
+ "epoch": 0.23,
+ "eval_loss": 0.2475069910287857,
+ "eval_runtime": 36.3235,
+ "eval_samples_per_second": 126.089,
+ "eval_steps_per_second": 5.258,
+ "step": 250
+ },
+ {
+ "epoch": 0.24,
+ "grad_norm": 0.6703325510025024,
+ "learning_rate": 9.987820251299122e-05,
+ "loss": 0.2425,
+ "step": 260
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 0.40366512537002563,
+ "learning_rate": 9.986784583502862e-05,
+ "loss": 0.2502,
+ "step": 270
+ },
+ {
+ "epoch": 0.26,
+ "grad_norm": 0.569157600402832,
+ "learning_rate": 9.985706719584888e-05,
+ "loss": 0.2599,
+ "step": 280
+ },
+ {
+ "epoch": 0.27,
+ "grad_norm": 1.02542245388031,
+ "learning_rate": 9.98458666866564e-05,
+ "loss": 0.244,
+ "step": 290
+ },
+ {
+ "epoch": 0.28,
+ "grad_norm": 0.5159379243850708,
+ "learning_rate": 9.983424440222531e-05,
+ "loss": 0.2355,
+ "step": 300
+ },
+ {
+ "epoch": 0.28,
+ "eval_loss": 0.23719529807567596,
+ "eval_runtime": 36.3327,
+ "eval_samples_per_second": 126.057,
+ "eval_steps_per_second": 5.257,
+ "step": 300
+ },
+ {
+ "epoch": 0.29,
+ "grad_norm": 0.5553289651870728,
+ "learning_rate": 9.982220044089859e-05,
+ "loss": 0.2368,
+ "step": 310
+ },
+ {
+ "epoch": 0.3,
+ "grad_norm": 0.8868921399116516,
+ "learning_rate": 9.980973490458728e-05,
+ "loss": 0.2509,
+ "step": 320
+ },
+ {
+ "epoch": 0.3,
+ "grad_norm": 0.48811423778533936,
+ "learning_rate": 9.979684789876965e-05,
+ "loss": 0.2539,
+ "step": 330
+ },
+ {
+ "epoch": 0.31,
+ "grad_norm": 0.669154167175293,
+ "learning_rate": 9.978353953249022e-05,
+ "loss": 0.2308,
+ "step": 340
+ },
+ {
+ "epoch": 0.32,
+ "grad_norm": 0.5228665471076965,
+ "learning_rate": 9.976980991835894e-05,
+ "loss": 0.2335,
+ "step": 350
+ },
+ {
+ "epoch": 0.32,
+ "eval_loss": 0.22817698121070862,
+ "eval_runtime": 36.312,
+ "eval_samples_per_second": 126.129,
+ "eval_steps_per_second": 5.26,
+ "step": 350
+ },
+ {
+ "epoch": 0.33,
+ "grad_norm": 0.5688114166259766,
+ "learning_rate": 9.975565917255016e-05,
+ "loss": 0.2046,
+ "step": 360
+ },
+ {
+ "epoch": 0.34,
+ "grad_norm": 0.8116939663887024,
+ "learning_rate": 9.974108741480165e-05,
+ "loss": 0.2174,
+ "step": 370
+ },
+ {
+ "epoch": 0.35,
+ "grad_norm": 0.4922645390033722,
+ "learning_rate": 9.972609476841367e-05,
+ "loss": 0.2346,
+ "step": 380
+ },
+ {
+ "epoch": 0.36,
+ "grad_norm": 0.8515651226043701,
+ "learning_rate": 9.971068136024781e-05,
+ "loss": 0.2291,
+ "step": 390
+ },
+ {
+ "epoch": 0.37,
+ "grad_norm": 0.5515058636665344,
+ "learning_rate": 9.9694847320726e-05,
+ "loss": 0.2226,
+ "step": 400
+ },
+ {
+ "epoch": 0.37,
+ "eval_loss": 0.22269846498966217,
+ "eval_runtime": 36.2361,
+ "eval_samples_per_second": 126.393,
+ "eval_steps_per_second": 5.271,
+ "step": 400
+ },
+ {
+ "epoch": 0.38,
+ "grad_norm": 0.4810548424720764,
+ "learning_rate": 9.967859278382938e-05,
+ "loss": 0.2235,
+ "step": 410
+ },
+ {
+ "epoch": 0.39,
+ "grad_norm": 0.74261873960495,
+ "learning_rate": 9.966191788709716e-05,
+ "loss": 0.2308,
+ "step": 420
+ },
+ {
+ "epoch": 0.4,
+ "grad_norm": 0.8025543689727783,
+ "learning_rate": 9.964482277162546e-05,
+ "loss": 0.193,
+ "step": 430
+ },
+ {
+ "epoch": 0.41,
+ "grad_norm": 0.5808039903640747,
+ "learning_rate": 9.962730758206611e-05,
+ "loss": 0.2144,
+ "step": 440
+ },
+ {
+ "epoch": 0.42,
+ "grad_norm": 0.5638976097106934,
+ "learning_rate": 9.960937246662546e-05,
+ "loss": 0.2098,
+ "step": 450
+ },
+ {
+ "epoch": 0.42,
+ "eval_loss": 0.2109217643737793,
+ "eval_runtime": 36.2318,
+ "eval_samples_per_second": 126.408,
+ "eval_steps_per_second": 5.272,
+ "step": 450
+ },
+ {
+ "epoch": 0.43,
+ "grad_norm": 1.0780441761016846,
+ "learning_rate": 9.959101757706308e-05,
+ "loss": 0.2355,
+ "step": 460
+ },
+ {
+ "epoch": 0.43,
+ "grad_norm": 0.8211221098899841,
+ "learning_rate": 9.957224306869053e-05,
+ "loss": 0.2108,
+ "step": 470
+ },
+ {
+ "epoch": 0.44,
+ "grad_norm": 0.8444514274597168,
+ "learning_rate": 9.955304910036993e-05,
+ "loss": 0.2295,
+ "step": 480
+ },
+ {
+ "epoch": 0.45,
+ "grad_norm": 0.47663894295692444,
+ "learning_rate": 9.95334358345128e-05,
+ "loss": 0.2129,
+ "step": 490
+ },
+ {
+ "epoch": 0.46,
+ "grad_norm": 1.289258360862732,
+ "learning_rate": 9.951340343707852e-05,
+ "loss": 0.1839,
+ "step": 500
+ },
+ {
+ "epoch": 0.46,
+ "eval_loss": 0.20476657152175903,
+ "eval_runtime": 36.255,
+ "eval_samples_per_second": 126.328,
+ "eval_steps_per_second": 5.268,
+ "step": 500
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 2.3407182693481445,
+ "learning_rate": 9.949295207757299e-05,
+ "loss": 0.1975,
+ "step": 510
+ },
+ {
+ "epoch": 0.48,
+ "grad_norm": 0.8705734014511108,
+ "learning_rate": 9.947208192904722e-05,
+ "loss": 0.2055,
+ "step": 520
+ },
+ {
+ "epoch": 0.49,
+ "grad_norm": 0.8187156915664673,
+ "learning_rate": 9.945079316809585e-05,
+ "loss": 0.242,
+ "step": 530
+ },
+ {
+ "epoch": 0.5,
+ "grad_norm": 1.010530710220337,
+ "learning_rate": 9.942908597485558e-05,
+ "loss": 0.1907,
+ "step": 540
+ },
+ {
+ "epoch": 0.51,
+ "grad_norm": 0.5775702595710754,
+ "learning_rate": 9.94069605330038e-05,
+ "loss": 0.2008,
+ "step": 550
+ },
+ {
+ "epoch": 0.51,
+ "eval_loss": 0.19918882846832275,
+ "eval_runtime": 36.2643,
+ "eval_samples_per_second": 126.295,
+ "eval_steps_per_second": 5.267,
+ "step": 550
+ },
+ {
+ "epoch": 0.52,
+ "grad_norm": 0.962810218334198,
+ "learning_rate": 9.938441702975689e-05,
+ "loss": 0.189,
+ "step": 560
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 0.5549082159996033,
+ "learning_rate": 9.936145565586871e-05,
+ "loss": 0.2045,
+ "step": 570
+ },
+ {
+ "epoch": 0.54,
+ "grad_norm": 0.6081735491752625,
+ "learning_rate": 9.933807660562898e-05,
+ "loss": 0.196,
+ "step": 580
+ },
+ {
+ "epoch": 0.55,
+ "grad_norm": 0.987080991268158,
+ "learning_rate": 9.931428007686158e-05,
+ "loss": 0.2054,
+ "step": 590
+ },
+ {
+ "epoch": 0.55,
+ "grad_norm": 0.7649418711662292,
+ "learning_rate": 9.929006627092299e-05,
+ "loss": 0.1945,
+ "step": 600
+ },
+ {
+ "epoch": 0.55,
+ "eval_loss": 0.20194485783576965,
+ "eval_runtime": 36.2524,
+ "eval_samples_per_second": 126.336,
+ "eval_steps_per_second": 5.269,
+ "step": 600
+ },
+ {
+ "epoch": 0.56,
+ "grad_norm": 0.547579824924469,
+ "learning_rate": 9.926543539270048e-05,
+ "loss": 0.2278,
+ "step": 610
+ },
+ {
+ "epoch": 0.57,
+ "grad_norm": 0.6617013812065125,
+ "learning_rate": 9.924038765061042e-05,
+ "loss": 0.1894,
+ "step": 620
+ },
+ {
+ "epoch": 0.58,
+ "grad_norm": 0.9552827477455139,
+ "learning_rate": 9.921492325659649e-05,
+ "loss": 0.1868,
+ "step": 630
+ },
+ {
+ "epoch": 0.59,
+ "grad_norm": 0.4771063029766083,
+ "learning_rate": 9.918904242612795e-05,
+ "loss": 0.1927,
+ "step": 640
+ },
+ {
+ "epoch": 0.6,
+ "grad_norm": 0.7816069722175598,
+ "learning_rate": 9.916274537819775e-05,
+ "loss": 0.1891,
+ "step": 650
+ },
+ {
+ "epoch": 0.6,
+ "eval_loss": 0.1859094649553299,
+ "eval_runtime": 36.2607,
+ "eval_samples_per_second": 126.307,
+ "eval_steps_per_second": 5.267,
+ "step": 650
+ },
+ {
+ "epoch": 0.61,
+ "grad_norm": 1.2409390211105347,
+ "learning_rate": 9.913603233532067e-05,
+ "loss": 0.1772,
+ "step": 660
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 0.4985053837299347,
+ "learning_rate": 9.910890352353153e-05,
+ "loss": 0.1787,
+ "step": 670
+ },
+ {
+ "epoch": 0.63,
+ "grad_norm": 0.6402477025985718,
+ "learning_rate": 9.908135917238321e-05,
+ "loss": 0.192,
+ "step": 680
+ },
+ {
+ "epoch": 0.64,
+ "grad_norm": 0.7117078304290771,
+ "learning_rate": 9.905339951494463e-05,
+ "loss": 0.1784,
+ "step": 690
+ },
+ {
+ "epoch": 0.65,
+ "grad_norm": 0.7569687962532043,
+ "learning_rate": 9.902502478779896e-05,
+ "loss": 0.2015,
+ "step": 700
+ },
+ {
+ "epoch": 0.65,
+ "eval_loss": 0.19662824273109436,
+ "eval_runtime": 36.2532,
+ "eval_samples_per_second": 126.334,
+ "eval_steps_per_second": 5.268,
+ "step": 700
+ },
+ {
+ "epoch": 0.66,
+ "grad_norm": 0.6098802089691162,
+ "learning_rate": 9.899623523104149e-05,
+ "loss": 0.188,
+ "step": 710
+ },
+ {
+ "epoch": 0.67,
+ "grad_norm": 0.8657363057136536,
+ "learning_rate": 9.896703108827759e-05,
+ "loss": 0.172,
+ "step": 720
+ },
+ {
+ "epoch": 0.67,
+ "grad_norm": 0.5754011869430542,
+ "learning_rate": 9.893741260662071e-05,
+ "loss": 0.1933,
+ "step": 730
+ },
+ {
+ "epoch": 0.68,
+ "grad_norm": 1.5085391998291016,
+ "learning_rate": 9.890738003669029e-05,
+ "loss": 0.1942,
+ "step": 740
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 0.7169360518455505,
+ "learning_rate": 9.887693363260958e-05,
+ "loss": 0.174,
+ "step": 750
+ },
+ {
+ "epoch": 0.69,
+ "eval_loss": 0.18010230362415314,
+ "eval_runtime": 36.2672,
+ "eval_samples_per_second": 126.285,
+ "eval_steps_per_second": 5.266,
+ "step": 750
+ },
+ {
+ "epoch": 0.7,
+ "grad_norm": 0.8828125596046448,
+ "learning_rate": 9.884607365200356e-05,
+ "loss": 0.1806,
+ "step": 760
+ },
+ {
+ "epoch": 0.71,
+ "grad_norm": 0.7980941534042358,
+ "learning_rate": 9.881480035599667e-05,
+ "loss": 0.1784,
+ "step": 770
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 0.7319965958595276,
+ "learning_rate": 9.878311400921072e-05,
+ "loss": 0.1707,
+ "step": 780
+ },
+ {
+ "epoch": 0.73,
+ "grad_norm": 0.8168091773986816,
+ "learning_rate": 9.875101487976253e-05,
+ "loss": 0.1732,
+ "step": 790
+ },
+ {
+ "epoch": 0.74,
+ "grad_norm": 1.2269237041473389,
+ "learning_rate": 9.871850323926177e-05,
+ "loss": 0.1565,
+ "step": 800
+ },
+ {
+ "epoch": 0.74,
+ "eval_loss": 0.17616184055805206,
+ "eval_runtime": 36.2739,
+ "eval_samples_per_second": 126.262,
+ "eval_steps_per_second": 5.265,
+ "step": 800
+ },
+ {
+ "epoch": 0.75,
+ "grad_norm": 0.5521104335784912,
+ "learning_rate": 9.868557936280855e-05,
+ "loss": 0.1855,
+ "step": 810
+ },
+ {
+ "epoch": 0.76,
+ "grad_norm": 0.6372039914131165,
+ "learning_rate": 9.865224352899119e-05,
+ "loss": 0.1763,
+ "step": 820
+ },
+ {
+ "epoch": 0.77,
+ "grad_norm": 0.9996755123138428,
+ "learning_rate": 9.861849601988383e-05,
+ "loss": 0.149,
+ "step": 830
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 1.2396740913391113,
+ "learning_rate": 9.858433712104403e-05,
+ "loss": 0.1773,
+ "step": 840
+ },
+ {
+ "epoch": 0.79,
+ "grad_norm": 0.946553647518158,
+ "learning_rate": 9.854976712151031e-05,
+ "loss": 0.1825,
+ "step": 850
+ },
+ {
+ "epoch": 0.79,
+ "eval_loss": 0.1716548502445221,
+ "eval_runtime": 36.2484,
+ "eval_samples_per_second": 126.35,
+ "eval_steps_per_second": 5.269,
+ "step": 850
+ },
+ {
+ "epoch": 0.79,
+ "grad_norm": 1.1854327917099,
+ "learning_rate": 9.851478631379982e-05,
+ "loss": 0.1608,
+ "step": 860
+ },
+ {
+ "epoch": 0.8,
+ "grad_norm": 0.6903740763664246,
+ "learning_rate": 9.84793949939058e-05,
+ "loss": 0.1723,
+ "step": 870
+ },
+ {
+ "epoch": 0.81,
+ "grad_norm": 0.929786741733551,
+ "learning_rate": 9.844359346129503e-05,
+ "loss": 0.1566,
+ "step": 880
+ },
+ {
+ "epoch": 0.82,
+ "grad_norm": 0.43247154355049133,
+ "learning_rate": 9.84073820189054e-05,
+ "loss": 0.1769,
+ "step": 890
+ },
+ {
+ "epoch": 0.83,
+ "grad_norm": 0.8210358619689941,
+ "learning_rate": 9.837076097314319e-05,
+ "loss": 0.1651,
+ "step": 900
+ },
+ {
+ "epoch": 0.83,
+ "eval_loss": 0.16817261278629303,
+ "eval_runtime": 36.2399,
+ "eval_samples_per_second": 126.38,
+ "eval_steps_per_second": 5.27,
+ "step": 900
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 0.9283536672592163,
+ "learning_rate": 9.83337306338807e-05,
+ "loss": 0.1472,
+ "step": 910
+ },
+ {
+ "epoch": 0.85,
+ "grad_norm": 0.7863032817840576,
+ "learning_rate": 9.829629131445342e-05,
+ "loss": 0.1683,
+ "step": 920
+ },
+ {
+ "epoch": 0.86,
+ "grad_norm": 0.5381516218185425,
+ "learning_rate": 9.825844333165748e-05,
+ "loss": 0.151,
+ "step": 930
+ },
+ {
+ "epoch": 0.87,
+ "grad_norm": 0.7078680396080017,
+ "learning_rate": 9.822018700574695e-05,
+ "loss": 0.1641,
+ "step": 940
+ },
+ {
+ "epoch": 0.88,
+ "grad_norm": 0.8207384943962097,
+ "learning_rate": 9.818152266043114e-05,
+ "loss": 0.1598,
+ "step": 950
+ },
+ {
+ "epoch": 0.88,
+ "eval_loss": 0.15981163084506989,
+ "eval_runtime": 36.2611,
+ "eval_samples_per_second": 126.306,
+ "eval_steps_per_second": 5.267,
+ "step": 950
+ },
+ {
+ "epoch": 0.89,
+ "grad_norm": 1.319566011428833,
+ "learning_rate": 9.814245062287189e-05,
+ "loss": 0.156,
+ "step": 960
+ },
+ {
+ "epoch": 0.9,
+ "grad_norm": 0.5811505317687988,
+ "learning_rate": 9.810297122368067e-05,
+ "loss": 0.1646,
+ "step": 970
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 0.7206919193267822,
+ "learning_rate": 9.806308479691595e-05,
+ "loss": 0.1727,
+ "step": 980
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 0.9073074460029602,
+ "learning_rate": 9.802279168008029e-05,
+ "loss": 0.1566,
+ "step": 990
+ },
+ {
+ "epoch": 0.92,
+ "grad_norm": 0.9229528903961182,
+ "learning_rate": 9.798209221411747e-05,
+ "loss": 0.1502,
+ "step": 1000
+ },
+ {
+ "epoch": 0.92,
+ "eval_loss": 0.15576273202896118,
+ "eval_runtime": 36.2741,
+ "eval_samples_per_second": 126.261,
+ "eval_steps_per_second": 5.265,
+ "step": 1000
+ },
+ {
+ "epoch": 0.93,
+ "grad_norm": 0.9960848093032837,
+ "learning_rate": 9.794098674340965e-05,
+ "loss": 0.1634,
+ "step": 1010
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 0.5757964253425598,
+ "learning_rate": 9.789947561577445e-05,
+ "loss": 0.1438,
+ "step": 1020
+ },
+ {
+ "epoch": 0.95,
+ "grad_norm": 0.7039881348609924,
+ "learning_rate": 9.785755918246194e-05,
+ "loss": 0.1297,
+ "step": 1030
+ },
+ {
+ "epoch": 0.96,
+ "grad_norm": 1.228461742401123,
+ "learning_rate": 9.781523779815179e-05,
+ "loss": 0.1525,
+ "step": 1040
+ },
+ {
+ "epoch": 0.97,
+ "grad_norm": 0.8237024545669556,
+ "learning_rate": 9.777251182095011e-05,
+ "loss": 0.1599,
+ "step": 1050
+ },
+ {
+ "epoch": 0.97,
+ "eval_loss": 0.1465296447277069,
+ "eval_runtime": 36.3321,
+ "eval_samples_per_second": 126.059,
+ "eval_steps_per_second": 5.257,
+ "step": 1050
+ },
+ {
+ "epoch": 0.98,
+ "grad_norm": 0.5836882591247559,
+ "learning_rate": 9.77293816123866e-05,
+ "loss": 0.1601,
+ "step": 1060
+ },
+ {
+ "epoch": 0.99,
+ "grad_norm": 0.9502392411231995,
+ "learning_rate": 9.768584753741134e-05,
+ "loss": 0.159,
+ "step": 1070
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 0.8163331151008606,
+ "learning_rate": 9.764190996439181e-05,
+ "loss": 0.1444,
+ "step": 1080
+ },
+ {
+ "epoch": 1.01,
+ "grad_norm": 1.476738452911377,
+ "learning_rate": 9.759756926510965e-05,
+ "loss": 0.1205,
+ "step": 1090
+ },
+ {
+ "epoch": 1.02,
+ "grad_norm": 1.338589072227478,
+ "learning_rate": 9.755282581475769e-05,
+ "loss": 0.0977,
+ "step": 1100
+ },
+ {
+ "epoch": 1.02,
+ "eval_loss": 0.15202057361602783,
+ "eval_runtime": 36.2683,
+ "eval_samples_per_second": 126.281,
+ "eval_steps_per_second": 5.266,
+ "step": 1100
+ },
+ {
+ "epoch": 1.03,
+ "grad_norm": 1.2897748947143555,
+ "learning_rate": 9.750767999193656e-05,
+ "loss": 0.1106,
+ "step": 1110
+ },
+ {
+ "epoch": 1.04,
+ "grad_norm": 0.640981912612915,
+ "learning_rate": 9.74621321786517e-05,
+ "loss": 0.0907,
+ "step": 1120
+ },
+ {
+ "epoch": 1.04,
+ "grad_norm": 1.5198509693145752,
+ "learning_rate": 9.741618276030997e-05,
+ "loss": 0.0832,
+ "step": 1130
+ },
+ {
+ "epoch": 1.05,
+ "grad_norm": 0.8561617136001587,
+ "learning_rate": 9.736983212571646e-05,
+ "loss": 0.1197,
+ "step": 1140
+ },
+ {
+ "epoch": 1.06,
+ "grad_norm": 0.8811647295951843,
+ "learning_rate": 9.732308066707122e-05,
+ "loss": 0.1166,
+ "step": 1150
+ },
+ {
+ "epoch": 1.06,
+ "eval_loss": 0.1403137743473053,
+ "eval_runtime": 36.2404,
+ "eval_samples_per_second": 126.378,
+ "eval_steps_per_second": 5.27,
+ "step": 1150
+ },
+ {
+ "epoch": 1.07,
+ "grad_norm": 1.1139312982559204,
+ "learning_rate": 9.727592877996585e-05,
+ "loss": 0.1138,
+ "step": 1160
+ },
+ {
+ "epoch": 1.08,
+ "grad_norm": 0.8331150412559509,
+ "learning_rate": 9.722837686338025e-05,
+ "loss": 0.1159,
+ "step": 1170
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 0.8520072102546692,
+ "learning_rate": 9.718042531967918e-05,
+ "loss": 0.0983,
+ "step": 1180
+ },
+ {
+ "epoch": 1.1,
+ "grad_norm": 0.5743900537490845,
+ "learning_rate": 9.713207455460894e-05,
+ "loss": 0.0913,
+ "step": 1190
+ },
+ {
+ "epoch": 1.11,
+ "grad_norm": 1.1309562921524048,
+ "learning_rate": 9.708332497729378e-05,
+ "loss": 0.0943,
+ "step": 1200
+ },
+ {
+ "epoch": 1.11,
+ "eval_loss": 0.13866838812828064,
+ "eval_runtime": 36.2659,
+ "eval_samples_per_second": 126.289,
+ "eval_steps_per_second": 5.267,
+ "step": 1200
+ },
+ {
+ "epoch": 1.12,
+ "grad_norm": 0.8129335045814514,
+ "learning_rate": 9.70341770002326e-05,
+ "loss": 0.0999,
+ "step": 1210
+ },
+ {
+ "epoch": 1.13,
+ "grad_norm": 1.7836413383483887,
+ "learning_rate": 9.698463103929542e-05,
+ "loss": 0.0914,
+ "step": 1220
+ },
+ {
+ "epoch": 1.14,
+ "grad_norm": 1.3467488288879395,
+ "learning_rate": 9.693468751371977e-05,
+ "loss": 0.0938,
+ "step": 1230
+ },
+ {
+ "epoch": 1.15,
+ "grad_norm": 0.7247940897941589,
+ "learning_rate": 9.688434684610726e-05,
+ "loss": 0.1101,
+ "step": 1240
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 0.9462648034095764,
+ "learning_rate": 9.683360946241989e-05,
+ "loss": 0.1007,
+ "step": 1250
+ },
+ {
+ "epoch": 1.16,
+ "eval_loss": 0.13109833002090454,
+ "eval_runtime": 36.3278,
+ "eval_samples_per_second": 126.074,
+ "eval_steps_per_second": 5.258,
+ "step": 1250
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 0.9187774062156677,
+ "learning_rate": 9.678247579197657e-05,
+ "loss": 0.1057,
+ "step": 1260
+ },
+ {
+ "epoch": 1.17,
+ "grad_norm": 1.120918869972229,
+ "learning_rate": 9.673094626744942e-05,
+ "loss": 0.0865,
+ "step": 1270
+ },
+ {
+ "epoch": 1.18,
+ "grad_norm": 1.1514744758605957,
+ "learning_rate": 9.667902132486009e-05,
+ "loss": 0.1077,
+ "step": 1280
+ },
+ {
+ "epoch": 1.19,
+ "grad_norm": 1.6133332252502441,
+ "learning_rate": 9.662670140357611e-05,
+ "loss": 0.0923,
+ "step": 1290
+ },
+ {
+ "epoch": 1.2,
+ "grad_norm": 0.9612036943435669,
+ "learning_rate": 9.657398694630712e-05,
+ "loss": 0.1035,
+ "step": 1300
+ },
+ {
+ "epoch": 1.2,
+ "eval_loss": 0.13247531652450562,
+ "eval_runtime": 36.3269,
+ "eval_samples_per_second": 126.077,
+ "eval_steps_per_second": 5.258,
+ "step": 1300
+ },
+ {
+ "epoch": 1.21,
+ "grad_norm": 2.6024136543273926,
+ "learning_rate": 9.652087839910124e-05,
+ "loss": 0.0803,
+ "step": 1310
+ },
+ {
+ "epoch": 1.22,
+ "grad_norm": 0.8841276168823242,
+ "learning_rate": 9.646737621134112e-05,
+ "loss": 0.0814,
+ "step": 1320
+ },
+ {
+ "epoch": 1.23,
+ "grad_norm": 0.7463160753250122,
+ "learning_rate": 9.641348083574034e-05,
+ "loss": 0.0976,
+ "step": 1330
+ },
+ {
+ "epoch": 1.24,
+ "grad_norm": 0.6614356637001038,
+ "learning_rate": 9.635919272833938e-05,
+ "loss": 0.1047,
+ "step": 1340
+ },
+ {
+ "epoch": 1.25,
+ "grad_norm": 0.8464844822883606,
+ "learning_rate": 9.63045123485019e-05,
+ "loss": 0.0842,
+ "step": 1350
+ },
+ {
+ "epoch": 1.25,
+ "eval_loss": 0.13089965283870697,
+ "eval_runtime": 36.2144,
+ "eval_samples_per_second": 126.469,
+ "eval_steps_per_second": 5.274,
+ "step": 1350
+ },
+ {
+ "epoch": 1.26,
+ "grad_norm": 1.1737573146820068,
+ "learning_rate": 9.62494401589108e-05,
+ "loss": 0.0631,
+ "step": 1360
+ },
+ {
+ "epoch": 1.27,
+ "grad_norm": 1.0628595352172852,
+ "learning_rate": 9.619397662556435e-05,
+ "loss": 0.0967,
+ "step": 1370
+ },
+ {
+ "epoch": 1.28,
+ "grad_norm": 0.6741960644721985,
+ "learning_rate": 9.613812221777212e-05,
+ "loss": 0.0727,
+ "step": 1380
+ },
+ {
+ "epoch": 1.28,
+ "grad_norm": 1.3467893600463867,
+ "learning_rate": 9.60818774081512e-05,
+ "loss": 0.0832,
+ "step": 1390
+ },
+ {
+ "epoch": 1.29,
+ "grad_norm": 0.5382059216499329,
+ "learning_rate": 9.602524267262203e-05,
+ "loss": 0.1114,
+ "step": 1400
+ },
+ {
+ "epoch": 1.29,
+ "eval_loss": 0.12248954176902771,
+ "eval_runtime": 36.2887,
+ "eval_samples_per_second": 126.21,
+ "eval_steps_per_second": 5.263,
+ "step": 1400
+ },
+ {
+ "epoch": 1.3,
+ "grad_norm": 1.2735854387283325,
+ "learning_rate": 9.596821849040447e-05,
+ "loss": 0.0997,
+ "step": 1410
+ },
+ {
+ "epoch": 1.31,
+ "grad_norm": 0.711742103099823,
+ "learning_rate": 9.591080534401371e-05,
+ "loss": 0.0917,
+ "step": 1420
+ },
+ {
+ "epoch": 1.32,
+ "grad_norm": 1.2457355260849,
+ "learning_rate": 9.58530037192562e-05,
+ "loss": 0.1039,
+ "step": 1430
+ },
+ {
+ "epoch": 1.33,
+ "grad_norm": 0.5564578175544739,
+ "learning_rate": 9.579481410522556e-05,
+ "loss": 0.0957,
+ "step": 1440
+ },
+ {
+ "epoch": 1.34,
+ "grad_norm": 1.5276597738265991,
+ "learning_rate": 9.573623699429836e-05,
+ "loss": 0.1047,
+ "step": 1450
+ },
+ {
+ "epoch": 1.34,
+ "eval_loss": 0.11836496740579605,
+ "eval_runtime": 36.2545,
+ "eval_samples_per_second": 126.329,
+ "eval_steps_per_second": 5.268,
+ "step": 1450
+ },
+ {
+ "epoch": 1.35,
+ "grad_norm": 0.865064263343811,
+ "learning_rate": 9.567727288213005e-05,
+ "loss": 0.0957,
+ "step": 1460
+ },
+ {
+ "epoch": 1.36,
+ "grad_norm": 0.6668936014175415,
+ "learning_rate": 9.561792226765072e-05,
+ "loss": 0.0973,
+ "step": 1470
+ },
+ {
+ "epoch": 1.37,
+ "grad_norm": 1.2213976383209229,
+ "learning_rate": 9.555818565306085e-05,
+ "loss": 0.0887,
+ "step": 1480
+ },
+ {
+ "epoch": 1.38,
+ "grad_norm": 0.7778081893920898,
+ "learning_rate": 9.549806354382717e-05,
+ "loss": 0.094,
+ "step": 1490
+ },
+ {
+ "epoch": 1.39,
+ "grad_norm": 0.8432282209396362,
+ "learning_rate": 9.543755644867822e-05,
+ "loss": 0.0807,
+ "step": 1500
+ },
+ {
+ "epoch": 1.39,
+ "eval_loss": 0.11355672031641006,
+ "eval_runtime": 36.2261,
+ "eval_samples_per_second": 126.428,
+ "eval_steps_per_second": 5.272,
+ "step": 1500
+ },
+ {
+ "epoch": 1.4,
+ "grad_norm": 0.9765787124633789,
+ "learning_rate": 9.537666487960019e-05,
+ "loss": 0.0829,
+ "step": 1510
+ },
+ {
+ "epoch": 1.4,
+ "grad_norm": 0.8252067565917969,
+ "learning_rate": 9.53153893518325e-05,
+ "loss": 0.0749,
+ "step": 1520
+ },
+ {
+ "epoch": 1.41,
+ "grad_norm": 1.0041134357452393,
+ "learning_rate": 9.52537303838635e-05,
+ "loss": 0.0647,
+ "step": 1530
+ },
+ {
+ "epoch": 1.42,
+ "grad_norm": 1.365193486213684,
+ "learning_rate": 9.519168849742604e-05,
+ "loss": 0.0713,
+ "step": 1540
+ },
+ {
+ "epoch": 1.43,
+ "grad_norm": 0.8681650161743164,
+ "learning_rate": 9.512926421749304e-05,
+ "loss": 0.0846,
+ "step": 1550
+ },
+ {
+ "epoch": 1.43,
+ "eval_loss": 0.12000197172164917,
+ "eval_runtime": 36.2616,
+ "eval_samples_per_second": 126.304,
+ "eval_steps_per_second": 5.267,
+ "step": 1550
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 0.7004525661468506,
+ "learning_rate": 9.506645807227311e-05,
+ "loss": 0.0724,
+ "step": 1560
+ },
+ {
+ "epoch": 1.45,
+ "grad_norm": 1.3950064182281494,
+ "learning_rate": 9.500327059320606e-05,
+ "loss": 0.0851,
+ "step": 1570
+ },
+ {
+ "epoch": 1.46,
+ "grad_norm": 1.4275237321853638,
+ "learning_rate": 9.493970231495835e-05,
+ "loss": 0.0984,
+ "step": 1580
+ },
+ {
+ "epoch": 1.47,
+ "grad_norm": 0.5745067596435547,
+ "learning_rate": 9.487575377541864e-05,
+ "loss": 0.0584,
+ "step": 1590
+ },
+ {
+ "epoch": 1.48,
+ "grad_norm": 1.4414701461791992,
+ "learning_rate": 9.481142551569318e-05,
+ "loss": 0.0737,
+ "step": 1600
+ },
+ {
+ "epoch": 1.48,
+ "eval_loss": 0.11450409889221191,
+ "eval_runtime": 36.2542,
+ "eval_samples_per_second": 126.33,
+ "eval_steps_per_second": 5.268,
+ "step": 1600
+ },
+ {
+ "epoch": 1.49,
+ "grad_norm": 0.9620345830917358,
+ "learning_rate": 9.474671808010126e-05,
+ "loss": 0.0962,
+ "step": 1610
+ },
+ {
+ "epoch": 1.5,
+ "grad_norm": 0.7017752528190613,
+ "learning_rate": 9.468163201617062e-05,
+ "loss": 0.0739,
+ "step": 1620
+ },
+ {
+ "epoch": 1.51,
+ "grad_norm": 0.8450036644935608,
+ "learning_rate": 9.461616787463278e-05,
+ "loss": 0.089,
+ "step": 1630
+ },
+ {
+ "epoch": 1.52,
+ "grad_norm": 1.1829959154129028,
+ "learning_rate": 9.45503262094184e-05,
+ "loss": 0.0914,
+ "step": 1640
+ },
+ {
+ "epoch": 1.52,
+ "grad_norm": 1.1722110509872437,
+ "learning_rate": 9.44841075776526e-05,
+ "loss": 0.0844,
+ "step": 1650
+ },
+ {
+ "epoch": 1.52,
+ "eval_loss": 0.1037188321352005,
+ "eval_runtime": 36.2499,
+ "eval_samples_per_second": 126.345,
+ "eval_steps_per_second": 5.269,
+ "step": 1650
+ },
+ {
+ "epoch": 1.53,
+ "grad_norm": 1.0115782022476196,
+ "learning_rate": 9.441751253965021e-05,
+ "loss": 0.0968,
+ "step": 1660
+ },
+ {
+ "epoch": 1.54,
+ "grad_norm": 0.6493613123893738,
+ "learning_rate": 9.435054165891109e-05,
+ "loss": 0.097,
+ "step": 1670
+ },
+ {
+ "epoch": 1.55,
+ "grad_norm": 0.8181868195533752,
+ "learning_rate": 9.42831955021153e-05,
+ "loss": 0.0699,
+ "step": 1680
+ },
+ {
+ "epoch": 1.56,
+ "grad_norm": 1.694252610206604,
+ "learning_rate": 9.421547463911835e-05,
+ "loss": 0.0781,
+ "step": 1690
+ },
+ {
+ "epoch": 1.57,
+ "grad_norm": 0.6897493600845337,
+ "learning_rate": 9.414737964294636e-05,
+ "loss": 0.0809,
+ "step": 1700
+ },
+ {
+ "epoch": 1.57,
+ "eval_loss": 0.09402556717395782,
+ "eval_runtime": 36.2393,
+ "eval_samples_per_second": 126.382,
+ "eval_steps_per_second": 5.271,
+ "step": 1700
+ },
+ {
+ "epoch": 1.58,
+ "grad_norm": 0.8747942447662354,
+ "learning_rate": 9.407891108979117e-05,
+ "loss": 0.0897,
+ "step": 1710
+ },
+ {
+ "epoch": 1.59,
+ "grad_norm": 1.006194829940796,
+ "learning_rate": 9.401006955900556e-05,
+ "loss": 0.0629,
+ "step": 1720
+ },
+ {
+ "epoch": 1.6,
+ "grad_norm": 0.4138026833534241,
+ "learning_rate": 9.394085563309827e-05,
+ "loss": 0.0671,
+ "step": 1730
+ },
+ {
+ "epoch": 1.61,
+ "grad_norm": 0.368488073348999,
+ "learning_rate": 9.38712698977291e-05,
+ "loss": 0.0736,
+ "step": 1740
+ },
+ {
+ "epoch": 1.62,
+ "grad_norm": 1.2116315364837646,
+ "learning_rate": 9.380131294170393e-05,
+ "loss": 0.0718,
+ "step": 1750
+ },
+ {
+ "epoch": 1.62,
+ "eval_loss": 0.093104287981987,
+ "eval_runtime": 36.3088,
+ "eval_samples_per_second": 126.14,
+ "eval_steps_per_second": 5.26,
+ "step": 1750
+ },
+ {
+ "epoch": 1.63,
+ "grad_norm": 0.5739853382110596,
+ "learning_rate": 9.373098535696979e-05,
+ "loss": 0.0644,
+ "step": 1760
+ },
+ {
+ "epoch": 1.64,
+ "grad_norm": 1.4135103225708008,
+ "learning_rate": 9.36602877386098e-05,
+ "loss": 0.0798,
+ "step": 1770
+ },
+ {
+ "epoch": 1.65,
+ "grad_norm": 1.0814074277877808,
+ "learning_rate": 9.358922068483812e-05,
+ "loss": 0.0717,
+ "step": 1780
+ },
+ {
+ "epoch": 1.65,
+ "grad_norm": 1.103225827217102,
+ "learning_rate": 9.351778479699499e-05,
+ "loss": 0.1072,
+ "step": 1790
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 0.9320874810218811,
+ "learning_rate": 9.344598067954152e-05,
+ "loss": 0.0687,
+ "step": 1800
+ },
+ {
+ "epoch": 1.66,
+ "eval_loss": 0.09301283955574036,
+ "eval_runtime": 36.2388,
+ "eval_samples_per_second": 126.384,
+ "eval_steps_per_second": 5.271,
+ "step": 1800
+ },
+ {
+ "epoch": 1.67,
+ "grad_norm": 0.9495887756347656,
+ "learning_rate": 9.337380894005463e-05,
+ "loss": 0.0611,
+ "step": 1810
+ },
+ {
+ "epoch": 1.68,
+ "grad_norm": 1.7665095329284668,
+ "learning_rate": 9.330127018922194e-05,
+ "loss": 0.0827,
+ "step": 1820
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 1.620908260345459,
+ "learning_rate": 9.322836504083654e-05,
+ "loss": 0.0693,
+ "step": 1830
+ },
+ {
+ "epoch": 1.7,
+ "grad_norm": 1.30322265625,
+ "learning_rate": 9.315509411179182e-05,
+ "loss": 0.058,
+ "step": 1840
+ },
+ {
+ "epoch": 1.71,
+ "grad_norm": 1.101680874824524,
+ "learning_rate": 9.308145802207629e-05,
+ "loss": 0.0629,
+ "step": 1850
+ },
+ {
+ "epoch": 1.71,
+ "eval_loss": 0.09685970097780228,
+ "eval_runtime": 36.2607,
+ "eval_samples_per_second": 126.307,
+ "eval_steps_per_second": 5.267,
+ "step": 1850
+ },
+ {
+ "epoch": 1.72,
+ "grad_norm": 0.38865023851394653,
+ "learning_rate": 9.300745739476829e-05,
+ "loss": 0.0717,
+ "step": 1860
+ },
+ {
+ "epoch": 1.73,
+ "grad_norm": 0.38753578066825867,
+ "learning_rate": 9.293309285603067e-05,
+ "loss": 0.0679,
+ "step": 1870
+ },
+ {
+ "epoch": 1.74,
+ "grad_norm": 1.5182372331619263,
+ "learning_rate": 9.285836503510562e-05,
+ "loss": 0.07,
+ "step": 1880
+ },
+ {
+ "epoch": 1.75,
+ "grad_norm": 1.267052412033081,
+ "learning_rate": 9.278327456430926e-05,
+ "loss": 0.0824,
+ "step": 1890
+ },
+ {
+ "epoch": 1.76,
+ "grad_norm": 1.3264389038085938,
+ "learning_rate": 9.270782207902629e-05,
+ "loss": 0.0852,
+ "step": 1900
+ },
+ {
+ "epoch": 1.76,
+ "eval_loss": 0.0872357115149498,
+ "eval_runtime": 36.2529,
+ "eval_samples_per_second": 126.335,
+ "eval_steps_per_second": 5.269,
+ "step": 1900
+ },
+ {
+ "epoch": 1.77,
+ "grad_norm": 0.5945495367050171,
+ "learning_rate": 9.263200821770461e-05,
+ "loss": 0.0749,
+ "step": 1910
+ },
+ {
+ "epoch": 1.77,
+ "grad_norm": 0.628018856048584,
+ "learning_rate": 9.255583362184999e-05,
+ "loss": 0.058,
+ "step": 1920
+ },
+ {
+ "epoch": 1.78,
+ "grad_norm": 1.6209118366241455,
+ "learning_rate": 9.247929893602054e-05,
+ "loss": 0.07,
+ "step": 1930
+ },
+ {
+ "epoch": 1.79,
+ "grad_norm": 0.5279895067214966,
+ "learning_rate": 9.24024048078213e-05,
+ "loss": 0.0638,
+ "step": 1940
+ },
+ {
+ "epoch": 1.8,
+ "grad_norm": 0.5834373831748962,
+ "learning_rate": 9.23251518878988e-05,
+ "loss": 0.0622,
+ "step": 1950
+ },
+ {
+ "epoch": 1.8,
+ "eval_loss": 0.08488291501998901,
+ "eval_runtime": 36.2558,
+ "eval_samples_per_second": 126.325,
+ "eval_steps_per_second": 5.268,
+ "step": 1950
+ },
+ {
+ "epoch": 1.81,
+ "grad_norm": 0.8667528033256531,
+ "learning_rate": 9.224754082993552e-05,
+ "loss": 0.0592,
+ "step": 1960
+ },
+ {
+ "epoch": 1.82,
+ "grad_norm": 0.9160845875740051,
+ "learning_rate": 9.21695722906443e-05,
+ "loss": 0.0709,
+ "step": 1970
+ },
+ {
+ "epoch": 1.83,
+ "grad_norm": 0.7025119662284851,
+ "learning_rate": 9.209124692976287e-05,
+ "loss": 0.0657,
+ "step": 1980
+ },
+ {
+ "epoch": 1.84,
+ "grad_norm": 1.0089232921600342,
+ "learning_rate": 9.201256541004829e-05,
+ "loss": 0.0644,
+ "step": 1990
+ },
+ {
+ "epoch": 1.85,
+ "grad_norm": 1.1696964502334595,
+ "learning_rate": 9.193352839727121e-05,
+ "loss": 0.0653,
+ "step": 2000
+ },
+ {
+ "epoch": 1.85,
+ "eval_loss": 0.08305433392524719,
+ "eval_runtime": 36.2595,
+ "eval_samples_per_second": 126.312,
+ "eval_steps_per_second": 5.268,
+ "step": 2000
+ },
+ {
+ "epoch": 1.86,
+ "grad_norm": 1.57039475440979,
+ "learning_rate": 9.185413656021036e-05,
+ "loss": 0.0752,
+ "step": 2010
+ },
+ {
+ "epoch": 1.87,
+ "grad_norm": 0.7407552599906921,
+ "learning_rate": 9.177439057064683e-05,
+ "loss": 0.0502,
+ "step": 2020
+ },
+ {
+ "epoch": 1.88,
+ "grad_norm": 1.2944762706756592,
+ "learning_rate": 9.169429110335841e-05,
+ "loss": 0.0717,
+ "step": 2030
+ },
+ {
+ "epoch": 1.89,
+ "grad_norm": 0.46426939964294434,
+ "learning_rate": 9.16138388361139e-05,
+ "loss": 0.0577,
+ "step": 2040
+ },
+ {
+ "epoch": 1.89,
+ "grad_norm": 0.3882431387901306,
+ "learning_rate": 9.153303444966727e-05,
+ "loss": 0.0507,
+ "step": 2050
+ },
+ {
+ "epoch": 1.89,
+ "eval_loss": 0.08292171359062195,
+ "eval_runtime": 36.2518,
+ "eval_samples_per_second": 126.339,
+ "eval_steps_per_second": 5.269,
+ "step": 2050
+ },
+ {
+ "epoch": 1.9,
+ "grad_norm": 0.5372634530067444,
+ "learning_rate": 9.145187862775209e-05,
+ "loss": 0.0632,
+ "step": 2060
+ },
+ {
+ "epoch": 1.91,
+ "grad_norm": 0.5599855780601501,
+ "learning_rate": 9.137037205707552e-05,
+ "loss": 0.0637,
+ "step": 2070
+ },
+ {
+ "epoch": 1.92,
+ "grad_norm": 0.7405185699462891,
+ "learning_rate": 9.128851542731271e-05,
+ "loss": 0.0462,
+ "step": 2080
+ },
+ {
+ "epoch": 1.93,
+ "grad_norm": 0.6935983896255493,
+ "learning_rate": 9.120630943110077e-05,
+ "loss": 0.0665,
+ "step": 2090
+ },
+ {
+ "epoch": 1.94,
+ "grad_norm": 0.5483436584472656,
+ "learning_rate": 9.112375476403312e-05,
+ "loss": 0.0518,
+ "step": 2100
+ },
+ {
+ "epoch": 1.94,
+ "eval_loss": 0.07847684621810913,
+ "eval_runtime": 36.2617,
+ "eval_samples_per_second": 126.304,
+ "eval_steps_per_second": 5.267,
+ "step": 2100
+ },
+ {
+ "epoch": 1.95,
+ "grad_norm": 0.6139508485794067,
+ "learning_rate": 9.104085212465336e-05,
+ "loss": 0.0523,
+ "step": 2110
+ },
+ {
+ "epoch": 1.96,
+ "grad_norm": 1.0022165775299072,
+ "learning_rate": 9.09576022144496e-05,
+ "loss": 0.0485,
+ "step": 2120
+ },
+ {
+ "epoch": 1.97,
+ "grad_norm": 1.1758086681365967,
+ "learning_rate": 9.087400573784833e-05,
+ "loss": 0.0613,
+ "step": 2130
+ },
+ {
+ "epoch": 1.98,
+ "grad_norm": 0.446209579706192,
+ "learning_rate": 9.079006340220862e-05,
+ "loss": 0.0652,
+ "step": 2140
+ },
+ {
+ "epoch": 1.99,
+ "grad_norm": 0.8512327075004578,
+ "learning_rate": 9.070577591781597e-05,
+ "loss": 0.0566,
+ "step": 2150
+ },
+ {
+ "epoch": 1.99,
+ "eval_loss": 0.07502878457307816,
+ "eval_runtime": 36.2465,
+ "eval_samples_per_second": 126.357,
+ "eval_steps_per_second": 5.269,
+ "step": 2150
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 1.0540813207626343,
+ "learning_rate": 9.062114399787647e-05,
+ "loss": 0.0703,
+ "step": 2160
+ },
+ {
+ "epoch": 2.01,
+ "grad_norm": 0.3436621129512787,
+ "learning_rate": 9.053616835851062e-05,
+ "loss": 0.0327,
+ "step": 2170
+ },
+ {
+ "epoch": 2.01,
+ "grad_norm": 0.8479847311973572,
+ "learning_rate": 9.045084971874738e-05,
+ "loss": 0.0259,
+ "step": 2180
+ },
+ {
+ "epoch": 2.02,
+ "grad_norm": 1.2036502361297607,
+ "learning_rate": 9.0365188800518e-05,
+ "loss": 0.0167,
+ "step": 2190
+ },
+ {
+ "epoch": 2.03,
+ "grad_norm": 0.8509168028831482,
+ "learning_rate": 9.027918632864997e-05,
+ "loss": 0.0193,
+ "step": 2200
+ },
+ {
+ "epoch": 2.03,
+ "eval_loss": 0.08374720066785812,
+ "eval_runtime": 36.2475,
+ "eval_samples_per_second": 126.354,
+ "eval_steps_per_second": 5.269,
+ "step": 2200
+ },
+ {
+ "epoch": 2.04,
+ "grad_norm": 0.3606647253036499,
+ "learning_rate": 9.019284303086087e-05,
+ "loss": 0.0206,
+ "step": 2210
+ },
+ {
+ "epoch": 2.05,
+ "grad_norm": 0.7698445320129395,
+ "learning_rate": 9.01061596377522e-05,
+ "loss": 0.0235,
+ "step": 2220
+ },
+ {
+ "epoch": 2.06,
+ "grad_norm": 1.9076602458953857,
+ "learning_rate": 9.00191368828032e-05,
+ "loss": 0.0177,
+ "step": 2230
+ },
+ {
+ "epoch": 2.07,
+ "grad_norm": 0.8590715527534485,
+ "learning_rate": 8.993177550236464e-05,
+ "loss": 0.0274,
+ "step": 2240
+ },
+ {
+ "epoch": 2.08,
+ "grad_norm": 0.1819429099559784,
+ "learning_rate": 8.984407623565267e-05,
+ "loss": 0.0233,
+ "step": 2250
+ },
+ {
+ "epoch": 2.08,
+ "eval_loss": 0.07661169022321701,
+ "eval_runtime": 36.2416,
+ "eval_samples_per_second": 126.374,
+ "eval_steps_per_second": 5.27,
+ "step": 2250
+ },
+ {
+ "epoch": 2.09,
+ "grad_norm": 0.24359861016273499,
+ "learning_rate": 8.97560398247424e-05,
+ "loss": 0.016,
+ "step": 2260
+ },
+ {
+ "epoch": 2.1,
+ "grad_norm": 0.6506161093711853,
+ "learning_rate": 8.966766701456177e-05,
+ "loss": 0.0123,
+ "step": 2270
+ },
+ {
+ "epoch": 2.11,
+ "grad_norm": 0.2782149314880371,
+ "learning_rate": 8.957895855288517e-05,
+ "loss": 0.0235,
+ "step": 2280
+ },
+ {
+ "epoch": 2.12,
+ "grad_norm": 1.4327374696731567,
+ "learning_rate": 8.948991519032716e-05,
+ "loss": 0.0209,
+ "step": 2290
+ },
+ {
+ "epoch": 2.13,
+ "grad_norm": 0.47919216752052307,
+ "learning_rate": 8.940053768033609e-05,
+ "loss": 0.0249,
+ "step": 2300
+ },
+ {
+ "epoch": 2.13,
+ "eval_loss": 0.08285840600728989,
+ "eval_runtime": 36.2486,
+ "eval_samples_per_second": 126.35,
+ "eval_steps_per_second": 5.269,
+ "step": 2300
+ },
+ {
+ "epoch": 2.13,
+ "grad_norm": 0.22004464268684387,
+ "learning_rate": 8.931082677918771e-05,
+ "loss": 0.0164,
+ "step": 2310
+ },
+ {
+ "epoch": 2.14,
+ "grad_norm": 0.05589359253644943,
+ "learning_rate": 8.922078324597879e-05,
+ "loss": 0.0253,
+ "step": 2320
+ },
+ {
+ "epoch": 2.15,
+ "grad_norm": 0.48298755288124084,
+ "learning_rate": 8.91304078426207e-05,
+ "loss": 0.0266,
+ "step": 2330
+ },
+ {
+ "epoch": 2.16,
+ "grad_norm": 0.6790844202041626,
+ "learning_rate": 8.903970133383297e-05,
+ "loss": 0.0191,
+ "step": 2340
+ },
+ {
+ "epoch": 2.17,
+ "grad_norm": 1.900855302810669,
+ "learning_rate": 8.894866448713679e-05,
+ "loss": 0.0217,
+ "step": 2350
+ },
+ {
+ "epoch": 2.17,
+ "eval_loss": 0.0823688879609108,
+ "eval_runtime": 36.277,
+ "eval_samples_per_second": 126.251,
+ "eval_steps_per_second": 5.265,
+ "step": 2350
+ },
+ {
+ "epoch": 2.18,
+ "grad_norm": 0.5196428298950195,
+ "learning_rate": 8.885729807284856e-05,
+ "loss": 0.0408,
+ "step": 2360
+ },
+ {
+ "epoch": 2.19,
+ "grad_norm": 1.6319361925125122,
+ "learning_rate": 8.87656028640733e-05,
+ "loss": 0.0335,
+ "step": 2370
+ },
+ {
+ "epoch": 2.2,
+ "grad_norm": 1.4224486351013184,
+ "learning_rate": 8.86735796366982e-05,
+ "loss": 0.0189,
+ "step": 2380
+ },
+ {
+ "epoch": 2.21,
+ "grad_norm": 0.8939641118049622,
+ "learning_rate": 8.858122916938601e-05,
+ "loss": 0.0255,
+ "step": 2390
+ },
+ {
+ "epoch": 2.22,
+ "grad_norm": 0.9012664556503296,
+ "learning_rate": 8.848855224356839e-05,
+ "loss": 0.0233,
+ "step": 2400
+ },
+ {
+ "epoch": 2.22,
+ "eval_loss": 0.07353760302066803,
+ "eval_runtime": 36.2483,
+ "eval_samples_per_second": 126.351,
+ "eval_steps_per_second": 5.269,
+ "step": 2400
+ },
+ {
+ "epoch": 2.23,
+ "grad_norm": 0.5575871467590332,
+ "learning_rate": 8.839554964343943e-05,
+ "loss": 0.0151,
+ "step": 2410
+ },
+ {
+ "epoch": 2.24,
+ "grad_norm": 0.34087488055229187,
+ "learning_rate": 8.83022221559489e-05,
+ "loss": 0.0178,
+ "step": 2420
+ },
+ {
+ "epoch": 2.25,
+ "grad_norm": 1.2612468004226685,
+ "learning_rate": 8.820857057079565e-05,
+ "loss": 0.0378,
+ "step": 2430
+ },
+ {
+ "epoch": 2.26,
+ "grad_norm": 0.8768627047538757,
+ "learning_rate": 8.811459568042091e-05,
+ "loss": 0.0273,
+ "step": 2440
+ },
+ {
+ "epoch": 2.26,
+ "grad_norm": 0.3403642475605011,
+ "learning_rate": 8.802029828000156e-05,
+ "loss": 0.0192,
+ "step": 2450
+ },
+ {
+ "epoch": 2.26,
+ "eval_loss": 0.07672559469938278,
+ "eval_runtime": 36.2454,
+ "eval_samples_per_second": 126.361,
+ "eval_steps_per_second": 5.27,
+ "step": 2450
+ },
+ {
+ "epoch": 2.27,
+ "grad_norm": 1.5420982837677002,
+ "learning_rate": 8.792567916744346e-05,
+ "loss": 0.0218,
+ "step": 2460
+ },
+ {
+ "epoch": 2.28,
+ "grad_norm": 0.20853710174560547,
+ "learning_rate": 8.783073914337466e-05,
+ "loss": 0.025,
+ "step": 2470
+ },
+ {
+ "epoch": 2.29,
+ "grad_norm": 1.2193341255187988,
+ "learning_rate": 8.773547901113862e-05,
+ "loss": 0.0328,
+ "step": 2480
+ },
+ {
+ "epoch": 2.3,
+ "grad_norm": 0.2289753556251526,
+ "learning_rate": 8.763989957678742e-05,
+ "loss": 0.0135,
+ "step": 2490
+ },
+ {
+ "epoch": 2.31,
+ "grad_norm": 1.0940682888031006,
+ "learning_rate": 8.754400164907497e-05,
+ "loss": 0.0207,
+ "step": 2500
+ },
+ {
+ "epoch": 2.31,
+ "eval_loss": 0.07941900193691254,
+ "eval_runtime": 36.2618,
+ "eval_samples_per_second": 126.304,
+ "eval_steps_per_second": 5.267,
+ "step": 2500
+ },
+ {
+ "epoch": 2.32,
+ "grad_norm": 0.9183884263038635,
+ "learning_rate": 8.744778603945011e-05,
+ "loss": 0.0168,
+ "step": 2510
+ },
+ {
+ "epoch": 2.33,
+ "grad_norm": 0.989913821220398,
+ "learning_rate": 8.73512535620498e-05,
+ "loss": 0.0254,
+ "step": 2520
+ },
+ {
+ "epoch": 2.34,
+ "grad_norm": 0.21799927949905396,
+ "learning_rate": 8.72544050336922e-05,
+ "loss": 0.0244,
+ "step": 2530
+ },
+ {
+ "epoch": 2.35,
+ "grad_norm": 1.1213247776031494,
+ "learning_rate": 8.715724127386972e-05,
+ "loss": 0.0221,
+ "step": 2540
+ },
+ {
+ "epoch": 2.36,
+ "grad_norm": 0.7733873128890991,
+ "learning_rate": 8.705976310474219e-05,
+ "loss": 0.0232,
+ "step": 2550
+ },
+ {
+ "epoch": 2.36,
+ "eval_loss": 0.08428460359573364,
+ "eval_runtime": 36.263,
+ "eval_samples_per_second": 126.3,
+ "eval_steps_per_second": 5.267,
+ "step": 2550
+ },
+ {
+ "epoch": 2.37,
+ "grad_norm": 0.16892109811306,
+ "learning_rate": 8.69619713511298e-05,
+ "loss": 0.0182,
+ "step": 2560
+ },
+ {
+ "epoch": 2.38,
+ "grad_norm": 0.6578019261360168,
+ "learning_rate": 8.68638668405062e-05,
+ "loss": 0.0134,
+ "step": 2570
+ },
+ {
+ "epoch": 2.38,
+ "grad_norm": 0.4529229700565338,
+ "learning_rate": 8.676545040299145e-05,
+ "loss": 0.0217,
+ "step": 2580
+ },
+ {
+ "epoch": 2.39,
+ "grad_norm": 1.304081678390503,
+ "learning_rate": 8.666672287134494e-05,
+ "loss": 0.0178,
+ "step": 2590
+ },
+ {
+ "epoch": 2.4,
+ "grad_norm": 1.2332367897033691,
+ "learning_rate": 8.656768508095853e-05,
+ "loss": 0.0295,
+ "step": 2600
+ },
+ {
+ "epoch": 2.4,
+ "eval_loss": 0.08000972867012024,
+ "eval_runtime": 36.2546,
+ "eval_samples_per_second": 126.329,
+ "eval_steps_per_second": 5.268,
+ "step": 2600
+ },
+ {
+ "epoch": 2.41,
+ "grad_norm": 1.8248018026351929,
+ "learning_rate": 8.646833786984927e-05,
+ "loss": 0.0257,
+ "step": 2610
+ },
+ {
+ "epoch": 2.42,
+ "grad_norm": 1.0469847917556763,
+ "learning_rate": 8.636868207865244e-05,
+ "loss": 0.0365,
+ "step": 2620
+ },
+ {
+ "epoch": 2.43,
+ "grad_norm": 0.9816425442695618,
+ "learning_rate": 8.626871855061438e-05,
+ "loss": 0.0304,
+ "step": 2630
+ },
+ {
+ "epoch": 2.44,
+ "grad_norm": 0.3567699193954468,
+ "learning_rate": 8.61684481315854e-05,
+ "loss": 0.0266,
+ "step": 2640
+ },
+ {
+ "epoch": 2.45,
+ "grad_norm": 0.1593473106622696,
+ "learning_rate": 8.606787167001257e-05,
+ "loss": 0.0185,
+ "step": 2650
+ },
+ {
+ "epoch": 2.45,
+ "eval_loss": 0.07773510366678238,
+ "eval_runtime": 36.238,
+ "eval_samples_per_second": 126.387,
+ "eval_steps_per_second": 5.271,
+ "step": 2650
+ },
+ {
+ "epoch": 2.46,
+ "grad_norm": 1.622788906097412,
+ "learning_rate": 8.596699001693255e-05,
+ "loss": 0.0336,
+ "step": 2660
+ },
+ {
+ "epoch": 2.47,
+ "grad_norm": 1.3989499807357788,
+ "learning_rate": 8.586580402596446e-05,
+ "loss": 0.0231,
+ "step": 2670
+ },
+ {
+ "epoch": 2.48,
+ "grad_norm": 0.629644513130188,
+ "learning_rate": 8.576431455330258e-05,
+ "loss": 0.017,
+ "step": 2680
+ },
+ {
+ "epoch": 2.49,
+ "grad_norm": 0.31903961300849915,
+ "learning_rate": 8.566252245770909e-05,
+ "loss": 0.02,
+ "step": 2690
+ },
+ {
+ "epoch": 2.5,
+ "grad_norm": 1.0299134254455566,
+ "learning_rate": 8.556042860050687e-05,
+ "loss": 0.0178,
+ "step": 2700
+ },
+ {
+ "epoch": 2.5,
+ "eval_loss": 0.07669008523225784,
+ "eval_runtime": 36.2452,
+ "eval_samples_per_second": 126.362,
+ "eval_steps_per_second": 5.27,
+ "step": 2700
+ },
+ {
+ "epoch": 2.5,
+ "grad_norm": 0.8042894005775452,
+ "learning_rate": 8.545803384557219e-05,
+ "loss": 0.0171,
+ "step": 2710
+ },
+ {
+ "epoch": 2.51,
+ "grad_norm": 0.5600835084915161,
+ "learning_rate": 8.535533905932738e-05,
+ "loss": 0.0248,
+ "step": 2720
+ },
+ {
+ "epoch": 2.52,
+ "grad_norm": 1.7625192403793335,
+ "learning_rate": 8.525234511073352e-05,
+ "loss": 0.0318,
+ "step": 2730
+ },
+ {
+ "epoch": 2.53,
+ "grad_norm": 0.7289332747459412,
+ "learning_rate": 8.51490528712831e-05,
+ "loss": 0.0123,
+ "step": 2740
+ },
+ {
+ "epoch": 2.54,
+ "grad_norm": 1.1776474714279175,
+ "learning_rate": 8.504546321499255e-05,
+ "loss": 0.0245,
+ "step": 2750
+ },
+ {
+ "epoch": 2.54,
+ "eval_loss": 0.07172290980815887,
+ "eval_runtime": 36.2485,
+ "eval_samples_per_second": 126.35,
+ "eval_steps_per_second": 5.269,
+ "step": 2750
+ },
+ {
+ "epoch": 2.55,
+ "grad_norm": 0.3856188952922821,
+ "learning_rate": 8.4941577018395e-05,
+ "loss": 0.0093,
+ "step": 2760
+ },
+ {
+ "epoch": 2.56,
+ "grad_norm": 0.5729599595069885,
+ "learning_rate": 8.483739516053276e-05,
+ "loss": 0.0177,
+ "step": 2770
+ },
+ {
+ "epoch": 2.57,
+ "grad_norm": 0.08334312587976456,
+ "learning_rate": 8.473291852294987e-05,
+ "loss": 0.0238,
+ "step": 2780
+ },
+ {
+ "epoch": 2.58,
+ "grad_norm": 0.7210456728935242,
+ "learning_rate": 8.462814798968472e-05,
+ "loss": 0.0132,
+ "step": 2790
+ },
+ {
+ "epoch": 2.59,
+ "grad_norm": 0.7902788519859314,
+ "learning_rate": 8.452308444726249e-05,
+ "loss": 0.0226,
+ "step": 2800
+ },
+ {
+ "epoch": 2.59,
+ "eval_loss": 0.0774235799908638,
+ "eval_runtime": 36.2636,
+ "eval_samples_per_second": 126.298,
+ "eval_steps_per_second": 5.267,
+ "step": 2800
+ },
+ {
+ "epoch": 2.6,
+ "grad_norm": 0.369211882352829,
+ "learning_rate": 8.44177287846877e-05,
+ "loss": 0.03,
+ "step": 2810
+ },
+ {
+ "epoch": 2.61,
+ "grad_norm": 0.7902100682258606,
+ "learning_rate": 8.43120818934367e-05,
+ "loss": 0.0269,
+ "step": 2820
+ },
+ {
+ "epoch": 2.62,
+ "grad_norm": 0.9871087074279785,
+ "learning_rate": 8.420614466745e-05,
+ "loss": 0.0178,
+ "step": 2830
+ },
+ {
+ "epoch": 2.62,
+ "grad_norm": 0.5393310189247131,
+ "learning_rate": 8.409991800312493e-05,
+ "loss": 0.0189,
+ "step": 2840
+ },
+ {
+ "epoch": 2.63,
+ "grad_norm": 0.3893219828605652,
+ "learning_rate": 8.399340279930786e-05,
+ "loss": 0.0222,
+ "step": 2850
+ },
+ {
+ "epoch": 2.63,
+ "eval_loss": 0.0670793429017067,
+ "eval_runtime": 36.2663,
+ "eval_samples_per_second": 126.288,
+ "eval_steps_per_second": 5.267,
+ "step": 2850
+ },
+ {
+ "epoch": 2.64,
+ "grad_norm": 0.6049796342849731,
+ "learning_rate": 8.388659995728663e-05,
+ "loss": 0.0187,
+ "step": 2860
+ },
+ {
+ "epoch": 2.65,
+ "grad_norm": 0.6915044784545898,
+ "learning_rate": 8.377951038078302e-05,
+ "loss": 0.0136,
+ "step": 2870
+ },
+ {
+ "epoch": 2.66,
+ "grad_norm": 0.8472715020179749,
+ "learning_rate": 8.367213497594502e-05,
+ "loss": 0.0318,
+ "step": 2880
+ },
+ {
+ "epoch": 2.67,
+ "grad_norm": 1.61133873462677,
+ "learning_rate": 8.356447465133919e-05,
+ "loss": 0.0228,
+ "step": 2890
+ },
+ {
+ "epoch": 2.68,
+ "grad_norm": 0.9213796257972717,
+ "learning_rate": 8.345653031794292e-05,
+ "loss": 0.0194,
+ "step": 2900
+ },
+ {
+ "epoch": 2.68,
+ "eval_loss": 0.0666012316942215,
+ "eval_runtime": 36.2588,
+ "eval_samples_per_second": 126.314,
+ "eval_steps_per_second": 5.268,
+ "step": 2900
+ },
+ {
+ "epoch": 2.69,
+ "grad_norm": 0.09682347625494003,
+ "learning_rate": 8.334830288913682e-05,
+ "loss": 0.0155,
+ "step": 2910
+ },
+ {
+ "epoch": 2.7,
+ "grad_norm": 0.9755958318710327,
+ "learning_rate": 8.323979328069689e-05,
+ "loss": 0.0159,
+ "step": 2920
+ },
+ {
+ "epoch": 2.71,
+ "grad_norm": 0.6496116518974304,
+ "learning_rate": 8.313100241078689e-05,
+ "loss": 0.017,
+ "step": 2930
+ },
+ {
+ "epoch": 2.72,
+ "grad_norm": 0.6899746060371399,
+ "learning_rate": 8.302193119995039e-05,
+ "loss": 0.024,
+ "step": 2940
+ },
+ {
+ "epoch": 2.73,
+ "grad_norm": 1.4230170249938965,
+ "learning_rate": 8.291258057110319e-05,
+ "loss": 0.0162,
+ "step": 2950
+ },
+ {
+ "epoch": 2.73,
+ "eval_loss": 0.07134513556957245,
+ "eval_runtime": 36.2555,
+ "eval_samples_per_second": 126.326,
+ "eval_steps_per_second": 5.268,
+ "step": 2950
+ },
+ {
+ "epoch": 2.74,
+ "grad_norm": 0.5962338447570801,
+ "learning_rate": 8.280295144952536e-05,
+ "loss": 0.0221,
+ "step": 2960
+ },
+ {
+ "epoch": 2.74,
+ "grad_norm": 1.1969221830368042,
+ "learning_rate": 8.269304476285349e-05,
+ "loss": 0.0107,
+ "step": 2970
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 1.6272106170654297,
+ "learning_rate": 8.258286144107276e-05,
+ "loss": 0.0185,
+ "step": 2980
+ },
+ {
+ "epoch": 2.76,
+ "grad_norm": 0.18976141512393951,
+ "learning_rate": 8.247240241650918e-05,
+ "loss": 0.0185,
+ "step": 2990
+ },
+ {
+ "epoch": 2.77,
+ "grad_norm": 1.8696092367172241,
+ "learning_rate": 8.236166862382163e-05,
+ "loss": 0.0184,
+ "step": 3000
+ },
+ {
+ "epoch": 2.77,
+ "eval_loss": 0.07399819046258926,
+ "eval_runtime": 36.249,
+ "eval_samples_per_second": 126.348,
+ "eval_steps_per_second": 5.269,
+ "step": 3000
+ },
+ {
+ "epoch": 2.78,
+ "grad_norm": 0.5066729784011841,
+ "learning_rate": 8.225066099999392e-05,
+ "loss": 0.0197,
+ "step": 3010
+ },
+ {
+ "epoch": 2.79,
+ "grad_norm": 0.5865077376365662,
+ "learning_rate": 8.213938048432697e-05,
+ "loss": 0.0231,
+ "step": 3020
+ },
+ {
+ "epoch": 2.8,
+ "grad_norm": 0.2946082651615143,
+ "learning_rate": 8.202782801843076e-05,
+ "loss": 0.013,
+ "step": 3030
+ },
+ {
+ "epoch": 2.81,
+ "grad_norm": 0.49251487851142883,
+ "learning_rate": 8.191600454621642e-05,
+ "loss": 0.0247,
+ "step": 3040
+ },
+ {
+ "epoch": 2.82,
+ "grad_norm": 0.34551000595092773,
+ "learning_rate": 8.18039110138882e-05,
+ "loss": 0.0227,
+ "step": 3050
+ },
+ {
+ "epoch": 2.82,
+ "eval_loss": 0.06754355877637863,
+ "eval_runtime": 36.2553,
+ "eval_samples_per_second": 126.326,
+ "eval_steps_per_second": 5.268,
+ "step": 3050
+ },
+ {
+ "epoch": 2.83,
+ "grad_norm": 1.2313387393951416,
+ "learning_rate": 8.169154836993551e-05,
+ "loss": 0.0206,
+ "step": 3060
+ },
+ {
+ "epoch": 2.84,
+ "grad_norm": 0.2834533154964447,
+ "learning_rate": 8.157891756512488e-05,
+ "loss": 0.0216,
+ "step": 3070
+ },
+ {
+ "epoch": 2.85,
+ "grad_norm": 2.936052083969116,
+ "learning_rate": 8.146601955249188e-05,
+ "loss": 0.0405,
+ "step": 3080
+ },
+ {
+ "epoch": 2.86,
+ "grad_norm": 1.2530442476272583,
+ "learning_rate": 8.135285528733308e-05,
+ "loss": 0.0319,
+ "step": 3090
+ },
+ {
+ "epoch": 2.87,
+ "grad_norm": 0.9805688858032227,
+ "learning_rate": 8.1239425727198e-05,
+ "loss": 0.0176,
+ "step": 3100
+ },
+ {
+ "epoch": 2.87,
+ "eval_loss": 0.07011596113443375,
+ "eval_runtime": 36.237,
+ "eval_samples_per_second": 126.39,
+ "eval_steps_per_second": 5.271,
+ "step": 3100
+ },
+ {
+ "epoch": 2.87,
+ "grad_norm": 1.820011854171753,
+ "learning_rate": 8.112573183188099e-05,
+ "loss": 0.0285,
+ "step": 3110
+ },
+ {
+ "epoch": 2.88,
+ "grad_norm": 0.15229858458042145,
+ "learning_rate": 8.1011774563413e-05,
+ "loss": 0.0149,
+ "step": 3120
+ },
+ {
+ "epoch": 2.89,
+ "grad_norm": 0.5576140880584717,
+ "learning_rate": 8.089755488605366e-05,
+ "loss": 0.0223,
+ "step": 3130
+ },
+ {
+ "epoch": 2.9,
+ "grad_norm": 1.394098162651062,
+ "learning_rate": 8.07830737662829e-05,
+ "loss": 0.015,
+ "step": 3140
+ },
+ {
+ "epoch": 2.91,
+ "grad_norm": 1.0313000679016113,
+ "learning_rate": 8.066833217279297e-05,
+ "loss": 0.034,
+ "step": 3150
+ },
+ {
+ "epoch": 2.91,
+ "eval_loss": 0.06750660389661789,
+ "eval_runtime": 36.2568,
+ "eval_samples_per_second": 126.321,
+ "eval_steps_per_second": 5.268,
+ "step": 3150
+ },
+ {
+ "epoch": 2.92,
+ "grad_norm": 1.3380006551742554,
+ "learning_rate": 8.055333107647999e-05,
+ "loss": 0.0187,
+ "step": 3160
+ },
+ {
+ "epoch": 2.93,
+ "grad_norm": 0.46096986532211304,
+ "learning_rate": 8.043807145043604e-05,
+ "loss": 0.0261,
+ "step": 3170
+ },
+ {
+ "epoch": 2.94,
+ "grad_norm": 0.7799313068389893,
+ "learning_rate": 8.032255426994069e-05,
+ "loss": 0.0175,
+ "step": 3180
+ },
+ {
+ "epoch": 2.95,
+ "grad_norm": 0.5040866732597351,
+ "learning_rate": 8.020678051245282e-05,
+ "loss": 0.0163,
+ "step": 3190
+ },
+ {
+ "epoch": 2.96,
+ "grad_norm": 0.3076965808868408,
+ "learning_rate": 8.009075115760243e-05,
+ "loss": 0.0148,
+ "step": 3200
+ },
+ {
+ "epoch": 2.96,
+ "eval_loss": 0.06875752657651901,
+ "eval_runtime": 36.2627,
+ "eval_samples_per_second": 126.3,
+ "eval_steps_per_second": 5.267,
+ "step": 3200
+ },
+ {
+ "epoch": 2.97,
+ "grad_norm": 0.6659747958183289,
+ "learning_rate": 7.99744671871822e-05,
+ "loss": 0.0445,
+ "step": 3210
+ },
+ {
+ "epoch": 2.98,
+ "grad_norm": 1.3347102403640747,
+ "learning_rate": 7.985792958513931e-05,
+ "loss": 0.0216,
+ "step": 3220
+ },
+ {
+ "epoch": 2.99,
+ "grad_norm": 1.407318115234375,
+ "learning_rate": 7.974113933756707e-05,
+ "loss": 0.0173,
+ "step": 3230
+ },
+ {
+ "epoch": 2.99,
+ "grad_norm": 0.534429669380188,
+ "learning_rate": 7.962409743269654e-05,
+ "loss": 0.0185,
+ "step": 3240
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 0.7592530846595764,
+ "learning_rate": 7.950680486088823e-05,
+ "loss": 0.014,
+ "step": 3250
+ },
+ {
+ "epoch": 3.0,
+ "eval_loss": 0.0672665610909462,
+ "eval_runtime": 36.2374,
+ "eval_samples_per_second": 126.389,
+ "eval_steps_per_second": 5.271,
+ "step": 3250
+ },
+ {
+ "epoch": 3.01,
+ "grad_norm": 0.2840610146522522,
+ "learning_rate": 7.938926261462366e-05,
+ "loss": 0.0234,
+ "step": 3260
+ },
+ {
+ "epoch": 3.02,
+ "grad_norm": 2.4856412410736084,
+ "learning_rate": 7.927147168849704e-05,
+ "loss": 0.0094,
+ "step": 3270
+ },
+ {
+ "epoch": 3.03,
+ "grad_norm": 1.395142674446106,
+ "learning_rate": 7.915343307920674e-05,
+ "loss": 0.007,
+ "step": 3280
+ },
+ {
+ "epoch": 3.04,
+ "grad_norm": 0.21749833226203918,
+ "learning_rate": 7.903514778554699e-05,
+ "loss": 0.0106,
+ "step": 3290
+ },
+ {
+ "epoch": 3.05,
+ "grad_norm": 2.8792037963867188,
+ "learning_rate": 7.891661680839932e-05,
+ "loss": 0.0178,
+ "step": 3300
+ },
+ {
+ "epoch": 3.05,
+ "eval_loss": 0.07193872332572937,
+ "eval_runtime": 36.2444,
+ "eval_samples_per_second": 126.364,
+ "eval_steps_per_second": 5.27,
+ "step": 3300
+ },
+ {
+ "epoch": 3.06,
+ "grad_norm": 0.2820728123188019,
+ "learning_rate": 7.879784115072417e-05,
+ "loss": 0.0051,
+ "step": 3310
+ },
+ {
+ "epoch": 3.07,
+ "grad_norm": 0.22677582502365112,
+ "learning_rate": 7.86788218175523e-05,
+ "loss": 0.0035,
+ "step": 3320
+ },
+ {
+ "epoch": 3.08,
+ "grad_norm": 0.14426374435424805,
+ "learning_rate": 7.855955981597643e-05,
+ "loss": 0.0028,
+ "step": 3330
+ },
+ {
+ "epoch": 3.09,
+ "grad_norm": 0.5178078413009644,
+ "learning_rate": 7.844005615514259e-05,
+ "loss": 0.0092,
+ "step": 3340
+ },
+ {
+ "epoch": 3.1,
+ "grad_norm": 0.049177393317222595,
+ "learning_rate": 7.832031184624164e-05,
+ "loss": 0.0059,
+ "step": 3350
+ },
+ {
+ "epoch": 3.1,
+ "eval_loss": 0.07338841259479523,
+ "eval_runtime": 36.2678,
+ "eval_samples_per_second": 126.283,
+ "eval_steps_per_second": 5.266,
+ "step": 3350
+ },
+ {
+ "epoch": 3.11,
+ "grad_norm": 0.20768703520298004,
+ "learning_rate": 7.820032790250074e-05,
+ "loss": 0.0145,
+ "step": 3360
+ },
+ {
+ "epoch": 3.11,
+ "grad_norm": 0.4482771158218384,
+ "learning_rate": 7.808010533917465e-05,
+ "loss": 0.0043,
+ "step": 3370
+ },
+ {
+ "epoch": 3.12,
+ "grad_norm": 0.7216786742210388,
+ "learning_rate": 7.795964517353735e-05,
+ "loss": 0.0125,
+ "step": 3380
+ },
+ {
+ "epoch": 3.13,
+ "grad_norm": 0.028145039454102516,
+ "learning_rate": 7.783894842487322e-05,
+ "loss": 0.0023,
+ "step": 3390
+ },
+ {
+ "epoch": 3.14,
+ "grad_norm": 0.02350945584475994,
+ "learning_rate": 7.771801611446858e-05,
+ "loss": 0.0069,
+ "step": 3400
+ },
+ {
+ "epoch": 3.14,
+ "eval_loss": 0.07644446939229965,
+ "eval_runtime": 36.2497,
+ "eval_samples_per_second": 126.346,
+ "eval_steps_per_second": 5.269,
+ "step": 3400
+ },
+ {
+ "epoch": 3.15,
+ "grad_norm": 0.12125283479690552,
+ "learning_rate": 7.75968492656029e-05,
+ "loss": 0.0118,
+ "step": 3410
+ },
+ {
+ "epoch": 3.16,
+ "grad_norm": 0.43455737829208374,
+ "learning_rate": 7.74754489035403e-05,
+ "loss": 0.0066,
+ "step": 3420
+ },
+ {
+ "epoch": 3.17,
+ "grad_norm": 1.3440496921539307,
+ "learning_rate": 7.735381605552073e-05,
+ "loss": 0.0187,
+ "step": 3430
+ },
+ {
+ "epoch": 3.18,
+ "grad_norm": 0.5088502168655396,
+ "learning_rate": 7.723195175075136e-05,
+ "loss": 0.0094,
+ "step": 3440
+ },
+ {
+ "epoch": 3.19,
+ "grad_norm": 0.38931986689567566,
+ "learning_rate": 7.710985702039786e-05,
+ "loss": 0.0074,
+ "step": 3450
+ },
+ {
+ "epoch": 3.19,
+ "eval_loss": 0.08178228884935379,
+ "eval_runtime": 36.2441,
+ "eval_samples_per_second": 126.365,
+ "eval_steps_per_second": 5.27,
+ "step": 3450
+ },
+ {
+ "epoch": 3.2,
+ "grad_norm": 1.8949205875396729,
+ "learning_rate": 7.698753289757565e-05,
+ "loss": 0.0038,
+ "step": 3460
+ },
+ {
+ "epoch": 3.21,
+ "grad_norm": 1.4405574798583984,
+ "learning_rate": 7.68649804173412e-05,
+ "loss": 0.0113,
+ "step": 3470
+ },
+ {
+ "epoch": 3.22,
+ "grad_norm": 0.03057631105184555,
+ "learning_rate": 7.674220061668322e-05,
+ "loss": 0.0099,
+ "step": 3480
+ },
+ {
+ "epoch": 3.23,
+ "grad_norm": 1.858884572982788,
+ "learning_rate": 7.661919453451394e-05,
+ "loss": 0.0089,
+ "step": 3490
+ },
+ {
+ "epoch": 3.23,
+ "grad_norm": 0.02921319007873535,
+ "learning_rate": 7.649596321166024e-05,
+ "loss": 0.009,
+ "step": 3500
+ },
+ {
+ "epoch": 3.23,
+ "eval_loss": 0.07047122716903687,
+ "eval_runtime": 36.2528,
+ "eval_samples_per_second": 126.335,
+ "eval_steps_per_second": 5.269,
+ "step": 3500
+ },
+ {
+ "epoch": 3.24,
+ "grad_norm": 0.7095614671707153,
+ "learning_rate": 7.6372507690855e-05,
+ "loss": 0.0084,
+ "step": 3510
+ },
+ {
+ "epoch": 3.25,
+ "grad_norm": 1.0134788751602173,
+ "learning_rate": 7.6248829016728e-05,
+ "loss": 0.0119,
+ "step": 3520
+ },
+ {
+ "epoch": 3.26,
+ "grad_norm": 0.09262863546609879,
+ "learning_rate": 7.612492823579745e-05,
+ "loss": 0.0139,
+ "step": 3530
+ },
+ {
+ "epoch": 3.27,
+ "grad_norm": 0.033623356372117996,
+ "learning_rate": 7.600080639646077e-05,
+ "loss": 0.0092,
+ "step": 3540
+ },
+ {
+ "epoch": 3.28,
+ "grad_norm": 3.299873113632202,
+ "learning_rate": 7.5876464548986e-05,
+ "loss": 0.0048,
+ "step": 3550
+ },
+ {
+ "epoch": 3.28,
+ "eval_loss": 0.07350648939609528,
+ "eval_runtime": 36.2532,
+ "eval_samples_per_second": 126.334,
+ "eval_steps_per_second": 5.268,
+ "step": 3550
+ },
+ {
+ "epoch": 3.29,
+ "grad_norm": 0.299811452627182,
+ "learning_rate": 7.575190374550272e-05,
+ "loss": 0.0095,
+ "step": 3560
+ },
+ {
+ "epoch": 3.3,
+ "grad_norm": 0.5699326395988464,
+ "learning_rate": 7.562712503999327e-05,
+ "loss": 0.0052,
+ "step": 3570
+ },
+ {
+ "epoch": 3.31,
+ "grad_norm": 0.2542770802974701,
+ "learning_rate": 7.550212948828377e-05,
+ "loss": 0.0037,
+ "step": 3580
+ },
+ {
+ "epoch": 3.32,
+ "grad_norm": 0.9009780287742615,
+ "learning_rate": 7.537691814803521e-05,
+ "loss": 0.0194,
+ "step": 3590
+ },
+ {
+ "epoch": 3.33,
+ "grad_norm": 0.22393372654914856,
+ "learning_rate": 7.52514920787345e-05,
+ "loss": 0.005,
+ "step": 3600
+ },
+ {
+ "epoch": 3.33,
+ "eval_loss": 0.07049556821584702,
+ "eval_runtime": 36.2616,
+ "eval_samples_per_second": 126.304,
+ "eval_steps_per_second": 5.267,
+ "step": 3600
+ },
+ {
+ "epoch": 3.34,
+ "grad_norm": 0.1645677536725998,
+ "learning_rate": 7.51258523416855e-05,
+ "loss": 0.0162,
+ "step": 3610
+ },
+ {
+ "epoch": 3.35,
+ "grad_norm": 1.0096102952957153,
+ "learning_rate": 7.500000000000001e-05,
+ "loss": 0.0108,
+ "step": 3620
+ },
+ {
+ "epoch": 3.35,
+ "grad_norm": 0.3511151373386383,
+ "learning_rate": 7.487393611858883e-05,
+ "loss": 0.0059,
+ "step": 3630
+ },
+ {
+ "epoch": 3.36,
+ "grad_norm": 0.08066729456186295,
+ "learning_rate": 7.474766176415271e-05,
+ "loss": 0.011,
+ "step": 3640
+ },
+ {
+ "epoch": 3.37,
+ "grad_norm": 0.27665212750434875,
+ "learning_rate": 7.462117800517336e-05,
+ "loss": 0.0073,
+ "step": 3650
+ },
+ {
+ "epoch": 3.37,
+ "eval_loss": 0.07236067205667496,
+ "eval_runtime": 36.2566,
+ "eval_samples_per_second": 126.322,
+ "eval_steps_per_second": 5.268,
+ "step": 3650
+ },
+ {
+ "epoch": 3.37,
+ "step": 3650,
+ "total_flos": 1.0476524335865528e+18,
+ "train_loss": 0.10634728888738645,
+ "train_runtime": 4965.2136,
+ "train_samples_per_second": 52.266,
+ "train_steps_per_second": 2.179
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 10820,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 10,
+ "save_steps": 500,
+ "total_flos": 1.0476524335865528e+18,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/llama2_13b_peft/elementary_math_qa/training_args.bin b/llama2_13b_peft/elementary_math_qa/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..442a982587a420a545e38664edc667b13a5fa527
--- /dev/null
+++ b/llama2_13b_peft/elementary_math_qa/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a5142d68e9751e132f8bdf3341b60c7413d1047e923e3e9b78bf437200c919
+size 5112
diff --git a/llama2_13b_peft/elementary_math_qa/training_eval_loss.png b/llama2_13b_peft/elementary_math_qa/training_eval_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..f8ba218cc73d73d8822405c023a181fc5c29e2bb
Binary files /dev/null and b/llama2_13b_peft/elementary_math_qa/training_eval_loss.png differ
diff --git a/llama2_13b_peft/elementary_math_qa/training_loss.png b/llama2_13b_peft/elementary_math_qa/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..03fc78b0804be357ab30b9b7a13f8df21677c272
Binary files /dev/null and b/llama2_13b_peft/elementary_math_qa/training_loss.png differ
diff --git a/llama2_13b_peft/epistemic_reasoning/README.md b/llama2_13b_peft/epistemic_reasoning/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..279452ef0d716753b459f055eb3d95668285b337
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/README.md
@@ -0,0 +1,70 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: epistemic_reasoning_no_sys
+ results: []
+---
+
+
+
+# epistemic_reasoning_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the epistemic_reasoning_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0637 | 0.5263 | 100 | 0.0353 |
+| 0.0001 | 1.0526 | 200 | 0.0001 |
+| 0.0 | 1.5789 | 300 | 0.0000 |
+| 0.0 | 2.1053 | 400 | 0.0000 |
+| 0.0 | 2.6316 | 500 | 0.0000 |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.19.1
\ No newline at end of file
diff --git a/llama2_13b_peft/epistemic_reasoning/adapter_config.json b/llama2_13b_peft/epistemic_reasoning/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8e9974519c9d362e56e6623ac7d27ec3ecde3b89
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "k_proj",
+ "gate_proj",
+ "o_proj",
+ "q_proj",
+ "up_proj",
+ "v_proj",
+ "down_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/epistemic_reasoning/adapter_model.safetensors b/llama2_13b_peft/epistemic_reasoning/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a15085ed8f9ffe92c6b31677bbaf783636809c5d
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa79b2a88be4cb133ae6dd764c9f382cf02b6c514052a3939e3b7f702b5139e
+size 125248064
diff --git a/llama2_13b_peft/epistemic_reasoning/all_results.json b/llama2_13b_peft/epistemic_reasoning/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..a3ff4034205c061174d7f1e913868215e8c321f8
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/all_results.json
@@ -0,0 +1,12 @@
+{
+ "epoch": 2.6315789473684212,
+ "eval_loss": 8.995843018055893e-06,
+ "eval_runtime": 0.935,
+ "eval_samples_per_second": 85.565,
+ "eval_steps_per_second": 10.696,
+ "total_flos": 3.922877488509747e+16,
+ "train_loss": 0.16288311984013126,
+ "train_runtime": 177.9523,
+ "train_samples_per_second": 42.708,
+ "train_steps_per_second": 5.339
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/epistemic_reasoning/eval_results.json b/llama2_13b_peft/epistemic_reasoning/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..6f7e954af1da455816cd99578b21b97db65d283c
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/eval_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 2.6315789473684212,
+ "eval_loss": 8.995843018055893e-06,
+ "eval_runtime": 0.935,
+ "eval_samples_per_second": 85.565,
+ "eval_steps_per_second": 10.696
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/epistemic_reasoning/special_tokens_map.json b/llama2_13b_peft/epistemic_reasoning/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/llama2_13b_peft/epistemic_reasoning/tokenizer.model b/llama2_13b_peft/epistemic_reasoning/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/llama2_13b_peft/epistemic_reasoning/tokenizer_config.json b/llama2_13b_peft/epistemic_reasoning/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a40266f39e5b5fed14de34710d35eb9e98d6bdad
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false
+}
diff --git a/llama2_13b_peft/epistemic_reasoning/train_results.json b/llama2_13b_peft/epistemic_reasoning/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..7adc50e4cf69ca1009fea712f9946a14b3c0518f
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/train_results.json
@@ -0,0 +1,8 @@
+{
+ "epoch": 2.6315789473684212,
+ "total_flos": 3.922877488509747e+16,
+ "train_loss": 0.16288311984013126,
+ "train_runtime": 177.9523,
+ "train_samples_per_second": 42.708,
+ "train_steps_per_second": 5.339
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/epistemic_reasoning/trainer_log.jsonl b/llama2_13b_peft/epistemic_reasoning/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..3038eb72f51e5d15d77fd5c211af9c9dd73bfb3c
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/trainer_log.jsonl
@@ -0,0 +1,57 @@
+{"current_steps": 10, "total_steps": 950, "loss": 4.1842, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 0.05263157894736842, "percentage": 1.05, "elapsed_time": "0:00:04", "remaining_time": "0:07:43"}
+{"current_steps": 20, "total_steps": 950, "loss": 2.6471, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5e-05, "epoch": 0.10526315789473684, "percentage": 2.11, "elapsed_time": "0:00:08", "remaining_time": "0:06:21"}
+{"current_steps": 30, "total_steps": 950, "loss": 0.31, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.998573727324295e-05, "epoch": 0.15789473684210525, "percentage": 3.16, "elapsed_time": "0:00:11", "remaining_time": "0:05:59"}
+{"current_steps": 40, "total_steps": 950, "loss": 0.1595, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.994296536700177e-05, "epoch": 0.21052631578947367, "percentage": 4.21, "elapsed_time": "0:00:14", "remaining_time": "0:05:38"}
+{"current_steps": 50, "total_steps": 950, "loss": 0.1462, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.987173308479738e-05, "epoch": 0.2631578947368421, "percentage": 5.26, "elapsed_time": "0:00:18", "remaining_time": "0:05:25"}
+{"current_steps": 60, "total_steps": 950, "loss": 0.1413, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.977212170395598e-05, "epoch": 0.3157894736842105, "percentage": 6.32, "elapsed_time": "0:00:21", "remaining_time": "0:05:14"}
+{"current_steps": 70, "total_steps": 950, "loss": 0.1202, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.964424488287009e-05, "epoch": 0.3684210526315789, "percentage": 7.37, "elapsed_time": "0:00:24", "remaining_time": "0:05:06"}
+{"current_steps": 80, "total_steps": 950, "loss": 0.1262, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.948824853131236e-05, "epoch": 0.42105263157894735, "percentage": 8.42, "elapsed_time": "0:00:27", "remaining_time": "0:04:59"}
+{"current_steps": 90, "total_steps": 950, "loss": 0.1133, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.930431064394977e-05, "epoch": 0.47368421052631576, "percentage": 9.47, "elapsed_time": "0:00:30", "remaining_time": "0:04:55"}
+{"current_steps": 100, "total_steps": 950, "loss": 0.0637, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.909264109724853e-05, "epoch": 0.5263157894736842, "percentage": 10.53, "elapsed_time": "0:00:34", "remaining_time": "0:04:51"}
+{"current_steps": 100, "total_steps": 950, "loss": null, "eval_loss": 0.03525802493095398, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.5263157894736842, "percentage": 10.53, "elapsed_time": "0:00:34", "remaining_time": "0:04:51"}
+{"current_steps": 110, "total_steps": 950, "loss": 0.0422, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.885348141000122e-05, "epoch": 0.5789473684210527, "percentage": 11.58, "elapsed_time": "0:00:38", "remaining_time": "0:04:56"}
+{"current_steps": 120, "total_steps": 950, "loss": 0.0171, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.858710446774951e-05, "epoch": 0.631578947368421, "percentage": 12.63, "elapsed_time": "0:00:42", "remaining_time": "0:04:50"}
+{"current_steps": 130, "total_steps": 950, "loss": 0.0178, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.829381421141671e-05, "epoch": 0.6842105263157895, "percentage": 13.68, "elapsed_time": "0:00:45", "remaining_time": "0:04:45"}
+{"current_steps": 140, "total_steps": 950, "loss": 0.0354, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7973945290505766e-05, "epoch": 0.7368421052631579, "percentage": 14.74, "elapsed_time": "0:00:48", "remaining_time": "0:04:41"}
+{"current_steps": 150, "total_steps": 950, "loss": 0.008, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7627862681258037e-05, "epoch": 0.7894736842105263, "percentage": 15.79, "elapsed_time": "0:00:52", "remaining_time": "0:04:37"}
+{"current_steps": 160, "total_steps": 950, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.725596127020879e-05, "epoch": 0.8421052631578947, "percentage": 16.84, "elapsed_time": "0:00:55", "remaining_time": "0:04:32"}
+{"current_steps": 170, "total_steps": 950, "loss": 0.0036, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.685866540361456e-05, "epoch": 0.8947368421052632, "percentage": 17.89, "elapsed_time": "0:00:58", "remaining_time": "0:04:28"}
+{"current_steps": 180, "total_steps": 950, "loss": 0.0064, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.643642840326627e-05, "epoch": 0.9473684210526315, "percentage": 18.95, "elapsed_time": "0:01:01", "remaining_time": "0:04:23"}
+{"current_steps": 190, "total_steps": 950, "loss": 0.0006, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.598973204924097e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:01:04", "remaining_time": "0:04:18"}
+{"current_steps": 200, "total_steps": 950, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.551908603018191e-05, "epoch": 1.0526315789473684, "percentage": 21.05, "elapsed_time": "0:01:07", "remaining_time": "0:04:14"}
+{"current_steps": 200, "total_steps": 950, "loss": null, "eval_loss": 5.087663885205984e-05, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.0526315789473684, "percentage": 21.05, "elapsed_time": "0:01:07", "remaining_time": "0:04:14"}
+{"current_steps": 210, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.502502736173462e-05, "epoch": 1.1052631578947367, "percentage": 22.11, "elapsed_time": "0:01:12", "remaining_time": "0:04:16"}
+{"current_steps": 220, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.45081197738023e-05, "epoch": 1.1578947368421053, "percentage": 23.16, "elapsed_time": "0:01:16", "remaining_time": "0:04:12"}
+{"current_steps": 230, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3968953067319777e-05, "epoch": 1.2105263157894737, "percentage": 24.21, "elapsed_time": "0:01:19", "remaining_time": "0:04:08"}
+{"current_steps": 240, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.340814244127993e-05, "epoch": 1.263157894736842, "percentage": 25.26, "elapsed_time": "0:01:22", "remaining_time": "0:04:04"}
+{"current_steps": 250, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.282632779078051e-05, "epoch": 1.3157894736842106, "percentage": 26.32, "elapsed_time": "0:01:25", "remaining_time": "0:04:00"}
+{"current_steps": 260, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.222417297689217e-05, "epoch": 1.368421052631579, "percentage": 27.37, "elapsed_time": "0:01:29", "remaining_time": "0:03:56"}
+{"current_steps": 270, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.160236506918098e-05, "epoch": 1.4210526315789473, "percentage": 28.42, "elapsed_time": "0:01:32", "remaining_time": "0:03:52"}
+{"current_steps": 280, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.096161356174959e-05, "epoch": 1.4736842105263157, "percentage": 29.47, "elapsed_time": "0:01:35", "remaining_time": "0:03:48"}
+{"current_steps": 290, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.030264956369157e-05, "epoch": 1.526315789473684, "percentage": 30.53, "elapsed_time": "0:01:38", "remaining_time": "0:03:44"}
+{"current_steps": 300, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.962622496488269e-05, "epoch": 1.5789473684210527, "percentage": 31.58, "elapsed_time": "0:01:41", "remaining_time": "0:03:40"}
+{"current_steps": 300, "total_steps": 950, "loss": null, "eval_loss": 1.916586552397348e-05, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.5789473684210527, "percentage": 31.58, "elapsed_time": "0:01:41", "remaining_time": "0:03:40"}
+{"current_steps": 310, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.893311157806091e-05, "epoch": 1.631578947368421, "percentage": 32.63, "elapsed_time": "0:01:46", "remaining_time": "0:03:39"}
+{"current_steps": 320, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.822410025817406e-05, "epoch": 1.6842105263157894, "percentage": 33.68, "elapsed_time": "0:01:49", "remaining_time": "0:03:35"}
+{"current_steps": 330, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7500000000000003e-05, "epoch": 1.736842105263158, "percentage": 34.74, "elapsed_time": "0:01:52", "remaining_time": "0:03:31"}
+{"current_steps": 340, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.67616370150689e-05, "epoch": 1.7894736842105263, "percentage": 35.79, "elapsed_time": "0:01:55", "remaining_time": "0:03:28"}
+{"current_steps": 350, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.600985378894086e-05, "epoch": 1.8421052631578947, "percentage": 36.84, "elapsed_time": "0:01:59", "remaining_time": "0:03:24"}
+{"current_steps": 360, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5245508119914687e-05, "epoch": 1.8947368421052633, "percentage": 37.89, "elapsed_time": "0:02:02", "remaining_time": "0:03:20"}
+{"current_steps": 370, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.44694721402644e-05, "epoch": 1.9473684210526314, "percentage": 38.95, "elapsed_time": "0:02:05", "remaining_time": "0:03:17"}
+{"current_steps": 380, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3682631321120504e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:02:08", "remaining_time": "0:03:13"}
+{"current_steps": 390, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2885883462131394e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "0:02:12", "remaining_time": "0:03:09"}
+{"current_steps": 400, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2080137667057595e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "0:02:15", "remaining_time": "0:03:06"}
+{"current_steps": 400, "total_steps": 950, "loss": null, "eval_loss": 1.2211120520078111e-05, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "0:02:15", "remaining_time": "0:03:06"}
+{"current_steps": 410, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.126631330646802e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "0:02:20", "remaining_time": "0:03:04"}
+{"current_steps": 420, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0445338968721287e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "0:02:23", "remaining_time": "0:03:00"}
+{"current_steps": 430, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.961815140042974e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "0:02:26", "remaining_time": "0:02:56"}
+{"current_steps": 440, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.878569443761442e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "0:02:29", "remaining_time": "0:02:53"}
+{"current_steps": 450, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7948917928771158e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "0:02:32", "remaining_time": "0:02:49"}
+{"current_steps": 460, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7108776651076118e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "0:02:36", "remaining_time": "0:02:46"}
+{"current_steps": 470, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6266229220967818e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "0:02:39", "remaining_time": "0:02:43"}
+{"current_steps": 480, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5422237000348276e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "0:02:43", "remaining_time": "0:02:39"}
+{"current_steps": 490, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4577762999651726e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "0:02:46", "remaining_time": "0:02:35"}
+{"current_steps": 500, "total_steps": 950, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3733770779032184e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "0:02:49", "remaining_time": "0:02:32"}
+{"current_steps": 500, "total_steps": 950, "loss": null, "eval_loss": 8.995843018055893e-06, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "0:02:49", "remaining_time": "0:02:32"}
+{"current_steps": 500, "total_steps": 950, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "0:02:49", "remaining_time": "0:02:32"}
+{"current_steps": 10, "total_steps": 10, "loss": null, "eval_loss": 8.995843018055893e-06, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.6315789473684212, "percentage": 100.0, "elapsed_time": "0:02:59", "remaining_time": "0:00:00"}
diff --git a/llama2_13b_peft/epistemic_reasoning/trainer_state.json b/llama2_13b_peft/epistemic_reasoning/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4a7a042c7e9c1a0c9e2aa574b7815edc1d26c439
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/trainer_state.json
@@ -0,0 +1,420 @@
+{
+ "best_metric": 8.995843018055893e-06,
+ "best_model_checkpoint": "ckpt/llama2_13b_fuze27_no_sys/epistemic_reasoning_no_sys/checkpoint-500",
+ "epoch": 2.6315789473684212,
+ "eval_steps": 100,
+ "global_step": 500,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.05263157894736842,
+ "grad_norm": 6.579661846160889,
+ "learning_rate": 2.5e-05,
+ "loss": 4.1842,
+ "step": 10
+ },
+ {
+ "epoch": 0.10526315789473684,
+ "grad_norm": 3.819920539855957,
+ "learning_rate": 5e-05,
+ "loss": 2.6471,
+ "step": 20
+ },
+ {
+ "epoch": 0.15789473684210525,
+ "grad_norm": 0.6500287055969238,
+ "learning_rate": 4.998573727324295e-05,
+ "loss": 0.31,
+ "step": 30
+ },
+ {
+ "epoch": 0.21052631578947367,
+ "grad_norm": 3.065582275390625,
+ "learning_rate": 4.994296536700177e-05,
+ "loss": 0.1595,
+ "step": 40
+ },
+ {
+ "epoch": 0.2631578947368421,
+ "grad_norm": 2.211399555206299,
+ "learning_rate": 4.987173308479738e-05,
+ "loss": 0.1462,
+ "step": 50
+ },
+ {
+ "epoch": 0.3157894736842105,
+ "grad_norm": 2.7942709922790527,
+ "learning_rate": 4.977212170395598e-05,
+ "loss": 0.1413,
+ "step": 60
+ },
+ {
+ "epoch": 0.3684210526315789,
+ "grad_norm": 1.0859003067016602,
+ "learning_rate": 4.964424488287009e-05,
+ "loss": 0.1202,
+ "step": 70
+ },
+ {
+ "epoch": 0.42105263157894735,
+ "grad_norm": 0.25432416796684265,
+ "learning_rate": 4.948824853131236e-05,
+ "loss": 0.1262,
+ "step": 80
+ },
+ {
+ "epoch": 0.47368421052631576,
+ "grad_norm": 0.5941969752311707,
+ "learning_rate": 4.930431064394977e-05,
+ "loss": 0.1133,
+ "step": 90
+ },
+ {
+ "epoch": 0.5263157894736842,
+ "grad_norm": 0.5798951983451843,
+ "learning_rate": 4.909264109724853e-05,
+ "loss": 0.0637,
+ "step": 100
+ },
+ {
+ "epoch": 0.5263157894736842,
+ "eval_loss": 0.03525802493095398,
+ "eval_runtime": 0.9308,
+ "eval_samples_per_second": 85.945,
+ "eval_steps_per_second": 10.743,
+ "step": 100
+ },
+ {
+ "epoch": 0.5789473684210527,
+ "grad_norm": 0.03817753493785858,
+ "learning_rate": 4.885348141000122e-05,
+ "loss": 0.0422,
+ "step": 110
+ },
+ {
+ "epoch": 0.631578947368421,
+ "grad_norm": 0.1301649510860443,
+ "learning_rate": 4.858710446774951e-05,
+ "loss": 0.0171,
+ "step": 120
+ },
+ {
+ "epoch": 0.6842105263157895,
+ "grad_norm": 7.279715538024902,
+ "learning_rate": 4.829381421141671e-05,
+ "loss": 0.0178,
+ "step": 130
+ },
+ {
+ "epoch": 0.7368421052631579,
+ "grad_norm": 0.01268183533102274,
+ "learning_rate": 4.7973945290505766e-05,
+ "loss": 0.0354,
+ "step": 140
+ },
+ {
+ "epoch": 0.7894736842105263,
+ "grad_norm": 0.008723316714167595,
+ "learning_rate": 4.7627862681258037e-05,
+ "loss": 0.008,
+ "step": 150
+ },
+ {
+ "epoch": 0.8421052631578947,
+ "grad_norm": 0.005658257752656937,
+ "learning_rate": 4.725596127020879e-05,
+ "loss": 0.0007,
+ "step": 160
+ },
+ {
+ "epoch": 0.8947368421052632,
+ "grad_norm": 0.00573640875518322,
+ "learning_rate": 4.685866540361456e-05,
+ "loss": 0.0036,
+ "step": 170
+ },
+ {
+ "epoch": 0.9473684210526315,
+ "grad_norm": 0.0025901510380208492,
+ "learning_rate": 4.643642840326627e-05,
+ "loss": 0.0064,
+ "step": 180
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 1.690902590751648,
+ "learning_rate": 4.598973204924097e-05,
+ "loss": 0.0006,
+ "step": 190
+ },
+ {
+ "epoch": 1.0526315789473684,
+ "grad_norm": 0.001473828568123281,
+ "learning_rate": 4.551908603018191e-05,
+ "loss": 0.0001,
+ "step": 200
+ },
+ {
+ "epoch": 1.0526315789473684,
+ "eval_loss": 5.087663885205984e-05,
+ "eval_runtime": 0.9345,
+ "eval_samples_per_second": 85.606,
+ "eval_steps_per_second": 10.701,
+ "step": 200
+ },
+ {
+ "epoch": 1.1052631578947367,
+ "grad_norm": 0.0009911700617522001,
+ "learning_rate": 4.502502736173462e-05,
+ "loss": 0.0,
+ "step": 210
+ },
+ {
+ "epoch": 1.1578947368421053,
+ "grad_norm": 0.0010419037425890565,
+ "learning_rate": 4.45081197738023e-05,
+ "loss": 0.0,
+ "step": 220
+ },
+ {
+ "epoch": 1.2105263157894737,
+ "grad_norm": 0.0012509481748566031,
+ "learning_rate": 4.3968953067319777e-05,
+ "loss": 0.0,
+ "step": 230
+ },
+ {
+ "epoch": 1.263157894736842,
+ "grad_norm": 0.0007601848337799311,
+ "learning_rate": 4.340814244127993e-05,
+ "loss": 0.0,
+ "step": 240
+ },
+ {
+ "epoch": 1.3157894736842106,
+ "grad_norm": 0.0007381394389085472,
+ "learning_rate": 4.282632779078051e-05,
+ "loss": 0.0,
+ "step": 250
+ },
+ {
+ "epoch": 1.368421052631579,
+ "grad_norm": 0.000822492060251534,
+ "learning_rate": 4.222417297689217e-05,
+ "loss": 0.0,
+ "step": 260
+ },
+ {
+ "epoch": 1.4210526315789473,
+ "grad_norm": 0.001167929614894092,
+ "learning_rate": 4.160236506918098e-05,
+ "loss": 0.0,
+ "step": 270
+ },
+ {
+ "epoch": 1.4736842105263157,
+ "grad_norm": 0.0006889003561809659,
+ "learning_rate": 4.096161356174959e-05,
+ "loss": 0.0,
+ "step": 280
+ },
+ {
+ "epoch": 1.526315789473684,
+ "grad_norm": 0.0006537819281220436,
+ "learning_rate": 4.030264956369157e-05,
+ "loss": 0.0,
+ "step": 290
+ },
+ {
+ "epoch": 1.5789473684210527,
+ "grad_norm": 0.0005895848153159022,
+ "learning_rate": 3.962622496488269e-05,
+ "loss": 0.0,
+ "step": 300
+ },
+ {
+ "epoch": 1.5789473684210527,
+ "eval_loss": 1.916586552397348e-05,
+ "eval_runtime": 0.9341,
+ "eval_samples_per_second": 85.644,
+ "eval_steps_per_second": 10.705,
+ "step": 300
+ },
+ {
+ "epoch": 1.631578947368421,
+ "grad_norm": 0.00041267831693403423,
+ "learning_rate": 3.893311157806091e-05,
+ "loss": 0.0,
+ "step": 310
+ },
+ {
+ "epoch": 1.6842105263157894,
+ "grad_norm": 0.00042886921437457204,
+ "learning_rate": 3.822410025817406e-05,
+ "loss": 0.0,
+ "step": 320
+ },
+ {
+ "epoch": 1.736842105263158,
+ "grad_norm": 0.0006562267662957311,
+ "learning_rate": 3.7500000000000003e-05,
+ "loss": 0.0,
+ "step": 330
+ },
+ {
+ "epoch": 1.7894736842105263,
+ "grad_norm": 0.00045172293903306127,
+ "learning_rate": 3.67616370150689e-05,
+ "loss": 0.0,
+ "step": 340
+ },
+ {
+ "epoch": 1.8421052631578947,
+ "grad_norm": 0.0003128020034637302,
+ "learning_rate": 3.600985378894086e-05,
+ "loss": 0.0,
+ "step": 350
+ },
+ {
+ "epoch": 1.8947368421052633,
+ "grad_norm": 0.00036892591742798686,
+ "learning_rate": 3.5245508119914687e-05,
+ "loss": 0.0,
+ "step": 360
+ },
+ {
+ "epoch": 1.9473684210526314,
+ "grad_norm": 0.00041946041164919734,
+ "learning_rate": 3.44694721402644e-05,
+ "loss": 0.0,
+ "step": 370
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 0.00044619792606681585,
+ "learning_rate": 3.3682631321120504e-05,
+ "loss": 0.0,
+ "step": 380
+ },
+ {
+ "epoch": 2.0526315789473686,
+ "grad_norm": 0.00034757808316498995,
+ "learning_rate": 3.2885883462131394e-05,
+ "loss": 0.0,
+ "step": 390
+ },
+ {
+ "epoch": 2.1052631578947367,
+ "grad_norm": 0.0004329316725488752,
+ "learning_rate": 3.2080137667057595e-05,
+ "loss": 0.0,
+ "step": 400
+ },
+ {
+ "epoch": 2.1052631578947367,
+ "eval_loss": 1.2211120520078111e-05,
+ "eval_runtime": 0.9376,
+ "eval_samples_per_second": 85.324,
+ "eval_steps_per_second": 10.665,
+ "step": 400
+ },
+ {
+ "epoch": 2.1578947368421053,
+ "grad_norm": 0.00034806900657713413,
+ "learning_rate": 3.126631330646802e-05,
+ "loss": 0.0,
+ "step": 410
+ },
+ {
+ "epoch": 2.2105263157894735,
+ "grad_norm": 0.0003566565574146807,
+ "learning_rate": 3.0445338968721287e-05,
+ "loss": 0.0,
+ "step": 420
+ },
+ {
+ "epoch": 2.263157894736842,
+ "grad_norm": 0.00035698447027243674,
+ "learning_rate": 2.961815140042974e-05,
+ "loss": 0.0,
+ "step": 430
+ },
+ {
+ "epoch": 2.3157894736842106,
+ "grad_norm": 0.00024169159587472677,
+ "learning_rate": 2.878569443761442e-05,
+ "loss": 0.0,
+ "step": 440
+ },
+ {
+ "epoch": 2.3684210526315788,
+ "grad_norm": 0.0003101905749645084,
+ "learning_rate": 2.7948917928771158e-05,
+ "loss": 0.0,
+ "step": 450
+ },
+ {
+ "epoch": 2.4210526315789473,
+ "grad_norm": 0.00032829289557412267,
+ "learning_rate": 2.7108776651076118e-05,
+ "loss": 0.0,
+ "step": 460
+ },
+ {
+ "epoch": 2.473684210526316,
+ "grad_norm": 0.0002047922316705808,
+ "learning_rate": 2.6266229220967818e-05,
+ "loss": 0.0,
+ "step": 470
+ },
+ {
+ "epoch": 2.526315789473684,
+ "grad_norm": 0.00021766829013358802,
+ "learning_rate": 2.5422237000348276e-05,
+ "loss": 0.0,
+ "step": 480
+ },
+ {
+ "epoch": 2.5789473684210527,
+ "grad_norm": 0.0002877192455343902,
+ "learning_rate": 2.4577762999651726e-05,
+ "loss": 0.0,
+ "step": 490
+ },
+ {
+ "epoch": 2.6315789473684212,
+ "grad_norm": 0.00021653489966411144,
+ "learning_rate": 2.3733770779032184e-05,
+ "loss": 0.0,
+ "step": 500
+ },
+ {
+ "epoch": 2.6315789473684212,
+ "eval_loss": 8.995843018055893e-06,
+ "eval_runtime": 0.9378,
+ "eval_samples_per_second": 85.301,
+ "eval_steps_per_second": 10.663,
+ "step": 500
+ },
+ {
+ "epoch": 2.6315789473684212,
+ "step": 500,
+ "total_flos": 3.922877488509747e+16,
+ "train_loss": 0.16288311984013126,
+ "train_runtime": 177.9523,
+ "train_samples_per_second": 42.708,
+ "train_steps_per_second": 5.339
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 950,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 100,
+ "total_flos": 3.922877488509747e+16,
+ "train_batch_size": 4,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/llama2_13b_peft/epistemic_reasoning/training_args.bin b/llama2_13b_peft/epistemic_reasoning/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d31ef9c3f3ad731dab61e17edbef926f1f3b1282
--- /dev/null
+++ b/llama2_13b_peft/epistemic_reasoning/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a618e61a3e6a9d9c0aa0b88800edcd7f8840e18dae67d6bea04c44e43cb93243
+size 5176
diff --git a/llama2_13b_peft/epistemic_reasoning/training_eval_loss.png b/llama2_13b_peft/epistemic_reasoning/training_eval_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..79327d7fc748fd0e17abf81ff4f2da51d78930f2
Binary files /dev/null and b/llama2_13b_peft/epistemic_reasoning/training_eval_loss.png differ
diff --git a/llama2_13b_peft/epistemic_reasoning/training_loss.png b/llama2_13b_peft/epistemic_reasoning/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..5b0e1d8c16b790432e2decba46ebcc5d49a73886
Binary files /dev/null and b/llama2_13b_peft/epistemic_reasoning/training_loss.png differ
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/README.md b/llama2_13b_peft/formal_fallacies_syllogisms_negation/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..647605be1de5bdebf9241ed3c5c7b2ddc72f592b
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/README.md
@@ -0,0 +1,118 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: formal_fallacies_syllogisms_negation_no_sys
+ results: []
+---
+
+
+
+# formal_fallacies_syllogisms_negation_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the formal_fallacies_syllogisms_negation_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0005
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- total_train_batch_size: 24
+- total_eval_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3929 | 0.12 | 50 | 0.3600 |
+| 0.3534 | 0.25 | 100 | 0.3503 |
+| 0.3577 | 0.37 | 150 | 0.3543 |
+| 0.351 | 0.5 | 200 | 0.3479 |
+| 0.3459 | 0.62 | 250 | 0.3508 |
+| 0.353 | 0.74 | 300 | 0.3515 |
+| 0.3591 | 0.87 | 350 | 0.3900 |
+| 0.3563 | 0.99 | 400 | 0.3496 |
+| 0.3351 | 1.12 | 450 | 0.3389 |
+| 0.26 | 1.24 | 500 | 0.3002 |
+| 0.187 | 1.36 | 550 | 0.1438 |
+| 0.0715 | 1.49 | 600 | 0.0493 |
+| 0.0695 | 1.61 | 650 | 0.0471 |
+| 0.0338 | 1.74 | 700 | 0.0307 |
+| 0.0422 | 1.86 | 750 | 0.0269 |
+| 0.0183 | 1.99 | 800 | 0.0091 |
+| 0.0055 | 2.11 | 850 | 0.0070 |
+| 0.0208 | 2.23 | 900 | 0.0032 |
+| 0.0014 | 2.36 | 950 | 0.0023 |
+| 0.0117 | 2.48 | 1000 | 0.0034 |
+| 0.0001 | 2.61 | 1050 | 0.0012 |
+| 0.0058 | 2.73 | 1100 | 0.0012 |
+| 0.0001 | 2.85 | 1150 | 0.0013 |
+| 0.0104 | 2.98 | 1200 | 0.0008 |
+| 0.0007 | 3.1 | 1250 | 0.0019 |
+| 0.0015 | 3.23 | 1300 | 0.0092 |
+| 0.0 | 3.35 | 1350 | 0.0016 |
+| 0.0001 | 3.47 | 1400 | 0.0004 |
+| 0.0059 | 3.6 | 1450 | 0.0003 |
+| 0.0 | 3.72 | 1500 | 0.0093 |
+| 0.0059 | 3.85 | 1550 | 0.0032 |
+| 0.0001 | 3.97 | 1600 | 0.0024 |
+| 0.0032 | 4.09 | 1650 | 0.0005 |
+| 0.0 | 4.22 | 1700 | 0.0037 |
+| 0.0 | 4.34 | 1750 | 0.0008 |
+| 0.0 | 4.47 | 1800 | 0.0008 |
+| 0.0 | 4.59 | 1850 | 0.0009 |
+| 0.0 | 4.71 | 1900 | 0.0006 |
+| 0.0002 | 4.84 | 1950 | 0.0001 |
+| 0.0 | 4.96 | 2000 | 0.0008 |
+| 0.0 | 5.09 | 2050 | 0.0001 |
+| 0.0 | 5.21 | 2100 | 0.0002 |
+| 0.0 | 5.33 | 2150 | 0.0002 |
+| 0.0 | 5.46 | 2200 | 0.0004 |
+| 0.0 | 5.58 | 2250 | 0.0004 |
+| 0.0 | 5.71 | 2300 | 0.0004 |
+| 0.0 | 5.83 | 2350 | 0.0004 |
+| 0.0 | 5.96 | 2400 | 0.0004 |
+| 0.0 | 6.08 | 2450 | 0.0004 |
+| 0.0 | 6.2 | 2500 | 0.0005 |
+| 0.0 | 6.33 | 2550 | 0.0005 |
+| 0.0 | 6.45 | 2600 | 0.0005 |
+| 0.0 | 6.58 | 2650 | 0.0004 |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2
\ No newline at end of file
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/adapter_config.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..97a417d3d933f0cdb8ea320af42ea1e71744cb29
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/adapter_config.json
@@ -0,0 +1,33 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "k_proj",
+ "down_proj",
+ "q_proj",
+ "o_proj",
+ "gate_proj",
+ "v_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/adapter_model.safetensors b/llama2_13b_peft/formal_fallacies_syllogisms_negation/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..495d26e294b36b9250215c17acb77e878d6628db
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e66a5c1fac40b3c4513a47149db4f3097c19c026e1ed290150ba4e0b610028c
+size 125248064
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/all_results.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..cbf6cc53c9fc38e1d207b4aed8f0a8c6078bccb0
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/all_results.json
@@ -0,0 +1,11 @@
+{
+ "epoch": 6.58,
+ "eval_loss": 0.00047402523341588676,
+ "eval_runtime": 16.7834,
+ "eval_samples_per_second": 101.529,
+ "eval_steps_per_second": 4.23,
+ "train_loss": 0.1188159689292002,
+ "train_runtime": 2950.0845,
+ "train_samples_per_second": 32.731,
+ "train_steps_per_second": 1.366
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/eval_results.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..db6e2cdee6d02f01edde9048b18aafb860b10d12
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/eval_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 6.58,
+ "eval_loss": 0.00047402523341588676,
+ "eval_runtime": 16.7834,
+ "eval_samples_per_second": 101.529,
+ "eval_steps_per_second": 4.23
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/special_tokens_map.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/tokenizer.model b/llama2_13b_peft/formal_fallacies_syllogisms_negation/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/tokenizer_config.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a40266f39e5b5fed14de34710d35eb9e98d6bdad
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false
+}
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/train_results.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..861e7d8e2eec1e309f54c703a9972d620af89f7a
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/train_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 6.58,
+ "train_loss": 0.1188159689292002,
+ "train_runtime": 2950.0845,
+ "train_samples_per_second": 32.731,
+ "train_steps_per_second": 1.366
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/trainer_log.jsonl b/llama2_13b_peft/formal_fallacies_syllogisms_negation/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..7d456773d42fbdbaeef4114c740c865535a8ff05
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/trainer_log.jsonl
@@ -0,0 +1,320 @@
+{"current_steps": 10, "total_steps": 4030, "loss": 9.3847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.02, "percentage": 0.25, "elapsed_time": "0:00:09", "remaining_time": "1:01:46"}
+{"current_steps": 20, "total_steps": 4030, "loss": 2.5484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 0.05, "percentage": 0.5, "elapsed_time": "0:00:16", "remaining_time": "0:56:23"}
+{"current_steps": 30, "total_steps": 4030, "loss": 0.3827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999846556397038e-05, "epoch": 0.07, "percentage": 0.74, "elapsed_time": "0:00:24", "remaining_time": "0:54:18"}
+{"current_steps": 40, "total_steps": 4030, "loss": 0.3554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999386235006125e-05, "epoch": 0.1, "percentage": 0.99, "elapsed_time": "0:00:32", "remaining_time": "0:53:16"}
+{"current_steps": 50, "total_steps": 4030, "loss": 0.3929, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998619064080611e-05, "epoch": 0.12, "percentage": 1.24, "elapsed_time": "0:00:39", "remaining_time": "0:52:50"}
+{"current_steps": 50, "total_steps": 4030, "loss": null, "eval_loss": 0.3599805533885956, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.12, "percentage": 1.24, "elapsed_time": "0:00:39", "remaining_time": "0:52:50"}
+{"current_steps": 60, "total_steps": 4030, "loss": 0.3588, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997545090707485e-05, "epoch": 0.15, "percentage": 1.49, "elapsed_time": "0:01:04", "remaining_time": "1:10:50"}
+{"current_steps": 70, "total_steps": 4030, "loss": 0.3594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996164380804483e-05, "epoch": 0.17, "percentage": 1.74, "elapsed_time": "0:01:12", "remaining_time": "1:07:54"}
+{"current_steps": 80, "total_steps": 4030, "loss": 0.3544, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994477019116049e-05, "epoch": 0.2, "percentage": 1.99, "elapsed_time": "0:01:19", "remaining_time": "1:05:33"}
+{"current_steps": 90, "total_steps": 4030, "loss": 0.3607, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992483109208122e-05, "epoch": 0.22, "percentage": 2.23, "elapsed_time": "0:01:27", "remaining_time": "1:03:47"}
+{"current_steps": 100, "total_steps": 4030, "loss": 0.3534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990182773461791e-05, "epoch": 0.25, "percentage": 2.48, "elapsed_time": "0:01:35", "remaining_time": "1:02:19"}
+{"current_steps": 100, "total_steps": 4030, "loss": null, "eval_loss": 0.35028183460235596, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.25, "percentage": 2.48, "elapsed_time": "0:01:35", "remaining_time": "1:02:19"}
+{"current_steps": 110, "total_steps": 4030, "loss": 0.3493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987576153065779e-05, "epoch": 0.27, "percentage": 2.73, "elapsed_time": "0:01:59", "remaining_time": "1:11:09"}
+{"current_steps": 120, "total_steps": 4030, "loss": 0.3519, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.984663408007777e-05, "epoch": 0.3, "percentage": 2.98, "elapsed_time": "0:02:07", "remaining_time": "1:09:16"}
+{"current_steps": 130, "total_steps": 4030, "loss": 0.3532, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98144471706462e-05, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:02:15", "remaining_time": "1:07:42"}
+{"current_steps": 140, "total_steps": 4030, "loss": 0.3526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.977920277791328e-05, "epoch": 0.35, "percentage": 3.47, "elapsed_time": "0:02:22", "remaining_time": "1:06:08"}
+{"current_steps": 150, "total_steps": 4030, "loss": 0.3577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.974090306508959e-05, "epoch": 0.37, "percentage": 3.72, "elapsed_time": "0:02:30", "remaining_time": "1:04:49"}
+{"current_steps": 150, "total_steps": 4030, "loss": null, "eval_loss": 0.3542585074901581, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.37, "percentage": 3.72, "elapsed_time": "0:02:30", "remaining_time": "1:04:49"}
+{"current_steps": 160, "total_steps": 4030, "loss": 0.3525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.969955038291353e-05, "epoch": 0.4, "percentage": 3.97, "elapsed_time": "0:02:55", "remaining_time": "1:10:38"}
+{"current_steps": 170, "total_steps": 4030, "loss": 0.3493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.965514726950693e-05, "epoch": 0.42, "percentage": 4.22, "elapsed_time": "0:03:02", "remaining_time": "1:09:10"}
+{"current_steps": 180, "total_steps": 4030, "loss": 0.3515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.960769645021923e-05, "epoch": 0.45, "percentage": 4.47, "elapsed_time": "0:03:10", "remaining_time": "1:07:58"}
+{"current_steps": 190, "total_steps": 4030, "loss": 0.349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.955720083746035e-05, "epoch": 0.47, "percentage": 4.71, "elapsed_time": "0:03:18", "remaining_time": "1:06:50"}
+{"current_steps": 200, "total_steps": 4030, "loss": 0.351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.950366353052175e-05, "epoch": 0.5, "percentage": 4.96, "elapsed_time": "0:03:26", "remaining_time": "1:05:45"}
+{"current_steps": 200, "total_steps": 4030, "loss": null, "eval_loss": 0.3478730320930481, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5, "percentage": 4.96, "elapsed_time": "0:03:26", "remaining_time": "1:05:45"}
+{"current_steps": 210, "total_steps": 4030, "loss": 0.3545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.944708781538636e-05, "epoch": 0.52, "percentage": 5.21, "elapsed_time": "0:03:50", "remaining_time": "1:09:54"}
+{"current_steps": 220, "total_steps": 4030, "loss": 0.3499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.93874771645268e-05, "epoch": 0.55, "percentage": 5.46, "elapsed_time": "0:03:58", "remaining_time": "1:08:45"}
+{"current_steps": 230, "total_steps": 4030, "loss": 0.3504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.932483523669231e-05, "epoch": 0.57, "percentage": 5.71, "elapsed_time": "0:04:05", "remaining_time": "1:07:43"}
+{"current_steps": 240, "total_steps": 4030, "loss": 0.3543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.925916587668409e-05, "epoch": 0.6, "percentage": 5.96, "elapsed_time": "0:04:14", "remaining_time": "1:06:52"}
+{"current_steps": 250, "total_steps": 4030, "loss": 0.3459, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.919047311511946e-05, "epoch": 0.62, "percentage": 6.2, "elapsed_time": "0:04:21", "remaining_time": "1:05:58"}
+{"current_steps": 250, "total_steps": 4030, "loss": null, "eval_loss": 0.35084518790245056, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.62, "percentage": 6.2, "elapsed_time": "0:04:21", "remaining_time": "1:05:58"}
+{"current_steps": 260, "total_steps": 4030, "loss": 0.3483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.911876116818433e-05, "epoch": 0.65, "percentage": 6.45, "elapsed_time": "0:04:46", "remaining_time": "1:09:16"}
+{"current_steps": 270, "total_steps": 4030, "loss": 0.3577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.904403443737454e-05, "epoch": 0.67, "percentage": 6.7, "elapsed_time": "0:04:54", "remaining_time": "1:08:15"}
+{"current_steps": 280, "total_steps": 4030, "loss": 0.3656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.896629750922555e-05, "epoch": 0.69, "percentage": 6.95, "elapsed_time": "0:05:01", "remaining_time": "1:07:20"}
+{"current_steps": 290, "total_steps": 4030, "loss": 0.3595, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.888555515503116e-05, "epoch": 0.72, "percentage": 7.2, "elapsed_time": "0:05:09", "remaining_time": "1:06:30"}
+{"current_steps": 300, "total_steps": 4030, "loss": 0.353, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.880181233055042e-05, "epoch": 0.74, "percentage": 7.44, "elapsed_time": "0:05:16", "remaining_time": "1:05:40"}
+{"current_steps": 300, "total_steps": 4030, "loss": null, "eval_loss": 0.351527601480484, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.74, "percentage": 7.44, "elapsed_time": "0:05:16", "remaining_time": "1:05:40"}
+{"current_steps": 310, "total_steps": 4030, "loss": 0.3552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.871507417570363e-05, "epoch": 0.77, "percentage": 7.69, "elapsed_time": "0:05:41", "remaining_time": "1:08:16"}
+{"current_steps": 320, "total_steps": 4030, "loss": 0.3515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.862534601425681e-05, "epoch": 0.79, "percentage": 7.94, "elapsed_time": "0:05:49", "remaining_time": "1:07:27"}
+{"current_steps": 330, "total_steps": 4030, "loss": 0.3445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.853263335349488e-05, "epoch": 0.82, "percentage": 8.19, "elapsed_time": "0:05:56", "remaining_time": "1:06:40"}
+{"current_steps": 340, "total_steps": 4030, "loss": 0.3579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.843694188388374e-05, "epoch": 0.84, "percentage": 8.44, "elapsed_time": "0:06:04", "remaining_time": "1:05:57"}
+{"current_steps": 350, "total_steps": 4030, "loss": 0.3591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.833827747872093e-05, "epoch": 0.87, "percentage": 8.68, "elapsed_time": "0:06:12", "remaining_time": "1:05:13"}
+{"current_steps": 350, "total_steps": 4030, "loss": null, "eval_loss": 0.3899991512298584, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.87, "percentage": 8.68, "elapsed_time": "0:06:12", "remaining_time": "1:05:13"}
+{"current_steps": 360, "total_steps": 4030, "loss": 0.3472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.823664619377518e-05, "epoch": 0.89, "percentage": 8.93, "elapsed_time": "0:06:36", "remaining_time": "1:07:25"}
+{"current_steps": 370, "total_steps": 4030, "loss": 0.3515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.81320542669147e-05, "epoch": 0.92, "percentage": 9.18, "elapsed_time": "0:06:44", "remaining_time": "1:06:42"}
+{"current_steps": 380, "total_steps": 4030, "loss": 0.3591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.802450811772435e-05, "epoch": 0.94, "percentage": 9.43, "elapsed_time": "0:06:52", "remaining_time": "1:05:59"}
+{"current_steps": 390, "total_steps": 4030, "loss": 0.3511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.791401434711154e-05, "epoch": 0.97, "percentage": 9.68, "elapsed_time": "0:06:59", "remaining_time": "1:05:19"}
+{"current_steps": 400, "total_steps": 4030, "loss": 0.3563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.78005797369012e-05, "epoch": 0.99, "percentage": 9.93, "elapsed_time": "0:07:07", "remaining_time": "1:04:39"}
+{"current_steps": 400, "total_steps": 4030, "loss": null, "eval_loss": 0.3495555818080902, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.99, "percentage": 9.93, "elapsed_time": "0:07:07", "remaining_time": "1:04:39"}
+{"current_steps": 410, "total_steps": 4030, "loss": 0.3384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.768421124941944e-05, "epoch": 1.02, "percentage": 10.17, "elapsed_time": "0:07:32", "remaining_time": "1:06:32"}
+{"current_steps": 420, "total_steps": 4030, "loss": 0.3545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.756491602706626e-05, "epoch": 1.04, "percentage": 10.42, "elapsed_time": "0:07:39", "remaining_time": "1:05:51"}
+{"current_steps": 430, "total_steps": 4030, "loss": 0.3449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.744270139187716e-05, "epoch": 1.07, "percentage": 10.67, "elapsed_time": "0:07:47", "remaining_time": "1:05:14"}
+{"current_steps": 440, "total_steps": 4030, "loss": 0.346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.731757484507371e-05, "epoch": 1.09, "percentage": 10.92, "elapsed_time": "0:07:55", "remaining_time": "1:04:37"}
+{"current_steps": 450, "total_steps": 4030, "loss": 0.3351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.718954406660318e-05, "epoch": 1.12, "percentage": 11.17, "elapsed_time": "0:08:02", "remaining_time": "1:04:01"}
+{"current_steps": 450, "total_steps": 4030, "loss": null, "eval_loss": 0.33888280391693115, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.12, "percentage": 11.17, "elapsed_time": "0:08:02", "remaining_time": "1:04:01"}
+{"current_steps": 460, "total_steps": 4030, "loss": 0.3306, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.705861691466716e-05, "epoch": 1.14, "percentage": 11.41, "elapsed_time": "0:08:27", "remaining_time": "1:05:39"}
+{"current_steps": 470, "total_steps": 4030, "loss": 0.3514, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.692480142523918e-05, "epoch": 1.17, "percentage": 11.66, "elapsed_time": "0:08:35", "remaining_time": "1:05:01"}
+{"current_steps": 480, "total_steps": 4030, "loss": 0.3159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.678810581157163e-05, "epoch": 1.19, "percentage": 11.91, "elapsed_time": "0:08:42", "remaining_time": "1:04:24"}
+{"current_steps": 490, "total_steps": 4030, "loss": 0.309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.664853846369144e-05, "epoch": 1.22, "percentage": 12.16, "elapsed_time": "0:08:50", "remaining_time": "1:03:50"}
+{"current_steps": 500, "total_steps": 4030, "loss": 0.26, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.650610794788533e-05, "epoch": 1.24, "percentage": 12.41, "elapsed_time": "0:08:58", "remaining_time": "1:03:19"}
+{"current_steps": 500, "total_steps": 4030, "loss": null, "eval_loss": 0.3002278506755829, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.24, "percentage": 12.41, "elapsed_time": "0:08:58", "remaining_time": "1:03:19"}
+{"current_steps": 510, "total_steps": 4030, "loss": 0.2472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.63608230061739e-05, "epoch": 1.27, "percentage": 12.66, "elapsed_time": "0:09:23", "remaining_time": "1:04:47"}
+{"current_steps": 520, "total_steps": 4030, "loss": 0.2212, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.621269255577512e-05, "epoch": 1.29, "percentage": 12.9, "elapsed_time": "0:09:30", "remaining_time": "1:04:12"}
+{"current_steps": 530, "total_steps": 4030, "loss": 0.2039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.606172568855698e-05, "epoch": 1.32, "percentage": 13.15, "elapsed_time": "0:09:38", "remaining_time": "1:03:38"}
+{"current_steps": 540, "total_steps": 4030, "loss": 0.2198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.590793167047951e-05, "epoch": 1.34, "percentage": 13.4, "elapsed_time": "0:09:46", "remaining_time": "1:03:07"}
+{"current_steps": 550, "total_steps": 4030, "loss": 0.187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.575131994102602e-05, "epoch": 1.36, "percentage": 13.65, "elapsed_time": "0:09:53", "remaining_time": "1:02:37"}
+{"current_steps": 550, "total_steps": 4030, "loss": null, "eval_loss": 0.14382539689540863, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.36, "percentage": 13.65, "elapsed_time": "0:09:53", "remaining_time": "1:02:37"}
+{"current_steps": 560, "total_steps": 4030, "loss": 0.1253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.559190011262369e-05, "epoch": 1.39, "percentage": 13.9, "elapsed_time": "0:10:18", "remaining_time": "1:03:50"}
+{"current_steps": 570, "total_steps": 4030, "loss": 0.1246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.542968197005367e-05, "epoch": 1.41, "percentage": 14.14, "elapsed_time": "0:10:26", "remaining_time": "1:03:20"}
+{"current_steps": 580, "total_steps": 4030, "loss": 0.1097, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.526467546985048e-05, "epoch": 1.44, "percentage": 14.39, "elapsed_time": "0:10:33", "remaining_time": "1:02:49"}
+{"current_steps": 590, "total_steps": 4030, "loss": 0.0995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.509689073969088e-05, "epoch": 1.46, "percentage": 14.64, "elapsed_time": "0:10:41", "remaining_time": "1:02:20"}
+{"current_steps": 600, "total_steps": 4030, "loss": 0.0715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.492633807777227e-05, "epoch": 1.49, "percentage": 14.89, "elapsed_time": "0:10:49", "remaining_time": "1:01:52"}
+{"current_steps": 600, "total_steps": 4030, "loss": null, "eval_loss": 0.0493486262857914, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.49, "percentage": 14.89, "elapsed_time": "0:10:49", "remaining_time": "1:01:52"}
+{"current_steps": 610, "total_steps": 4030, "loss": 0.0715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.475302795218061e-05, "epoch": 1.51, "percentage": 15.14, "elapsed_time": "0:11:14", "remaining_time": "1:02:59"}
+{"current_steps": 620, "total_steps": 4030, "loss": 0.0797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.457697100024798e-05, "epoch": 1.54, "percentage": 15.38, "elapsed_time": "0:11:22", "remaining_time": "1:02:31"}
+{"current_steps": 630, "total_steps": 4030, "loss": 0.065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.439817802789958e-05, "epoch": 1.56, "percentage": 15.63, "elapsed_time": "0:11:29", "remaining_time": "1:02:03"}
+{"current_steps": 640, "total_steps": 4030, "loss": 0.0534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.421666000899052e-05, "epoch": 1.59, "percentage": 15.88, "elapsed_time": "0:11:37", "remaining_time": "1:01:33"}
+{"current_steps": 650, "total_steps": 4030, "loss": 0.0695, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.403242808463237e-05, "epoch": 1.61, "percentage": 16.13, "elapsed_time": "0:11:44", "remaining_time": "1:01:05"}
+{"current_steps": 650, "total_steps": 4030, "loss": null, "eval_loss": 0.047055672854185104, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.61, "percentage": 16.13, "elapsed_time": "0:11:44", "remaining_time": "1:01:05"}
+{"current_steps": 660, "total_steps": 4030, "loss": 0.0259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.38454935625092e-05, "epoch": 1.64, "percentage": 16.38, "elapsed_time": "0:12:09", "remaining_time": "1:02:06"}
+{"current_steps": 670, "total_steps": 4030, "loss": 0.0388, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.365586791618368e-05, "epoch": 1.66, "percentage": 16.63, "elapsed_time": "0:12:17", "remaining_time": "1:01:38"}
+{"current_steps": 680, "total_steps": 4030, "loss": 0.0514, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.346356278439275e-05, "epoch": 1.69, "percentage": 16.87, "elapsed_time": "0:12:25", "remaining_time": "1:01:13"}
+{"current_steps": 690, "total_steps": 4030, "loss": 0.0382, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.32685899703333e-05, "epoch": 1.71, "percentage": 17.12, "elapsed_time": "0:12:33", "remaining_time": "1:00:46"}
+{"current_steps": 700, "total_steps": 4030, "loss": 0.0338, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.307096144093781e-05, "epoch": 1.74, "percentage": 17.37, "elapsed_time": "0:12:41", "remaining_time": "1:00:21"}
+{"current_steps": 700, "total_steps": 4030, "loss": null, "eval_loss": 0.030666794627904892, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.74, "percentage": 17.37, "elapsed_time": "0:12:41", "remaining_time": "1:00:21"}
+{"current_steps": 710, "total_steps": 4030, "loss": 0.0635, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.287068932613968e-05, "epoch": 1.76, "percentage": 17.62, "elapsed_time": "0:13:05", "remaining_time": "1:01:14"}
+{"current_steps": 720, "total_steps": 4030, "loss": 0.0303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.266778591812886e-05, "epoch": 1.79, "percentage": 17.87, "elapsed_time": "0:13:13", "remaining_time": "1:00:47"}
+{"current_steps": 730, "total_steps": 4030, "loss": 0.0094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.246226367059736e-05, "epoch": 1.81, "percentage": 18.11, "elapsed_time": "0:13:21", "remaining_time": "1:00:21"}
+{"current_steps": 740, "total_steps": 4030, "loss": 0.0217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.225413519797482e-05, "epoch": 1.84, "percentage": 18.36, "elapsed_time": "0:13:28", "remaining_time": "0:59:55"}
+{"current_steps": 750, "total_steps": 4030, "loss": 0.0422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.204341327465434e-05, "epoch": 1.86, "percentage": 18.61, "elapsed_time": "0:13:36", "remaining_time": "0:59:30"}
+{"current_steps": 750, "total_steps": 4030, "loss": null, "eval_loss": 0.02686377428472042, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.86, "percentage": 18.61, "elapsed_time": "0:13:36", "remaining_time": "0:59:30"}
+{"current_steps": 760, "total_steps": 4030, "loss": 0.046, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.183011083420838e-05, "epoch": 1.89, "percentage": 18.86, "elapsed_time": "0:14:00", "remaining_time": "1:00:17"}
+{"current_steps": 770, "total_steps": 4030, "loss": 0.0192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.161424096859493e-05, "epoch": 1.91, "percentage": 19.11, "elapsed_time": "0:14:08", "remaining_time": "0:59:52"}
+{"current_steps": 780, "total_steps": 4030, "loss": 0.0159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.139581692735394e-05, "epoch": 1.94, "percentage": 19.35, "elapsed_time": "0:14:16", "remaining_time": "0:59:27"}
+{"current_steps": 790, "total_steps": 4030, "loss": 0.0188, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.11748521167942e-05, "epoch": 1.96, "percentage": 19.6, "elapsed_time": "0:14:24", "remaining_time": "0:59:04"}
+{"current_steps": 800, "total_steps": 4030, "loss": 0.0183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.095136009917036e-05, "epoch": 1.99, "percentage": 19.85, "elapsed_time": "0:14:31", "remaining_time": "0:58:39"}
+{"current_steps": 800, "total_steps": 4030, "loss": null, "eval_loss": 0.009065705351531506, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.99, "percentage": 19.85, "elapsed_time": "0:14:31", "remaining_time": "0:58:39"}
+{"current_steps": 810, "total_steps": 4030, "loss": 0.0317, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.072535459185056e-05, "epoch": 2.01, "percentage": 20.1, "elapsed_time": "0:14:56", "remaining_time": "0:59:23"}
+{"current_steps": 820, "total_steps": 4030, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.049684946647459e-05, "epoch": 2.03, "percentage": 20.35, "elapsed_time": "0:15:04", "remaining_time": "0:58:59"}
+{"current_steps": 830, "total_steps": 4030, "loss": 0.0009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.026585874810227e-05, "epoch": 2.06, "percentage": 20.6, "elapsed_time": "0:15:11", "remaining_time": "0:58:35"}
+{"current_steps": 840, "total_steps": 4030, "loss": 0.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.003239661435289e-05, "epoch": 2.08, "percentage": 20.84, "elapsed_time": "0:15:19", "remaining_time": "0:58:13"}
+{"current_steps": 850, "total_steps": 4030, "loss": 0.0055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.979647739453481e-05, "epoch": 2.11, "percentage": 21.09, "elapsed_time": "0:15:27", "remaining_time": "0:57:50"}
+{"current_steps": 850, "total_steps": 4030, "loss": null, "eval_loss": 0.007036147639155388, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.11, "percentage": 21.09, "elapsed_time": "0:15:27", "remaining_time": "0:57:50"}
+{"current_steps": 860, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.955811556876605e-05, "epoch": 2.13, "percentage": 21.34, "elapsed_time": "0:15:51", "remaining_time": "0:58:29"}
+{"current_steps": 870, "total_steps": 4030, "loss": 0.0172, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.93173257670856e-05, "epoch": 2.16, "percentage": 21.59, "elapsed_time": "0:15:59", "remaining_time": "0:58:05"}
+{"current_steps": 880, "total_steps": 4030, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.907412276855531e-05, "epoch": 2.18, "percentage": 21.84, "elapsed_time": "0:16:07", "remaining_time": "0:57:42"}
+{"current_steps": 890, "total_steps": 4030, "loss": 0.0025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.882852150035295e-05, "epoch": 2.21, "percentage": 22.08, "elapsed_time": "0:16:15", "remaining_time": "0:57:20"}
+{"current_steps": 900, "total_steps": 4030, "loss": 0.0208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.858053703685587e-05, "epoch": 2.23, "percentage": 22.33, "elapsed_time": "0:16:22", "remaining_time": "0:56:57"}
+{"current_steps": 900, "total_steps": 4030, "loss": null, "eval_loss": 0.003154078498482704, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.23, "percentage": 22.33, "elapsed_time": "0:16:22", "remaining_time": "0:56:57"}
+{"current_steps": 910, "total_steps": 4030, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.833018459871594e-05, "epoch": 2.26, "percentage": 22.58, "elapsed_time": "0:16:47", "remaining_time": "0:57:32"}
+{"current_steps": 920, "total_steps": 4030, "loss": 0.0139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.807747955192516e-05, "epoch": 2.28, "percentage": 22.83, "elapsed_time": "0:16:55", "remaining_time": "0:57:11"}
+{"current_steps": 930, "total_steps": 4030, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.782243740687273e-05, "epoch": 2.31, "percentage": 23.08, "elapsed_time": "0:17:02", "remaining_time": "0:56:49"}
+{"current_steps": 940, "total_steps": 4030, "loss": 0.0149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.756507381739288e-05, "epoch": 2.33, "percentage": 23.33, "elapsed_time": "0:17:10", "remaining_time": "0:56:28"}
+{"current_steps": 950, "total_steps": 4030, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.730540457980418e-05, "epoch": 2.36, "percentage": 23.57, "elapsed_time": "0:17:18", "remaining_time": "0:56:06"}
+{"current_steps": 950, "total_steps": 4030, "loss": null, "eval_loss": 0.002297737170010805, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.36, "percentage": 23.57, "elapsed_time": "0:17:18", "remaining_time": "0:56:06"}
+{"current_steps": 960, "total_steps": 4030, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.704344563193997e-05, "epoch": 2.38, "percentage": 23.82, "elapsed_time": "0:17:43", "remaining_time": "0:56:40"}
+{"current_steps": 970, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.677921305217023e-05, "epoch": 2.41, "percentage": 24.07, "elapsed_time": "0:17:50", "remaining_time": "0:56:18"}
+{"current_steps": 980, "total_steps": 4030, "loss": 0.0207, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.651272305841454e-05, "epoch": 2.43, "percentage": 24.32, "elapsed_time": "0:17:58", "remaining_time": "0:55:57"}
+{"current_steps": 990, "total_steps": 4030, "loss": 0.0011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.62439920071468e-05, "epoch": 2.46, "percentage": 24.57, "elapsed_time": "0:18:06", "remaining_time": "0:55:35"}
+{"current_steps": 1000, "total_steps": 4030, "loss": 0.0117, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.597303639239134e-05, "epoch": 2.48, "percentage": 24.81, "elapsed_time": "0:18:13", "remaining_time": "0:55:14"}
+{"current_steps": 1000, "total_steps": 4030, "loss": null, "eval_loss": 0.0033970780204981565, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.48, "percentage": 24.81, "elapsed_time": "0:18:13", "remaining_time": "0:55:14"}
+{"current_steps": 1010, "total_steps": 4030, "loss": 0.0026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.569987284471046e-05, "epoch": 2.51, "percentage": 25.06, "elapsed_time": "0:18:39", "remaining_time": "0:55:45"}
+{"current_steps": 1020, "total_steps": 4030, "loss": 0.0022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.542451813018372e-05, "epoch": 2.53, "percentage": 25.31, "elapsed_time": "0:18:46", "remaining_time": "0:55:25"}
+{"current_steps": 1030, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.514698914937894e-05, "epoch": 2.56, "percentage": 25.56, "elapsed_time": "0:18:54", "remaining_time": "0:55:04"}
+{"current_steps": 1040, "total_steps": 4030, "loss": 0.0019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.486730293631481e-05, "epoch": 2.58, "percentage": 25.81, "elapsed_time": "0:19:02", "remaining_time": "0:54:44"}
+{"current_steps": 1050, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.458547665741543e-05, "epoch": 2.61, "percentage": 26.05, "elapsed_time": "0:19:09", "remaining_time": "0:54:23"}
+{"current_steps": 1050, "total_steps": 4030, "loss": null, "eval_loss": 0.001217635115608573, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.61, "percentage": 26.05, "elapsed_time": "0:19:09", "remaining_time": "0:54:23"}
+{"current_steps": 1060, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.430152761045664e-05, "epoch": 2.63, "percentage": 26.3, "elapsed_time": "0:19:34", "remaining_time": "0:54:50"}
+{"current_steps": 1070, "total_steps": 4030, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.401547322350438e-05, "epoch": 2.66, "percentage": 26.55, "elapsed_time": "0:19:42", "remaining_time": "0:54:31"}
+{"current_steps": 1080, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.372733105384496e-05, "epoch": 2.68, "percentage": 26.8, "elapsed_time": "0:19:50", "remaining_time": "0:54:11"}
+{"current_steps": 1090, "total_steps": 4030, "loss": 0.0171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.343711878690746e-05, "epoch": 2.7, "percentage": 27.05, "elapsed_time": "0:19:57", "remaining_time": "0:53:51"}
+{"current_steps": 1100, "total_steps": 4030, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.314485423517819e-05, "epoch": 2.73, "percentage": 27.3, "elapsed_time": "0:20:05", "remaining_time": "0:53:31"}
+{"current_steps": 1100, "total_steps": 4030, "loss": null, "eval_loss": 0.0012037238338962197, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.73, "percentage": 27.3, "elapsed_time": "0:20:05", "remaining_time": "0:53:31"}
+{"current_steps": 1110, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.285055533710753e-05, "epoch": 2.75, "percentage": 27.54, "elapsed_time": "0:20:30", "remaining_time": "0:53:56"}
+{"current_steps": 1120, "total_steps": 4030, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.255424015600876e-05, "epoch": 2.78, "percentage": 27.79, "elapsed_time": "0:20:38", "remaining_time": "0:53:37"}
+{"current_steps": 1130, "total_steps": 4030, "loss": 0.0028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.225592687894949e-05, "epoch": 2.8, "percentage": 28.04, "elapsed_time": "0:20:45", "remaining_time": "0:53:16"}
+{"current_steps": 1140, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.195563381563536e-05, "epoch": 2.83, "percentage": 28.29, "elapsed_time": "0:20:53", "remaining_time": "0:52:57"}
+{"current_steps": 1150, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.165337939728614e-05, "epoch": 2.85, "percentage": 28.54, "elapsed_time": "0:21:00", "remaining_time": "0:52:37"}
+{"current_steps": 1150, "total_steps": 4030, "loss": null, "eval_loss": 0.0012541119940578938, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.85, "percentage": 28.54, "elapsed_time": "0:21:00", "remaining_time": "0:52:37"}
+{"current_steps": 1160, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.134918217550467e-05, "epoch": 2.88, "percentage": 28.78, "elapsed_time": "0:21:25", "remaining_time": "0:53:01"}
+{"current_steps": 1170, "total_steps": 4030, "loss": 0.0017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.104306082113802e-05, "epoch": 2.9, "percentage": 29.03, "elapsed_time": "0:21:33", "remaining_time": "0:52:41"}
+{"current_steps": 1180, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.073503412313159e-05, "epoch": 2.93, "percentage": 29.28, "elapsed_time": "0:21:41", "remaining_time": "0:52:22"}
+{"current_steps": 1190, "total_steps": 4030, "loss": 0.001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.042512098737598e-05, "epoch": 2.95, "percentage": 29.53, "elapsed_time": "0:21:48", "remaining_time": "0:52:02"}
+{"current_steps": 1200, "total_steps": 4030, "loss": 0.0104, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.01133404355464e-05, "epoch": 2.98, "percentage": 29.78, "elapsed_time": "0:21:56", "remaining_time": "0:51:44"}
+{"current_steps": 1200, "total_steps": 4030, "loss": null, "eval_loss": 0.0007884196820668876, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.98, "percentage": 29.78, "elapsed_time": "0:21:56", "remaining_time": "0:51:44"}
+{"current_steps": 1210, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.979971160393535e-05, "epoch": 3.0, "percentage": 30.02, "elapsed_time": "0:22:20", "remaining_time": "0:52:05"}
+{"current_steps": 1220, "total_steps": 4030, "loss": 0.0131, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.948425374227799e-05, "epoch": 3.03, "percentage": 30.27, "elapsed_time": "0:22:28", "remaining_time": "0:51:46"}
+{"current_steps": 1230, "total_steps": 4030, "loss": 0.0006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.916698621257068e-05, "epoch": 3.05, "percentage": 30.52, "elapsed_time": "0:22:36", "remaining_time": "0:51:27"}
+{"current_steps": 1240, "total_steps": 4030, "loss": 0.0028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.884792848788257e-05, "epoch": 3.08, "percentage": 30.77, "elapsed_time": "0:22:43", "remaining_time": "0:51:08"}
+{"current_steps": 1250, "total_steps": 4030, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.852710015116036e-05, "epoch": 3.1, "percentage": 31.02, "elapsed_time": "0:22:51", "remaining_time": "0:50:50"}
+{"current_steps": 1250, "total_steps": 4030, "loss": null, "eval_loss": 0.0018942987080663443, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.1, "percentage": 31.02, "elapsed_time": "0:22:51", "remaining_time": "0:50:50"}
+{"current_steps": 1260, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.820452089402645e-05, "epoch": 3.13, "percentage": 31.27, "elapsed_time": "0:23:16", "remaining_time": "0:51:10"}
+{"current_steps": 1270, "total_steps": 4030, "loss": 0.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.788021051557022e-05, "epoch": 3.15, "percentage": 31.51, "elapsed_time": "0:23:24", "remaining_time": "0:50:52"}
+{"current_steps": 1280, "total_steps": 4030, "loss": 0.0006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.755418892113282e-05, "epoch": 3.18, "percentage": 31.76, "elapsed_time": "0:23:32", "remaining_time": "0:50:33"}
+{"current_steps": 1290, "total_steps": 4030, "loss": 0.0011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.722647612108553e-05, "epoch": 3.2, "percentage": 32.01, "elapsed_time": "0:23:39", "remaining_time": "0:50:15"}
+{"current_steps": 1300, "total_steps": 4030, "loss": 0.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.689709222960144e-05, "epoch": 3.23, "percentage": 32.26, "elapsed_time": "0:23:47", "remaining_time": "0:49:57"}
+{"current_steps": 1300, "total_steps": 4030, "loss": null, "eval_loss": 0.00915015209466219, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.23, "percentage": 32.26, "elapsed_time": "0:23:47", "remaining_time": "0:49:57"}
+{"current_steps": 1310, "total_steps": 4030, "loss": 0.0118, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.656605746342096e-05, "epoch": 3.25, "percentage": 32.51, "elapsed_time": "0:24:12", "remaining_time": "0:50:14"}
+{"current_steps": 1320, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.6233392140611e-05, "epoch": 3.28, "percentage": 32.75, "elapsed_time": "0:24:19", "remaining_time": "0:49:56"}
+{"current_steps": 1330, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.589911667931786e-05, "epoch": 3.3, "percentage": 33.0, "elapsed_time": "0:24:27", "remaining_time": "0:49:38"}
+{"current_steps": 1340, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.556325159651399e-05, "epoch": 3.33, "percentage": 33.25, "elapsed_time": "0:24:35", "remaining_time": "0:49:21"}
+{"current_steps": 1350, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.522581750673872e-05, "epoch": 3.35, "percentage": 33.5, "elapsed_time": "0:24:42", "remaining_time": "0:49:03"}
+{"current_steps": 1350, "total_steps": 4030, "loss": null, "eval_loss": 0.0016158341895788908, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.35, "percentage": 33.5, "elapsed_time": "0:24:42", "remaining_time": "0:49:03"}
+{"current_steps": 1360, "total_steps": 4030, "loss": 0.0005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.48868351208331e-05, "epoch": 3.37, "percentage": 33.75, "elapsed_time": "0:25:07", "remaining_time": "0:49:19"}
+{"current_steps": 1370, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.454632524466857e-05, "epoch": 3.4, "percentage": 34.0, "elapsed_time": "0:25:15", "remaining_time": "0:49:02"}
+{"current_steps": 1380, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.420430877787004e-05, "epoch": 3.42, "percentage": 34.24, "elapsed_time": "0:25:22", "remaining_time": "0:48:44"}
+{"current_steps": 1390, "total_steps": 4030, "loss": 0.004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.386080671253307e-05, "epoch": 3.45, "percentage": 34.49, "elapsed_time": "0:25:30", "remaining_time": "0:48:26"}
+{"current_steps": 1400, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.351584013193543e-05, "epoch": 3.47, "percentage": 34.74, "elapsed_time": "0:25:38", "remaining_time": "0:48:10"}
+{"current_steps": 1400, "total_steps": 4030, "loss": null, "eval_loss": 0.000445638841483742, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.47, "percentage": 34.74, "elapsed_time": "0:25:38", "remaining_time": "0:48:10"}
+{"current_steps": 1410, "total_steps": 4030, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.316943020924319e-05, "epoch": 3.5, "percentage": 34.99, "elapsed_time": "0:26:03", "remaining_time": "0:48:24"}
+{"current_steps": 1420, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.2821598206211e-05, "epoch": 3.52, "percentage": 35.24, "elapsed_time": "0:26:10", "remaining_time": "0:48:07"}
+{"current_steps": 1430, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.247236547187716e-05, "epoch": 3.55, "percentage": 35.48, "elapsed_time": "0:26:18", "remaining_time": "0:47:49"}
+{"current_steps": 1440, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.212175344125327e-05, "epoch": 3.57, "percentage": 35.73, "elapsed_time": "0:26:26", "remaining_time": "0:47:32"}
+{"current_steps": 1450, "total_steps": 4030, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.176978363400863e-05, "epoch": 3.6, "percentage": 35.98, "elapsed_time": "0:26:33", "remaining_time": "0:47:16"}
+{"current_steps": 1450, "total_steps": 4030, "loss": null, "eval_loss": 0.0003264049591962248, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.6, "percentage": 35.98, "elapsed_time": "0:26:33", "remaining_time": "0:47:16"}
+{"current_steps": 1460, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.141647765314938e-05, "epoch": 3.62, "percentage": 36.23, "elapsed_time": "0:26:58", "remaining_time": "0:47:28"}
+{"current_steps": 1470, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.106185718369259e-05, "epoch": 3.65, "percentage": 36.48, "elapsed_time": "0:27:06", "remaining_time": "0:47:11"}
+{"current_steps": 1480, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.070594399133525e-05, "epoch": 3.67, "percentage": 36.72, "elapsed_time": "0:27:13", "remaining_time": "0:46:55"}
+{"current_steps": 1490, "total_steps": 4030, "loss": 0.0038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.03487599211184e-05, "epoch": 3.7, "percentage": 36.97, "elapsed_time": "0:27:21", "remaining_time": "0:46:38"}
+{"current_steps": 1500, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.999032689608629e-05, "epoch": 3.72, "percentage": 37.22, "elapsed_time": "0:27:29", "remaining_time": "0:46:22"}
+{"current_steps": 1500, "total_steps": 4030, "loss": null, "eval_loss": 0.009298658929765224, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.72, "percentage": 37.22, "elapsed_time": "0:27:29", "remaining_time": "0:46:22"}
+{"current_steps": 1510, "total_steps": 4030, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.963066691594084e-05, "epoch": 3.75, "percentage": 37.47, "elapsed_time": "0:27:54", "remaining_time": "0:46:34"}
+{"current_steps": 1520, "total_steps": 4030, "loss": 0.0113, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.926980205569136e-05, "epoch": 3.77, "percentage": 37.72, "elapsed_time": "0:28:02", "remaining_time": "0:46:17"}
+{"current_steps": 1530, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.890775446429954e-05, "epoch": 3.8, "percentage": 37.97, "elapsed_time": "0:28:09", "remaining_time": "0:46:01"}
+{"current_steps": 1540, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.854454636332013e-05, "epoch": 3.82, "percentage": 38.21, "elapsed_time": "0:28:17", "remaining_time": "0:45:44"}
+{"current_steps": 1550, "total_steps": 4030, "loss": 0.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.818020004553702e-05, "epoch": 3.85, "percentage": 38.46, "elapsed_time": "0:28:25", "remaining_time": "0:45:28"}
+{"current_steps": 1550, "total_steps": 4030, "loss": null, "eval_loss": 0.0031606056727468967, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.85, "percentage": 38.46, "elapsed_time": "0:28:25", "remaining_time": "0:45:28"}
+{"current_steps": 1560, "total_steps": 4030, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.781473787359488e-05, "epoch": 3.87, "percentage": 38.71, "elapsed_time": "0:28:50", "remaining_time": "0:45:39"}
+{"current_steps": 1570, "total_steps": 4030, "loss": 0.0131, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.744818227862668e-05, "epoch": 3.9, "percentage": 38.96, "elapsed_time": "0:28:57", "remaining_time": "0:45:22"}
+{"current_steps": 1580, "total_steps": 4030, "loss": 0.0042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.708055575887687e-05, "epoch": 3.92, "percentage": 39.21, "elapsed_time": "0:29:05", "remaining_time": "0:45:06"}
+{"current_steps": 1590, "total_steps": 4030, "loss": 0.0056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.671188087832057e-05, "epoch": 3.95, "percentage": 39.45, "elapsed_time": "0:29:13", "remaining_time": "0:44:50"}
+{"current_steps": 1600, "total_steps": 4030, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.634218026527856e-05, "epoch": 3.97, "percentage": 39.7, "elapsed_time": "0:29:20", "remaining_time": "0:44:34"}
+{"current_steps": 1600, "total_steps": 4030, "loss": null, "eval_loss": 0.002365908119827509, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.97, "percentage": 39.7, "elapsed_time": "0:29:20", "remaining_time": "0:44:34"}
+{"current_steps": 1610, "total_steps": 4030, "loss": 0.002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.59714766110285e-05, "epoch": 4.0, "percentage": 39.95, "elapsed_time": "0:29:45", "remaining_time": "0:44:43"}
+{"current_steps": 1620, "total_steps": 4030, "loss": 0.005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.559979266841209e-05, "epoch": 4.02, "percentage": 40.2, "elapsed_time": "0:29:52", "remaining_time": "0:44:27"}
+{"current_steps": 1630, "total_steps": 4030, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.522715125043868e-05, "epoch": 4.04, "percentage": 40.45, "elapsed_time": "0:30:00", "remaining_time": "0:44:11"}
+{"current_steps": 1640, "total_steps": 4030, "loss": 0.0028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.485357522888496e-05, "epoch": 4.07, "percentage": 40.69, "elapsed_time": "0:30:08", "remaining_time": "0:43:55"}
+{"current_steps": 1650, "total_steps": 4030, "loss": 0.0032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.447908753289127e-05, "epoch": 4.09, "percentage": 40.94, "elapsed_time": "0:30:15", "remaining_time": "0:43:39"}
+{"current_steps": 1650, "total_steps": 4030, "loss": null, "eval_loss": 0.00048677672748453915, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.09, "percentage": 40.94, "elapsed_time": "0:30:15", "remaining_time": "0:43:39"}
+{"current_steps": 1660, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.410371114755409e-05, "epoch": 4.12, "percentage": 41.19, "elapsed_time": "0:30:40", "remaining_time": "0:43:47"}
+{"current_steps": 1670, "total_steps": 4030, "loss": 0.0003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.372746911251548e-05, "epoch": 4.14, "percentage": 41.44, "elapsed_time": "0:30:48", "remaining_time": "0:43:31"}
+{"current_steps": 1680, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.335038452054878e-05, "epoch": 4.17, "percentage": 41.69, "elapsed_time": "0:30:55", "remaining_time": "0:43:15"}
+{"current_steps": 1690, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.297248051614137e-05, "epoch": 4.19, "percentage": 41.94, "elapsed_time": "0:31:03", "remaining_time": "0:43:00"}
+{"current_steps": 1700, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.259378029407407e-05, "epoch": 4.22, "percentage": 42.18, "elapsed_time": "0:31:11", "remaining_time": "0:42:45"}
+{"current_steps": 1700, "total_steps": 4030, "loss": null, "eval_loss": 0.003695528022944927, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.22, "percentage": 42.18, "elapsed_time": "0:31:11", "remaining_time": "0:42:45"}
+{"current_steps": 1710, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.221430709799746e-05, "epoch": 4.24, "percentage": 42.43, "elapsed_time": "0:31:36", "remaining_time": "0:42:52"}
+{"current_steps": 1720, "total_steps": 4030, "loss": 0.0064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.183408421900532e-05, "epoch": 4.27, "percentage": 42.68, "elapsed_time": "0:31:43", "remaining_time": "0:42:36"}
+{"current_steps": 1730, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.145313499420506e-05, "epoch": 4.29, "percentage": 42.93, "elapsed_time": "0:31:51", "remaining_time": "0:42:21"}
+{"current_steps": 1740, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.10714828052853e-05, "epoch": 4.32, "percentage": 43.18, "elapsed_time": "0:31:59", "remaining_time": "0:42:05"}
+{"current_steps": 1750, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.068915107708084e-05, "epoch": 4.34, "percentage": 43.42, "elapsed_time": "0:32:06", "remaining_time": "0:41:50"}
+{"current_steps": 1750, "total_steps": 4030, "loss": null, "eval_loss": 0.000846256734803319, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.34, "percentage": 43.42, "elapsed_time": "0:32:06", "remaining_time": "0:41:50"}
+{"current_steps": 1760, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.030616327613482e-05, "epoch": 4.37, "percentage": 43.67, "elapsed_time": "0:32:31", "remaining_time": "0:41:57"}
+{"current_steps": 1770, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.992254290925847e-05, "epoch": 4.39, "percentage": 43.92, "elapsed_time": "0:32:39", "remaining_time": "0:41:41"}
+{"current_steps": 1780, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.953831352208831e-05, "epoch": 4.42, "percentage": 44.17, "elapsed_time": "0:32:47", "remaining_time": "0:41:26"}
+{"current_steps": 1790, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.915349869764093e-05, "epoch": 4.44, "percentage": 44.42, "elapsed_time": "0:32:54", "remaining_time": "0:41:11"}
+{"current_steps": 1800, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.87681220548656e-05, "epoch": 4.47, "percentage": 44.67, "elapsed_time": "0:33:02", "remaining_time": "0:40:56"}
+{"current_steps": 1800, "total_steps": 4030, "loss": null, "eval_loss": 0.0008095924276858568, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.47, "percentage": 44.67, "elapsed_time": "0:33:02", "remaining_time": "0:40:56"}
+{"current_steps": 1810, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.838220724719454e-05, "epoch": 4.49, "percentage": 44.91, "elapsed_time": "0:33:27", "remaining_time": "0:41:01"}
+{"current_steps": 1820, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.7995777961091167e-05, "epoch": 4.52, "percentage": 45.16, "elapsed_time": "0:33:34", "remaining_time": "0:40:46"}
+{"current_steps": 1830, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.760885791459627e-05, "epoch": 4.54, "percentage": 45.41, "elapsed_time": "0:33:42", "remaining_time": "0:40:31"}
+{"current_steps": 1840, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.722147085587223e-05, "epoch": 4.57, "percentage": 45.66, "elapsed_time": "0:33:50", "remaining_time": "0:40:16"}
+{"current_steps": 1850, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.683364056174545e-05, "epoch": 4.59, "percentage": 45.91, "elapsed_time": "0:33:57", "remaining_time": "0:40:01"}
+{"current_steps": 1850, "total_steps": 4030, "loss": null, "eval_loss": 0.0008772177388891578, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.59, "percentage": 45.91, "elapsed_time": "0:33:57", "remaining_time": "0:40:01"}
+{"current_steps": 1860, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.644539083624701e-05, "epoch": 4.62, "percentage": 46.15, "elapsed_time": "0:34:22", "remaining_time": "0:40:06"}
+{"current_steps": 1870, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.605674550915161e-05, "epoch": 4.64, "percentage": 46.4, "elapsed_time": "0:34:29", "remaining_time": "0:39:50"}
+{"current_steps": 1880, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.566772843451495e-05, "epoch": 4.67, "percentage": 46.65, "elapsed_time": "0:34:37", "remaining_time": "0:39:35"}
+{"current_steps": 1890, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.527836348920965e-05, "epoch": 4.69, "percentage": 46.9, "elapsed_time": "0:34:45", "remaining_time": "0:39:20"}
+{"current_steps": 1900, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.488867457145974e-05, "epoch": 4.71, "percentage": 47.15, "elapsed_time": "0:34:52", "remaining_time": "0:39:06"}
+{"current_steps": 1900, "total_steps": 4030, "loss": null, "eval_loss": 0.0006057315040379763, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.71, "percentage": 47.15, "elapsed_time": "0:34:52", "remaining_time": "0:39:06"}
+{"current_steps": 1910, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.449868559937384e-05, "epoch": 4.74, "percentage": 47.39, "elapsed_time": "0:35:17", "remaining_time": "0:39:10"}
+{"current_steps": 1920, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.4108420509477145e-05, "epoch": 4.76, "percentage": 47.64, "elapsed_time": "0:35:24", "remaining_time": "0:38:55"}
+{"current_steps": 1930, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.3717903255242284e-05, "epoch": 4.79, "percentage": 47.89, "elapsed_time": "0:35:32", "remaining_time": "0:38:40"}
+{"current_steps": 1940, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.3327157805619035e-05, "epoch": 4.81, "percentage": 48.14, "elapsed_time": "0:35:40", "remaining_time": "0:38:25"}
+{"current_steps": 1950, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.293620814356326e-05, "epoch": 4.84, "percentage": 48.39, "elapsed_time": "0:35:48", "remaining_time": "0:38:11"}
+{"current_steps": 1950, "total_steps": 4030, "loss": null, "eval_loss": 0.0001224023144459352, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.84, "percentage": 48.39, "elapsed_time": "0:35:48", "remaining_time": "0:38:11"}
+{"current_steps": 1960, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.254507826456483e-05, "epoch": 4.86, "percentage": 48.64, "elapsed_time": "0:36:12", "remaining_time": "0:38:14"}
+{"current_steps": 1970, "total_steps": 4030, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.215379217517492e-05, "epoch": 4.89, "percentage": 48.88, "elapsed_time": "0:36:21", "remaining_time": "0:38:00"}
+{"current_steps": 1980, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.176237389153246e-05, "epoch": 4.91, "percentage": 49.13, "elapsed_time": "0:36:28", "remaining_time": "0:37:46"}
+{"current_steps": 1990, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.137084743789012e-05, "epoch": 4.94, "percentage": 49.38, "elapsed_time": "0:36:36", "remaining_time": "0:37:31"}
+{"current_steps": 2000, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.097923684513979e-05, "epoch": 4.96, "percentage": 49.63, "elapsed_time": "0:36:43", "remaining_time": "0:37:16"}
+{"current_steps": 2000, "total_steps": 4030, "loss": null, "eval_loss": 0.0007657750975340605, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.96, "percentage": 49.63, "elapsed_time": "0:36:43", "remaining_time": "0:37:16"}
+{"current_steps": 2010, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.058756614933757e-05, "epoch": 4.99, "percentage": 49.88, "elapsed_time": "0:37:08", "remaining_time": "0:37:19"}
+{"current_steps": 2020, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.019585939022859e-05, "epoch": 5.01, "percentage": 50.12, "elapsed_time": "0:37:16", "remaining_time": "0:37:05"}
+{"current_steps": 2030, "total_steps": 4030, "loss": 0.0089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.980414060977142e-05, "epoch": 5.04, "percentage": 50.37, "elapsed_time": "0:37:24", "remaining_time": "0:36:51"}
+{"current_steps": 2040, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9412433850662434e-05, "epoch": 5.06, "percentage": 50.62, "elapsed_time": "0:37:31", "remaining_time": "0:36:36"}
+{"current_steps": 2050, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.902076315486023e-05, "epoch": 5.09, "percentage": 50.87, "elapsed_time": "0:37:39", "remaining_time": "0:36:22"}
+{"current_steps": 2050, "total_steps": 4030, "loss": null, "eval_loss": 0.00010947392001980916, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.09, "percentage": 50.87, "elapsed_time": "0:37:39", "remaining_time": "0:36:22"}
+{"current_steps": 2060, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.86291525621099e-05, "epoch": 5.11, "percentage": 51.12, "elapsed_time": "0:38:04", "remaining_time": "0:36:24"}
+{"current_steps": 2070, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.823762610846755e-05, "epoch": 5.14, "percentage": 51.36, "elapsed_time": "0:38:11", "remaining_time": "0:36:10"}
+{"current_steps": 2080, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.784620782482509e-05, "epoch": 5.16, "percentage": 51.61, "elapsed_time": "0:38:19", "remaining_time": "0:35:55"}
+{"current_steps": 2090, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.745492173543517e-05, "epoch": 5.19, "percentage": 51.86, "elapsed_time": "0:38:27", "remaining_time": "0:35:41"}
+{"current_steps": 2100, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.706379185643675e-05, "epoch": 5.21, "percentage": 52.11, "elapsed_time": "0:38:35", "remaining_time": "0:35:27"}
+{"current_steps": 2100, "total_steps": 4030, "loss": null, "eval_loss": 0.00016069799312390387, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.21, "percentage": 52.11, "elapsed_time": "0:38:35", "remaining_time": "0:35:27"}
+{"current_steps": 2110, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.667284219438098e-05, "epoch": 5.24, "percentage": 52.36, "elapsed_time": "0:38:59", "remaining_time": "0:35:29"}
+{"current_steps": 2120, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.628209674475773e-05, "epoch": 5.26, "percentage": 52.61, "elapsed_time": "0:39:07", "remaining_time": "0:35:15"}
+{"current_steps": 2130, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.589157949052287e-05, "epoch": 5.29, "percentage": 52.85, "elapsed_time": "0:39:15", "remaining_time": "0:35:01"}
+{"current_steps": 2140, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.550131440062617e-05, "epoch": 5.31, "percentage": 53.1, "elapsed_time": "0:39:23", "remaining_time": "0:34:47"}
+{"current_steps": 2150, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.511132542854027e-05, "epoch": 5.33, "percentage": 53.35, "elapsed_time": "0:39:30", "remaining_time": "0:34:33"}
+{"current_steps": 2150, "total_steps": 4030, "loss": null, "eval_loss": 0.00017579211271367967, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.33, "percentage": 53.35, "elapsed_time": "0:39:30", "remaining_time": "0:34:33"}
+{"current_steps": 2160, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4721636510790365e-05, "epoch": 5.36, "percentage": 53.6, "elapsed_time": "0:39:55", "remaining_time": "0:34:33"}
+{"current_steps": 2170, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4332271565485053e-05, "epoch": 5.38, "percentage": 53.85, "elapsed_time": "0:40:02", "remaining_time": "0:34:19"}
+{"current_steps": 2180, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.39432544908484e-05, "epoch": 5.41, "percentage": 54.09, "elapsed_time": "0:40:10", "remaining_time": "0:34:05"}
+{"current_steps": 2190, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.355460916375299e-05, "epoch": 5.43, "percentage": 54.34, "elapsed_time": "0:40:18", "remaining_time": "0:33:51"}
+{"current_steps": 2200, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3166359438254564e-05, "epoch": 5.46, "percentage": 54.59, "elapsed_time": "0:40:26", "remaining_time": "0:33:38"}
+{"current_steps": 2200, "total_steps": 4030, "loss": null, "eval_loss": 0.0004463446675799787, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.46, "percentage": 54.59, "elapsed_time": "0:40:26", "remaining_time": "0:33:38"}
+{"current_steps": 2210, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.27785291441278e-05, "epoch": 5.48, "percentage": 54.84, "elapsed_time": "0:40:50", "remaining_time": "0:33:38"}
+{"current_steps": 2220, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.239114208540374e-05, "epoch": 5.51, "percentage": 55.09, "elapsed_time": "0:40:58", "remaining_time": "0:33:24"}
+{"current_steps": 2230, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2004222038908845e-05, "epoch": 5.53, "percentage": 55.33, "elapsed_time": "0:41:06", "remaining_time": "0:33:10"}
+{"current_steps": 2240, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.161779275280546e-05, "epoch": 5.56, "percentage": 55.58, "elapsed_time": "0:41:14", "remaining_time": "0:32:57"}
+{"current_steps": 2250, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.123187794513441e-05, "epoch": 5.58, "percentage": 55.83, "elapsed_time": "0:41:21", "remaining_time": "0:32:43"}
+{"current_steps": 2250, "total_steps": 4030, "loss": null, "eval_loss": 0.00039042255957610905, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.58, "percentage": 55.83, "elapsed_time": "0:41:21", "remaining_time": "0:32:43"}
+{"current_steps": 2260, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.084650130235909e-05, "epoch": 5.61, "percentage": 56.08, "elapsed_time": "0:41:46", "remaining_time": "0:32:43"}
+{"current_steps": 2270, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.046168647791171e-05, "epoch": 5.63, "percentage": 56.33, "elapsed_time": "0:41:54", "remaining_time": "0:32:29"}
+{"current_steps": 2280, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.007745709074154e-05, "epoch": 5.66, "percentage": 56.58, "elapsed_time": "0:42:01", "remaining_time": "0:32:15"}
+{"current_steps": 2290, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.969383672386518e-05, "epoch": 5.68, "percentage": 56.82, "elapsed_time": "0:42:09", "remaining_time": "0:32:02"}
+{"current_steps": 2300, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.931084892291917e-05, "epoch": 5.71, "percentage": 57.07, "elapsed_time": "0:42:17", "remaining_time": "0:31:48"}
+{"current_steps": 2300, "total_steps": 4030, "loss": null, "eval_loss": 0.0004175197391305119, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.71, "percentage": 57.07, "elapsed_time": "0:42:17", "remaining_time": "0:31:48"}
+{"current_steps": 2310, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8928517194714706e-05, "epoch": 5.73, "percentage": 57.32, "elapsed_time": "0:42:42", "remaining_time": "0:31:47"}
+{"current_steps": 2320, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.854686500579494e-05, "epoch": 5.76, "percentage": 57.57, "elapsed_time": "0:42:50", "remaining_time": "0:31:34"}
+{"current_steps": 2330, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.816591578099468e-05, "epoch": 5.78, "percentage": 57.82, "elapsed_time": "0:42:57", "remaining_time": "0:31:20"}
+{"current_steps": 2340, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.778569290200254e-05, "epoch": 5.81, "percentage": 58.06, "elapsed_time": "0:43:05", "remaining_time": "0:31:07"}
+{"current_steps": 2350, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7406219705925945e-05, "epoch": 5.83, "percentage": 58.31, "elapsed_time": "0:43:13", "remaining_time": "0:30:54"}
+{"current_steps": 2350, "total_steps": 4030, "loss": null, "eval_loss": 0.0003901799500454217, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.83, "percentage": 58.31, "elapsed_time": "0:43:13", "remaining_time": "0:30:54"}
+{"current_steps": 2360, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.702751948385864e-05, "epoch": 5.86, "percentage": 58.56, "elapsed_time": "0:43:38", "remaining_time": "0:30:52"}
+{"current_steps": 2370, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6649615479451226e-05, "epoch": 5.88, "percentage": 58.81, "elapsed_time": "0:43:45", "remaining_time": "0:30:39"}
+{"current_steps": 2380, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6272530887484535e-05, "epoch": 5.91, "percentage": 59.06, "elapsed_time": "0:43:53", "remaining_time": "0:30:25"}
+{"current_steps": 2390, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5896288852445906e-05, "epoch": 5.93, "percentage": 59.31, "elapsed_time": "0:44:00", "remaining_time": "0:30:12"}
+{"current_steps": 2400, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.552091246710875e-05, "epoch": 5.96, "percentage": 59.55, "elapsed_time": "0:44:08", "remaining_time": "0:29:58"}
+{"current_steps": 2400, "total_steps": 4030, "loss": null, "eval_loss": 0.00044537056237459183, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.96, "percentage": 59.55, "elapsed_time": "0:44:08", "remaining_time": "0:29:58"}
+{"current_steps": 2410, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.514642477111505e-05, "epoch": 5.98, "percentage": 59.8, "elapsed_time": "0:44:32", "remaining_time": "0:29:56"}
+{"current_steps": 2420, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.477284874956134e-05, "epoch": 6.0, "percentage": 60.05, "elapsed_time": "0:44:40", "remaining_time": "0:29:43"}
+{"current_steps": 2430, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.440020733158792e-05, "epoch": 6.03, "percentage": 60.3, "elapsed_time": "0:44:48", "remaining_time": "0:29:29"}
+{"current_steps": 2440, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.402852338897151e-05, "epoch": 6.05, "percentage": 60.55, "elapsed_time": "0:44:56", "remaining_time": "0:29:16"}
+{"current_steps": 2450, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.365781973472144e-05, "epoch": 6.08, "percentage": 60.79, "elapsed_time": "0:45:03", "remaining_time": "0:29:03"}
+{"current_steps": 2450, "total_steps": 4030, "loss": null, "eval_loss": 0.00038982907426543534, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.08, "percentage": 60.79, "elapsed_time": "0:45:03", "remaining_time": "0:29:03"}
+{"current_steps": 2460, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.328811912167945e-05, "epoch": 6.1, "percentage": 61.04, "elapsed_time": "0:45:28", "remaining_time": "0:29:01"}
+{"current_steps": 2470, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.291944424112314e-05, "epoch": 6.13, "percentage": 61.29, "elapsed_time": "0:45:36", "remaining_time": "0:28:48"}
+{"current_steps": 2480, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2551817721373335e-05, "epoch": 6.15, "percentage": 61.54, "elapsed_time": "0:45:43", "remaining_time": "0:28:34"}
+{"current_steps": 2490, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.218526212640511e-05, "epoch": 6.18, "percentage": 61.79, "elapsed_time": "0:45:51", "remaining_time": "0:28:21"}
+{"current_steps": 2500, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1819799954462983e-05, "epoch": 6.2, "percentage": 62.03, "elapsed_time": "0:45:59", "remaining_time": "0:28:08"}
+{"current_steps": 2500, "total_steps": 4030, "loss": null, "eval_loss": 0.00047402523341588676, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.2, "percentage": 62.03, "elapsed_time": "0:45:59", "remaining_time": "0:28:08"}
+{"current_steps": 2510, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1455453636679866e-05, "epoch": 6.23, "percentage": 62.28, "elapsed_time": "0:46:24", "remaining_time": "0:28:05"}
+{"current_steps": 2520, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.109224553570047e-05, "epoch": 6.25, "percentage": 62.53, "elapsed_time": "0:46:31", "remaining_time": "0:27:52"}
+{"current_steps": 2530, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.073019794430866e-05, "epoch": 6.28, "percentage": 62.78, "elapsed_time": "0:46:39", "remaining_time": "0:27:39"}
+{"current_steps": 2540, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0369333084059148e-05, "epoch": 6.3, "percentage": 63.03, "elapsed_time": "0:46:47", "remaining_time": "0:27:26"}
+{"current_steps": 2550, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0009673103913725e-05, "epoch": 6.33, "percentage": 63.28, "elapsed_time": "0:46:54", "remaining_time": "0:27:13"}
+{"current_steps": 2550, "total_steps": 4030, "loss": null, "eval_loss": 0.00047384999925270677, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.33, "percentage": 63.28, "elapsed_time": "0:46:54", "remaining_time": "0:27:13"}
+{"current_steps": 2560, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9651240078881625e-05, "epoch": 6.35, "percentage": 63.52, "elapsed_time": "0:47:19", "remaining_time": "0:27:10"}
+{"current_steps": 2570, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9294056008664762e-05, "epoch": 6.38, "percentage": 63.77, "elapsed_time": "0:47:27", "remaining_time": "0:26:57"}
+{"current_steps": 2580, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.893814281630744e-05, "epoch": 6.4, "percentage": 64.02, "elapsed_time": "0:47:34", "remaining_time": "0:26:44"}
+{"current_steps": 2590, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8583522346850632e-05, "epoch": 6.43, "percentage": 64.27, "elapsed_time": "0:47:42", "remaining_time": "0:26:31"}
+{"current_steps": 2600, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.823021636599137e-05, "epoch": 6.45, "percentage": 64.52, "elapsed_time": "0:47:50", "remaining_time": "0:26:18"}
+{"current_steps": 2600, "total_steps": 4030, "loss": null, "eval_loss": 0.0005336844478733838, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.45, "percentage": 64.52, "elapsed_time": "0:47:50", "remaining_time": "0:26:18"}
+{"current_steps": 2610, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.787824655874674e-05, "epoch": 6.48, "percentage": 64.76, "elapsed_time": "0:48:14", "remaining_time": "0:26:14"}
+{"current_steps": 2620, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7527634528122847e-05, "epoch": 6.5, "percentage": 65.01, "elapsed_time": "0:48:22", "remaining_time": "0:26:02"}
+{"current_steps": 2630, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7178401793789012e-05, "epoch": 6.53, "percentage": 65.26, "elapsed_time": "0:48:30", "remaining_time": "0:25:49"}
+{"current_steps": 2640, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6830569790756805e-05, "epoch": 6.55, "percentage": 65.51, "elapsed_time": "0:48:38", "remaining_time": "0:25:36"}
+{"current_steps": 2650, "total_steps": 4030, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6484159868064583e-05, "epoch": 6.58, "percentage": 65.76, "elapsed_time": "0:48:46", "remaining_time": "0:25:23"}
+{"current_steps": 2650, "total_steps": 4030, "loss": null, "eval_loss": 0.0004447665123734623, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.58, "percentage": 65.76, "elapsed_time": "0:48:46", "remaining_time": "0:25:23"}
+{"current_steps": 2650, "total_steps": 4030, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.58, "percentage": 65.76, "elapsed_time": "0:48:46", "remaining_time": "0:25:23"}
+{"current_steps": 71, "total_steps": 71, "loss": null, "eval_loss": 0.00047402523341588676, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.58, "percentage": 100.0, "elapsed_time": "0:49:33", "remaining_time": "0:00:00"}
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/trainer_state.json b/llama2_13b_peft/formal_fallacies_syllogisms_negation/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3d7f32a354a1e70c1afd132665f52d8604ae763
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/trainer_state.json
@@ -0,0 +1,2309 @@
+{
+ "best_metric": 0.00047402523341588676,
+ "best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/formal_fallacies_syllogisms_negation_no_sys/checkpoint-2500",
+ "epoch": 6.575682382133995,
+ "eval_steps": 50,
+ "global_step": 2650,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.02,
+ "grad_norm": 17.027812957763672,
+ "learning_rate": 5e-05,
+ "loss": 9.3847,
+ "step": 10
+ },
+ {
+ "epoch": 0.05,
+ "grad_norm": 3.365567684173584,
+ "learning_rate": 0.0001,
+ "loss": 2.5484,
+ "step": 20
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 2.732487201690674,
+ "learning_rate": 9.999846556397038e-05,
+ "loss": 0.3827,
+ "step": 30
+ },
+ {
+ "epoch": 0.1,
+ "grad_norm": 1.364671230316162,
+ "learning_rate": 9.999386235006125e-05,
+ "loss": 0.3554,
+ "step": 40
+ },
+ {
+ "epoch": 0.12,
+ "grad_norm": 0.4866187870502472,
+ "learning_rate": 9.998619064080611e-05,
+ "loss": 0.3929,
+ "step": 50
+ },
+ {
+ "epoch": 0.12,
+ "eval_loss": 0.3599805533885956,
+ "eval_runtime": 16.7693,
+ "eval_samples_per_second": 101.615,
+ "eval_steps_per_second": 4.234,
+ "step": 50
+ },
+ {
+ "epoch": 0.15,
+ "grad_norm": 0.651821494102478,
+ "learning_rate": 9.997545090707485e-05,
+ "loss": 0.3588,
+ "step": 60
+ },
+ {
+ "epoch": 0.17,
+ "grad_norm": 0.1661490499973297,
+ "learning_rate": 9.996164380804483e-05,
+ "loss": 0.3594,
+ "step": 70
+ },
+ {
+ "epoch": 0.2,
+ "grad_norm": 0.2540946304798126,
+ "learning_rate": 9.994477019116049e-05,
+ "loss": 0.3544,
+ "step": 80
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 0.48444175720214844,
+ "learning_rate": 9.992483109208122e-05,
+ "loss": 0.3607,
+ "step": 90
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 0.08022764325141907,
+ "learning_rate": 9.990182773461791e-05,
+ "loss": 0.3534,
+ "step": 100
+ },
+ {
+ "epoch": 0.25,
+ "eval_loss": 0.35028183460235596,
+ "eval_runtime": 16.8797,
+ "eval_samples_per_second": 100.95,
+ "eval_steps_per_second": 4.206,
+ "step": 100
+ },
+ {
+ "epoch": 0.27,
+ "grad_norm": 0.22653889656066895,
+ "learning_rate": 9.987576153065779e-05,
+ "loss": 0.3493,
+ "step": 110
+ },
+ {
+ "epoch": 0.3,
+ "grad_norm": 0.18461823463439941,
+ "learning_rate": 9.984663408007777e-05,
+ "loss": 0.3519,
+ "step": 120
+ },
+ {
+ "epoch": 0.32,
+ "grad_norm": 0.8559591770172119,
+ "learning_rate": 9.98144471706462e-05,
+ "loss": 0.3532,
+ "step": 130
+ },
+ {
+ "epoch": 0.35,
+ "grad_norm": 0.2931515574455261,
+ "learning_rate": 9.977920277791328e-05,
+ "loss": 0.3526,
+ "step": 140
+ },
+ {
+ "epoch": 0.37,
+ "grad_norm": 0.24398167431354523,
+ "learning_rate": 9.974090306508959e-05,
+ "loss": 0.3577,
+ "step": 150
+ },
+ {
+ "epoch": 0.37,
+ "eval_loss": 0.3542585074901581,
+ "eval_runtime": 16.8699,
+ "eval_samples_per_second": 101.008,
+ "eval_steps_per_second": 4.209,
+ "step": 150
+ },
+ {
+ "epoch": 0.4,
+ "grad_norm": 0.1573762148618698,
+ "learning_rate": 9.969955038291353e-05,
+ "loss": 0.3525,
+ "step": 160
+ },
+ {
+ "epoch": 0.42,
+ "grad_norm": 0.1686459630727768,
+ "learning_rate": 9.965514726950693e-05,
+ "loss": 0.3493,
+ "step": 170
+ },
+ {
+ "epoch": 0.45,
+ "grad_norm": 0.5627509951591492,
+ "learning_rate": 9.960769645021923e-05,
+ "loss": 0.3515,
+ "step": 180
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 0.24285666644573212,
+ "learning_rate": 9.955720083746035e-05,
+ "loss": 0.349,
+ "step": 190
+ },
+ {
+ "epoch": 0.5,
+ "grad_norm": 0.07683099806308746,
+ "learning_rate": 9.950366353052175e-05,
+ "loss": 0.351,
+ "step": 200
+ },
+ {
+ "epoch": 0.5,
+ "eval_loss": 0.3478730320930481,
+ "eval_runtime": 16.8735,
+ "eval_samples_per_second": 100.987,
+ "eval_steps_per_second": 4.208,
+ "step": 200
+ },
+ {
+ "epoch": 0.52,
+ "grad_norm": 0.36977964639663696,
+ "learning_rate": 9.944708781538636e-05,
+ "loss": 0.3545,
+ "step": 210
+ },
+ {
+ "epoch": 0.55,
+ "grad_norm": 0.05500698462128639,
+ "learning_rate": 9.93874771645268e-05,
+ "loss": 0.3499,
+ "step": 220
+ },
+ {
+ "epoch": 0.57,
+ "grad_norm": 0.10918760299682617,
+ "learning_rate": 9.932483523669231e-05,
+ "loss": 0.3504,
+ "step": 230
+ },
+ {
+ "epoch": 0.6,
+ "grad_norm": 0.08242153376340866,
+ "learning_rate": 9.925916587668409e-05,
+ "loss": 0.3543,
+ "step": 240
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 0.06469199061393738,
+ "learning_rate": 9.919047311511946e-05,
+ "loss": 0.3459,
+ "step": 250
+ },
+ {
+ "epoch": 0.62,
+ "eval_loss": 0.35084518790245056,
+ "eval_runtime": 16.8753,
+ "eval_samples_per_second": 100.976,
+ "eval_steps_per_second": 4.207,
+ "step": 250
+ },
+ {
+ "epoch": 0.65,
+ "grad_norm": 0.27665790915489197,
+ "learning_rate": 9.911876116818433e-05,
+ "loss": 0.3483,
+ "step": 260
+ },
+ {
+ "epoch": 0.67,
+ "grad_norm": 0.1749347299337387,
+ "learning_rate": 9.904403443737454e-05,
+ "loss": 0.3577,
+ "step": 270
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 0.06966757029294968,
+ "learning_rate": 9.896629750922555e-05,
+ "loss": 0.3656,
+ "step": 280
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 0.35240188241004944,
+ "learning_rate": 9.888555515503116e-05,
+ "loss": 0.3595,
+ "step": 290
+ },
+ {
+ "epoch": 0.74,
+ "grad_norm": 0.1216234564781189,
+ "learning_rate": 9.880181233055042e-05,
+ "loss": 0.353,
+ "step": 300
+ },
+ {
+ "epoch": 0.74,
+ "eval_loss": 0.351527601480484,
+ "eval_runtime": 16.8754,
+ "eval_samples_per_second": 100.975,
+ "eval_steps_per_second": 4.207,
+ "step": 300
+ },
+ {
+ "epoch": 0.77,
+ "grad_norm": 0.32111746072769165,
+ "learning_rate": 9.871507417570363e-05,
+ "loss": 0.3552,
+ "step": 310
+ },
+ {
+ "epoch": 0.79,
+ "grad_norm": 0.08302031457424164,
+ "learning_rate": 9.862534601425681e-05,
+ "loss": 0.3515,
+ "step": 320
+ },
+ {
+ "epoch": 0.82,
+ "grad_norm": 0.2720988690853119,
+ "learning_rate": 9.853263335349488e-05,
+ "loss": 0.3445,
+ "step": 330
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 0.2636917531490326,
+ "learning_rate": 9.843694188388374e-05,
+ "loss": 0.3579,
+ "step": 340
+ },
+ {
+ "epoch": 0.87,
+ "grad_norm": 0.6955106258392334,
+ "learning_rate": 9.833827747872093e-05,
+ "loss": 0.3591,
+ "step": 350
+ },
+ {
+ "epoch": 0.87,
+ "eval_loss": 0.3899991512298584,
+ "eval_runtime": 16.8704,
+ "eval_samples_per_second": 101.005,
+ "eval_steps_per_second": 4.209,
+ "step": 350
+ },
+ {
+ "epoch": 0.89,
+ "grad_norm": 0.08135569840669632,
+ "learning_rate": 9.823664619377518e-05,
+ "loss": 0.3472,
+ "step": 360
+ },
+ {
+ "epoch": 0.92,
+ "grad_norm": 0.30241286754608154,
+ "learning_rate": 9.81320542669147e-05,
+ "loss": 0.3515,
+ "step": 370
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 0.19453191757202148,
+ "learning_rate": 9.802450811772435e-05,
+ "loss": 0.3591,
+ "step": 380
+ },
+ {
+ "epoch": 0.97,
+ "grad_norm": 0.16131022572517395,
+ "learning_rate": 9.791401434711154e-05,
+ "loss": 0.3511,
+ "step": 390
+ },
+ {
+ "epoch": 0.99,
+ "grad_norm": 0.0854898989200592,
+ "learning_rate": 9.78005797369012e-05,
+ "loss": 0.3563,
+ "step": 400
+ },
+ {
+ "epoch": 0.99,
+ "eval_loss": 0.3495555818080902,
+ "eval_runtime": 16.8811,
+ "eval_samples_per_second": 100.941,
+ "eval_steps_per_second": 4.206,
+ "step": 400
+ },
+ {
+ "epoch": 1.02,
+ "grad_norm": 0.12075020372867584,
+ "learning_rate": 9.768421124941944e-05,
+ "loss": 0.3384,
+ "step": 410
+ },
+ {
+ "epoch": 1.04,
+ "grad_norm": 0.44095876812934875,
+ "learning_rate": 9.756491602706626e-05,
+ "loss": 0.3545,
+ "step": 420
+ },
+ {
+ "epoch": 1.07,
+ "grad_norm": 0.16610263288021088,
+ "learning_rate": 9.744270139187716e-05,
+ "loss": 0.3449,
+ "step": 430
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 0.26342347264289856,
+ "learning_rate": 9.731757484507371e-05,
+ "loss": 0.346,
+ "step": 440
+ },
+ {
+ "epoch": 1.12,
+ "grad_norm": 0.35193535685539246,
+ "learning_rate": 9.718954406660318e-05,
+ "loss": 0.3351,
+ "step": 450
+ },
+ {
+ "epoch": 1.12,
+ "eval_loss": 0.33888280391693115,
+ "eval_runtime": 16.8683,
+ "eval_samples_per_second": 101.018,
+ "eval_steps_per_second": 4.209,
+ "step": 450
+ },
+ {
+ "epoch": 1.14,
+ "grad_norm": 0.8358747363090515,
+ "learning_rate": 9.705861691466716e-05,
+ "loss": 0.3306,
+ "step": 460
+ },
+ {
+ "epoch": 1.17,
+ "grad_norm": 0.2413673996925354,
+ "learning_rate": 9.692480142523918e-05,
+ "loss": 0.3514,
+ "step": 470
+ },
+ {
+ "epoch": 1.19,
+ "grad_norm": 0.7732076048851013,
+ "learning_rate": 9.678810581157163e-05,
+ "loss": 0.3159,
+ "step": 480
+ },
+ {
+ "epoch": 1.22,
+ "grad_norm": 0.7405707836151123,
+ "learning_rate": 9.664853846369144e-05,
+ "loss": 0.309,
+ "step": 490
+ },
+ {
+ "epoch": 1.24,
+ "grad_norm": 2.760390520095825,
+ "learning_rate": 9.650610794788533e-05,
+ "loss": 0.26,
+ "step": 500
+ },
+ {
+ "epoch": 1.24,
+ "eval_loss": 0.3002278506755829,
+ "eval_runtime": 16.8732,
+ "eval_samples_per_second": 100.988,
+ "eval_steps_per_second": 4.208,
+ "step": 500
+ },
+ {
+ "epoch": 1.27,
+ "grad_norm": 2.7352631092071533,
+ "learning_rate": 9.63608230061739e-05,
+ "loss": 0.2472,
+ "step": 510
+ },
+ {
+ "epoch": 1.29,
+ "grad_norm": 2.589384078979492,
+ "learning_rate": 9.621269255577512e-05,
+ "loss": 0.2212,
+ "step": 520
+ },
+ {
+ "epoch": 1.32,
+ "grad_norm": 2.2857918739318848,
+ "learning_rate": 9.606172568855698e-05,
+ "loss": 0.2039,
+ "step": 530
+ },
+ {
+ "epoch": 1.34,
+ "grad_norm": 0.7525045275688171,
+ "learning_rate": 9.590793167047951e-05,
+ "loss": 0.2198,
+ "step": 540
+ },
+ {
+ "epoch": 1.36,
+ "grad_norm": 0.9323859810829163,
+ "learning_rate": 9.575131994102602e-05,
+ "loss": 0.187,
+ "step": 550
+ },
+ {
+ "epoch": 1.36,
+ "eval_loss": 0.14382539689540863,
+ "eval_runtime": 16.8737,
+ "eval_samples_per_second": 100.985,
+ "eval_steps_per_second": 4.208,
+ "step": 550
+ },
+ {
+ "epoch": 1.39,
+ "grad_norm": 1.6801602840423584,
+ "learning_rate": 9.559190011262369e-05,
+ "loss": 0.1253,
+ "step": 560
+ },
+ {
+ "epoch": 1.41,
+ "grad_norm": 0.5075914263725281,
+ "learning_rate": 9.542968197005367e-05,
+ "loss": 0.1246,
+ "step": 570
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 1.5305324792861938,
+ "learning_rate": 9.526467546985048e-05,
+ "loss": 0.1097,
+ "step": 580
+ },
+ {
+ "epoch": 1.46,
+ "grad_norm": 0.5779011249542236,
+ "learning_rate": 9.509689073969088e-05,
+ "loss": 0.0995,
+ "step": 590
+ },
+ {
+ "epoch": 1.49,
+ "grad_norm": 2.8470897674560547,
+ "learning_rate": 9.492633807777227e-05,
+ "loss": 0.0715,
+ "step": 600
+ },
+ {
+ "epoch": 1.49,
+ "eval_loss": 0.0493486262857914,
+ "eval_runtime": 16.8798,
+ "eval_samples_per_second": 100.949,
+ "eval_steps_per_second": 4.206,
+ "step": 600
+ },
+ {
+ "epoch": 1.51,
+ "grad_norm": 0.08935365825891495,
+ "learning_rate": 9.475302795218061e-05,
+ "loss": 0.0715,
+ "step": 610
+ },
+ {
+ "epoch": 1.54,
+ "grad_norm": 0.732679545879364,
+ "learning_rate": 9.457697100024798e-05,
+ "loss": 0.0797,
+ "step": 620
+ },
+ {
+ "epoch": 1.56,
+ "grad_norm": 1.6677818298339844,
+ "learning_rate": 9.439817802789958e-05,
+ "loss": 0.065,
+ "step": 630
+ },
+ {
+ "epoch": 1.59,
+ "grad_norm": 2.5735604763031006,
+ "learning_rate": 9.421666000899052e-05,
+ "loss": 0.0534,
+ "step": 640
+ },
+ {
+ "epoch": 1.61,
+ "grad_norm": 1.0087685585021973,
+ "learning_rate": 9.403242808463237e-05,
+ "loss": 0.0695,
+ "step": 650
+ },
+ {
+ "epoch": 1.61,
+ "eval_loss": 0.047055672854185104,
+ "eval_runtime": 16.8872,
+ "eval_samples_per_second": 100.905,
+ "eval_steps_per_second": 4.204,
+ "step": 650
+ },
+ {
+ "epoch": 1.64,
+ "grad_norm": 1.0158408880233765,
+ "learning_rate": 9.38454935625092e-05,
+ "loss": 0.0259,
+ "step": 660
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 1.2724292278289795,
+ "learning_rate": 9.365586791618368e-05,
+ "loss": 0.0388,
+ "step": 670
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 1.6942436695098877,
+ "learning_rate": 9.346356278439275e-05,
+ "loss": 0.0514,
+ "step": 680
+ },
+ {
+ "epoch": 1.71,
+ "grad_norm": 0.5555233955383301,
+ "learning_rate": 9.32685899703333e-05,
+ "loss": 0.0382,
+ "step": 690
+ },
+ {
+ "epoch": 1.74,
+ "grad_norm": 0.1289750039577484,
+ "learning_rate": 9.307096144093781e-05,
+ "loss": 0.0338,
+ "step": 700
+ },
+ {
+ "epoch": 1.74,
+ "eval_loss": 0.030666794627904892,
+ "eval_runtime": 16.8789,
+ "eval_samples_per_second": 100.955,
+ "eval_steps_per_second": 4.206,
+ "step": 700
+ },
+ {
+ "epoch": 1.76,
+ "grad_norm": 0.195440873503685,
+ "learning_rate": 9.287068932613968e-05,
+ "loss": 0.0635,
+ "step": 710
+ },
+ {
+ "epoch": 1.79,
+ "grad_norm": 0.9766190052032471,
+ "learning_rate": 9.266778591812886e-05,
+ "loss": 0.0303,
+ "step": 720
+ },
+ {
+ "epoch": 1.81,
+ "grad_norm": 0.9638659358024597,
+ "learning_rate": 9.246226367059736e-05,
+ "loss": 0.0094,
+ "step": 730
+ },
+ {
+ "epoch": 1.84,
+ "grad_norm": 1.7231276035308838,
+ "learning_rate": 9.225413519797482e-05,
+ "loss": 0.0217,
+ "step": 740
+ },
+ {
+ "epoch": 1.86,
+ "grad_norm": 1.7973217964172363,
+ "learning_rate": 9.204341327465434e-05,
+ "loss": 0.0422,
+ "step": 750
+ },
+ {
+ "epoch": 1.86,
+ "eval_loss": 0.02686377428472042,
+ "eval_runtime": 16.8806,
+ "eval_samples_per_second": 100.945,
+ "eval_steps_per_second": 4.206,
+ "step": 750
+ },
+ {
+ "epoch": 1.89,
+ "grad_norm": 1.0615655183792114,
+ "learning_rate": 9.183011083420838e-05,
+ "loss": 0.046,
+ "step": 760
+ },
+ {
+ "epoch": 1.91,
+ "grad_norm": 2.6027116775512695,
+ "learning_rate": 9.161424096859493e-05,
+ "loss": 0.0192,
+ "step": 770
+ },
+ {
+ "epoch": 1.94,
+ "grad_norm": 0.3014383316040039,
+ "learning_rate": 9.139581692735394e-05,
+ "loss": 0.0159,
+ "step": 780
+ },
+ {
+ "epoch": 1.96,
+ "grad_norm": 0.13248316943645477,
+ "learning_rate": 9.11748521167942e-05,
+ "loss": 0.0188,
+ "step": 790
+ },
+ {
+ "epoch": 1.99,
+ "grad_norm": 0.43969258666038513,
+ "learning_rate": 9.095136009917036e-05,
+ "loss": 0.0183,
+ "step": 800
+ },
+ {
+ "epoch": 1.99,
+ "eval_loss": 0.009065705351531506,
+ "eval_runtime": 16.8746,
+ "eval_samples_per_second": 100.98,
+ "eval_steps_per_second": 4.208,
+ "step": 800
+ },
+ {
+ "epoch": 2.01,
+ "grad_norm": 0.16183876991271973,
+ "learning_rate": 9.072535459185056e-05,
+ "loss": 0.0317,
+ "step": 810
+ },
+ {
+ "epoch": 2.03,
+ "grad_norm": 0.011793575249612331,
+ "learning_rate": 9.049684946647459e-05,
+ "loss": 0.0059,
+ "step": 820
+ },
+ {
+ "epoch": 2.06,
+ "grad_norm": 0.01810554228723049,
+ "learning_rate": 9.026585874810227e-05,
+ "loss": 0.0009,
+ "step": 830
+ },
+ {
+ "epoch": 2.08,
+ "grad_norm": 0.17199455201625824,
+ "learning_rate": 9.003239661435289e-05,
+ "loss": 0.0015,
+ "step": 840
+ },
+ {
+ "epoch": 2.11,
+ "grad_norm": 5.362873554229736,
+ "learning_rate": 8.979647739453481e-05,
+ "loss": 0.0055,
+ "step": 850
+ },
+ {
+ "epoch": 2.11,
+ "eval_loss": 0.007036147639155388,
+ "eval_runtime": 16.8747,
+ "eval_samples_per_second": 100.98,
+ "eval_steps_per_second": 4.207,
+ "step": 850
+ },
+ {
+ "epoch": 2.13,
+ "grad_norm": 0.0009894347749650478,
+ "learning_rate": 8.955811556876605e-05,
+ "loss": 0.0002,
+ "step": 860
+ },
+ {
+ "epoch": 2.16,
+ "grad_norm": 0.0041043683886528015,
+ "learning_rate": 8.93173257670856e-05,
+ "loss": 0.0172,
+ "step": 870
+ },
+ {
+ "epoch": 2.18,
+ "grad_norm": 0.01311841607093811,
+ "learning_rate": 8.907412276855531e-05,
+ "loss": 0.0014,
+ "step": 880
+ },
+ {
+ "epoch": 2.21,
+ "grad_norm": 0.007052562665194273,
+ "learning_rate": 8.882852150035295e-05,
+ "loss": 0.0025,
+ "step": 890
+ },
+ {
+ "epoch": 2.23,
+ "grad_norm": 0.0044655706733465195,
+ "learning_rate": 8.858053703685587e-05,
+ "loss": 0.0208,
+ "step": 900
+ },
+ {
+ "epoch": 2.23,
+ "eval_loss": 0.003154078498482704,
+ "eval_runtime": 16.8784,
+ "eval_samples_per_second": 100.958,
+ "eval_steps_per_second": 4.207,
+ "step": 900
+ },
+ {
+ "epoch": 2.26,
+ "grad_norm": 0.0044303881004452705,
+ "learning_rate": 8.833018459871594e-05,
+ "loss": 0.0016,
+ "step": 910
+ },
+ {
+ "epoch": 2.28,
+ "grad_norm": 0.15879973769187927,
+ "learning_rate": 8.807747955192516e-05,
+ "loss": 0.0139,
+ "step": 920
+ },
+ {
+ "epoch": 2.31,
+ "grad_norm": 0.006470128428190947,
+ "learning_rate": 8.782243740687273e-05,
+ "loss": 0.0007,
+ "step": 930
+ },
+ {
+ "epoch": 2.33,
+ "grad_norm": 0.0031656241044402122,
+ "learning_rate": 8.756507381739288e-05,
+ "loss": 0.0149,
+ "step": 940
+ },
+ {
+ "epoch": 2.36,
+ "grad_norm": 0.7405675649642944,
+ "learning_rate": 8.730540457980418e-05,
+ "loss": 0.0014,
+ "step": 950
+ },
+ {
+ "epoch": 2.36,
+ "eval_loss": 0.002297737170010805,
+ "eval_runtime": 16.8743,
+ "eval_samples_per_second": 100.982,
+ "eval_steps_per_second": 4.208,
+ "step": 950
+ },
+ {
+ "epoch": 2.38,
+ "grad_norm": 0.514784574508667,
+ "learning_rate": 8.704344563193997e-05,
+ "loss": 0.0014,
+ "step": 960
+ },
+ {
+ "epoch": 2.41,
+ "grad_norm": 0.01349685899913311,
+ "learning_rate": 8.677921305217023e-05,
+ "loss": 0.0002,
+ "step": 970
+ },
+ {
+ "epoch": 2.43,
+ "grad_norm": 0.0020194160751998425,
+ "learning_rate": 8.651272305841454e-05,
+ "loss": 0.0207,
+ "step": 980
+ },
+ {
+ "epoch": 2.46,
+ "grad_norm": 1.934012532234192,
+ "learning_rate": 8.62439920071468e-05,
+ "loss": 0.0011,
+ "step": 990
+ },
+ {
+ "epoch": 2.48,
+ "grad_norm": 0.04069426655769348,
+ "learning_rate": 8.597303639239134e-05,
+ "loss": 0.0117,
+ "step": 1000
+ },
+ {
+ "epoch": 2.48,
+ "eval_loss": 0.0033970780204981565,
+ "eval_runtime": 16.8634,
+ "eval_samples_per_second": 101.047,
+ "eval_steps_per_second": 4.21,
+ "step": 1000
+ },
+ {
+ "epoch": 2.51,
+ "grad_norm": 0.03683527931571007,
+ "learning_rate": 8.569987284471046e-05,
+ "loss": 0.0026,
+ "step": 1010
+ },
+ {
+ "epoch": 2.53,
+ "grad_norm": 0.050554804503917694,
+ "learning_rate": 8.542451813018372e-05,
+ "loss": 0.0022,
+ "step": 1020
+ },
+ {
+ "epoch": 2.56,
+ "grad_norm": 0.0019483251962810755,
+ "learning_rate": 8.514698914937894e-05,
+ "loss": 0.0002,
+ "step": 1030
+ },
+ {
+ "epoch": 2.58,
+ "grad_norm": 1.8008921146392822,
+ "learning_rate": 8.486730293631481e-05,
+ "loss": 0.0019,
+ "step": 1040
+ },
+ {
+ "epoch": 2.61,
+ "grad_norm": 0.001593997934833169,
+ "learning_rate": 8.458547665741543e-05,
+ "loss": 0.0001,
+ "step": 1050
+ },
+ {
+ "epoch": 2.61,
+ "eval_loss": 0.001217635115608573,
+ "eval_runtime": 16.8779,
+ "eval_samples_per_second": 100.96,
+ "eval_steps_per_second": 4.207,
+ "step": 1050
+ },
+ {
+ "epoch": 2.63,
+ "grad_norm": 0.003130235243588686,
+ "learning_rate": 8.430152761045664e-05,
+ "loss": 0.0002,
+ "step": 1060
+ },
+ {
+ "epoch": 2.66,
+ "grad_norm": 0.001099205925129354,
+ "learning_rate": 8.401547322350438e-05,
+ "loss": 0.0004,
+ "step": 1070
+ },
+ {
+ "epoch": 2.68,
+ "grad_norm": 0.18462316691875458,
+ "learning_rate": 8.372733105384496e-05,
+ "loss": 0.0002,
+ "step": 1080
+ },
+ {
+ "epoch": 2.7,
+ "grad_norm": 0.001120097003877163,
+ "learning_rate": 8.343711878690746e-05,
+ "loss": 0.0171,
+ "step": 1090
+ },
+ {
+ "epoch": 2.73,
+ "grad_norm": 0.9607303738594055,
+ "learning_rate": 8.314485423517819e-05,
+ "loss": 0.0058,
+ "step": 1100
+ },
+ {
+ "epoch": 2.73,
+ "eval_loss": 0.0012037238338962197,
+ "eval_runtime": 16.8925,
+ "eval_samples_per_second": 100.873,
+ "eval_steps_per_second": 4.203,
+ "step": 1100
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 0.0029547882732003927,
+ "learning_rate": 8.285055533710753e-05,
+ "loss": 0.0001,
+ "step": 1110
+ },
+ {
+ "epoch": 2.78,
+ "grad_norm": 0.0008037490188144147,
+ "learning_rate": 8.255424015600876e-05,
+ "loss": 0.0059,
+ "step": 1120
+ },
+ {
+ "epoch": 2.8,
+ "grad_norm": 0.0015891498187556863,
+ "learning_rate": 8.225592687894949e-05,
+ "loss": 0.0028,
+ "step": 1130
+ },
+ {
+ "epoch": 2.83,
+ "grad_norm": 0.0007602926343679428,
+ "learning_rate": 8.195563381563536e-05,
+ "loss": 0.0001,
+ "step": 1140
+ },
+ {
+ "epoch": 2.85,
+ "grad_norm": 0.0008714946452528238,
+ "learning_rate": 8.165337939728614e-05,
+ "loss": 0.0001,
+ "step": 1150
+ },
+ {
+ "epoch": 2.85,
+ "eval_loss": 0.0012541119940578938,
+ "eval_runtime": 16.8751,
+ "eval_samples_per_second": 100.977,
+ "eval_steps_per_second": 4.207,
+ "step": 1150
+ },
+ {
+ "epoch": 2.88,
+ "grad_norm": 0.0005839269142597914,
+ "learning_rate": 8.134918217550467e-05,
+ "loss": 0.0001,
+ "step": 1160
+ },
+ {
+ "epoch": 2.9,
+ "grad_norm": 0.09183517843484879,
+ "learning_rate": 8.104306082113802e-05,
+ "loss": 0.0017,
+ "step": 1170
+ },
+ {
+ "epoch": 2.93,
+ "grad_norm": 0.0006280924426391721,
+ "learning_rate": 8.073503412313159e-05,
+ "loss": 0.0,
+ "step": 1180
+ },
+ {
+ "epoch": 2.95,
+ "grad_norm": 0.0005470833857543766,
+ "learning_rate": 8.042512098737598e-05,
+ "loss": 0.001,
+ "step": 1190
+ },
+ {
+ "epoch": 2.98,
+ "grad_norm": 0.001008176477625966,
+ "learning_rate": 8.01133404355464e-05,
+ "loss": 0.0104,
+ "step": 1200
+ },
+ {
+ "epoch": 2.98,
+ "eval_loss": 0.0007884196820668876,
+ "eval_runtime": 16.8766,
+ "eval_samples_per_second": 100.968,
+ "eval_steps_per_second": 4.207,
+ "step": 1200
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 0.000660700083244592,
+ "learning_rate": 7.979971160393535e-05,
+ "loss": 0.0,
+ "step": 1210
+ },
+ {
+ "epoch": 3.03,
+ "grad_norm": 0.004391908645629883,
+ "learning_rate": 7.948425374227799e-05,
+ "loss": 0.0131,
+ "step": 1220
+ },
+ {
+ "epoch": 3.05,
+ "grad_norm": 0.0010901394998654723,
+ "learning_rate": 7.916698621257068e-05,
+ "loss": 0.0006,
+ "step": 1230
+ },
+ {
+ "epoch": 3.08,
+ "grad_norm": 0.0011236576829105616,
+ "learning_rate": 7.884792848788257e-05,
+ "loss": 0.0028,
+ "step": 1240
+ },
+ {
+ "epoch": 3.1,
+ "grad_norm": 0.0004985715495422482,
+ "learning_rate": 7.852710015116036e-05,
+ "loss": 0.0007,
+ "step": 1250
+ },
+ {
+ "epoch": 3.1,
+ "eval_loss": 0.0018942987080663443,
+ "eval_runtime": 16.8648,
+ "eval_samples_per_second": 101.039,
+ "eval_steps_per_second": 4.21,
+ "step": 1250
+ },
+ {
+ "epoch": 3.13,
+ "grad_norm": 0.0006551850237883627,
+ "learning_rate": 7.820452089402645e-05,
+ "loss": 0.0001,
+ "step": 1260
+ },
+ {
+ "epoch": 3.15,
+ "grad_norm": 0.0009159449255093932,
+ "learning_rate": 7.788021051557022e-05,
+ "loss": 0.0015,
+ "step": 1270
+ },
+ {
+ "epoch": 3.18,
+ "grad_norm": 0.3894294500350952,
+ "learning_rate": 7.755418892113282e-05,
+ "loss": 0.0006,
+ "step": 1280
+ },
+ {
+ "epoch": 3.2,
+ "grad_norm": 0.0011728698154911399,
+ "learning_rate": 7.722647612108553e-05,
+ "loss": 0.0011,
+ "step": 1290
+ },
+ {
+ "epoch": 3.23,
+ "grad_norm": 0.0003914556000381708,
+ "learning_rate": 7.689709222960144e-05,
+ "loss": 0.0015,
+ "step": 1300
+ },
+ {
+ "epoch": 3.23,
+ "eval_loss": 0.00915015209466219,
+ "eval_runtime": 16.8561,
+ "eval_samples_per_second": 101.091,
+ "eval_steps_per_second": 4.212,
+ "step": 1300
+ },
+ {
+ "epoch": 3.25,
+ "grad_norm": 0.0004285429895389825,
+ "learning_rate": 7.656605746342096e-05,
+ "loss": 0.0118,
+ "step": 1310
+ },
+ {
+ "epoch": 3.28,
+ "grad_norm": 0.001354528358206153,
+ "learning_rate": 7.6233392140611e-05,
+ "loss": 0.0,
+ "step": 1320
+ },
+ {
+ "epoch": 3.3,
+ "grad_norm": 0.0010014220606535673,
+ "learning_rate": 7.589911667931786e-05,
+ "loss": 0.0001,
+ "step": 1330
+ },
+ {
+ "epoch": 3.33,
+ "grad_norm": 0.017791859805583954,
+ "learning_rate": 7.556325159651399e-05,
+ "loss": 0.0001,
+ "step": 1340
+ },
+ {
+ "epoch": 3.35,
+ "grad_norm": 0.003636227687820792,
+ "learning_rate": 7.522581750673872e-05,
+ "loss": 0.0,
+ "step": 1350
+ },
+ {
+ "epoch": 3.35,
+ "eval_loss": 0.0016158341895788908,
+ "eval_runtime": 16.872,
+ "eval_samples_per_second": 100.996,
+ "eval_steps_per_second": 4.208,
+ "step": 1350
+ },
+ {
+ "epoch": 3.37,
+ "grad_norm": 0.0002491871709935367,
+ "learning_rate": 7.48868351208331e-05,
+ "loss": 0.0005,
+ "step": 1360
+ },
+ {
+ "epoch": 3.4,
+ "grad_norm": 0.0009618819458410144,
+ "learning_rate": 7.454632524466857e-05,
+ "loss": 0.0,
+ "step": 1370
+ },
+ {
+ "epoch": 3.42,
+ "grad_norm": 0.0006681958911940455,
+ "learning_rate": 7.420430877787004e-05,
+ "loss": 0.0,
+ "step": 1380
+ },
+ {
+ "epoch": 3.45,
+ "grad_norm": 0.0005440477398224175,
+ "learning_rate": 7.386080671253307e-05,
+ "loss": 0.004,
+ "step": 1390
+ },
+ {
+ "epoch": 3.47,
+ "grad_norm": 0.0004287729097995907,
+ "learning_rate": 7.351584013193543e-05,
+ "loss": 0.0001,
+ "step": 1400
+ },
+ {
+ "epoch": 3.47,
+ "eval_loss": 0.000445638841483742,
+ "eval_runtime": 16.8657,
+ "eval_samples_per_second": 101.033,
+ "eval_steps_per_second": 4.21,
+ "step": 1400
+ },
+ {
+ "epoch": 3.5,
+ "grad_norm": 0.0007876464514993131,
+ "learning_rate": 7.316943020924319e-05,
+ "loss": 0.0003,
+ "step": 1410
+ },
+ {
+ "epoch": 3.52,
+ "grad_norm": 0.0006684191175736487,
+ "learning_rate": 7.2821598206211e-05,
+ "loss": 0.0,
+ "step": 1420
+ },
+ {
+ "epoch": 3.55,
+ "grad_norm": 0.000733783992473036,
+ "learning_rate": 7.247236547187716e-05,
+ "loss": 0.0002,
+ "step": 1430
+ },
+ {
+ "epoch": 3.57,
+ "grad_norm": 0.00019874260760843754,
+ "learning_rate": 7.212175344125327e-05,
+ "loss": 0.0,
+ "step": 1440
+ },
+ {
+ "epoch": 3.6,
+ "grad_norm": 0.00011918343079742044,
+ "learning_rate": 7.176978363400863e-05,
+ "loss": 0.0059,
+ "step": 1450
+ },
+ {
+ "epoch": 3.6,
+ "eval_loss": 0.0003264049591962248,
+ "eval_runtime": 16.8679,
+ "eval_samples_per_second": 101.02,
+ "eval_steps_per_second": 4.209,
+ "step": 1450
+ },
+ {
+ "epoch": 3.62,
+ "grad_norm": 0.0008113720687106252,
+ "learning_rate": 7.141647765314938e-05,
+ "loss": 0.0,
+ "step": 1460
+ },
+ {
+ "epoch": 3.65,
+ "grad_norm": 0.00023584155132994056,
+ "learning_rate": 7.106185718369259e-05,
+ "loss": 0.0,
+ "step": 1470
+ },
+ {
+ "epoch": 3.67,
+ "grad_norm": 0.000526837189681828,
+ "learning_rate": 7.070594399133525e-05,
+ "loss": 0.0,
+ "step": 1480
+ },
+ {
+ "epoch": 3.7,
+ "grad_norm": 0.00017550899065099657,
+ "learning_rate": 7.03487599211184e-05,
+ "loss": 0.0038,
+ "step": 1490
+ },
+ {
+ "epoch": 3.72,
+ "grad_norm": 0.06627130508422852,
+ "learning_rate": 6.999032689608629e-05,
+ "loss": 0.0,
+ "step": 1500
+ },
+ {
+ "epoch": 3.72,
+ "eval_loss": 0.009298658929765224,
+ "eval_runtime": 16.8719,
+ "eval_samples_per_second": 100.996,
+ "eval_steps_per_second": 4.208,
+ "step": 1500
+ },
+ {
+ "epoch": 3.75,
+ "grad_norm": 0.00021741975797340274,
+ "learning_rate": 6.963066691594084e-05,
+ "loss": 0.0037,
+ "step": 1510
+ },
+ {
+ "epoch": 3.77,
+ "grad_norm": 0.005204753950238228,
+ "learning_rate": 6.926980205569136e-05,
+ "loss": 0.0113,
+ "step": 1520
+ },
+ {
+ "epoch": 3.8,
+ "grad_norm": 0.0006932571996003389,
+ "learning_rate": 6.890775446429954e-05,
+ "loss": 0.0,
+ "step": 1530
+ },
+ {
+ "epoch": 3.82,
+ "grad_norm": 0.006194334477186203,
+ "learning_rate": 6.854454636332013e-05,
+ "loss": 0.0002,
+ "step": 1540
+ },
+ {
+ "epoch": 3.85,
+ "grad_norm": 0.0016646990552544594,
+ "learning_rate": 6.818020004553702e-05,
+ "loss": 0.0059,
+ "step": 1550
+ },
+ {
+ "epoch": 3.85,
+ "eval_loss": 0.0031606056727468967,
+ "eval_runtime": 16.8924,
+ "eval_samples_per_second": 100.874,
+ "eval_steps_per_second": 4.203,
+ "step": 1550
+ },
+ {
+ "epoch": 3.87,
+ "grad_norm": 8.5881986618042,
+ "learning_rate": 6.781473787359488e-05,
+ "loss": 0.0058,
+ "step": 1560
+ },
+ {
+ "epoch": 3.9,
+ "grad_norm": 0.0005570609937421978,
+ "learning_rate": 6.744818227862668e-05,
+ "loss": 0.0131,
+ "step": 1570
+ },
+ {
+ "epoch": 3.92,
+ "grad_norm": 0.4314500093460083,
+ "learning_rate": 6.708055575887687e-05,
+ "loss": 0.0042,
+ "step": 1580
+ },
+ {
+ "epoch": 3.95,
+ "grad_norm": 0.01640118658542633,
+ "learning_rate": 6.671188087832057e-05,
+ "loss": 0.0056,
+ "step": 1590
+ },
+ {
+ "epoch": 3.97,
+ "grad_norm": 0.0034761123824864626,
+ "learning_rate": 6.634218026527856e-05,
+ "loss": 0.0001,
+ "step": 1600
+ },
+ {
+ "epoch": 3.97,
+ "eval_loss": 0.002365908119827509,
+ "eval_runtime": 16.8762,
+ "eval_samples_per_second": 100.971,
+ "eval_steps_per_second": 4.207,
+ "step": 1600
+ },
+ {
+ "epoch": 4.0,
+ "grad_norm": 2.214448928833008,
+ "learning_rate": 6.59714766110285e-05,
+ "loss": 0.002,
+ "step": 1610
+ },
+ {
+ "epoch": 4.02,
+ "grad_norm": 0.002197085879743099,
+ "learning_rate": 6.559979266841209e-05,
+ "loss": 0.005,
+ "step": 1620
+ },
+ {
+ "epoch": 4.04,
+ "grad_norm": 0.10025832056999207,
+ "learning_rate": 6.522715125043868e-05,
+ "loss": 0.0007,
+ "step": 1630
+ },
+ {
+ "epoch": 4.07,
+ "grad_norm": 0.002808921504765749,
+ "learning_rate": 6.485357522888496e-05,
+ "loss": 0.0028,
+ "step": 1640
+ },
+ {
+ "epoch": 4.09,
+ "grad_norm": 0.0002055912627838552,
+ "learning_rate": 6.447908753289127e-05,
+ "loss": 0.0032,
+ "step": 1650
+ },
+ {
+ "epoch": 4.09,
+ "eval_loss": 0.00048677672748453915,
+ "eval_runtime": 16.8716,
+ "eval_samples_per_second": 100.998,
+ "eval_steps_per_second": 4.208,
+ "step": 1650
+ },
+ {
+ "epoch": 4.12,
+ "grad_norm": 0.0012891364749521017,
+ "learning_rate": 6.410371114755409e-05,
+ "loss": 0.0,
+ "step": 1660
+ },
+ {
+ "epoch": 4.14,
+ "grad_norm": 0.14440464973449707,
+ "learning_rate": 6.372746911251548e-05,
+ "loss": 0.0003,
+ "step": 1670
+ },
+ {
+ "epoch": 4.17,
+ "grad_norm": 0.00040509516838938,
+ "learning_rate": 6.335038452054878e-05,
+ "loss": 0.0,
+ "step": 1680
+ },
+ {
+ "epoch": 4.19,
+ "grad_norm": 0.00013587850844487548,
+ "learning_rate": 6.297248051614137e-05,
+ "loss": 0.0,
+ "step": 1690
+ },
+ {
+ "epoch": 4.22,
+ "grad_norm": 0.000756852503400296,
+ "learning_rate": 6.259378029407407e-05,
+ "loss": 0.0,
+ "step": 1700
+ },
+ {
+ "epoch": 4.22,
+ "eval_loss": 0.003695528022944927,
+ "eval_runtime": 16.873,
+ "eval_samples_per_second": 100.99,
+ "eval_steps_per_second": 4.208,
+ "step": 1700
+ },
+ {
+ "epoch": 4.24,
+ "grad_norm": 0.00020980635599698871,
+ "learning_rate": 6.221430709799746e-05,
+ "loss": 0.0,
+ "step": 1710
+ },
+ {
+ "epoch": 4.27,
+ "grad_norm": 0.0003155861923005432,
+ "learning_rate": 6.183408421900532e-05,
+ "loss": 0.0064,
+ "step": 1720
+ },
+ {
+ "epoch": 4.29,
+ "grad_norm": 0.00015093179536052048,
+ "learning_rate": 6.145313499420506e-05,
+ "loss": 0.0,
+ "step": 1730
+ },
+ {
+ "epoch": 4.32,
+ "grad_norm": 0.00022122553491499275,
+ "learning_rate": 6.10714828052853e-05,
+ "loss": 0.0,
+ "step": 1740
+ },
+ {
+ "epoch": 4.34,
+ "grad_norm": 0.00024218260659836233,
+ "learning_rate": 6.068915107708084e-05,
+ "loss": 0.0,
+ "step": 1750
+ },
+ {
+ "epoch": 4.34,
+ "eval_loss": 0.000846256734803319,
+ "eval_runtime": 16.8681,
+ "eval_samples_per_second": 101.019,
+ "eval_steps_per_second": 4.209,
+ "step": 1750
+ },
+ {
+ "epoch": 4.37,
+ "grad_norm": 0.0001305171608692035,
+ "learning_rate": 6.030616327613482e-05,
+ "loss": 0.0,
+ "step": 1760
+ },
+ {
+ "epoch": 4.39,
+ "grad_norm": 0.00025666801957413554,
+ "learning_rate": 5.992254290925847e-05,
+ "loss": 0.0,
+ "step": 1770
+ },
+ {
+ "epoch": 4.42,
+ "grad_norm": 0.0001890121930046007,
+ "learning_rate": 5.953831352208831e-05,
+ "loss": 0.0,
+ "step": 1780
+ },
+ {
+ "epoch": 4.44,
+ "grad_norm": 0.00020163397130090743,
+ "learning_rate": 5.915349869764093e-05,
+ "loss": 0.0,
+ "step": 1790
+ },
+ {
+ "epoch": 4.47,
+ "grad_norm": 0.00012597240856848657,
+ "learning_rate": 5.87681220548656e-05,
+ "loss": 0.0,
+ "step": 1800
+ },
+ {
+ "epoch": 4.47,
+ "eval_loss": 0.0008095924276858568,
+ "eval_runtime": 16.8799,
+ "eval_samples_per_second": 100.948,
+ "eval_steps_per_second": 4.206,
+ "step": 1800
+ },
+ {
+ "epoch": 4.49,
+ "grad_norm": 0.00033845013240352273,
+ "learning_rate": 5.838220724719454e-05,
+ "loss": 0.0,
+ "step": 1810
+ },
+ {
+ "epoch": 4.52,
+ "grad_norm": 0.00031902611954137683,
+ "learning_rate": 5.7995777961091167e-05,
+ "loss": 0.0,
+ "step": 1820
+ },
+ {
+ "epoch": 4.54,
+ "grad_norm": 0.0010548951104283333,
+ "learning_rate": 5.760885791459627e-05,
+ "loss": 0.0,
+ "step": 1830
+ },
+ {
+ "epoch": 4.57,
+ "grad_norm": 8.980428538052365e-05,
+ "learning_rate": 5.722147085587223e-05,
+ "loss": 0.0,
+ "step": 1840
+ },
+ {
+ "epoch": 4.59,
+ "grad_norm": 0.00012754097406286746,
+ "learning_rate": 5.683364056174545e-05,
+ "loss": 0.0,
+ "step": 1850
+ },
+ {
+ "epoch": 4.59,
+ "eval_loss": 0.0008772177388891578,
+ "eval_runtime": 16.8757,
+ "eval_samples_per_second": 100.974,
+ "eval_steps_per_second": 4.207,
+ "step": 1850
+ },
+ {
+ "epoch": 4.62,
+ "grad_norm": 0.0010455192532390356,
+ "learning_rate": 5.644539083624701e-05,
+ "loss": 0.0,
+ "step": 1860
+ },
+ {
+ "epoch": 4.64,
+ "grad_norm": 0.00021354724594857544,
+ "learning_rate": 5.605674550915161e-05,
+ "loss": 0.0,
+ "step": 1870
+ },
+ {
+ "epoch": 4.67,
+ "grad_norm": 0.00022464946960099041,
+ "learning_rate": 5.566772843451495e-05,
+ "loss": 0.0,
+ "step": 1880
+ },
+ {
+ "epoch": 4.69,
+ "grad_norm": 6.343223503790796e-05,
+ "learning_rate": 5.527836348920965e-05,
+ "loss": 0.0,
+ "step": 1890
+ },
+ {
+ "epoch": 4.71,
+ "grad_norm": 0.0007182627450674772,
+ "learning_rate": 5.488867457145974e-05,
+ "loss": 0.0,
+ "step": 1900
+ },
+ {
+ "epoch": 4.71,
+ "eval_loss": 0.0006057315040379763,
+ "eval_runtime": 16.8716,
+ "eval_samples_per_second": 100.998,
+ "eval_steps_per_second": 4.208,
+ "step": 1900
+ },
+ {
+ "epoch": 4.74,
+ "grad_norm": 0.00021247757831588387,
+ "learning_rate": 5.449868559937384e-05,
+ "loss": 0.0,
+ "step": 1910
+ },
+ {
+ "epoch": 4.76,
+ "grad_norm": 0.00025663134874776006,
+ "learning_rate": 5.4108420509477145e-05,
+ "loss": 0.0,
+ "step": 1920
+ },
+ {
+ "epoch": 4.79,
+ "grad_norm": 0.00013280168059282005,
+ "learning_rate": 5.3717903255242284e-05,
+ "loss": 0.0,
+ "step": 1930
+ },
+ {
+ "epoch": 4.81,
+ "grad_norm": 5.64151669095736e-05,
+ "learning_rate": 5.3327157805619035e-05,
+ "loss": 0.0,
+ "step": 1940
+ },
+ {
+ "epoch": 4.84,
+ "grad_norm": 7.619507232448086e-05,
+ "learning_rate": 5.293620814356326e-05,
+ "loss": 0.0002,
+ "step": 1950
+ },
+ {
+ "epoch": 4.84,
+ "eval_loss": 0.0001224023144459352,
+ "eval_runtime": 16.8859,
+ "eval_samples_per_second": 100.913,
+ "eval_steps_per_second": 4.205,
+ "step": 1950
+ },
+ {
+ "epoch": 4.86,
+ "grad_norm": 0.0001947753335116431,
+ "learning_rate": 5.254507826456483e-05,
+ "loss": 0.0,
+ "step": 1960
+ },
+ {
+ "epoch": 4.89,
+ "grad_norm": 8.741691272007301e-05,
+ "learning_rate": 5.215379217517492e-05,
+ "loss": 0.0002,
+ "step": 1970
+ },
+ {
+ "epoch": 4.91,
+ "grad_norm": 0.00012889545178040862,
+ "learning_rate": 5.176237389153246e-05,
+ "loss": 0.0,
+ "step": 1980
+ },
+ {
+ "epoch": 4.94,
+ "grad_norm": 5.485777364810929e-05,
+ "learning_rate": 5.137084743789012e-05,
+ "loss": 0.0,
+ "step": 1990
+ },
+ {
+ "epoch": 4.96,
+ "grad_norm": 0.00056857755407691,
+ "learning_rate": 5.097923684513979e-05,
+ "loss": 0.0,
+ "step": 2000
+ },
+ {
+ "epoch": 4.96,
+ "eval_loss": 0.0007657750975340605,
+ "eval_runtime": 16.8738,
+ "eval_samples_per_second": 100.985,
+ "eval_steps_per_second": 4.208,
+ "step": 2000
+ },
+ {
+ "epoch": 4.99,
+ "grad_norm": 0.0005150920478627086,
+ "learning_rate": 5.058756614933757e-05,
+ "loss": 0.0,
+ "step": 2010
+ },
+ {
+ "epoch": 5.01,
+ "grad_norm": 0.00031274749198928475,
+ "learning_rate": 5.019585939022859e-05,
+ "loss": 0.0,
+ "step": 2020
+ },
+ {
+ "epoch": 5.04,
+ "grad_norm": 8.435914060100913e-05,
+ "learning_rate": 4.980414060977142e-05,
+ "loss": 0.0089,
+ "step": 2030
+ },
+ {
+ "epoch": 5.06,
+ "grad_norm": 7.393726264126599e-05,
+ "learning_rate": 4.9412433850662434e-05,
+ "loss": 0.0,
+ "step": 2040
+ },
+ {
+ "epoch": 5.09,
+ "grad_norm": 9.885100735118613e-05,
+ "learning_rate": 4.902076315486023e-05,
+ "loss": 0.0,
+ "step": 2050
+ },
+ {
+ "epoch": 5.09,
+ "eval_loss": 0.00010947392001980916,
+ "eval_runtime": 16.8917,
+ "eval_samples_per_second": 100.878,
+ "eval_steps_per_second": 4.203,
+ "step": 2050
+ },
+ {
+ "epoch": 5.11,
+ "grad_norm": 0.0005973571678623557,
+ "learning_rate": 4.86291525621099e-05,
+ "loss": 0.0,
+ "step": 2060
+ },
+ {
+ "epoch": 5.14,
+ "grad_norm": 5.217625221121125e-05,
+ "learning_rate": 4.823762610846755e-05,
+ "loss": 0.0,
+ "step": 2070
+ },
+ {
+ "epoch": 5.16,
+ "grad_norm": 0.0002454821078572422,
+ "learning_rate": 4.784620782482509e-05,
+ "loss": 0.0,
+ "step": 2080
+ },
+ {
+ "epoch": 5.19,
+ "grad_norm": 9.69076863839291e-05,
+ "learning_rate": 4.745492173543517e-05,
+ "loss": 0.0,
+ "step": 2090
+ },
+ {
+ "epoch": 5.21,
+ "grad_norm": 8.641201566206291e-05,
+ "learning_rate": 4.706379185643675e-05,
+ "loss": 0.0,
+ "step": 2100
+ },
+ {
+ "epoch": 5.21,
+ "eval_loss": 0.00016069799312390387,
+ "eval_runtime": 16.8743,
+ "eval_samples_per_second": 100.982,
+ "eval_steps_per_second": 4.208,
+ "step": 2100
+ },
+ {
+ "epoch": 5.24,
+ "grad_norm": 6.417043914552778e-05,
+ "learning_rate": 4.667284219438098e-05,
+ "loss": 0.0,
+ "step": 2110
+ },
+ {
+ "epoch": 5.26,
+ "grad_norm": 0.00013219700485933572,
+ "learning_rate": 4.628209674475773e-05,
+ "loss": 0.0,
+ "step": 2120
+ },
+ {
+ "epoch": 5.29,
+ "grad_norm": 6.98563817422837e-05,
+ "learning_rate": 4.589157949052287e-05,
+ "loss": 0.0,
+ "step": 2130
+ },
+ {
+ "epoch": 5.31,
+ "grad_norm": 9.513930126558989e-05,
+ "learning_rate": 4.550131440062617e-05,
+ "loss": 0.0,
+ "step": 2140
+ },
+ {
+ "epoch": 5.33,
+ "grad_norm": 5.327581675373949e-05,
+ "learning_rate": 4.511132542854027e-05,
+ "loss": 0.0,
+ "step": 2150
+ },
+ {
+ "epoch": 5.33,
+ "eval_loss": 0.00017579211271367967,
+ "eval_runtime": 16.8732,
+ "eval_samples_per_second": 100.989,
+ "eval_steps_per_second": 4.208,
+ "step": 2150
+ },
+ {
+ "epoch": 5.36,
+ "grad_norm": 0.00013409934763330966,
+ "learning_rate": 4.4721636510790365e-05,
+ "loss": 0.0,
+ "step": 2160
+ },
+ {
+ "epoch": 5.38,
+ "grad_norm": 8.724403596716002e-05,
+ "learning_rate": 4.4332271565485053e-05,
+ "loss": 0.0,
+ "step": 2170
+ },
+ {
+ "epoch": 5.41,
+ "grad_norm": 6.426259642466903e-05,
+ "learning_rate": 4.39432544908484e-05,
+ "loss": 0.0,
+ "step": 2180
+ },
+ {
+ "epoch": 5.43,
+ "grad_norm": 0.00012114330456824973,
+ "learning_rate": 4.355460916375299e-05,
+ "loss": 0.0,
+ "step": 2190
+ },
+ {
+ "epoch": 5.46,
+ "grad_norm": 9.614200826035812e-05,
+ "learning_rate": 4.3166359438254564e-05,
+ "loss": 0.0,
+ "step": 2200
+ },
+ {
+ "epoch": 5.46,
+ "eval_loss": 0.0004463446675799787,
+ "eval_runtime": 16.8612,
+ "eval_samples_per_second": 101.06,
+ "eval_steps_per_second": 4.211,
+ "step": 2200
+ },
+ {
+ "epoch": 5.48,
+ "grad_norm": 0.0002929608745034784,
+ "learning_rate": 4.27785291441278e-05,
+ "loss": 0.0,
+ "step": 2210
+ },
+ {
+ "epoch": 5.51,
+ "grad_norm": 4.366716166259721e-05,
+ "learning_rate": 4.239114208540374e-05,
+ "loss": 0.0,
+ "step": 2220
+ },
+ {
+ "epoch": 5.53,
+ "grad_norm": 3.860508149955422e-05,
+ "learning_rate": 4.2004222038908845e-05,
+ "loss": 0.0,
+ "step": 2230
+ },
+ {
+ "epoch": 5.56,
+ "grad_norm": 5.3087976993992925e-05,
+ "learning_rate": 4.161779275280546e-05,
+ "loss": 0.0,
+ "step": 2240
+ },
+ {
+ "epoch": 5.58,
+ "grad_norm": 0.00015269150026142597,
+ "learning_rate": 4.123187794513441e-05,
+ "loss": 0.0,
+ "step": 2250
+ },
+ {
+ "epoch": 5.58,
+ "eval_loss": 0.00039042255957610905,
+ "eval_runtime": 16.8755,
+ "eval_samples_per_second": 100.975,
+ "eval_steps_per_second": 4.207,
+ "step": 2250
+ },
+ {
+ "epoch": 5.61,
+ "grad_norm": 0.00011781427747337148,
+ "learning_rate": 4.084650130235909e-05,
+ "loss": 0.0,
+ "step": 2260
+ },
+ {
+ "epoch": 5.63,
+ "grad_norm": 7.544765685452148e-05,
+ "learning_rate": 4.046168647791171e-05,
+ "loss": 0.0,
+ "step": 2270
+ },
+ {
+ "epoch": 5.66,
+ "grad_norm": 4.577730942401104e-05,
+ "learning_rate": 4.007745709074154e-05,
+ "loss": 0.0,
+ "step": 2280
+ },
+ {
+ "epoch": 5.68,
+ "grad_norm": 0.00011316941527184099,
+ "learning_rate": 3.969383672386518e-05,
+ "loss": 0.0,
+ "step": 2290
+ },
+ {
+ "epoch": 5.71,
+ "grad_norm": 4.33563363912981e-05,
+ "learning_rate": 3.931084892291917e-05,
+ "loss": 0.0,
+ "step": 2300
+ },
+ {
+ "epoch": 5.71,
+ "eval_loss": 0.0004175197391305119,
+ "eval_runtime": 16.8721,
+ "eval_samples_per_second": 100.995,
+ "eval_steps_per_second": 4.208,
+ "step": 2300
+ },
+ {
+ "epoch": 5.73,
+ "grad_norm": 3.2948159059742466e-05,
+ "learning_rate": 3.8928517194714706e-05,
+ "loss": 0.0,
+ "step": 2310
+ },
+ {
+ "epoch": 5.76,
+ "grad_norm": 6.737465446349233e-05,
+ "learning_rate": 3.854686500579494e-05,
+ "loss": 0.0,
+ "step": 2320
+ },
+ {
+ "epoch": 5.78,
+ "grad_norm": 8.004607661860064e-05,
+ "learning_rate": 3.816591578099468e-05,
+ "loss": 0.0,
+ "step": 2330
+ },
+ {
+ "epoch": 5.81,
+ "grad_norm": 6.167278479551896e-05,
+ "learning_rate": 3.778569290200254e-05,
+ "loss": 0.0,
+ "step": 2340
+ },
+ {
+ "epoch": 5.83,
+ "grad_norm": 0.0003750508767552674,
+ "learning_rate": 3.7406219705925945e-05,
+ "loss": 0.0,
+ "step": 2350
+ },
+ {
+ "epoch": 5.83,
+ "eval_loss": 0.0003901799500454217,
+ "eval_runtime": 16.875,
+ "eval_samples_per_second": 100.978,
+ "eval_steps_per_second": 4.207,
+ "step": 2350
+ },
+ {
+ "epoch": 5.86,
+ "grad_norm": 4.658477337216027e-05,
+ "learning_rate": 3.702751948385864e-05,
+ "loss": 0.0,
+ "step": 2360
+ },
+ {
+ "epoch": 5.88,
+ "grad_norm": 0.00017428740102332085,
+ "learning_rate": 3.6649615479451226e-05,
+ "loss": 0.0,
+ "step": 2370
+ },
+ {
+ "epoch": 5.91,
+ "grad_norm": 0.0001236279495060444,
+ "learning_rate": 3.6272530887484535e-05,
+ "loss": 0.0,
+ "step": 2380
+ },
+ {
+ "epoch": 5.93,
+ "grad_norm": 7.120491500245407e-05,
+ "learning_rate": 3.5896288852445906e-05,
+ "loss": 0.0,
+ "step": 2390
+ },
+ {
+ "epoch": 5.96,
+ "grad_norm": 9.089993545785546e-05,
+ "learning_rate": 3.552091246710875e-05,
+ "loss": 0.0,
+ "step": 2400
+ },
+ {
+ "epoch": 5.96,
+ "eval_loss": 0.00044537056237459183,
+ "eval_runtime": 16.8732,
+ "eval_samples_per_second": 100.989,
+ "eval_steps_per_second": 4.208,
+ "step": 2400
+ },
+ {
+ "epoch": 5.98,
+ "grad_norm": 3.8834048609714955e-05,
+ "learning_rate": 3.514642477111505e-05,
+ "loss": 0.0,
+ "step": 2410
+ },
+ {
+ "epoch": 6.0,
+ "grad_norm": 0.0027178339660167694,
+ "learning_rate": 3.477284874956134e-05,
+ "loss": 0.0,
+ "step": 2420
+ },
+ {
+ "epoch": 6.03,
+ "grad_norm": 0.0001490208087489009,
+ "learning_rate": 3.440020733158792e-05,
+ "loss": 0.0,
+ "step": 2430
+ },
+ {
+ "epoch": 6.05,
+ "grad_norm": 3.5653181839734316e-05,
+ "learning_rate": 3.402852338897151e-05,
+ "loss": 0.0,
+ "step": 2440
+ },
+ {
+ "epoch": 6.08,
+ "grad_norm": 5.699761095456779e-05,
+ "learning_rate": 3.365781973472144e-05,
+ "loss": 0.0,
+ "step": 2450
+ },
+ {
+ "epoch": 6.08,
+ "eval_loss": 0.00038982907426543534,
+ "eval_runtime": 16.8883,
+ "eval_samples_per_second": 100.899,
+ "eval_steps_per_second": 4.204,
+ "step": 2450
+ },
+ {
+ "epoch": 6.1,
+ "grad_norm": 5.417722786660306e-05,
+ "learning_rate": 3.328811912167945e-05,
+ "loss": 0.0,
+ "step": 2460
+ },
+ {
+ "epoch": 6.13,
+ "grad_norm": 3.579606709536165e-05,
+ "learning_rate": 3.291944424112314e-05,
+ "loss": 0.0,
+ "step": 2470
+ },
+ {
+ "epoch": 6.15,
+ "grad_norm": 7.697240653214976e-05,
+ "learning_rate": 3.2551817721373335e-05,
+ "loss": 0.0,
+ "step": 2480
+ },
+ {
+ "epoch": 6.18,
+ "grad_norm": 4.500555223785341e-05,
+ "learning_rate": 3.218526212640511e-05,
+ "loss": 0.0,
+ "step": 2490
+ },
+ {
+ "epoch": 6.2,
+ "grad_norm": 7.687577453907579e-05,
+ "learning_rate": 3.1819799954462983e-05,
+ "loss": 0.0,
+ "step": 2500
+ },
+ {
+ "epoch": 6.2,
+ "eval_loss": 0.00047402523341588676,
+ "eval_runtime": 16.889,
+ "eval_samples_per_second": 100.894,
+ "eval_steps_per_second": 4.204,
+ "step": 2500
+ },
+ {
+ "epoch": 6.23,
+ "grad_norm": 6.375756493071094e-05,
+ "learning_rate": 3.1455453636679866e-05,
+ "loss": 0.0,
+ "step": 2510
+ },
+ {
+ "epoch": 6.25,
+ "grad_norm": 0.00015971327957231551,
+ "learning_rate": 3.109224553570047e-05,
+ "loss": 0.0,
+ "step": 2520
+ },
+ {
+ "epoch": 6.28,
+ "grad_norm": 0.00012273038737475872,
+ "learning_rate": 3.073019794430866e-05,
+ "loss": 0.0,
+ "step": 2530
+ },
+ {
+ "epoch": 6.3,
+ "grad_norm": 5.869157030247152e-05,
+ "learning_rate": 3.0369333084059148e-05,
+ "loss": 0.0,
+ "step": 2540
+ },
+ {
+ "epoch": 6.33,
+ "grad_norm": 9.306817082688212e-05,
+ "learning_rate": 3.0009673103913725e-05,
+ "loss": 0.0,
+ "step": 2550
+ },
+ {
+ "epoch": 6.33,
+ "eval_loss": 0.00047384999925270677,
+ "eval_runtime": 16.8848,
+ "eval_samples_per_second": 100.919,
+ "eval_steps_per_second": 4.205,
+ "step": 2550
+ },
+ {
+ "epoch": 6.35,
+ "grad_norm": 6.814825610490516e-05,
+ "learning_rate": 2.9651240078881625e-05,
+ "loss": 0.0,
+ "step": 2560
+ },
+ {
+ "epoch": 6.38,
+ "grad_norm": 4.082039595232345e-05,
+ "learning_rate": 2.9294056008664762e-05,
+ "loss": 0.0,
+ "step": 2570
+ },
+ {
+ "epoch": 6.4,
+ "grad_norm": 4.88782134198118e-05,
+ "learning_rate": 2.893814281630744e-05,
+ "loss": 0.0,
+ "step": 2580
+ },
+ {
+ "epoch": 6.43,
+ "grad_norm": 0.0004272049991413951,
+ "learning_rate": 2.8583522346850632e-05,
+ "loss": 0.0,
+ "step": 2590
+ },
+ {
+ "epoch": 6.45,
+ "grad_norm": 0.00017715679132379591,
+ "learning_rate": 2.823021636599137e-05,
+ "loss": 0.0,
+ "step": 2600
+ },
+ {
+ "epoch": 6.45,
+ "eval_loss": 0.0005336844478733838,
+ "eval_runtime": 16.8679,
+ "eval_samples_per_second": 101.02,
+ "eval_steps_per_second": 4.209,
+ "step": 2600
+ },
+ {
+ "epoch": 6.48,
+ "grad_norm": 5.479040555655956e-05,
+ "learning_rate": 2.787824655874674e-05,
+ "loss": 0.0,
+ "step": 2610
+ },
+ {
+ "epoch": 6.5,
+ "grad_norm": 4.12812405556906e-05,
+ "learning_rate": 2.7527634528122847e-05,
+ "loss": 0.0,
+ "step": 2620
+ },
+ {
+ "epoch": 6.53,
+ "grad_norm": 5.893718480365351e-05,
+ "learning_rate": 2.7178401793789012e-05,
+ "loss": 0.0,
+ "step": 2630
+ },
+ {
+ "epoch": 6.55,
+ "grad_norm": 0.00015176544548012316,
+ "learning_rate": 2.6830569790756805e-05,
+ "loss": 0.0,
+ "step": 2640
+ },
+ {
+ "epoch": 6.58,
+ "grad_norm": 4.401996557135135e-05,
+ "learning_rate": 2.6484159868064583e-05,
+ "loss": 0.0,
+ "step": 2650
+ },
+ {
+ "epoch": 6.58,
+ "eval_loss": 0.0004447665123734623,
+ "eval_runtime": 16.8689,
+ "eval_samples_per_second": 101.014,
+ "eval_steps_per_second": 4.209,
+ "step": 2650
+ },
+ {
+ "epoch": 6.58,
+ "step": 2650,
+ "total_flos": 9.885928322204959e+17,
+ "train_loss": 0.1188159689292002,
+ "train_runtime": 2950.0845,
+ "train_samples_per_second": 32.731,
+ "train_steps_per_second": 1.366
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 4030,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 10,
+ "save_steps": 500,
+ "total_flos": 9.885928322204959e+17,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_args.bin b/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b3bdf3e9dab8fa0883c0c1cb4079b5e737c7fc16
--- /dev/null
+++ b/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1559a7415ad61fab7820fa5c6cd769ade83d2e33096f4ebf8b568f21882c89d7
+size 5112
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_eval_loss.png b/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_eval_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..2ce7967aed695ecf81f80895bb7997e69c8cb7b9
Binary files /dev/null and b/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_eval_loss.png differ
diff --git a/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_loss.png b/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..f2df1604a21138e79129b6c17f932f1d56842115
Binary files /dev/null and b/llama2_13b_peft/formal_fallacies_syllogisms_negation/training_loss.png differ
diff --git a/llama2_13b_peft/goal_step_wikihow/README.md b/llama2_13b_peft/goal_step_wikihow/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..15716a021c929faf3c8ca0b5d00447422a66f756
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/README.md
@@ -0,0 +1,71 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: goal_step_wikihow_no_sys
+ results: []
+---
+
+
+
+# goal_step_wikihow_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the goal_step_wikihow_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0155
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0578 | 0.1493 | 100 | 0.0387 |
+| 0.0211 | 0.2985 | 200 | 0.0247 |
+| 0.0188 | 0.4478 | 300 | 0.0155 |
+| 0.0348 | 0.5970 | 400 | 0.0209 |
+| 0.0174 | 0.7463 | 500 | 0.0189 |
+| 0.0322 | 0.8955 | 600 | 0.0163 |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.19.1
\ No newline at end of file
diff --git a/llama2_13b_peft/goal_step_wikihow/adapter_config.json b/llama2_13b_peft/goal_step_wikihow/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b5aec6db723ba34a3a10ba30843b044c6b60ad43
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "down_proj",
+ "v_proj",
+ "gate_proj",
+ "k_proj",
+ "q_proj",
+ "o_proj",
+ "up_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/goal_step_wikihow/adapter_model.safetensors b/llama2_13b_peft/goal_step_wikihow/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..07c728ce140a0a647078bf31db4713cc82343de9
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fd68ef1b71aef1f8c0fa41c4cee8b73ffa36a061e9facae7af29e2c9792bc9
+size 125248064
diff --git a/llama2_13b_peft/goal_step_wikihow/all_results.json b/llama2_13b_peft/goal_step_wikihow/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..c8fd03497f6190fd4d134c886aedbcde68ba74c0
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/all_results.json
@@ -0,0 +1,12 @@
+{
+ "epoch": 0.8955223880597015,
+ "eval_loss": 0.01549521740525961,
+ "eval_runtime": 3.3948,
+ "eval_samples_per_second": 83.363,
+ "eval_steps_per_second": 10.605,
+ "total_flos": 4.751779802854195e+16,
+ "train_loss": 0.0911922578016917,
+ "train_runtime": 229.4716,
+ "train_samples_per_second": 116.79,
+ "train_steps_per_second": 14.599
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/goal_step_wikihow/eval_results.json b/llama2_13b_peft/goal_step_wikihow/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..672f46c9fbfa306382d7952eacd4baf0749b7341
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/eval_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 0.8955223880597015,
+ "eval_loss": 0.01549521740525961,
+ "eval_runtime": 3.3948,
+ "eval_samples_per_second": 83.363,
+ "eval_steps_per_second": 10.605
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/goal_step_wikihow/special_tokens_map.json b/llama2_13b_peft/goal_step_wikihow/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/llama2_13b_peft/goal_step_wikihow/tokenizer.model b/llama2_13b_peft/goal_step_wikihow/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/llama2_13b_peft/goal_step_wikihow/tokenizer_config.json b/llama2_13b_peft/goal_step_wikihow/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a40266f39e5b5fed14de34710d35eb9e98d6bdad
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false
+}
diff --git a/llama2_13b_peft/goal_step_wikihow/train_results.json b/llama2_13b_peft/goal_step_wikihow/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..2c28066f41c299315554de69620d1abe7fef7950
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/train_results.json
@@ -0,0 +1,8 @@
+{
+ "epoch": 0.8955223880597015,
+ "total_flos": 4.751779802854195e+16,
+ "train_loss": 0.0911922578016917,
+ "train_runtime": 229.4716,
+ "train_samples_per_second": 116.79,
+ "train_steps_per_second": 14.599
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/goal_step_wikihow/trainer_log.jsonl b/llama2_13b_peft/goal_step_wikihow/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..64df38bec622c46360e784cb25941135aa2f41a4
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/trainer_log.jsonl
@@ -0,0 +1,68 @@
+{"current_steps": 10, "total_steps": 3350, "loss": 2.0772, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 0.014925373134328358, "percentage": 0.3, "elapsed_time": "0:00:04", "remaining_time": "0:26:32"}
+{"current_steps": 20, "total_steps": 3350, "loss": 1.4248, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5e-05, "epoch": 0.029850746268656716, "percentage": 0.6, "elapsed_time": "0:00:08", "remaining_time": "0:22:15"}
+{"current_steps": 30, "total_steps": 3350, "loss": 0.243, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999888745376028e-05, "epoch": 0.04477611940298507, "percentage": 0.9, "elapsed_time": "0:00:11", "remaining_time": "0:20:49"}
+{"current_steps": 40, "total_steps": 3350, "loss": 0.0968, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9995549914061836e-05, "epoch": 0.05970149253731343, "percentage": 1.19, "elapsed_time": "0:00:14", "remaining_time": "0:19:53"}
+{"current_steps": 50, "total_steps": 3350, "loss": 0.0677, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.998998767795805e-05, "epoch": 0.07462686567164178, "percentage": 1.49, "elapsed_time": "0:00:17", "remaining_time": "0:19:23"}
+{"current_steps": 60, "total_steps": 3350, "loss": 0.0456, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.99822012405085e-05, "epoch": 0.08955223880597014, "percentage": 1.79, "elapsed_time": "0:00:21", "remaining_time": "0:19:13"}
+{"current_steps": 70, "total_steps": 3350, "loss": 0.0692, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.997219129473495e-05, "epoch": 0.1044776119402985, "percentage": 2.09, "elapsed_time": "0:00:24", "remaining_time": "0:18:54"}
+{"current_steps": 80, "total_steps": 3350, "loss": 0.0554, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.995995873155958e-05, "epoch": 0.11940298507462686, "percentage": 2.39, "elapsed_time": "0:00:27", "remaining_time": "0:18:37"}
+{"current_steps": 90, "total_steps": 3350, "loss": 0.0359, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.994550463972577e-05, "epoch": 0.13432835820895522, "percentage": 2.69, "elapsed_time": "0:00:30", "remaining_time": "0:18:38"}
+{"current_steps": 100, "total_steps": 3350, "loss": 0.0578, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.992883030570116e-05, "epoch": 0.14925373134328357, "percentage": 2.99, "elapsed_time": "0:00:33", "remaining_time": "0:18:23"}
+{"current_steps": 100, "total_steps": 3350, "loss": null, "eval_loss": 0.03871197998523712, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.14925373134328357, "percentage": 2.99, "elapsed_time": "0:00:33", "remaining_time": "0:18:23"}
+{"current_steps": 110, "total_steps": 3350, "loss": 0.0466, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9909937213563165e-05, "epoch": 0.16417910447761194, "percentage": 3.28, "elapsed_time": "0:00:41", "remaining_time": "0:20:16"}
+{"current_steps": 120, "total_steps": 3350, "loss": 0.0458, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.988882704486687e-05, "epoch": 0.1791044776119403, "percentage": 3.58, "elapsed_time": "0:00:44", "remaining_time": "0:20:09"}
+{"current_steps": 130, "total_steps": 3350, "loss": 0.0303, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9865501678495375e-05, "epoch": 0.19402985074626866, "percentage": 3.88, "elapsed_time": "0:00:48", "remaining_time": "0:19:56"}
+{"current_steps": 140, "total_steps": 3350, "loss": 0.0302, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9839963190492576e-05, "epoch": 0.208955223880597, "percentage": 4.18, "elapsed_time": "0:00:51", "remaining_time": "0:19:49"}
+{"current_steps": 150, "total_steps": 3350, "loss": 0.0256, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9812213853878376e-05, "epoch": 0.22388059701492538, "percentage": 4.48, "elapsed_time": "0:00:55", "remaining_time": "0:19:45"}
+{"current_steps": 160, "total_steps": 3350, "loss": 0.0333, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.978225613844639e-05, "epoch": 0.23880597014925373, "percentage": 4.78, "elapsed_time": "0:00:58", "remaining_time": "0:19:31"}
+{"current_steps": 170, "total_steps": 3350, "loss": 0.033, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.975009271054409e-05, "epoch": 0.2537313432835821, "percentage": 5.07, "elapsed_time": "0:01:01", "remaining_time": "0:19:18"}
+{"current_steps": 180, "total_steps": 3350, "loss": 0.0427, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.971572643283557e-05, "epoch": 0.26865671641791045, "percentage": 5.37, "elapsed_time": "0:01:05", "remaining_time": "0:19:10"}
+{"current_steps": 190, "total_steps": 3350, "loss": 0.0313, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9679160364046644e-05, "epoch": 0.2835820895522388, "percentage": 5.67, "elapsed_time": "0:01:08", "remaining_time": "0:18:58"}
+{"current_steps": 200, "total_steps": 3350, "loss": 0.0211, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9640397758692715e-05, "epoch": 0.29850746268656714, "percentage": 5.97, "elapsed_time": "0:01:11", "remaining_time": "0:18:47"}
+{"current_steps": 200, "total_steps": 3350, "loss": null, "eval_loss": 0.02473926544189453, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.29850746268656714, "percentage": 5.97, "elapsed_time": "0:01:11", "remaining_time": "0:18:47"}
+{"current_steps": 210, "total_steps": 3350, "loss": 0.0211, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9599442066789035e-05, "epoch": 0.31343283582089554, "percentage": 6.27, "elapsed_time": "0:01:18", "remaining_time": "0:19:39"}
+{"current_steps": 220, "total_steps": 3350, "loss": 0.0206, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.95562969335437e-05, "epoch": 0.3283582089552239, "percentage": 6.57, "elapsed_time": "0:01:22", "remaining_time": "0:19:30"}
+{"current_steps": 230, "total_steps": 3350, "loss": 0.031, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9510966199033174e-05, "epoch": 0.34328358208955223, "percentage": 6.87, "elapsed_time": "0:01:25", "remaining_time": "0:19:18"}
+{"current_steps": 240, "total_steps": 3350, "loss": 0.0346, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.946345389786049e-05, "epoch": 0.3582089552238806, "percentage": 7.16, "elapsed_time": "0:01:28", "remaining_time": "0:19:11"}
+{"current_steps": 250, "total_steps": 3350, "loss": 0.0134, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.941376425879624e-05, "epoch": 0.373134328358209, "percentage": 7.46, "elapsed_time": "0:01:32", "remaining_time": "0:19:06"}
+{"current_steps": 260, "total_steps": 3350, "loss": 0.0197, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.936190170440208e-05, "epoch": 0.3880597014925373, "percentage": 7.76, "elapsed_time": "0:01:35", "remaining_time": "0:18:57"}
+{"current_steps": 270, "total_steps": 3350, "loss": 0.0256, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.930787085063723e-05, "epoch": 0.40298507462686567, "percentage": 8.06, "elapsed_time": "0:01:39", "remaining_time": "0:18:50"}
+{"current_steps": 280, "total_steps": 3350, "loss": 0.02, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.925167650644752e-05, "epoch": 0.417910447761194, "percentage": 8.36, "elapsed_time": "0:01:43", "remaining_time": "0:18:51"}
+{"current_steps": 290, "total_steps": 3350, "loss": 0.0272, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9193323673337476e-05, "epoch": 0.43283582089552236, "percentage": 8.66, "elapsed_time": "0:01:46", "remaining_time": "0:18:41"}
+{"current_steps": 300, "total_steps": 3350, "loss": 0.0188, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9132817544925085e-05, "epoch": 0.44776119402985076, "percentage": 8.96, "elapsed_time": "0:01:49", "remaining_time": "0:18:32"}
+{"current_steps": 300, "total_steps": 3350, "loss": null, "eval_loss": 0.01549521740525961, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.44776119402985076, "percentage": 8.96, "elapsed_time": "0:01:49", "remaining_time": "0:18:32"}
+{"current_steps": 310, "total_steps": 3350, "loss": 0.0274, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.907016350647961e-05, "epoch": 0.4626865671641791, "percentage": 9.25, "elapsed_time": "0:01:56", "remaining_time": "0:19:02"}
+{"current_steps": 320, "total_steps": 3350, "loss": 0.0189, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9005367134442235e-05, "epoch": 0.47761194029850745, "percentage": 9.55, "elapsed_time": "0:01:59", "remaining_time": "0:18:53"}
+{"current_steps": 330, "total_steps": 3350, "loss": 0.0399, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.893843419592977e-05, "epoch": 0.4925373134328358, "percentage": 9.85, "elapsed_time": "0:02:02", "remaining_time": "0:18:43"}
+{"current_steps": 340, "total_steps": 3350, "loss": 0.0305, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.886937064822134e-05, "epoch": 0.5074626865671642, "percentage": 10.15, "elapsed_time": "0:02:06", "remaining_time": "0:18:35"}
+{"current_steps": 350, "total_steps": 3350, "loss": 0.0188, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8798182638228166e-05, "epoch": 0.5223880597014925, "percentage": 10.45, "elapsed_time": "0:02:09", "remaining_time": "0:18:29"}
+{"current_steps": 360, "total_steps": 3350, "loss": 0.0078, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.872487650194647e-05, "epoch": 0.5373134328358209, "percentage": 10.75, "elapsed_time": "0:02:12", "remaining_time": "0:18:20"}
+{"current_steps": 370, "total_steps": 3350, "loss": 0.0306, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.864945876389356e-05, "epoch": 0.5522388059701493, "percentage": 11.04, "elapsed_time": "0:02:15", "remaining_time": "0:18:14"}
+{"current_steps": 380, "total_steps": 3350, "loss": 0.0462, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.857193613652711e-05, "epoch": 0.5671641791044776, "percentage": 11.34, "elapsed_time": "0:02:19", "remaining_time": "0:18:07"}
+{"current_steps": 390, "total_steps": 3350, "loss": 0.0258, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.849231551964771e-05, "epoch": 0.582089552238806, "percentage": 11.64, "elapsed_time": "0:02:22", "remaining_time": "0:18:01"}
+{"current_steps": 400, "total_steps": 3350, "loss": 0.0348, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.841060399978481e-05, "epoch": 0.5970149253731343, "percentage": 11.94, "elapsed_time": "0:02:25", "remaining_time": "0:17:56"}
+{"current_steps": 400, "total_steps": 3350, "loss": null, "eval_loss": 0.02090635895729065, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.5970149253731343, "percentage": 11.94, "elapsed_time": "0:02:25", "remaining_time": "0:17:56"}
+{"current_steps": 410, "total_steps": 3350, "loss": 0.0232, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8326808849565936e-05, "epoch": 0.6119402985074627, "percentage": 12.24, "elapsed_time": "0:02:33", "remaining_time": "0:18:17"}
+{"current_steps": 420, "total_steps": 3350, "loss": 0.0128, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.824093752706943e-05, "epoch": 0.6268656716417911, "percentage": 12.54, "elapsed_time": "0:02:36", "remaining_time": "0:18:11"}
+{"current_steps": 430, "total_steps": 3350, "loss": 0.029, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.815299767516065e-05, "epoch": 0.6417910447761194, "percentage": 12.84, "elapsed_time": "0:02:39", "remaining_time": "0:18:03"}
+{"current_steps": 440, "total_steps": 3350, "loss": 0.0191, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.806299712081172e-05, "epoch": 0.6567164179104478, "percentage": 13.13, "elapsed_time": "0:02:42", "remaining_time": "0:17:56"}
+{"current_steps": 450, "total_steps": 3350, "loss": 0.0334, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.797094387440491e-05, "epoch": 0.6716417910447762, "percentage": 13.43, "elapsed_time": "0:02:46", "remaining_time": "0:17:51"}
+{"current_steps": 460, "total_steps": 3350, "loss": 0.0247, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.787684612901965e-05, "epoch": 0.6865671641791045, "percentage": 13.73, "elapsed_time": "0:02:49", "remaining_time": "0:17:44"}
+{"current_steps": 470, "total_steps": 3350, "loss": 0.0322, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.77807122597034e-05, "epoch": 0.7014925373134329, "percentage": 14.03, "elapsed_time": "0:02:52", "remaining_time": "0:17:39"}
+{"current_steps": 480, "total_steps": 3350, "loss": 0.0192, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.768255082272611e-05, "epoch": 0.7164179104477612, "percentage": 14.33, "elapsed_time": "0:02:56", "remaining_time": "0:17:33"}
+{"current_steps": 490, "total_steps": 3350, "loss": 0.0187, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.758237055481881e-05, "epoch": 0.7313432835820896, "percentage": 14.63, "elapsed_time": "0:02:59", "remaining_time": "0:17:25"}
+{"current_steps": 500, "total_steps": 3350, "loss": 0.0174, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.748018037239592e-05, "epoch": 0.746268656716418, "percentage": 14.93, "elapsed_time": "0:03:02", "remaining_time": "0:17:18"}
+{"current_steps": 500, "total_steps": 3350, "loss": null, "eval_loss": 0.018901415169239044, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.746268656716418, "percentage": 14.93, "elapsed_time": "0:03:02", "remaining_time": "0:17:18"}
+{"current_steps": 510, "total_steps": 3350, "loss": 0.019, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7375989370761695e-05, "epoch": 0.7611940298507462, "percentage": 15.22, "elapsed_time": "0:03:09", "remaining_time": "0:17:33"}
+{"current_steps": 520, "total_steps": 3350, "loss": 0.0233, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.726980682330071e-05, "epoch": 0.7761194029850746, "percentage": 15.52, "elapsed_time": "0:03:12", "remaining_time": "0:17:26"}
+{"current_steps": 530, "total_steps": 3350, "loss": 0.0094, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7161642180652464e-05, "epoch": 0.7910447761194029, "percentage": 15.82, "elapsed_time": "0:03:15", "remaining_time": "0:17:21"}
+{"current_steps": 540, "total_steps": 3350, "loss": 0.011, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7051505069870286e-05, "epoch": 0.8059701492537313, "percentage": 16.12, "elapsed_time": "0:03:18", "remaining_time": "0:17:15"}
+{"current_steps": 550, "total_steps": 3350, "loss": 0.0263, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.693940529356444e-05, "epoch": 0.8208955223880597, "percentage": 16.42, "elapsed_time": "0:03:22", "remaining_time": "0:17:09"}
+{"current_steps": 560, "total_steps": 3350, "loss": 0.0324, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6825352829029705e-05, "epoch": 0.835820895522388, "percentage": 16.72, "elapsed_time": "0:03:25", "remaining_time": "0:17:03"}
+{"current_steps": 570, "total_steps": 3350, "loss": 0.0232, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.670935782735732e-05, "epoch": 0.8507462686567164, "percentage": 17.01, "elapsed_time": "0:03:28", "remaining_time": "0:16:57"}
+{"current_steps": 580, "total_steps": 3350, "loss": 0.022, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6591430612531515e-05, "epoch": 0.8656716417910447, "percentage": 17.31, "elapsed_time": "0:03:31", "remaining_time": "0:16:52"}
+{"current_steps": 590, "total_steps": 3350, "loss": 0.0171, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.647158168051066e-05, "epoch": 0.8805970149253731, "percentage": 17.61, "elapsed_time": "0:03:35", "remaining_time": "0:16:47"}
+{"current_steps": 600, "total_steps": 3350, "loss": 0.0322, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6349821698293025e-05, "epoch": 0.8955223880597015, "percentage": 17.91, "elapsed_time": "0:03:39", "remaining_time": "0:16:43"}
+{"current_steps": 600, "total_steps": 3350, "loss": null, "eval_loss": 0.01632905751466751, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.8955223880597015, "percentage": 17.91, "elapsed_time": "0:03:39", "remaining_time": "0:16:43"}
+{"current_steps": 600, "total_steps": 3350, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.8955223880597015, "percentage": 17.91, "elapsed_time": "0:03:39", "remaining_time": "0:16:43"}
+{"current_steps": 36, "total_steps": 36, "loss": null, "eval_loss": 0.01549521740525961, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.8955223880597015, "percentage": 100.0, "elapsed_time": "0:03:54", "remaining_time": "0:00:00"}
diff --git a/llama2_13b_peft/goal_step_wikihow/trainer_state.json b/llama2_13b_peft/goal_step_wikihow/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecc5b8c3682b2823834b4e898925d000753adc
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/trainer_state.json
@@ -0,0 +1,498 @@
+{
+ "best_metric": 0.01549521740525961,
+ "best_model_checkpoint": "ckpt/llama2_13b_fuze27_no_sys/goal_step_wikihow_no_sys/checkpoint-300",
+ "epoch": 0.8955223880597015,
+ "eval_steps": 100,
+ "global_step": 600,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.014925373134328358,
+ "grad_norm": 1.120189905166626,
+ "learning_rate": 2.5e-05,
+ "loss": 2.0772,
+ "step": 10
+ },
+ {
+ "epoch": 0.029850746268656716,
+ "grad_norm": 1.9035515785217285,
+ "learning_rate": 5e-05,
+ "loss": 1.4248,
+ "step": 20
+ },
+ {
+ "epoch": 0.04477611940298507,
+ "grad_norm": 0.7899401187896729,
+ "learning_rate": 4.999888745376028e-05,
+ "loss": 0.243,
+ "step": 30
+ },
+ {
+ "epoch": 0.05970149253731343,
+ "grad_norm": 0.6186442971229553,
+ "learning_rate": 4.9995549914061836e-05,
+ "loss": 0.0968,
+ "step": 40
+ },
+ {
+ "epoch": 0.07462686567164178,
+ "grad_norm": 0.2080095410346985,
+ "learning_rate": 4.998998767795805e-05,
+ "loss": 0.0677,
+ "step": 50
+ },
+ {
+ "epoch": 0.08955223880597014,
+ "grad_norm": 0.9628311991691589,
+ "learning_rate": 4.99822012405085e-05,
+ "loss": 0.0456,
+ "step": 60
+ },
+ {
+ "epoch": 0.1044776119402985,
+ "grad_norm": 0.22719591856002808,
+ "learning_rate": 4.997219129473495e-05,
+ "loss": 0.0692,
+ "step": 70
+ },
+ {
+ "epoch": 0.11940298507462686,
+ "grad_norm": 0.9114218950271606,
+ "learning_rate": 4.995995873155958e-05,
+ "loss": 0.0554,
+ "step": 80
+ },
+ {
+ "epoch": 0.13432835820895522,
+ "grad_norm": 0.7211790084838867,
+ "learning_rate": 4.994550463972577e-05,
+ "loss": 0.0359,
+ "step": 90
+ },
+ {
+ "epoch": 0.14925373134328357,
+ "grad_norm": 0.5946223735809326,
+ "learning_rate": 4.992883030570116e-05,
+ "loss": 0.0578,
+ "step": 100
+ },
+ {
+ "epoch": 0.14925373134328357,
+ "eval_loss": 0.03871197998523712,
+ "eval_runtime": 3.3964,
+ "eval_samples_per_second": 83.324,
+ "eval_steps_per_second": 10.599,
+ "step": 100
+ },
+ {
+ "epoch": 0.16417910447761194,
+ "grad_norm": 0.5560318231582642,
+ "learning_rate": 4.9909937213563165e-05,
+ "loss": 0.0466,
+ "step": 110
+ },
+ {
+ "epoch": 0.1791044776119403,
+ "grad_norm": 0.4391833543777466,
+ "learning_rate": 4.988882704486687e-05,
+ "loss": 0.0458,
+ "step": 120
+ },
+ {
+ "epoch": 0.19402985074626866,
+ "grad_norm": 1.3032832145690918,
+ "learning_rate": 4.9865501678495375e-05,
+ "loss": 0.0303,
+ "step": 130
+ },
+ {
+ "epoch": 0.208955223880597,
+ "grad_norm": 0.7368983626365662,
+ "learning_rate": 4.9839963190492576e-05,
+ "loss": 0.0302,
+ "step": 140
+ },
+ {
+ "epoch": 0.22388059701492538,
+ "grad_norm": 0.4908844530582428,
+ "learning_rate": 4.9812213853878376e-05,
+ "loss": 0.0256,
+ "step": 150
+ },
+ {
+ "epoch": 0.23880597014925373,
+ "grad_norm": 0.19529247283935547,
+ "learning_rate": 4.978225613844639e-05,
+ "loss": 0.0333,
+ "step": 160
+ },
+ {
+ "epoch": 0.2537313432835821,
+ "grad_norm": 1.0576449632644653,
+ "learning_rate": 4.975009271054409e-05,
+ "loss": 0.033,
+ "step": 170
+ },
+ {
+ "epoch": 0.26865671641791045,
+ "grad_norm": 0.9957035183906555,
+ "learning_rate": 4.971572643283557e-05,
+ "loss": 0.0427,
+ "step": 180
+ },
+ {
+ "epoch": 0.2835820895522388,
+ "grad_norm": 1.6194720268249512,
+ "learning_rate": 4.9679160364046644e-05,
+ "loss": 0.0313,
+ "step": 190
+ },
+ {
+ "epoch": 0.29850746268656714,
+ "grad_norm": 0.8167016506195068,
+ "learning_rate": 4.9640397758692715e-05,
+ "loss": 0.0211,
+ "step": 200
+ },
+ {
+ "epoch": 0.29850746268656714,
+ "eval_loss": 0.02473926544189453,
+ "eval_runtime": 3.4096,
+ "eval_samples_per_second": 83.001,
+ "eval_steps_per_second": 10.558,
+ "step": 200
+ },
+ {
+ "epoch": 0.31343283582089554,
+ "grad_norm": 1.0900298357009888,
+ "learning_rate": 4.9599442066789035e-05,
+ "loss": 0.0211,
+ "step": 210
+ },
+ {
+ "epoch": 0.3283582089552239,
+ "grad_norm": 0.07477018237113953,
+ "learning_rate": 4.95562969335437e-05,
+ "loss": 0.0206,
+ "step": 220
+ },
+ {
+ "epoch": 0.34328358208955223,
+ "grad_norm": 0.09038381278514862,
+ "learning_rate": 4.9510966199033174e-05,
+ "loss": 0.031,
+ "step": 230
+ },
+ {
+ "epoch": 0.3582089552238806,
+ "grad_norm": 0.16180317103862762,
+ "learning_rate": 4.946345389786049e-05,
+ "loss": 0.0346,
+ "step": 240
+ },
+ {
+ "epoch": 0.373134328358209,
+ "grad_norm": 0.16372862458229065,
+ "learning_rate": 4.941376425879624e-05,
+ "loss": 0.0134,
+ "step": 250
+ },
+ {
+ "epoch": 0.3880597014925373,
+ "grad_norm": 0.9981012344360352,
+ "learning_rate": 4.936190170440208e-05,
+ "loss": 0.0197,
+ "step": 260
+ },
+ {
+ "epoch": 0.40298507462686567,
+ "grad_norm": 0.7528088688850403,
+ "learning_rate": 4.930787085063723e-05,
+ "loss": 0.0256,
+ "step": 270
+ },
+ {
+ "epoch": 0.417910447761194,
+ "grad_norm": 0.19578298926353455,
+ "learning_rate": 4.925167650644752e-05,
+ "loss": 0.02,
+ "step": 280
+ },
+ {
+ "epoch": 0.43283582089552236,
+ "grad_norm": 0.5017349720001221,
+ "learning_rate": 4.9193323673337476e-05,
+ "loss": 0.0272,
+ "step": 290
+ },
+ {
+ "epoch": 0.44776119402985076,
+ "grad_norm": 0.11107462644577026,
+ "learning_rate": 4.9132817544925085e-05,
+ "loss": 0.0188,
+ "step": 300
+ },
+ {
+ "epoch": 0.44776119402985076,
+ "eval_loss": 0.01549521740525961,
+ "eval_runtime": 3.4071,
+ "eval_samples_per_second": 83.063,
+ "eval_steps_per_second": 10.566,
+ "step": 300
+ },
+ {
+ "epoch": 0.4626865671641791,
+ "grad_norm": 0.5003395676612854,
+ "learning_rate": 4.907016350647961e-05,
+ "loss": 0.0274,
+ "step": 310
+ },
+ {
+ "epoch": 0.47761194029850745,
+ "grad_norm": 0.9313437938690186,
+ "learning_rate": 4.9005367134442235e-05,
+ "loss": 0.0189,
+ "step": 320
+ },
+ {
+ "epoch": 0.4925373134328358,
+ "grad_norm": 0.5654332637786865,
+ "learning_rate": 4.893843419592977e-05,
+ "loss": 0.0399,
+ "step": 330
+ },
+ {
+ "epoch": 0.5074626865671642,
+ "grad_norm": 0.31965282559394836,
+ "learning_rate": 4.886937064822134e-05,
+ "loss": 0.0305,
+ "step": 340
+ },
+ {
+ "epoch": 0.5223880597014925,
+ "grad_norm": 1.1818617582321167,
+ "learning_rate": 4.8798182638228166e-05,
+ "loss": 0.0188,
+ "step": 350
+ },
+ {
+ "epoch": 0.5373134328358209,
+ "grad_norm": 0.7235459685325623,
+ "learning_rate": 4.872487650194647e-05,
+ "loss": 0.0078,
+ "step": 360
+ },
+ {
+ "epoch": 0.5522388059701493,
+ "grad_norm": 0.2298729419708252,
+ "learning_rate": 4.864945876389356e-05,
+ "loss": 0.0306,
+ "step": 370
+ },
+ {
+ "epoch": 0.5671641791044776,
+ "grad_norm": 0.8177179098129272,
+ "learning_rate": 4.857193613652711e-05,
+ "loss": 0.0462,
+ "step": 380
+ },
+ {
+ "epoch": 0.582089552238806,
+ "grad_norm": 0.56449955701828,
+ "learning_rate": 4.849231551964771e-05,
+ "loss": 0.0258,
+ "step": 390
+ },
+ {
+ "epoch": 0.5970149253731343,
+ "grad_norm": 0.07830353826284409,
+ "learning_rate": 4.841060399978481e-05,
+ "loss": 0.0348,
+ "step": 400
+ },
+ {
+ "epoch": 0.5970149253731343,
+ "eval_loss": 0.02090635895729065,
+ "eval_runtime": 3.4174,
+ "eval_samples_per_second": 82.812,
+ "eval_steps_per_second": 10.534,
+ "step": 400
+ },
+ {
+ "epoch": 0.6119402985074627,
+ "grad_norm": 0.09485949575901031,
+ "learning_rate": 4.8326808849565936e-05,
+ "loss": 0.0232,
+ "step": 410
+ },
+ {
+ "epoch": 0.6268656716417911,
+ "grad_norm": 0.11512016505002975,
+ "learning_rate": 4.824093752706943e-05,
+ "loss": 0.0128,
+ "step": 420
+ },
+ {
+ "epoch": 0.6417910447761194,
+ "grad_norm": 0.5873417854309082,
+ "learning_rate": 4.815299767516065e-05,
+ "loss": 0.029,
+ "step": 430
+ },
+ {
+ "epoch": 0.6567164179104478,
+ "grad_norm": 0.21897241473197937,
+ "learning_rate": 4.806299712081172e-05,
+ "loss": 0.0191,
+ "step": 440
+ },
+ {
+ "epoch": 0.6716417910447762,
+ "grad_norm": 0.40686163306236267,
+ "learning_rate": 4.797094387440491e-05,
+ "loss": 0.0334,
+ "step": 450
+ },
+ {
+ "epoch": 0.6865671641791045,
+ "grad_norm": 0.21303780376911163,
+ "learning_rate": 4.787684612901965e-05,
+ "loss": 0.0247,
+ "step": 460
+ },
+ {
+ "epoch": 0.7014925373134329,
+ "grad_norm": 0.22599412500858307,
+ "learning_rate": 4.77807122597034e-05,
+ "loss": 0.0322,
+ "step": 470
+ },
+ {
+ "epoch": 0.7164179104477612,
+ "grad_norm": 1.112415075302124,
+ "learning_rate": 4.768255082272611e-05,
+ "loss": 0.0192,
+ "step": 480
+ },
+ {
+ "epoch": 0.7313432835820896,
+ "grad_norm": 0.2906021475791931,
+ "learning_rate": 4.758237055481881e-05,
+ "loss": 0.0187,
+ "step": 490
+ },
+ {
+ "epoch": 0.746268656716418,
+ "grad_norm": 0.9070213437080383,
+ "learning_rate": 4.748018037239592e-05,
+ "loss": 0.0174,
+ "step": 500
+ },
+ {
+ "epoch": 0.746268656716418,
+ "eval_loss": 0.018901415169239044,
+ "eval_runtime": 3.4236,
+ "eval_samples_per_second": 82.661,
+ "eval_steps_per_second": 10.515,
+ "step": 500
+ },
+ {
+ "epoch": 0.7611940298507462,
+ "grad_norm": 0.14662091434001923,
+ "learning_rate": 4.7375989370761695e-05,
+ "loss": 0.019,
+ "step": 510
+ },
+ {
+ "epoch": 0.7761194029850746,
+ "grad_norm": 0.4166763722896576,
+ "learning_rate": 4.726980682330071e-05,
+ "loss": 0.0233,
+ "step": 520
+ },
+ {
+ "epoch": 0.7910447761194029,
+ "grad_norm": 1.4465707540512085,
+ "learning_rate": 4.7161642180652464e-05,
+ "loss": 0.0094,
+ "step": 530
+ },
+ {
+ "epoch": 0.8059701492537313,
+ "grad_norm": 0.06211471930146217,
+ "learning_rate": 4.7051505069870286e-05,
+ "loss": 0.011,
+ "step": 540
+ },
+ {
+ "epoch": 0.8208955223880597,
+ "grad_norm": 0.9001145958900452,
+ "learning_rate": 4.693940529356444e-05,
+ "loss": 0.0263,
+ "step": 550
+ },
+ {
+ "epoch": 0.835820895522388,
+ "grad_norm": 0.13082529604434967,
+ "learning_rate": 4.6825352829029705e-05,
+ "loss": 0.0324,
+ "step": 560
+ },
+ {
+ "epoch": 0.8507462686567164,
+ "grad_norm": 0.05113005265593529,
+ "learning_rate": 4.670935782735732e-05,
+ "loss": 0.0232,
+ "step": 570
+ },
+ {
+ "epoch": 0.8656716417910447,
+ "grad_norm": 0.25802016258239746,
+ "learning_rate": 4.6591430612531515e-05,
+ "loss": 0.022,
+ "step": 580
+ },
+ {
+ "epoch": 0.8805970149253731,
+ "grad_norm": 0.08641457557678223,
+ "learning_rate": 4.647158168051066e-05,
+ "loss": 0.0171,
+ "step": 590
+ },
+ {
+ "epoch": 0.8955223880597015,
+ "grad_norm": 0.1270509511232376,
+ "learning_rate": 4.6349821698293025e-05,
+ "loss": 0.0322,
+ "step": 600
+ },
+ {
+ "epoch": 0.8955223880597015,
+ "eval_loss": 0.01632905751466751,
+ "eval_runtime": 3.4247,
+ "eval_samples_per_second": 82.635,
+ "eval_steps_per_second": 10.512,
+ "step": 600
+ },
+ {
+ "epoch": 0.8955223880597015,
+ "step": 600,
+ "total_flos": 4.751779802854195e+16,
+ "train_loss": 0.0911922578016917,
+ "train_runtime": 229.4716,
+ "train_samples_per_second": 116.79,
+ "train_steps_per_second": 14.599
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 3350,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 100,
+ "total_flos": 4.751779802854195e+16,
+ "train_batch_size": 4,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/llama2_13b_peft/goal_step_wikihow/training_args.bin b/llama2_13b_peft/goal_step_wikihow/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b0319e32edc479a05de1030461f868dc44ad6de2
--- /dev/null
+++ b/llama2_13b_peft/goal_step_wikihow/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12855ddad282e99923537ea60226a5c934f272b30d3bbc479c8d1e80eacd58bf
+size 5176
diff --git a/llama2_13b_peft/goal_step_wikihow/training_eval_loss.png b/llama2_13b_peft/goal_step_wikihow/training_eval_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..2cc74b2088f239cca5b98b4efbc45afccf72e630
Binary files /dev/null and b/llama2_13b_peft/goal_step_wikihow/training_eval_loss.png differ
diff --git a/llama2_13b_peft/goal_step_wikihow/training_loss.png b/llama2_13b_peft/goal_step_wikihow/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..07c0a743af8d51a19ca56d706afd3104c30d9f4a
Binary files /dev/null and b/llama2_13b_peft/goal_step_wikihow/training_loss.png differ
diff --git a/llama2_13b_peft/gsm8k/README.md b/llama2_13b_peft/gsm8k/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..41f061167bad6d3f1e4a5a5d6e138e7b808447db
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/README.md
@@ -0,0 +1,85 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: gsm8k_no_sys
+ results: []
+---
+
+
+
+# gsm8k_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the gsm8k_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3435
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4745 | 0.1126 | 100 | 0.4416 |
+| 0.4714 | 0.2252 | 200 | 0.4106 |
+| 0.4732 | 0.3378 | 300 | 0.3975 |
+| 0.3662 | 0.4505 | 400 | 0.3874 |
+| 0.363 | 0.5631 | 500 | 0.3789 |
+| 0.3912 | 0.6757 | 600 | 0.3732 |
+| 0.3738 | 0.7883 | 700 | 0.3662 |
+| 0.3729 | 0.9009 | 800 | 0.3624 |
+| 0.3573 | 1.0135 | 900 | 0.3588 |
+| 0.3603 | 1.1261 | 1000 | 0.3570 |
+| 0.3501 | 1.2387 | 1100 | 0.3555 |
+| 0.3335 | 1.3514 | 1200 | 0.3528 |
+| 0.3372 | 1.4640 | 1300 | 0.3515 |
+| 0.3565 | 1.5766 | 1400 | 0.3502 |
+| 0.3313 | 1.6892 | 1500 | 0.3492 |
+| 0.3653 | 1.8018 | 1600 | 0.3448 |
+| 0.3412 | 1.9144 | 1700 | 0.3435 |
+| 0.2738 | 2.0270 | 1800 | 0.3494 |
+| 0.3159 | 2.1396 | 1900 | 0.3488 |
+| 0.2892 | 2.2523 | 2000 | 0.3520 |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.19.1
\ No newline at end of file
diff --git a/llama2_13b_peft/gsm8k/adapter_config.json b/llama2_13b_peft/gsm8k/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8debde6383a2ebd65af40d7a8282ca081916e38a
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "down_proj",
+ "gate_proj",
+ "o_proj",
+ "v_proj",
+ "q_proj",
+ "k_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/gsm8k/adapter_model.safetensors b/llama2_13b_peft/gsm8k/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dc203c34678c58d75960bc9d0dd94376b638ec10
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ccee9e3e8038805b1a669e8edb66c5634547ca48e295effb86d95afaa2b8b9
+size 125248064
diff --git a/llama2_13b_peft/gsm8k/all_results.json b/llama2_13b_peft/gsm8k/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..4dc12591bbf343147fa4555f7ac859f07898cc9d
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/all_results.json
@@ -0,0 +1,12 @@
+{
+ "epoch": 2.2522522522522523,
+ "eval_loss": 0.3434712886810303,
+ "eval_runtime": 8.1854,
+ "eval_samples_per_second": 45.691,
+ "eval_steps_per_second": 5.742,
+ "total_flos": 3.569474683755561e+17,
+ "train_loss": 0.3791467320919037,
+ "train_runtime": 1418.2267,
+ "train_samples_per_second": 25.028,
+ "train_steps_per_second": 3.131
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/gsm8k/eval_results.json b/llama2_13b_peft/gsm8k/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..bbbbf102a622115859faa0f883d3840e511e30f4
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/eval_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 2.2522522522522523,
+ "eval_loss": 0.3434712886810303,
+ "eval_runtime": 8.1854,
+ "eval_samples_per_second": 45.691,
+ "eval_steps_per_second": 5.742
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/gsm8k/special_tokens_map.json b/llama2_13b_peft/gsm8k/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/llama2_13b_peft/gsm8k/tokenizer.model b/llama2_13b_peft/gsm8k/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/llama2_13b_peft/gsm8k/tokenizer_config.json b/llama2_13b_peft/gsm8k/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a40266f39e5b5fed14de34710d35eb9e98d6bdad
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false
+}
diff --git a/llama2_13b_peft/gsm8k/train_results.json b/llama2_13b_peft/gsm8k/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..3a2b70e621b52ece767077d6be3224ca9d6f9a82
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/train_results.json
@@ -0,0 +1,8 @@
+{
+ "epoch": 2.2522522522522523,
+ "total_flos": 3.569474683755561e+17,
+ "train_loss": 0.3791467320919037,
+ "train_runtime": 1418.2267,
+ "train_samples_per_second": 25.028,
+ "train_steps_per_second": 3.131
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/gsm8k/trainer_log.jsonl b/llama2_13b_peft/gsm8k/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..cc18a98efb76b67d9559e204fc0e982027ae331c
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/trainer_log.jsonl
@@ -0,0 +1,222 @@
+{"current_steps": 10, "total_steps": 4440, "loss": 1.1013, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 0.01126126126126126, "percentage": 0.23, "elapsed_time": "0:00:07", "remaining_time": "0:54:01"}
+{"current_steps": 20, "total_steps": 4440, "loss": 1.0292, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5e-05, "epoch": 0.02252252252252252, "percentage": 0.45, "elapsed_time": "0:00:12", "remaining_time": "0:47:21"}
+{"current_steps": 30, "total_steps": 4440, "loss": 0.8085, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999936851448764e-05, "epoch": 0.033783783783783786, "percentage": 0.68, "elapsed_time": "0:00:18", "remaining_time": "0:45:21"}
+{"current_steps": 40, "total_steps": 4440, "loss": 0.5884, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999747408985249e-05, "epoch": 0.04504504504504504, "percentage": 0.9, "elapsed_time": "0:00:24", "remaining_time": "0:44:25"}
+{"current_steps": 50, "total_steps": 4440, "loss": 0.4774, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999431682179867e-05, "epoch": 0.05630630630630631, "percentage": 1.13, "elapsed_time": "0:00:30", "remaining_time": "0:44:27"}
+{"current_steps": 60, "total_steps": 4440, "loss": 0.5014, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9989896869827705e-05, "epoch": 0.06756756756756757, "percentage": 1.35, "elapsed_time": "0:00:35", "remaining_time": "0:43:35"}
+{"current_steps": 70, "total_steps": 4440, "loss": 0.5193, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.998421445723046e-05, "epoch": 0.07882882882882883, "percentage": 1.58, "elapsed_time": "0:00:41", "remaining_time": "0:43:10"}
+{"current_steps": 80, "total_steps": 4440, "loss": 0.4532, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.997726987107582e-05, "epoch": 0.09009009009009009, "percentage": 1.8, "elapsed_time": "0:00:47", "remaining_time": "0:43:06"}
+{"current_steps": 90, "total_steps": 4440, "loss": 0.4591, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.996906346219623e-05, "epoch": 0.10135135135135136, "percentage": 2.03, "elapsed_time": "0:00:53", "remaining_time": "0:43:03"}
+{"current_steps": 100, "total_steps": 4440, "loss": 0.4745, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.995959564516997e-05, "epoch": 0.11261261261261261, "percentage": 2.25, "elapsed_time": "0:00:59", "remaining_time": "0:42:59"}
+{"current_steps": 100, "total_steps": 4440, "loss": null, "eval_loss": 0.4415845274925232, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.11261261261261261, "percentage": 2.25, "elapsed_time": "0:00:59", "remaining_time": "0:42:59"}
+{"current_steps": 110, "total_steps": 4440, "loss": 0.4956, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.994886689830015e-05, "epoch": 0.12387387387387387, "percentage": 2.48, "elapsed_time": "0:01:13", "remaining_time": "0:48:02"}
+{"current_steps": 120, "total_steps": 4440, "loss": 0.4031, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9936877763590664e-05, "epoch": 0.13513513513513514, "percentage": 2.7, "elapsed_time": "0:01:18", "remaining_time": "0:47:07"}
+{"current_steps": 130, "total_steps": 4440, "loss": 0.4411, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9923628846718685e-05, "epoch": 0.1463963963963964, "percentage": 2.93, "elapsed_time": "0:01:24", "remaining_time": "0:46:40"}
+{"current_steps": 140, "total_steps": 4440, "loss": 0.4396, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.990912081700413e-05, "epoch": 0.15765765765765766, "percentage": 3.15, "elapsed_time": "0:01:30", "remaining_time": "0:46:22"}
+{"current_steps": 150, "total_steps": 4440, "loss": 0.4137, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.989335440737586e-05, "epoch": 0.16891891891891891, "percentage": 3.38, "elapsed_time": "0:01:36", "remaining_time": "0:45:48"}
+{"current_steps": 160, "total_steps": 4440, "loss": 0.436, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9876330414334614e-05, "epoch": 0.18018018018018017, "percentage": 3.6, "elapsed_time": "0:01:41", "remaining_time": "0:45:18"}
+{"current_steps": 170, "total_steps": 4440, "loss": 0.4391, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.985804969791279e-05, "epoch": 0.19144144144144143, "percentage": 3.83, "elapsed_time": "0:01:48", "remaining_time": "0:45:13"}
+{"current_steps": 180, "total_steps": 4440, "loss": 0.4504, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.983851318163097e-05, "epoch": 0.20270270270270271, "percentage": 4.05, "elapsed_time": "0:01:53", "remaining_time": "0:44:56"}
+{"current_steps": 190, "total_steps": 4440, "loss": 0.437, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.981772185245135e-05, "epoch": 0.21396396396396397, "percentage": 4.28, "elapsed_time": "0:02:00", "remaining_time": "0:44:47"}
+{"current_steps": 200, "total_steps": 4440, "loss": 0.4714, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.979567676072776e-05, "epoch": 0.22522522522522523, "percentage": 4.5, "elapsed_time": "0:02:05", "remaining_time": "0:44:23"}
+{"current_steps": 200, "total_steps": 4440, "loss": null, "eval_loss": 0.410622775554657, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.22522522522522523, "percentage": 4.5, "elapsed_time": "0:02:05", "remaining_time": "0:44:23"}
+{"current_steps": 210, "total_steps": 4440, "loss": 0.432, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.977237902015269e-05, "epoch": 0.23648648648648649, "percentage": 4.73, "elapsed_time": "0:02:20", "remaining_time": "0:47:01"}
+{"current_steps": 220, "total_steps": 4440, "loss": 0.4514, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9747829807701e-05, "epoch": 0.24774774774774774, "percentage": 4.95, "elapsed_time": "0:02:25", "remaining_time": "0:46:40"}
+{"current_steps": 230, "total_steps": 4440, "loss": 0.4396, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9722030363570425e-05, "epoch": 0.25900900900900903, "percentage": 5.18, "elapsed_time": "0:02:32", "remaining_time": "0:46:34"}
+{"current_steps": 240, "total_steps": 4440, "loss": 0.3982, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9694981991119004e-05, "epoch": 0.2702702702702703, "percentage": 5.41, "elapsed_time": "0:02:38", "remaining_time": "0:46:15"}
+{"current_steps": 250, "total_steps": 4440, "loss": 0.46, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.966668605679916e-05, "epoch": 0.28153153153153154, "percentage": 5.63, "elapsed_time": "0:02:44", "remaining_time": "0:45:56"}
+{"current_steps": 260, "total_steps": 4440, "loss": 0.4344, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.963714399008869e-05, "epoch": 0.2927927927927928, "percentage": 5.86, "elapsed_time": "0:02:50", "remaining_time": "0:45:40"}
+{"current_steps": 270, "total_steps": 4440, "loss": 0.4197, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9606357283418575e-05, "epoch": 0.30405405405405406, "percentage": 6.08, "elapsed_time": "0:02:56", "remaining_time": "0:45:26"}
+{"current_steps": 280, "total_steps": 4440, "loss": 0.4109, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.957432749209755e-05, "epoch": 0.3153153153153153, "percentage": 6.31, "elapsed_time": "0:03:01", "remaining_time": "0:45:03"}
+{"current_steps": 290, "total_steps": 4440, "loss": 0.3968, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.954105623423354e-05, "epoch": 0.32657657657657657, "percentage": 6.53, "elapsed_time": "0:03:08", "remaining_time": "0:44:52"}
+{"current_steps": 300, "total_steps": 4440, "loss": 0.4732, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.950654519065195e-05, "epoch": 0.33783783783783783, "percentage": 6.76, "elapsed_time": "0:03:13", "remaining_time": "0:44:32"}
+{"current_steps": 300, "total_steps": 4440, "loss": null, "eval_loss": 0.3975336253643036, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.33783783783783783, "percentage": 6.76, "elapsed_time": "0:03:13", "remaining_time": "0:44:32"}
+{"current_steps": 310, "total_steps": 4440, "loss": 0.3804, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.947079610481069e-05, "epoch": 0.3490990990990991, "percentage": 6.98, "elapsed_time": "0:03:28", "remaining_time": "0:46:20"}
+{"current_steps": 320, "total_steps": 4440, "loss": 0.4183, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.943381078271214e-05, "epoch": 0.36036036036036034, "percentage": 7.21, "elapsed_time": "0:03:34", "remaining_time": "0:46:05"}
+{"current_steps": 330, "total_steps": 4440, "loss": 0.4299, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.939559109281192e-05, "epoch": 0.3716216216216216, "percentage": 7.43, "elapsed_time": "0:03:40", "remaining_time": "0:45:41"}
+{"current_steps": 340, "total_steps": 4440, "loss": 0.4385, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.935613896592446e-05, "epoch": 0.38288288288288286, "percentage": 7.66, "elapsed_time": "0:03:45", "remaining_time": "0:45:19"}
+{"current_steps": 350, "total_steps": 4440, "loss": 0.4223, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.931545639512547e-05, "epoch": 0.39414414414414417, "percentage": 7.88, "elapsed_time": "0:03:52", "remaining_time": "0:45:17"}
+{"current_steps": 360, "total_steps": 4440, "loss": 0.4305, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.92735454356513e-05, "epoch": 0.40540540540540543, "percentage": 8.11, "elapsed_time": "0:03:58", "remaining_time": "0:45:07"}
+{"current_steps": 370, "total_steps": 4440, "loss": 0.4059, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9230408204795034e-05, "epoch": 0.4166666666666667, "percentage": 8.33, "elapsed_time": "0:04:04", "remaining_time": "0:44:52"}
+{"current_steps": 380, "total_steps": 4440, "loss": 0.4161, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.918604688179958e-05, "epoch": 0.42792792792792794, "percentage": 8.56, "elapsed_time": "0:04:11", "remaining_time": "0:44:45"}
+{"current_steps": 390, "total_steps": 4440, "loss": 0.4544, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.914046370774756e-05, "epoch": 0.4391891891891892, "percentage": 8.78, "elapsed_time": "0:04:17", "remaining_time": "0:44:30"}
+{"current_steps": 400, "total_steps": 4440, "loss": 0.3662, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9093660985448097e-05, "epoch": 0.45045045045045046, "percentage": 9.01, "elapsed_time": "0:04:23", "remaining_time": "0:44:21"}
+{"current_steps": 400, "total_steps": 4440, "loss": null, "eval_loss": 0.38735634088516235, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.45045045045045046, "percentage": 9.01, "elapsed_time": "0:04:23", "remaining_time": "0:44:21"}
+{"current_steps": 410, "total_steps": 4440, "loss": 0.4029, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9045641079320484e-05, "epoch": 0.4617117117117117, "percentage": 9.23, "elapsed_time": "0:04:38", "remaining_time": "0:45:34"}
+{"current_steps": 420, "total_steps": 4440, "loss": 0.38, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.89964064152747e-05, "epoch": 0.47297297297297297, "percentage": 9.46, "elapsed_time": "0:04:43", "remaining_time": "0:45:15"}
+{"current_steps": 430, "total_steps": 4440, "loss": 0.3566, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.894595948058893e-05, "epoch": 0.48423423423423423, "percentage": 9.68, "elapsed_time": "0:04:49", "remaining_time": "0:44:59"}
+{"current_steps": 440, "total_steps": 4440, "loss": 0.3881, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.889430282378385e-05, "epoch": 0.4954954954954955, "percentage": 9.91, "elapsed_time": "0:04:55", "remaining_time": "0:44:48"}
+{"current_steps": 450, "total_steps": 4440, "loss": 0.4058, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.884143905449387e-05, "epoch": 0.5067567567567568, "percentage": 10.14, "elapsed_time": "0:05:01", "remaining_time": "0:44:35"}
+{"current_steps": 460, "total_steps": 4440, "loss": 0.4095, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8787370843335355e-05, "epoch": 0.5180180180180181, "percentage": 10.36, "elapsed_time": "0:05:07", "remaining_time": "0:44:23"}
+{"current_steps": 470, "total_steps": 4440, "loss": 0.4363, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.873210092177167e-05, "epoch": 0.5292792792792793, "percentage": 10.59, "elapsed_time": "0:05:14", "remaining_time": "0:44:13"}
+{"current_steps": 480, "total_steps": 4440, "loss": 0.371, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.86756320819752e-05, "epoch": 0.5405405405405406, "percentage": 10.81, "elapsed_time": "0:05:20", "remaining_time": "0:44:02"}
+{"current_steps": 490, "total_steps": 4440, "loss": 0.4014, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8617967176686266e-05, "epoch": 0.5518018018018018, "percentage": 11.04, "elapsed_time": "0:05:26", "remaining_time": "0:43:52"}
+{"current_steps": 500, "total_steps": 4440, "loss": 0.363, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.855910911906906e-05, "epoch": 0.5630630630630631, "percentage": 11.26, "elapsed_time": "0:05:32", "remaining_time": "0:43:38"}
+{"current_steps": 500, "total_steps": 4440, "loss": null, "eval_loss": 0.378948450088501, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.5630630630630631, "percentage": 11.26, "elapsed_time": "0:05:32", "remaining_time": "0:43:38"}
+{"current_steps": 510, "total_steps": 4440, "loss": 0.3872, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.849906088256443e-05, "epoch": 0.5743243243243243, "percentage": 11.49, "elapsed_time": "0:05:47", "remaining_time": "0:44:34"}
+{"current_steps": 520, "total_steps": 4440, "loss": 0.4229, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8437825500739696e-05, "epoch": 0.5855855855855856, "percentage": 11.71, "elapsed_time": "0:05:53", "remaining_time": "0:44:21"}
+{"current_steps": 530, "total_steps": 4440, "loss": 0.4228, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.837540606713538e-05, "epoch": 0.5968468468468469, "percentage": 11.94, "elapsed_time": "0:05:58", "remaining_time": "0:44:06"}
+{"current_steps": 540, "total_steps": 4440, "loss": 0.3683, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8311805735108894e-05, "epoch": 0.6081081081081081, "percentage": 12.16, "elapsed_time": "0:06:04", "remaining_time": "0:43:55"}
+{"current_steps": 550, "total_steps": 4440, "loss": 0.4516, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.824702771767533e-05, "epoch": 0.6193693693693694, "percentage": 12.39, "elapsed_time": "0:06:11", "remaining_time": "0:43:46"}
+{"current_steps": 560, "total_steps": 4440, "loss": 0.3849, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.818107528734504e-05, "epoch": 0.6306306306306306, "percentage": 12.61, "elapsed_time": "0:06:17", "remaining_time": "0:43:34"}
+{"current_steps": 570, "total_steps": 4440, "loss": 0.4075, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.811395177595836e-05, "epoch": 0.6418918918918919, "percentage": 12.84, "elapsed_time": "0:06:23", "remaining_time": "0:43:24"}
+{"current_steps": 580, "total_steps": 4440, "loss": 0.3984, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.804566057451729e-05, "epoch": 0.6531531531531531, "percentage": 13.06, "elapsed_time": "0:06:29", "remaining_time": "0:43:12"}
+{"current_steps": 590, "total_steps": 4440, "loss": 0.3875, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.797620513301418e-05, "epoch": 0.6644144144144144, "percentage": 13.29, "elapsed_time": "0:06:35", "remaining_time": "0:43:00"}
+{"current_steps": 600, "total_steps": 4440, "loss": 0.3912, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.790558896025743e-05, "epoch": 0.6756756756756757, "percentage": 13.51, "elapsed_time": "0:06:41", "remaining_time": "0:42:48"}
+{"current_steps": 600, "total_steps": 4440, "loss": null, "eval_loss": 0.37321507930755615, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.6756756756756757, "percentage": 13.51, "elapsed_time": "0:06:41", "remaining_time": "0:42:48"}
+{"current_steps": 610, "total_steps": 4440, "loss": 0.3794, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7833815623694256e-05, "epoch": 0.6869369369369369, "percentage": 13.74, "elapsed_time": "0:06:55", "remaining_time": "0:43:31"}
+{"current_steps": 620, "total_steps": 4440, "loss": 0.3995, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7760888749230416e-05, "epoch": 0.6981981981981982, "percentage": 13.96, "elapsed_time": "0:07:01", "remaining_time": "0:43:18"}
+{"current_steps": 630, "total_steps": 4440, "loss": 0.3974, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7686812021047087e-05, "epoch": 0.7094594594594594, "percentage": 14.19, "elapsed_time": "0:07:07", "remaining_time": "0:43:05"}
+{"current_steps": 640, "total_steps": 4440, "loss": 0.3982, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.761158918141474e-05, "epoch": 0.7207207207207207, "percentage": 14.41, "elapsed_time": "0:07:13", "remaining_time": "0:42:53"}
+{"current_steps": 650, "total_steps": 4440, "loss": 0.4243, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.753522403050403e-05, "epoch": 0.7319819819819819, "percentage": 14.64, "elapsed_time": "0:07:18", "remaining_time": "0:42:39"}
+{"current_steps": 660, "total_steps": 4440, "loss": 0.4118, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.745772042619388e-05, "epoch": 0.7432432432432432, "percentage": 14.86, "elapsed_time": "0:07:24", "remaining_time": "0:42:27"}
+{"current_steps": 670, "total_steps": 4440, "loss": 0.3857, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7379082283876566e-05, "epoch": 0.7545045045045045, "percentage": 15.09, "elapsed_time": "0:07:30", "remaining_time": "0:42:13"}
+{"current_steps": 680, "total_steps": 4440, "loss": 0.4273, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7299313576259864e-05, "epoch": 0.7657657657657657, "percentage": 15.32, "elapsed_time": "0:07:36", "remaining_time": "0:42:02"}
+{"current_steps": 690, "total_steps": 4440, "loss": 0.4107, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7218418333166455e-05, "epoch": 0.777027027027027, "percentage": 15.54, "elapsed_time": "0:07:41", "remaining_time": "0:41:50"}
+{"current_steps": 700, "total_steps": 4440, "loss": 0.3738, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.713640064133025e-05, "epoch": 0.7882882882882883, "percentage": 15.77, "elapsed_time": "0:07:47", "remaining_time": "0:41:39"}
+{"current_steps": 700, "total_steps": 4440, "loss": null, "eval_loss": 0.3662475049495697, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.7882882882882883, "percentage": 15.77, "elapsed_time": "0:07:47", "remaining_time": "0:41:39"}
+{"current_steps": 710, "total_steps": 4440, "loss": 0.4, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.705326464418999e-05, "epoch": 0.7995495495495496, "percentage": 15.99, "elapsed_time": "0:08:02", "remaining_time": "0:42:14"}
+{"current_steps": 720, "total_steps": 4440, "loss": 0.4041, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.696901454167988e-05, "epoch": 0.8108108108108109, "percentage": 16.22, "elapsed_time": "0:08:08", "remaining_time": "0:42:04"}
+{"current_steps": 730, "total_steps": 4440, "loss": 0.4202, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.688365459001747e-05, "epoch": 0.8220720720720721, "percentage": 16.44, "elapsed_time": "0:08:14", "remaining_time": "0:41:53"}
+{"current_steps": 740, "total_steps": 4440, "loss": 0.4156, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6797189101488584e-05, "epoch": 0.8333333333333334, "percentage": 16.67, "elapsed_time": "0:08:20", "remaining_time": "0:41:42"}
+{"current_steps": 750, "total_steps": 4440, "loss": 0.3884, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.670962244422946e-05, "epoch": 0.8445945945945946, "percentage": 16.89, "elapsed_time": "0:08:26", "remaining_time": "0:41:32"}
+{"current_steps": 760, "total_steps": 4440, "loss": 0.3989, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6620959042006174e-05, "epoch": 0.8558558558558559, "percentage": 17.12, "elapsed_time": "0:08:32", "remaining_time": "0:41:21"}
+{"current_steps": 770, "total_steps": 4440, "loss": 0.4036, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6531203373991014e-05, "epoch": 0.8671171171171171, "percentage": 17.34, "elapsed_time": "0:08:38", "remaining_time": "0:41:09"}
+{"current_steps": 780, "total_steps": 4440, "loss": 0.3985, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6440359974536306e-05, "epoch": 0.8783783783783784, "percentage": 17.57, "elapsed_time": "0:08:43", "remaining_time": "0:40:58"}
+{"current_steps": 790, "total_steps": 4440, "loss": 0.38, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.634843343294531e-05, "epoch": 0.8896396396396397, "percentage": 17.79, "elapsed_time": "0:08:50", "remaining_time": "0:40:51"}
+{"current_steps": 800, "total_steps": 4440, "loss": 0.3729, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.625542839324036e-05, "epoch": 0.9009009009009009, "percentage": 18.02, "elapsed_time": "0:08:56", "remaining_time": "0:40:42"}
+{"current_steps": 800, "total_steps": 4440, "loss": null, "eval_loss": 0.3623661696910858, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9009009009009009, "percentage": 18.02, "elapsed_time": "0:08:56", "remaining_time": "0:40:42"}
+{"current_steps": 810, "total_steps": 4440, "loss": 0.3577, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.616134955392826e-05, "epoch": 0.9121621621621622, "percentage": 18.24, "elapsed_time": "0:09:11", "remaining_time": "0:41:10"}
+{"current_steps": 820, "total_steps": 4440, "loss": 0.3393, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.606620166776294e-05, "epoch": 0.9234234234234234, "percentage": 18.47, "elapsed_time": "0:09:16", "remaining_time": "0:40:58"}
+{"current_steps": 830, "total_steps": 4440, "loss": 0.3964, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.596998954150534e-05, "epoch": 0.9346846846846847, "percentage": 18.69, "elapsed_time": "0:09:22", "remaining_time": "0:40:48"}
+{"current_steps": 840, "total_steps": 4440, "loss": 0.3988, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.587271803568056e-05, "epoch": 0.9459459459459459, "percentage": 18.92, "elapsed_time": "0:09:29", "remaining_time": "0:40:39"}
+{"current_steps": 850, "total_steps": 4440, "loss": 0.359, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.577439206433233e-05, "epoch": 0.9572072072072072, "percentage": 19.14, "elapsed_time": "0:09:35", "remaining_time": "0:40:29"}
+{"current_steps": 860, "total_steps": 4440, "loss": 0.4198, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.567501659477477e-05, "epoch": 0.9684684684684685, "percentage": 19.37, "elapsed_time": "0:09:41", "remaining_time": "0:40:21"}
+{"current_steps": 870, "total_steps": 4440, "loss": 0.3708, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.557459664734141e-05, "epoch": 0.9797297297297297, "percentage": 19.59, "elapsed_time": "0:09:47", "remaining_time": "0:40:10"}
+{"current_steps": 880, "total_steps": 4440, "loss": 0.3956, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.547313729513163e-05, "epoch": 0.990990990990991, "percentage": 19.82, "elapsed_time": "0:09:53", "remaining_time": "0:40:00"}
+{"current_steps": 890, "total_steps": 4440, "loss": 0.3563, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.537064366375429e-05, "epoch": 1.0022522522522523, "percentage": 20.05, "elapsed_time": "0:09:59", "remaining_time": "0:39:49"}
+{"current_steps": 900, "total_steps": 4440, "loss": 0.3573, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5267120931068875e-05, "epoch": 1.0135135135135136, "percentage": 20.27, "elapsed_time": "0:10:05", "remaining_time": "0:39:41"}
+{"current_steps": 900, "total_steps": 4440, "loss": null, "eval_loss": 0.35875043272972107, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.0135135135135136, "percentage": 20.27, "elapsed_time": "0:10:05", "remaining_time": "0:39:41"}
+{"current_steps": 910, "total_steps": 4440, "loss": 0.3158, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5162574326923834e-05, "epoch": 1.0247747747747749, "percentage": 20.5, "elapsed_time": "0:10:20", "remaining_time": "0:40:06"}
+{"current_steps": 920, "total_steps": 4440, "loss": 0.3412, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.505700913289246e-05, "epoch": 1.0360360360360361, "percentage": 20.72, "elapsed_time": "0:10:26", "remaining_time": "0:39:56"}
+{"current_steps": 930, "total_steps": 4440, "loss": 0.3365, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4950430682006e-05, "epoch": 1.0472972972972974, "percentage": 20.95, "elapsed_time": "0:10:31", "remaining_time": "0:39:44"}
+{"current_steps": 940, "total_steps": 4440, "loss": 0.3537, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4842844358484236e-05, "epoch": 1.0585585585585586, "percentage": 21.17, "elapsed_time": "0:10:37", "remaining_time": "0:39:34"}
+{"current_steps": 950, "total_steps": 4440, "loss": 0.399, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.473425559746358e-05, "epoch": 1.0698198198198199, "percentage": 21.4, "elapsed_time": "0:10:43", "remaining_time": "0:39:25"}
+{"current_steps": 960, "total_steps": 4440, "loss": 0.3445, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.462466988472237e-05, "epoch": 1.0810810810810811, "percentage": 21.62, "elapsed_time": "0:10:49", "remaining_time": "0:39:15"}
+{"current_steps": 970, "total_steps": 4440, "loss": 0.4066, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.451409275640379e-05, "epoch": 1.0923423423423424, "percentage": 21.85, "elapsed_time": "0:10:55", "remaining_time": "0:39:05"}
+{"current_steps": 980, "total_steps": 4440, "loss": 0.3408, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.440252979873622e-05, "epoch": 1.1036036036036037, "percentage": 22.07, "elapsed_time": "0:11:01", "remaining_time": "0:38:55"}
+{"current_steps": 990, "total_steps": 4440, "loss": 0.3706, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.428998664775097e-05, "epoch": 1.114864864864865, "percentage": 22.3, "elapsed_time": "0:11:06", "remaining_time": "0:38:43"}
+{"current_steps": 1000, "total_steps": 4440, "loss": 0.3603, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4176468988997586e-05, "epoch": 1.1261261261261262, "percentage": 22.52, "elapsed_time": "0:11:12", "remaining_time": "0:38:34"}
+{"current_steps": 1000, "total_steps": 4440, "loss": null, "eval_loss": 0.3570348024368286, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.1261261261261262, "percentage": 22.52, "elapsed_time": "0:11:12", "remaining_time": "0:38:34"}
+{"current_steps": 1010, "total_steps": 4440, "loss": 0.3608, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.406198255725662e-05, "epoch": 1.1373873873873874, "percentage": 22.75, "elapsed_time": "0:11:27", "remaining_time": "0:38:54"}
+{"current_steps": 1020, "total_steps": 4440, "loss": 0.3329, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3946533136249926e-05, "epoch": 1.1486486486486487, "percentage": 22.97, "elapsed_time": "0:11:33", "remaining_time": "0:38:46"}
+{"current_steps": 1030, "total_steps": 4440, "loss": 0.3317, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.383012655834842e-05, "epoch": 1.15990990990991, "percentage": 23.2, "elapsed_time": "0:11:39", "remaining_time": "0:38:36"}
+{"current_steps": 1040, "total_steps": 4440, "loss": 0.3212, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.371276870427753e-05, "epoch": 1.1711711711711712, "percentage": 23.42, "elapsed_time": "0:11:46", "remaining_time": "0:38:28"}
+{"current_steps": 1050, "total_steps": 4440, "loss": 0.3012, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.359446550282001e-05, "epoch": 1.1824324324324325, "percentage": 23.65, "elapsed_time": "0:11:51", "remaining_time": "0:38:17"}
+{"current_steps": 1060, "total_steps": 4440, "loss": 0.3308, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.347522293051648e-05, "epoch": 1.1936936936936937, "percentage": 23.87, "elapsed_time": "0:11:57", "remaining_time": "0:38:06"}
+{"current_steps": 1070, "total_steps": 4440, "loss": 0.332, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.33550470113635e-05, "epoch": 1.204954954954955, "percentage": 24.1, "elapsed_time": "0:12:03", "remaining_time": "0:37:58"}
+{"current_steps": 1080, "total_steps": 4440, "loss": 0.3723, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3233943816509204e-05, "epoch": 1.2162162162162162, "percentage": 24.32, "elapsed_time": "0:12:09", "remaining_time": "0:37:49"}
+{"current_steps": 1090, "total_steps": 4440, "loss": 0.3577, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.311191946394665e-05, "epoch": 1.2274774774774775, "percentage": 24.55, "elapsed_time": "0:12:15", "remaining_time": "0:37:41"}
+{"current_steps": 1100, "total_steps": 4440, "loss": 0.3501, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2988980118204705e-05, "epoch": 1.2387387387387387, "percentage": 24.77, "elapsed_time": "0:12:21", "remaining_time": "0:37:32"}
+{"current_steps": 1100, "total_steps": 4440, "loss": null, "eval_loss": 0.3554933965206146, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.2387387387387387, "percentage": 24.77, "elapsed_time": "0:12:21", "remaining_time": "0:37:32"}
+{"current_steps": 1110, "total_steps": 4440, "loss": 0.3517, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2865131990036614e-05, "epoch": 1.25, "percentage": 25.0, "elapsed_time": "0:12:36", "remaining_time": "0:37:48"}
+{"current_steps": 1120, "total_steps": 4440, "loss": 0.3482, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.274038133610628e-05, "epoch": 1.2612612612612613, "percentage": 25.23, "elapsed_time": "0:12:42", "remaining_time": "0:37:40"}
+{"current_steps": 1130, "total_steps": 4440, "loss": 0.3224, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.261473445867215e-05, "epoch": 1.2725225225225225, "percentage": 25.45, "elapsed_time": "0:12:47", "remaining_time": "0:37:29"}
+{"current_steps": 1140, "total_steps": 4440, "loss": 0.3717, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.248819770526885e-05, "epoch": 1.2837837837837838, "percentage": 25.68, "elapsed_time": "0:12:53", "remaining_time": "0:37:20"}
+{"current_steps": 1150, "total_steps": 4440, "loss": 0.338, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.236077746838649e-05, "epoch": 1.295045045045045, "percentage": 25.9, "elapsed_time": "0:12:59", "remaining_time": "0:37:09"}
+{"current_steps": 1160, "total_steps": 4440, "loss": 0.3637, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.223248018514777e-05, "epoch": 1.3063063063063063, "percentage": 26.13, "elapsed_time": "0:13:05", "remaining_time": "0:37:01"}
+{"current_steps": 1170, "total_steps": 4440, "loss": 0.3865, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2103312336982734e-05, "epoch": 1.3175675675675675, "percentage": 26.35, "elapsed_time": "0:13:11", "remaining_time": "0:36:53"}
+{"current_steps": 1180, "total_steps": 4440, "loss": 0.3802, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.197328044930137e-05, "epoch": 1.3288288288288288, "percentage": 26.58, "elapsed_time": "0:13:18", "remaining_time": "0:36:45"}
+{"current_steps": 1190, "total_steps": 4440, "loss": 0.3778, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.184239109116393e-05, "epoch": 1.34009009009009, "percentage": 26.8, "elapsed_time": "0:13:24", "remaining_time": "0:36:35"}
+{"current_steps": 1200, "total_steps": 4440, "loss": 0.3335, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.171065087494909e-05, "epoch": 1.3513513513513513, "percentage": 27.03, "elapsed_time": "0:13:30", "remaining_time": "0:36:27"}
+{"current_steps": 1200, "total_steps": 4440, "loss": null, "eval_loss": 0.3528105914592743, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.3513513513513513, "percentage": 27.03, "elapsed_time": "0:13:30", "remaining_time": "0:36:27"}
+{"current_steps": 1210, "total_steps": 4440, "loss": 0.3463, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.157806645601988e-05, "epoch": 1.3626126126126126, "percentage": 27.25, "elapsed_time": "0:13:44", "remaining_time": "0:36:41"}
+{"current_steps": 1220, "total_steps": 4440, "loss": 0.3516, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.144464453238748e-05, "epoch": 1.3738738738738738, "percentage": 27.48, "elapsed_time": "0:13:50", "remaining_time": "0:36:32"}
+{"current_steps": 1230, "total_steps": 4440, "loss": 0.3575, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.131039184437283e-05, "epoch": 1.385135135135135, "percentage": 27.7, "elapsed_time": "0:13:57", "remaining_time": "0:36:24"}
+{"current_steps": 1240, "total_steps": 4440, "loss": 0.3291, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.117531517426614e-05, "epoch": 1.3963963963963963, "percentage": 27.93, "elapsed_time": "0:14:02", "remaining_time": "0:36:15"}
+{"current_steps": 1250, "total_steps": 4440, "loss": 0.3402, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.103942134598422e-05, "epoch": 1.4076576576576576, "percentage": 28.15, "elapsed_time": "0:14:09", "remaining_time": "0:36:07"}
+{"current_steps": 1260, "total_steps": 4440, "loss": 0.3137, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0902717224725766e-05, "epoch": 1.4189189189189189, "percentage": 28.38, "elapsed_time": "0:14:15", "remaining_time": "0:35:58"}
+{"current_steps": 1270, "total_steps": 4440, "loss": 0.3348, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.076520971662455e-05, "epoch": 1.4301801801801801, "percentage": 28.6, "elapsed_time": "0:14:21", "remaining_time": "0:35:49"}
+{"current_steps": 1280, "total_steps": 4440, "loss": 0.3248, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0626905768400516e-05, "epoch": 1.4414414414414414, "percentage": 28.83, "elapsed_time": "0:14:27", "remaining_time": "0:35:41"}
+{"current_steps": 1290, "total_steps": 4440, "loss": 0.3523, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0487812367008814e-05, "epoch": 1.4527027027027026, "percentage": 29.05, "elapsed_time": "0:14:33", "remaining_time": "0:35:32"}
+{"current_steps": 1300, "total_steps": 4440, "loss": 0.3372, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0347936539286876e-05, "epoch": 1.4639639639639639, "percentage": 29.28, "elapsed_time": "0:14:39", "remaining_time": "0:35:24"}
+{"current_steps": 1300, "total_steps": 4440, "loss": null, "eval_loss": 0.3515435755252838, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.4639639639639639, "percentage": 29.28, "elapsed_time": "0:14:39", "remaining_time": "0:35:24"}
+{"current_steps": 1310, "total_steps": 4440, "loss": 0.353, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.020728535159942e-05, "epoch": 1.4752252252252251, "percentage": 29.5, "elapsed_time": "0:14:54", "remaining_time": "0:35:36"}
+{"current_steps": 1320, "total_steps": 4440, "loss": 0.3395, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0065865909481417e-05, "epoch": 1.4864864864864864, "percentage": 29.73, "elapsed_time": "0:15:00", "remaining_time": "0:35:27"}
+{"current_steps": 1330, "total_steps": 4440, "loss": 0.347, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.9923685357279166e-05, "epoch": 1.4977477477477477, "percentage": 29.95, "elapsed_time": "0:15:06", "remaining_time": "0:35:19"}
+{"current_steps": 1340, "total_steps": 4440, "loss": 0.3372, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.97807508777894e-05, "epoch": 1.509009009009009, "percentage": 30.18, "elapsed_time": "0:15:12", "remaining_time": "0:35:10"}
+{"current_steps": 1350, "total_steps": 4440, "loss": 0.3327, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.963706969189633e-05, "epoch": 1.5202702702702702, "percentage": 30.41, "elapsed_time": "0:15:17", "remaining_time": "0:35:00"}
+{"current_steps": 1360, "total_steps": 4440, "loss": 0.359, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.949264905820697e-05, "epoch": 1.5315315315315314, "percentage": 30.63, "elapsed_time": "0:15:23", "remaining_time": "0:34:51"}
+{"current_steps": 1370, "total_steps": 4440, "loss": 0.3083, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.9347496272684325e-05, "epoch": 1.5427927927927927, "percentage": 30.86, "elapsed_time": "0:15:29", "remaining_time": "0:34:42"}
+{"current_steps": 1380, "total_steps": 4440, "loss": 0.3241, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.920161866827889e-05, "epoch": 1.554054054054054, "percentage": 31.08, "elapsed_time": "0:15:34", "remaining_time": "0:34:33"}
+{"current_steps": 1390, "total_steps": 4440, "loss": 0.3517, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.905502361455818e-05, "epoch": 1.5653153153153152, "percentage": 31.31, "elapsed_time": "0:15:41", "remaining_time": "0:34:25"}
+{"current_steps": 1400, "total_steps": 4440, "loss": 0.3565, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.89077185173344e-05, "epoch": 1.5765765765765765, "percentage": 31.53, "elapsed_time": "0:15:47", "remaining_time": "0:34:16"}
+{"current_steps": 1400, "total_steps": 4440, "loss": null, "eval_loss": 0.3501906991004944, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.5765765765765765, "percentage": 31.53, "elapsed_time": "0:15:47", "remaining_time": "0:34:16"}
+{"current_steps": 1410, "total_steps": 4440, "loss": 0.3359, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.875971081829033e-05, "epoch": 1.5878378378378377, "percentage": 31.76, "elapsed_time": "0:16:01", "remaining_time": "0:34:27"}
+{"current_steps": 1420, "total_steps": 4440, "loss": 0.3624, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.8611007994603365e-05, "epoch": 1.599099099099099, "percentage": 31.98, "elapsed_time": "0:16:07", "remaining_time": "0:34:17"}
+{"current_steps": 1430, "total_steps": 4440, "loss": 0.3489, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.8461617558567845e-05, "epoch": 1.6103603603603602, "percentage": 32.21, "elapsed_time": "0:16:13", "remaining_time": "0:34:09"}
+{"current_steps": 1440, "total_steps": 4440, "loss": 0.3306, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.831154705721541e-05, "epoch": 1.6216216216216215, "percentage": 32.43, "elapsed_time": "0:16:19", "remaining_time": "0:34:00"}
+{"current_steps": 1450, "total_steps": 4440, "loss": 0.3325, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.81608040719339e-05, "epoch": 1.6328828828828827, "percentage": 32.66, "elapsed_time": "0:16:25", "remaining_time": "0:33:51"}
+{"current_steps": 1460, "total_steps": 4440, "loss": 0.3224, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.8009396218084195e-05, "epoch": 1.644144144144144, "percentage": 32.88, "elapsed_time": "0:16:30", "remaining_time": "0:33:42"}
+{"current_steps": 1470, "total_steps": 4440, "loss": 0.3319, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7857331144615574e-05, "epoch": 1.6554054054054053, "percentage": 33.11, "elapsed_time": "0:16:36", "remaining_time": "0:33:34"}
+{"current_steps": 1480, "total_steps": 4440, "loss": 0.3333, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.770461653367934e-05, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:16:42", "remaining_time": "0:33:25"}
+{"current_steps": 1490, "total_steps": 4440, "loss": 0.37, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.75512601002406e-05, "epoch": 1.6779279279279278, "percentage": 33.56, "elapsed_time": "0:16:48", "remaining_time": "0:33:16"}
+{"current_steps": 1500, "total_steps": 4440, "loss": 0.3313, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.739726959168867e-05, "epoch": 1.689189189189189, "percentage": 33.78, "elapsed_time": "0:16:54", "remaining_time": "0:33:08"}
+{"current_steps": 1500, "total_steps": 4440, "loss": null, "eval_loss": 0.34918585419654846, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.689189189189189, "percentage": 33.78, "elapsed_time": "0:16:54", "remaining_time": "0:33:08"}
+{"current_steps": 1510, "total_steps": 4440, "loss": 0.3388, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7242652787445525e-05, "epoch": 1.7004504504504503, "percentage": 34.01, "elapsed_time": "0:17:08", "remaining_time": "0:33:16"}
+{"current_steps": 1520, "total_steps": 4440, "loss": 0.3719, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7087417498572944e-05, "epoch": 1.7117117117117115, "percentage": 34.23, "elapsed_time": "0:17:14", "remaining_time": "0:33:07"}
+{"current_steps": 1530, "total_steps": 4440, "loss": 0.3593, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.693157156737778e-05, "epoch": 1.722972972972973, "percentage": 34.46, "elapsed_time": "0:17:21", "remaining_time": "0:33:00"}
+{"current_steps": 1540, "total_steps": 4440, "loss": 0.3202, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.677512286701587e-05, "epoch": 1.7342342342342343, "percentage": 34.68, "elapsed_time": "0:17:27", "remaining_time": "0:32:52"}
+{"current_steps": 1550, "total_steps": 4440, "loss": 0.34, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6618079301094216e-05, "epoch": 1.7454954954954955, "percentage": 34.91, "elapsed_time": "0:17:33", "remaining_time": "0:32:43"}
+{"current_steps": 1560, "total_steps": 4440, "loss": 0.3455, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6460448803271754e-05, "epoch": 1.7567567567567568, "percentage": 35.14, "elapsed_time": "0:17:39", "remaining_time": "0:32:36"}
+{"current_steps": 1570, "total_steps": 4440, "loss": 0.3415, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6302239336858545e-05, "epoch": 1.768018018018018, "percentage": 35.36, "elapsed_time": "0:17:45", "remaining_time": "0:32:27"}
+{"current_steps": 1580, "total_steps": 4440, "loss": 0.3442, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6143458894413465e-05, "epoch": 1.7792792792792793, "percentage": 35.59, "elapsed_time": "0:17:51", "remaining_time": "0:32:19"}
+{"current_steps": 1590, "total_steps": 4440, "loss": 0.3357, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.598411549734042e-05, "epoch": 1.7905405405405406, "percentage": 35.81, "elapsed_time": "0:17:57", "remaining_time": "0:32:10"}
+{"current_steps": 1600, "total_steps": 4440, "loss": 0.3653, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.582421719548318e-05, "epoch": 1.8018018018018018, "percentage": 36.04, "elapsed_time": "0:18:02", "remaining_time": "0:32:02"}
+{"current_steps": 1600, "total_steps": 4440, "loss": null, "eval_loss": 0.3447774648666382, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.8018018018018018, "percentage": 36.04, "elapsed_time": "0:18:02", "remaining_time": "0:32:02"}
+{"current_steps": 1610, "total_steps": 4440, "loss": 0.3736, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.56637720667186e-05, "epoch": 1.813063063063063, "percentage": 36.26, "elapsed_time": "0:18:17", "remaining_time": "0:32:08"}
+{"current_steps": 1620, "total_steps": 4440, "loss": 0.3275, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.550278821654866e-05, "epoch": 1.8243243243243243, "percentage": 36.49, "elapsed_time": "0:18:23", "remaining_time": "0:32:00"}
+{"current_steps": 1630, "total_steps": 4440, "loss": 0.3611, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5341273777690865e-05, "epoch": 1.8355855855855856, "percentage": 36.71, "elapsed_time": "0:18:29", "remaining_time": "0:31:53"}
+{"current_steps": 1640, "total_steps": 4440, "loss": 0.3252, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5179236909667465e-05, "epoch": 1.8468468468468469, "percentage": 36.94, "elapsed_time": "0:18:36", "remaining_time": "0:31:45"}
+{"current_steps": 1650, "total_steps": 4440, "loss": 0.3394, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5016685798393244e-05, "epoch": 1.8581081081081081, "percentage": 37.16, "elapsed_time": "0:18:42", "remaining_time": "0:31:37"}
+{"current_steps": 1660, "total_steps": 4440, "loss": 0.3233, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.485362865576194e-05, "epoch": 1.8693693693693694, "percentage": 37.39, "elapsed_time": "0:18:48", "remaining_time": "0:31:29"}
+{"current_steps": 1670, "total_steps": 4440, "loss": 0.382, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.4690073719231425e-05, "epoch": 1.8806306306306306, "percentage": 37.61, "elapsed_time": "0:18:54", "remaining_time": "0:31:22"}
+{"current_steps": 1680, "total_steps": 4440, "loss": 0.3762, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.452602925140751e-05, "epoch": 1.8918918918918919, "percentage": 37.84, "elapsed_time": "0:19:00", "remaining_time": "0:31:14"}
+{"current_steps": 1690, "total_steps": 4440, "loss": 0.3233, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.436150353962659e-05, "epoch": 1.9031531531531531, "percentage": 38.06, "elapsed_time": "0:19:06", "remaining_time": "0:31:06"}
+{"current_steps": 1700, "total_steps": 4440, "loss": 0.3412, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.419650489553695e-05, "epoch": 1.9144144144144144, "percentage": 38.29, "elapsed_time": "0:19:13", "remaining_time": "0:30:58"}
+{"current_steps": 1700, "total_steps": 4440, "loss": null, "eval_loss": 0.3434712886810303, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.9144144144144144, "percentage": 38.29, "elapsed_time": "0:19:13", "remaining_time": "0:30:58"}
+{"current_steps": 1710, "total_steps": 4440, "loss": 0.36, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.403104165467883e-05, "epoch": 1.9256756756756757, "percentage": 38.51, "elapsed_time": "0:19:27", "remaining_time": "0:31:03"}
+{"current_steps": 1720, "total_steps": 4440, "loss": 0.3209, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.386512217606339e-05, "epoch": 1.936936936936937, "percentage": 38.74, "elapsed_time": "0:19:32", "remaining_time": "0:30:54"}
+{"current_steps": 1730, "total_steps": 4440, "loss": 0.35, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.36987548417504e-05, "epoch": 1.9481981981981982, "percentage": 38.96, "elapsed_time": "0:19:39", "remaining_time": "0:30:46"}
+{"current_steps": 1740, "total_steps": 4440, "loss": 0.3442, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.353194805642477e-05, "epoch": 1.9594594594594594, "percentage": 39.19, "elapsed_time": "0:19:45", "remaining_time": "0:30:39"}
+{"current_steps": 1750, "total_steps": 4440, "loss": 0.3479, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3364710246971934e-05, "epoch": 1.9707207207207207, "percentage": 39.41, "elapsed_time": "0:19:51", "remaining_time": "0:30:30"}
+{"current_steps": 1760, "total_steps": 4440, "loss": 0.3507, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.319704986205223e-05, "epoch": 1.981981981981982, "percentage": 39.64, "elapsed_time": "0:19:57", "remaining_time": "0:30:22"}
+{"current_steps": 1770, "total_steps": 4440, "loss": 0.322, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.302897537167397e-05, "epoch": 1.9932432432432432, "percentage": 39.86, "elapsed_time": "0:20:02", "remaining_time": "0:30:14"}
+{"current_steps": 1780, "total_steps": 4440, "loss": 0.2991, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.28604952667656e-05, "epoch": 2.0045045045045047, "percentage": 40.09, "elapsed_time": "0:20:09", "remaining_time": "0:30:06"}
+{"current_steps": 1790, "total_steps": 4440, "loss": 0.285, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2691618058746756e-05, "epoch": 2.015765765765766, "percentage": 40.32, "elapsed_time": "0:20:14", "remaining_time": "0:29:58"}
+{"current_steps": 1800, "total_steps": 4440, "loss": 0.2738, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.252235227909826e-05, "epoch": 2.027027027027027, "percentage": 40.54, "elapsed_time": "0:20:20", "remaining_time": "0:29:49"}
+{"current_steps": 1800, "total_steps": 4440, "loss": null, "eval_loss": 0.34939834475517273, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.027027027027027, "percentage": 40.54, "elapsed_time": "0:20:20", "remaining_time": "0:29:49"}
+{"current_steps": 1810, "total_steps": 4440, "loss": 0.3052, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2352706478931106e-05, "epoch": 2.0382882882882885, "percentage": 40.77, "elapsed_time": "0:20:34", "remaining_time": "0:29:53"}
+{"current_steps": 1820, "total_steps": 4440, "loss": 0.291, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2182689228554517e-05, "epoch": 2.0495495495495497, "percentage": 40.99, "elapsed_time": "0:20:39", "remaining_time": "0:29:45"}
+{"current_steps": 1830, "total_steps": 4440, "loss": 0.2901, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.201230911704292e-05, "epoch": 2.060810810810811, "percentage": 41.22, "elapsed_time": "0:20:46", "remaining_time": "0:29:37"}
+{"current_steps": 1840, "total_steps": 4440, "loss": 0.296, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1841574751802076e-05, "epoch": 2.0720720720720722, "percentage": 41.44, "elapsed_time": "0:20:52", "remaining_time": "0:29:29"}
+{"current_steps": 1850, "total_steps": 4440, "loss": 0.3048, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1670494758134235e-05, "epoch": 2.0833333333333335, "percentage": 41.67, "elapsed_time": "0:20:59", "remaining_time": "0:29:22"}
+{"current_steps": 1860, "total_steps": 4440, "loss": 0.3232, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1499077778802385e-05, "epoch": 2.0945945945945947, "percentage": 41.89, "elapsed_time": "0:21:05", "remaining_time": "0:29:15"}
+{"current_steps": 1870, "total_steps": 4440, "loss": 0.2836, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.132733247359366e-05, "epoch": 2.105855855855856, "percentage": 42.12, "elapsed_time": "0:21:11", "remaining_time": "0:29:07"}
+{"current_steps": 1880, "total_steps": 4440, "loss": 0.288, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.115526751888181e-05, "epoch": 2.1171171171171173, "percentage": 42.34, "elapsed_time": "0:21:17", "remaining_time": "0:28:59"}
+{"current_steps": 1890, "total_steps": 4440, "loss": 0.3112, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.098289160718895e-05, "epoch": 2.1283783783783785, "percentage": 42.57, "elapsed_time": "0:21:24", "remaining_time": "0:28:52"}
+{"current_steps": 1900, "total_steps": 4440, "loss": 0.3159, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.081021344674632e-05, "epoch": 2.1396396396396398, "percentage": 42.79, "elapsed_time": "0:21:30", "remaining_time": "0:28:44"}
+{"current_steps": 1900, "total_steps": 4440, "loss": null, "eval_loss": 0.3487659990787506, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.1396396396396398, "percentage": 42.79, "elapsed_time": "0:21:30", "remaining_time": "0:28:44"}
+{"current_steps": 1910, "total_steps": 4440, "loss": 0.2923, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.063724176105447e-05, "epoch": 2.150900900900901, "percentage": 43.02, "elapsed_time": "0:21:44", "remaining_time": "0:28:48"}
+{"current_steps": 1920, "total_steps": 4440, "loss": 0.2931, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0463985288442475e-05, "epoch": 2.1621621621621623, "percentage": 43.24, "elapsed_time": "0:21:50", "remaining_time": "0:28:40"}
+{"current_steps": 1930, "total_steps": 4440, "loss": 0.2884, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0290452781626526e-05, "epoch": 2.1734234234234235, "percentage": 43.47, "elapsed_time": "0:21:56", "remaining_time": "0:28:32"}
+{"current_steps": 1940, "total_steps": 4440, "loss": 0.3101, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0116653007267753e-05, "epoch": 2.184684684684685, "percentage": 43.69, "elapsed_time": "0:22:02", "remaining_time": "0:28:24"}
+{"current_steps": 1950, "total_steps": 4440, "loss": 0.2692, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9942594745529307e-05, "epoch": 2.195945945945946, "percentage": 43.92, "elapsed_time": "0:22:08", "remaining_time": "0:28:16"}
+{"current_steps": 1960, "total_steps": 4440, "loss": 0.2642, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9768286789632844e-05, "epoch": 2.2072072072072073, "percentage": 44.14, "elapsed_time": "0:22:14", "remaining_time": "0:28:08"}
+{"current_steps": 1970, "total_steps": 4440, "loss": 0.3233, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9593737945414264e-05, "epoch": 2.2184684684684686, "percentage": 44.37, "elapsed_time": "0:22:20", "remaining_time": "0:28:00"}
+{"current_steps": 1980, "total_steps": 4440, "loss": 0.2886, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9418957030878874e-05, "epoch": 2.22972972972973, "percentage": 44.59, "elapsed_time": "0:22:26", "remaining_time": "0:27:53"}
+{"current_steps": 1990, "total_steps": 4440, "loss": 0.2879, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9243952875755904e-05, "epoch": 2.240990990990991, "percentage": 44.82, "elapsed_time": "0:22:32", "remaining_time": "0:27:44"}
+{"current_steps": 2000, "total_steps": 4440, "loss": 0.2892, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9068734321052444e-05, "epoch": 2.2522522522522523, "percentage": 45.05, "elapsed_time": "0:22:38", "remaining_time": "0:27:37"}
+{"current_steps": 2000, "total_steps": 4440, "loss": null, "eval_loss": 0.3520003855228424, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.2522522522522523, "percentage": 45.05, "elapsed_time": "0:22:38", "remaining_time": "0:27:37"}
+{"current_steps": 2000, "total_steps": 4440, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.2522522522522523, "percentage": 45.05, "elapsed_time": "0:22:38", "remaining_time": "0:27:37"}
+{"current_steps": 47, "total_steps": 47, "loss": null, "eval_loss": 0.3434712886810303, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.2522522522522523, "percentage": 100.0, "elapsed_time": "0:23:04", "remaining_time": "0:00:00"}
diff --git a/llama2_13b_peft/gsm8k/trainer_state.json b/llama2_13b_peft/gsm8k/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1ffb1a8d97e7e9c32e45deac7a34e4d698ccb690
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/trainer_state.json
@@ -0,0 +1,1590 @@
+{
+ "best_metric": 0.3434712886810303,
+ "best_model_checkpoint": "ckpt/llama2_13b_fuze27_no_sys/gsm8k_no_sys/checkpoint-1700",
+ "epoch": 2.2522522522522523,
+ "eval_steps": 100,
+ "global_step": 2000,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01126126126126126,
+ "grad_norm": 0.44569775462150574,
+ "learning_rate": 2.5e-05,
+ "loss": 1.1013,
+ "step": 10
+ },
+ {
+ "epoch": 0.02252252252252252,
+ "grad_norm": 0.4194127023220062,
+ "learning_rate": 5e-05,
+ "loss": 1.0292,
+ "step": 20
+ },
+ {
+ "epoch": 0.033783783783783786,
+ "grad_norm": 0.4140234589576721,
+ "learning_rate": 4.999936851448764e-05,
+ "loss": 0.8085,
+ "step": 30
+ },
+ {
+ "epoch": 0.04504504504504504,
+ "grad_norm": 0.38155531883239746,
+ "learning_rate": 4.999747408985249e-05,
+ "loss": 0.5884,
+ "step": 40
+ },
+ {
+ "epoch": 0.05630630630630631,
+ "grad_norm": 0.5921621918678284,
+ "learning_rate": 4.999431682179867e-05,
+ "loss": 0.4774,
+ "step": 50
+ },
+ {
+ "epoch": 0.06756756756756757,
+ "grad_norm": 0.5223663449287415,
+ "learning_rate": 4.9989896869827705e-05,
+ "loss": 0.5014,
+ "step": 60
+ },
+ {
+ "epoch": 0.07882882882882883,
+ "grad_norm": 0.4871968924999237,
+ "learning_rate": 4.998421445723046e-05,
+ "loss": 0.5193,
+ "step": 70
+ },
+ {
+ "epoch": 0.09009009009009009,
+ "grad_norm": 0.43759605288505554,
+ "learning_rate": 4.997726987107582e-05,
+ "loss": 0.4532,
+ "step": 80
+ },
+ {
+ "epoch": 0.10135135135135136,
+ "grad_norm": 0.42087432742118835,
+ "learning_rate": 4.996906346219623e-05,
+ "loss": 0.4591,
+ "step": 90
+ },
+ {
+ "epoch": 0.11261261261261261,
+ "grad_norm": 0.41199395060539246,
+ "learning_rate": 4.995959564516997e-05,
+ "loss": 0.4745,
+ "step": 100
+ },
+ {
+ "epoch": 0.11261261261261261,
+ "eval_loss": 0.4415845274925232,
+ "eval_runtime": 8.1488,
+ "eval_samples_per_second": 45.896,
+ "eval_steps_per_second": 5.768,
+ "step": 100
+ },
+ {
+ "epoch": 0.12387387387387387,
+ "grad_norm": 0.4192087650299072,
+ "learning_rate": 4.994886689830015e-05,
+ "loss": 0.4956,
+ "step": 110
+ },
+ {
+ "epoch": 0.13513513513513514,
+ "grad_norm": 0.40617257356643677,
+ "learning_rate": 4.9936877763590664e-05,
+ "loss": 0.4031,
+ "step": 120
+ },
+ {
+ "epoch": 0.1463963963963964,
+ "grad_norm": 0.40602198243141174,
+ "learning_rate": 4.9923628846718685e-05,
+ "loss": 0.4411,
+ "step": 130
+ },
+ {
+ "epoch": 0.15765765765765766,
+ "grad_norm": 0.39895886182785034,
+ "learning_rate": 4.990912081700413e-05,
+ "loss": 0.4396,
+ "step": 140
+ },
+ {
+ "epoch": 0.16891891891891891,
+ "grad_norm": 0.4391745328903198,
+ "learning_rate": 4.989335440737586e-05,
+ "loss": 0.4137,
+ "step": 150
+ },
+ {
+ "epoch": 0.18018018018018017,
+ "grad_norm": 0.40873247385025024,
+ "learning_rate": 4.9876330414334614e-05,
+ "loss": 0.436,
+ "step": 160
+ },
+ {
+ "epoch": 0.19144144144144143,
+ "grad_norm": 0.42072224617004395,
+ "learning_rate": 4.985804969791279e-05,
+ "loss": 0.4391,
+ "step": 170
+ },
+ {
+ "epoch": 0.20270270270270271,
+ "grad_norm": 0.3831063508987427,
+ "learning_rate": 4.983851318163097e-05,
+ "loss": 0.4504,
+ "step": 180
+ },
+ {
+ "epoch": 0.21396396396396397,
+ "grad_norm": 0.4725155234336853,
+ "learning_rate": 4.981772185245135e-05,
+ "loss": 0.437,
+ "step": 190
+ },
+ {
+ "epoch": 0.22522522522522523,
+ "grad_norm": 0.4084461033344269,
+ "learning_rate": 4.979567676072776e-05,
+ "loss": 0.4714,
+ "step": 200
+ },
+ {
+ "epoch": 0.22522522522522523,
+ "eval_loss": 0.410622775554657,
+ "eval_runtime": 8.1944,
+ "eval_samples_per_second": 45.641,
+ "eval_steps_per_second": 5.736,
+ "step": 200
+ },
+ {
+ "epoch": 0.23648648648648649,
+ "grad_norm": 0.46888473629951477,
+ "learning_rate": 4.977237902015269e-05,
+ "loss": 0.432,
+ "step": 210
+ },
+ {
+ "epoch": 0.24774774774774774,
+ "grad_norm": 0.5587989091873169,
+ "learning_rate": 4.9747829807701e-05,
+ "loss": 0.4514,
+ "step": 220
+ },
+ {
+ "epoch": 0.25900900900900903,
+ "grad_norm": 0.39721232652664185,
+ "learning_rate": 4.9722030363570425e-05,
+ "loss": 0.4396,
+ "step": 230
+ },
+ {
+ "epoch": 0.2702702702702703,
+ "grad_norm": 0.46742600202560425,
+ "learning_rate": 4.9694981991119004e-05,
+ "loss": 0.3982,
+ "step": 240
+ },
+ {
+ "epoch": 0.28153153153153154,
+ "grad_norm": 0.5924170017242432,
+ "learning_rate": 4.966668605679916e-05,
+ "loss": 0.46,
+ "step": 250
+ },
+ {
+ "epoch": 0.2927927927927928,
+ "grad_norm": 0.5489402413368225,
+ "learning_rate": 4.963714399008869e-05,
+ "loss": 0.4344,
+ "step": 260
+ },
+ {
+ "epoch": 0.30405405405405406,
+ "grad_norm": 0.3809150159358978,
+ "learning_rate": 4.9606357283418575e-05,
+ "loss": 0.4197,
+ "step": 270
+ },
+ {
+ "epoch": 0.3153153153153153,
+ "grad_norm": 0.4925936460494995,
+ "learning_rate": 4.957432749209755e-05,
+ "loss": 0.4109,
+ "step": 280
+ },
+ {
+ "epoch": 0.32657657657657657,
+ "grad_norm": 0.46872758865356445,
+ "learning_rate": 4.954105623423354e-05,
+ "loss": 0.3968,
+ "step": 290
+ },
+ {
+ "epoch": 0.33783783783783783,
+ "grad_norm": 0.5101854205131531,
+ "learning_rate": 4.950654519065195e-05,
+ "loss": 0.4732,
+ "step": 300
+ },
+ {
+ "epoch": 0.33783783783783783,
+ "eval_loss": 0.3975336253643036,
+ "eval_runtime": 8.211,
+ "eval_samples_per_second": 45.548,
+ "eval_steps_per_second": 5.724,
+ "step": 300
+ },
+ {
+ "epoch": 0.3490990990990991,
+ "grad_norm": 0.3665778934955597,
+ "learning_rate": 4.947079610481069e-05,
+ "loss": 0.3804,
+ "step": 310
+ },
+ {
+ "epoch": 0.36036036036036034,
+ "grad_norm": 0.5073620676994324,
+ "learning_rate": 4.943381078271214e-05,
+ "loss": 0.4183,
+ "step": 320
+ },
+ {
+ "epoch": 0.3716216216216216,
+ "grad_norm": 0.44081416726112366,
+ "learning_rate": 4.939559109281192e-05,
+ "loss": 0.4299,
+ "step": 330
+ },
+ {
+ "epoch": 0.38288288288288286,
+ "grad_norm": 0.4474439322948456,
+ "learning_rate": 4.935613896592446e-05,
+ "loss": 0.4385,
+ "step": 340
+ },
+ {
+ "epoch": 0.39414414414414417,
+ "grad_norm": 0.3917205035686493,
+ "learning_rate": 4.931545639512547e-05,
+ "loss": 0.4223,
+ "step": 350
+ },
+ {
+ "epoch": 0.40540540540540543,
+ "grad_norm": 0.5575543642044067,
+ "learning_rate": 4.92735454356513e-05,
+ "loss": 0.4305,
+ "step": 360
+ },
+ {
+ "epoch": 0.4166666666666667,
+ "grad_norm": 0.6872532367706299,
+ "learning_rate": 4.9230408204795034e-05,
+ "loss": 0.4059,
+ "step": 370
+ },
+ {
+ "epoch": 0.42792792792792794,
+ "grad_norm": 0.5098163485527039,
+ "learning_rate": 4.918604688179958e-05,
+ "loss": 0.4161,
+ "step": 380
+ },
+ {
+ "epoch": 0.4391891891891892,
+ "grad_norm": 0.489063560962677,
+ "learning_rate": 4.914046370774756e-05,
+ "loss": 0.4544,
+ "step": 390
+ },
+ {
+ "epoch": 0.45045045045045046,
+ "grad_norm": 0.370416522026062,
+ "learning_rate": 4.9093660985448097e-05,
+ "loss": 0.3662,
+ "step": 400
+ },
+ {
+ "epoch": 0.45045045045045046,
+ "eval_loss": 0.38735634088516235,
+ "eval_runtime": 8.1962,
+ "eval_samples_per_second": 45.631,
+ "eval_steps_per_second": 5.734,
+ "step": 400
+ },
+ {
+ "epoch": 0.4617117117117117,
+ "grad_norm": 0.6157602667808533,
+ "learning_rate": 4.9045641079320484e-05,
+ "loss": 0.4029,
+ "step": 410
+ },
+ {
+ "epoch": 0.47297297297297297,
+ "grad_norm": 0.5846096277236938,
+ "learning_rate": 4.89964064152747e-05,
+ "loss": 0.38,
+ "step": 420
+ },
+ {
+ "epoch": 0.48423423423423423,
+ "grad_norm": 0.7061562538146973,
+ "learning_rate": 4.894595948058893e-05,
+ "loss": 0.3566,
+ "step": 430
+ },
+ {
+ "epoch": 0.4954954954954955,
+ "grad_norm": 0.46312642097473145,
+ "learning_rate": 4.889430282378385e-05,
+ "loss": 0.3881,
+ "step": 440
+ },
+ {
+ "epoch": 0.5067567567567568,
+ "grad_norm": 0.5435507297515869,
+ "learning_rate": 4.884143905449387e-05,
+ "loss": 0.4058,
+ "step": 450
+ },
+ {
+ "epoch": 0.5180180180180181,
+ "grad_norm": 0.5244076251983643,
+ "learning_rate": 4.8787370843335355e-05,
+ "loss": 0.4095,
+ "step": 460
+ },
+ {
+ "epoch": 0.5292792792792793,
+ "grad_norm": 0.4451825022697449,
+ "learning_rate": 4.873210092177167e-05,
+ "loss": 0.4363,
+ "step": 470
+ },
+ {
+ "epoch": 0.5405405405405406,
+ "grad_norm": 0.4931471347808838,
+ "learning_rate": 4.86756320819752e-05,
+ "loss": 0.371,
+ "step": 480
+ },
+ {
+ "epoch": 0.5518018018018018,
+ "grad_norm": 0.5563647747039795,
+ "learning_rate": 4.8617967176686266e-05,
+ "loss": 0.4014,
+ "step": 490
+ },
+ {
+ "epoch": 0.5630630630630631,
+ "grad_norm": 0.69095379114151,
+ "learning_rate": 4.855910911906906e-05,
+ "loss": 0.363,
+ "step": 500
+ },
+ {
+ "epoch": 0.5630630630630631,
+ "eval_loss": 0.378948450088501,
+ "eval_runtime": 8.2022,
+ "eval_samples_per_second": 45.597,
+ "eval_steps_per_second": 5.73,
+ "step": 500
+ },
+ {
+ "epoch": 0.5743243243243243,
+ "grad_norm": 0.5200828313827515,
+ "learning_rate": 4.849906088256443e-05,
+ "loss": 0.3872,
+ "step": 510
+ },
+ {
+ "epoch": 0.5855855855855856,
+ "grad_norm": 0.39602842926979065,
+ "learning_rate": 4.8437825500739696e-05,
+ "loss": 0.4229,
+ "step": 520
+ },
+ {
+ "epoch": 0.5968468468468469,
+ "grad_norm": 0.6842754483222961,
+ "learning_rate": 4.837540606713538e-05,
+ "loss": 0.4228,
+ "step": 530
+ },
+ {
+ "epoch": 0.6081081081081081,
+ "grad_norm": 0.5598196983337402,
+ "learning_rate": 4.8311805735108894e-05,
+ "loss": 0.3683,
+ "step": 540
+ },
+ {
+ "epoch": 0.6193693693693694,
+ "grad_norm": 0.4672955870628357,
+ "learning_rate": 4.824702771767533e-05,
+ "loss": 0.4516,
+ "step": 550
+ },
+ {
+ "epoch": 0.6306306306306306,
+ "grad_norm": 0.5013401508331299,
+ "learning_rate": 4.818107528734504e-05,
+ "loss": 0.3849,
+ "step": 560
+ },
+ {
+ "epoch": 0.6418918918918919,
+ "grad_norm": 0.5412279367446899,
+ "learning_rate": 4.811395177595836e-05,
+ "loss": 0.4075,
+ "step": 570
+ },
+ {
+ "epoch": 0.6531531531531531,
+ "grad_norm": 0.4712611436843872,
+ "learning_rate": 4.804566057451729e-05,
+ "loss": 0.3984,
+ "step": 580
+ },
+ {
+ "epoch": 0.6644144144144144,
+ "grad_norm": 0.5282795429229736,
+ "learning_rate": 4.797620513301418e-05,
+ "loss": 0.3875,
+ "step": 590
+ },
+ {
+ "epoch": 0.6756756756756757,
+ "grad_norm": 0.5164788365364075,
+ "learning_rate": 4.790558896025743e-05,
+ "loss": 0.3912,
+ "step": 600
+ },
+ {
+ "epoch": 0.6756756756756757,
+ "eval_loss": 0.37321507930755615,
+ "eval_runtime": 8.2005,
+ "eval_samples_per_second": 45.607,
+ "eval_steps_per_second": 5.731,
+ "step": 600
+ },
+ {
+ "epoch": 0.6869369369369369,
+ "grad_norm": 0.5996334552764893,
+ "learning_rate": 4.7833815623694256e-05,
+ "loss": 0.3794,
+ "step": 610
+ },
+ {
+ "epoch": 0.6981981981981982,
+ "grad_norm": 0.6625643968582153,
+ "learning_rate": 4.7760888749230416e-05,
+ "loss": 0.3995,
+ "step": 620
+ },
+ {
+ "epoch": 0.7094594594594594,
+ "grad_norm": 0.5413252115249634,
+ "learning_rate": 4.7686812021047087e-05,
+ "loss": 0.3974,
+ "step": 630
+ },
+ {
+ "epoch": 0.7207207207207207,
+ "grad_norm": 0.5730133652687073,
+ "learning_rate": 4.761158918141474e-05,
+ "loss": 0.3982,
+ "step": 640
+ },
+ {
+ "epoch": 0.7319819819819819,
+ "grad_norm": 0.5036820769309998,
+ "learning_rate": 4.753522403050403e-05,
+ "loss": 0.4243,
+ "step": 650
+ },
+ {
+ "epoch": 0.7432432432432432,
+ "grad_norm": 0.6623256802558899,
+ "learning_rate": 4.745772042619388e-05,
+ "loss": 0.4118,
+ "step": 660
+ },
+ {
+ "epoch": 0.7545045045045045,
+ "grad_norm": 0.5830026865005493,
+ "learning_rate": 4.7379082283876566e-05,
+ "loss": 0.3857,
+ "step": 670
+ },
+ {
+ "epoch": 0.7657657657657657,
+ "grad_norm": 0.5006307363510132,
+ "learning_rate": 4.7299313576259864e-05,
+ "loss": 0.4273,
+ "step": 680
+ },
+ {
+ "epoch": 0.777027027027027,
+ "grad_norm": 0.5556634664535522,
+ "learning_rate": 4.7218418333166455e-05,
+ "loss": 0.4107,
+ "step": 690
+ },
+ {
+ "epoch": 0.7882882882882883,
+ "grad_norm": 0.496698260307312,
+ "learning_rate": 4.713640064133025e-05,
+ "loss": 0.3738,
+ "step": 700
+ },
+ {
+ "epoch": 0.7882882882882883,
+ "eval_loss": 0.3662475049495697,
+ "eval_runtime": 8.1988,
+ "eval_samples_per_second": 45.617,
+ "eval_steps_per_second": 5.733,
+ "step": 700
+ },
+ {
+ "epoch": 0.7995495495495496,
+ "grad_norm": 0.6803075075149536,
+ "learning_rate": 4.705326464418999e-05,
+ "loss": 0.4,
+ "step": 710
+ },
+ {
+ "epoch": 0.8108108108108109,
+ "grad_norm": 0.46191635727882385,
+ "learning_rate": 4.696901454167988e-05,
+ "loss": 0.4041,
+ "step": 720
+ },
+ {
+ "epoch": 0.8220720720720721,
+ "grad_norm": 0.5346249938011169,
+ "learning_rate": 4.688365459001747e-05,
+ "loss": 0.4202,
+ "step": 730
+ },
+ {
+ "epoch": 0.8333333333333334,
+ "grad_norm": 0.48924916982650757,
+ "learning_rate": 4.6797189101488584e-05,
+ "loss": 0.4156,
+ "step": 740
+ },
+ {
+ "epoch": 0.8445945945945946,
+ "grad_norm": 0.5989688634872437,
+ "learning_rate": 4.670962244422946e-05,
+ "loss": 0.3884,
+ "step": 750
+ },
+ {
+ "epoch": 0.8558558558558559,
+ "grad_norm": 0.5550072193145752,
+ "learning_rate": 4.6620959042006174e-05,
+ "loss": 0.3989,
+ "step": 760
+ },
+ {
+ "epoch": 0.8671171171171171,
+ "grad_norm": 0.6869233846664429,
+ "learning_rate": 4.6531203373991014e-05,
+ "loss": 0.4036,
+ "step": 770
+ },
+ {
+ "epoch": 0.8783783783783784,
+ "grad_norm": 0.480530709028244,
+ "learning_rate": 4.6440359974536306e-05,
+ "loss": 0.3985,
+ "step": 780
+ },
+ {
+ "epoch": 0.8896396396396397,
+ "grad_norm": 0.4647653102874756,
+ "learning_rate": 4.634843343294531e-05,
+ "loss": 0.38,
+ "step": 790
+ },
+ {
+ "epoch": 0.9009009009009009,
+ "grad_norm": 0.3987728953361511,
+ "learning_rate": 4.625542839324036e-05,
+ "loss": 0.3729,
+ "step": 800
+ },
+ {
+ "epoch": 0.9009009009009009,
+ "eval_loss": 0.3623661696910858,
+ "eval_runtime": 8.2012,
+ "eval_samples_per_second": 45.603,
+ "eval_steps_per_second": 5.731,
+ "step": 800
+ },
+ {
+ "epoch": 0.9121621621621622,
+ "grad_norm": 0.5637523531913757,
+ "learning_rate": 4.616134955392826e-05,
+ "loss": 0.3577,
+ "step": 810
+ },
+ {
+ "epoch": 0.9234234234234234,
+ "grad_norm": 0.6415589451789856,
+ "learning_rate": 4.606620166776294e-05,
+ "loss": 0.3393,
+ "step": 820
+ },
+ {
+ "epoch": 0.9346846846846847,
+ "grad_norm": 0.534212589263916,
+ "learning_rate": 4.596998954150534e-05,
+ "loss": 0.3964,
+ "step": 830
+ },
+ {
+ "epoch": 0.9459459459459459,
+ "grad_norm": 0.45441269874572754,
+ "learning_rate": 4.587271803568056e-05,
+ "loss": 0.3988,
+ "step": 840
+ },
+ {
+ "epoch": 0.9572072072072072,
+ "grad_norm": 0.3887268006801605,
+ "learning_rate": 4.577439206433233e-05,
+ "loss": 0.359,
+ "step": 850
+ },
+ {
+ "epoch": 0.9684684684684685,
+ "grad_norm": 0.45505017042160034,
+ "learning_rate": 4.567501659477477e-05,
+ "loss": 0.4198,
+ "step": 860
+ },
+ {
+ "epoch": 0.9797297297297297,
+ "grad_norm": 0.614913284778595,
+ "learning_rate": 4.557459664734141e-05,
+ "loss": 0.3708,
+ "step": 870
+ },
+ {
+ "epoch": 0.990990990990991,
+ "grad_norm": 0.6321812272071838,
+ "learning_rate": 4.547313729513163e-05,
+ "loss": 0.3956,
+ "step": 880
+ },
+ {
+ "epoch": 1.0022522522522523,
+ "grad_norm": 0.5617508292198181,
+ "learning_rate": 4.537064366375429e-05,
+ "loss": 0.3563,
+ "step": 890
+ },
+ {
+ "epoch": 1.0135135135135136,
+ "grad_norm": 0.5184743404388428,
+ "learning_rate": 4.5267120931068875e-05,
+ "loss": 0.3573,
+ "step": 900
+ },
+ {
+ "epoch": 1.0135135135135136,
+ "eval_loss": 0.35875043272972107,
+ "eval_runtime": 8.1958,
+ "eval_samples_per_second": 45.633,
+ "eval_steps_per_second": 5.735,
+ "step": 900
+ },
+ {
+ "epoch": 1.0247747747747749,
+ "grad_norm": 0.47627612948417664,
+ "learning_rate": 4.5162574326923834e-05,
+ "loss": 0.3158,
+ "step": 910
+ },
+ {
+ "epoch": 1.0360360360360361,
+ "grad_norm": 0.6007285714149475,
+ "learning_rate": 4.505700913289246e-05,
+ "loss": 0.3412,
+ "step": 920
+ },
+ {
+ "epoch": 1.0472972972972974,
+ "grad_norm": 0.46858587861061096,
+ "learning_rate": 4.4950430682006e-05,
+ "loss": 0.3365,
+ "step": 930
+ },
+ {
+ "epoch": 1.0585585585585586,
+ "grad_norm": 0.6188820004463196,
+ "learning_rate": 4.4842844358484236e-05,
+ "loss": 0.3537,
+ "step": 940
+ },
+ {
+ "epoch": 1.0698198198198199,
+ "grad_norm": 0.5940184593200684,
+ "learning_rate": 4.473425559746358e-05,
+ "loss": 0.399,
+ "step": 950
+ },
+ {
+ "epoch": 1.0810810810810811,
+ "grad_norm": 0.6671022176742554,
+ "learning_rate": 4.462466988472237e-05,
+ "loss": 0.3445,
+ "step": 960
+ },
+ {
+ "epoch": 1.0923423423423424,
+ "grad_norm": 0.7214995622634888,
+ "learning_rate": 4.451409275640379e-05,
+ "loss": 0.4066,
+ "step": 970
+ },
+ {
+ "epoch": 1.1036036036036037,
+ "grad_norm": 1.5398939847946167,
+ "learning_rate": 4.440252979873622e-05,
+ "loss": 0.3408,
+ "step": 980
+ },
+ {
+ "epoch": 1.114864864864865,
+ "grad_norm": 0.7890127301216125,
+ "learning_rate": 4.428998664775097e-05,
+ "loss": 0.3706,
+ "step": 990
+ },
+ {
+ "epoch": 1.1261261261261262,
+ "grad_norm": 0.8278851509094238,
+ "learning_rate": 4.4176468988997586e-05,
+ "loss": 0.3603,
+ "step": 1000
+ },
+ {
+ "epoch": 1.1261261261261262,
+ "eval_loss": 0.3570348024368286,
+ "eval_runtime": 8.1964,
+ "eval_samples_per_second": 45.63,
+ "eval_steps_per_second": 5.734,
+ "step": 1000
+ },
+ {
+ "epoch": 1.1373873873873874,
+ "grad_norm": 0.6090120673179626,
+ "learning_rate": 4.406198255725662e-05,
+ "loss": 0.3608,
+ "step": 1010
+ },
+ {
+ "epoch": 1.1486486486486487,
+ "grad_norm": 0.5922278165817261,
+ "learning_rate": 4.3946533136249926e-05,
+ "loss": 0.3329,
+ "step": 1020
+ },
+ {
+ "epoch": 1.15990990990991,
+ "grad_norm": 0.6958382725715637,
+ "learning_rate": 4.383012655834842e-05,
+ "loss": 0.3317,
+ "step": 1030
+ },
+ {
+ "epoch": 1.1711711711711712,
+ "grad_norm": 0.5835362672805786,
+ "learning_rate": 4.371276870427753e-05,
+ "loss": 0.3212,
+ "step": 1040
+ },
+ {
+ "epoch": 1.1824324324324325,
+ "grad_norm": 0.47040149569511414,
+ "learning_rate": 4.359446550282001e-05,
+ "loss": 0.3012,
+ "step": 1050
+ },
+ {
+ "epoch": 1.1936936936936937,
+ "grad_norm": 0.6414148807525635,
+ "learning_rate": 4.347522293051648e-05,
+ "loss": 0.3308,
+ "step": 1060
+ },
+ {
+ "epoch": 1.204954954954955,
+ "grad_norm": 0.7301586270332336,
+ "learning_rate": 4.33550470113635e-05,
+ "loss": 0.332,
+ "step": 1070
+ },
+ {
+ "epoch": 1.2162162162162162,
+ "grad_norm": 0.6913548707962036,
+ "learning_rate": 4.3233943816509204e-05,
+ "loss": 0.3723,
+ "step": 1080
+ },
+ {
+ "epoch": 1.2274774774774775,
+ "grad_norm": 0.7655626535415649,
+ "learning_rate": 4.311191946394665e-05,
+ "loss": 0.3577,
+ "step": 1090
+ },
+ {
+ "epoch": 1.2387387387387387,
+ "grad_norm": 0.5891656875610352,
+ "learning_rate": 4.2988980118204705e-05,
+ "loss": 0.3501,
+ "step": 1100
+ },
+ {
+ "epoch": 1.2387387387387387,
+ "eval_loss": 0.3554933965206146,
+ "eval_runtime": 8.2012,
+ "eval_samples_per_second": 45.603,
+ "eval_steps_per_second": 5.731,
+ "step": 1100
+ },
+ {
+ "epoch": 1.25,
+ "grad_norm": 0.596078634262085,
+ "learning_rate": 4.2865131990036614e-05,
+ "loss": 0.3517,
+ "step": 1110
+ },
+ {
+ "epoch": 1.2612612612612613,
+ "grad_norm": 0.6539855003356934,
+ "learning_rate": 4.274038133610628e-05,
+ "loss": 0.3482,
+ "step": 1120
+ },
+ {
+ "epoch": 1.2725225225225225,
+ "grad_norm": 0.7913669943809509,
+ "learning_rate": 4.261473445867215e-05,
+ "loss": 0.3224,
+ "step": 1130
+ },
+ {
+ "epoch": 1.2837837837837838,
+ "grad_norm": 0.7654316425323486,
+ "learning_rate": 4.248819770526885e-05,
+ "loss": 0.3717,
+ "step": 1140
+ },
+ {
+ "epoch": 1.295045045045045,
+ "grad_norm": 0.708782970905304,
+ "learning_rate": 4.236077746838649e-05,
+ "loss": 0.338,
+ "step": 1150
+ },
+ {
+ "epoch": 1.3063063063063063,
+ "grad_norm": 0.7497960925102234,
+ "learning_rate": 4.223248018514777e-05,
+ "loss": 0.3637,
+ "step": 1160
+ },
+ {
+ "epoch": 1.3175675675675675,
+ "grad_norm": 0.7006718516349792,
+ "learning_rate": 4.2103312336982734e-05,
+ "loss": 0.3865,
+ "step": 1170
+ },
+ {
+ "epoch": 1.3288288288288288,
+ "grad_norm": 0.7535539269447327,
+ "learning_rate": 4.197328044930137e-05,
+ "loss": 0.3802,
+ "step": 1180
+ },
+ {
+ "epoch": 1.34009009009009,
+ "grad_norm": 0.7530516982078552,
+ "learning_rate": 4.184239109116393e-05,
+ "loss": 0.3778,
+ "step": 1190
+ },
+ {
+ "epoch": 1.3513513513513513,
+ "grad_norm": 0.6120439171791077,
+ "learning_rate": 4.171065087494909e-05,
+ "loss": 0.3335,
+ "step": 1200
+ },
+ {
+ "epoch": 1.3513513513513513,
+ "eval_loss": 0.3528105914592743,
+ "eval_runtime": 8.2069,
+ "eval_samples_per_second": 45.571,
+ "eval_steps_per_second": 5.727,
+ "step": 1200
+ },
+ {
+ "epoch": 1.3626126126126126,
+ "grad_norm": 0.5910629630088806,
+ "learning_rate": 4.157806645601988e-05,
+ "loss": 0.3463,
+ "step": 1210
+ },
+ {
+ "epoch": 1.3738738738738738,
+ "grad_norm": 0.6855325102806091,
+ "learning_rate": 4.144464453238748e-05,
+ "loss": 0.3516,
+ "step": 1220
+ },
+ {
+ "epoch": 1.385135135135135,
+ "grad_norm": 0.6499032378196716,
+ "learning_rate": 4.131039184437283e-05,
+ "loss": 0.3575,
+ "step": 1230
+ },
+ {
+ "epoch": 1.3963963963963963,
+ "grad_norm": 0.7425965070724487,
+ "learning_rate": 4.117531517426614e-05,
+ "loss": 0.3291,
+ "step": 1240
+ },
+ {
+ "epoch": 1.4076576576576576,
+ "grad_norm": 0.6581376791000366,
+ "learning_rate": 4.103942134598422e-05,
+ "loss": 0.3402,
+ "step": 1250
+ },
+ {
+ "epoch": 1.4189189189189189,
+ "grad_norm": 0.7019423246383667,
+ "learning_rate": 4.0902717224725766e-05,
+ "loss": 0.3137,
+ "step": 1260
+ },
+ {
+ "epoch": 1.4301801801801801,
+ "grad_norm": 0.7479864954948425,
+ "learning_rate": 4.076520971662455e-05,
+ "loss": 0.3348,
+ "step": 1270
+ },
+ {
+ "epoch": 1.4414414414414414,
+ "grad_norm": 0.7250381112098694,
+ "learning_rate": 4.0626905768400516e-05,
+ "loss": 0.3248,
+ "step": 1280
+ },
+ {
+ "epoch": 1.4527027027027026,
+ "grad_norm": 0.6881899833679199,
+ "learning_rate": 4.0487812367008814e-05,
+ "loss": 0.3523,
+ "step": 1290
+ },
+ {
+ "epoch": 1.4639639639639639,
+ "grad_norm": 0.6837844252586365,
+ "learning_rate": 4.0347936539286876e-05,
+ "loss": 0.3372,
+ "step": 1300
+ },
+ {
+ "epoch": 1.4639639639639639,
+ "eval_loss": 0.3515435755252838,
+ "eval_runtime": 8.1967,
+ "eval_samples_per_second": 45.628,
+ "eval_steps_per_second": 5.734,
+ "step": 1300
+ },
+ {
+ "epoch": 1.4752252252252251,
+ "grad_norm": 0.9053608179092407,
+ "learning_rate": 4.020728535159942e-05,
+ "loss": 0.353,
+ "step": 1310
+ },
+ {
+ "epoch": 1.4864864864864864,
+ "grad_norm": 0.7456597089767456,
+ "learning_rate": 4.0065865909481417e-05,
+ "loss": 0.3395,
+ "step": 1320
+ },
+ {
+ "epoch": 1.4977477477477477,
+ "grad_norm": 0.6326711773872375,
+ "learning_rate": 3.9923685357279166e-05,
+ "loss": 0.347,
+ "step": 1330
+ },
+ {
+ "epoch": 1.509009009009009,
+ "grad_norm": 0.7098799347877502,
+ "learning_rate": 3.97807508777894e-05,
+ "loss": 0.3372,
+ "step": 1340
+ },
+ {
+ "epoch": 1.5202702702702702,
+ "grad_norm": 0.7150790691375732,
+ "learning_rate": 3.963706969189633e-05,
+ "loss": 0.3327,
+ "step": 1350
+ },
+ {
+ "epoch": 1.5315315315315314,
+ "grad_norm": 0.720104992389679,
+ "learning_rate": 3.949264905820697e-05,
+ "loss": 0.359,
+ "step": 1360
+ },
+ {
+ "epoch": 1.5427927927927927,
+ "grad_norm": 0.6558349132537842,
+ "learning_rate": 3.9347496272684325e-05,
+ "loss": 0.3083,
+ "step": 1370
+ },
+ {
+ "epoch": 1.554054054054054,
+ "grad_norm": 0.714012861251831,
+ "learning_rate": 3.920161866827889e-05,
+ "loss": 0.3241,
+ "step": 1380
+ },
+ {
+ "epoch": 1.5653153153153152,
+ "grad_norm": 0.6730446815490723,
+ "learning_rate": 3.905502361455818e-05,
+ "loss": 0.3517,
+ "step": 1390
+ },
+ {
+ "epoch": 1.5765765765765765,
+ "grad_norm": 0.6450095176696777,
+ "learning_rate": 3.89077185173344e-05,
+ "loss": 0.3565,
+ "step": 1400
+ },
+ {
+ "epoch": 1.5765765765765765,
+ "eval_loss": 0.3501906991004944,
+ "eval_runtime": 8.1951,
+ "eval_samples_per_second": 45.637,
+ "eval_steps_per_second": 5.735,
+ "step": 1400
+ },
+ {
+ "epoch": 1.5878378378378377,
+ "grad_norm": 0.6281234622001648,
+ "learning_rate": 3.875971081829033e-05,
+ "loss": 0.3359,
+ "step": 1410
+ },
+ {
+ "epoch": 1.599099099099099,
+ "grad_norm": 0.8155395984649658,
+ "learning_rate": 3.8611007994603365e-05,
+ "loss": 0.3624,
+ "step": 1420
+ },
+ {
+ "epoch": 1.6103603603603602,
+ "grad_norm": 0.6452349424362183,
+ "learning_rate": 3.8461617558567845e-05,
+ "loss": 0.3489,
+ "step": 1430
+ },
+ {
+ "epoch": 1.6216216216216215,
+ "grad_norm": 0.9718044996261597,
+ "learning_rate": 3.831154705721541e-05,
+ "loss": 0.3306,
+ "step": 1440
+ },
+ {
+ "epoch": 1.6328828828828827,
+ "grad_norm": 0.7829695343971252,
+ "learning_rate": 3.81608040719339e-05,
+ "loss": 0.3325,
+ "step": 1450
+ },
+ {
+ "epoch": 1.644144144144144,
+ "grad_norm": 0.7047085165977478,
+ "learning_rate": 3.8009396218084195e-05,
+ "loss": 0.3224,
+ "step": 1460
+ },
+ {
+ "epoch": 1.6554054054054053,
+ "grad_norm": 0.6780081391334534,
+ "learning_rate": 3.7857331144615574e-05,
+ "loss": 0.3319,
+ "step": 1470
+ },
+ {
+ "epoch": 1.6666666666666665,
+ "grad_norm": 0.6606218218803406,
+ "learning_rate": 3.770461653367934e-05,
+ "loss": 0.3333,
+ "step": 1480
+ },
+ {
+ "epoch": 1.6779279279279278,
+ "grad_norm": 0.7966985106468201,
+ "learning_rate": 3.75512601002406e-05,
+ "loss": 0.37,
+ "step": 1490
+ },
+ {
+ "epoch": 1.689189189189189,
+ "grad_norm": 0.6693293452262878,
+ "learning_rate": 3.739726959168867e-05,
+ "loss": 0.3313,
+ "step": 1500
+ },
+ {
+ "epoch": 1.689189189189189,
+ "eval_loss": 0.34918585419654846,
+ "eval_runtime": 8.1972,
+ "eval_samples_per_second": 45.626,
+ "eval_steps_per_second": 5.734,
+ "step": 1500
+ },
+ {
+ "epoch": 1.7004504504504503,
+ "grad_norm": 0.94988614320755,
+ "learning_rate": 3.7242652787445525e-05,
+ "loss": 0.3388,
+ "step": 1510
+ },
+ {
+ "epoch": 1.7117117117117115,
+ "grad_norm": 0.7464775443077087,
+ "learning_rate": 3.7087417498572944e-05,
+ "loss": 0.3719,
+ "step": 1520
+ },
+ {
+ "epoch": 1.722972972972973,
+ "grad_norm": 0.7086770534515381,
+ "learning_rate": 3.693157156737778e-05,
+ "loss": 0.3593,
+ "step": 1530
+ },
+ {
+ "epoch": 1.7342342342342343,
+ "grad_norm": 0.5240457057952881,
+ "learning_rate": 3.677512286701587e-05,
+ "loss": 0.3202,
+ "step": 1540
+ },
+ {
+ "epoch": 1.7454954954954955,
+ "grad_norm": 0.6813139915466309,
+ "learning_rate": 3.6618079301094216e-05,
+ "loss": 0.34,
+ "step": 1550
+ },
+ {
+ "epoch": 1.7567567567567568,
+ "grad_norm": 0.7653558254241943,
+ "learning_rate": 3.6460448803271754e-05,
+ "loss": 0.3455,
+ "step": 1560
+ },
+ {
+ "epoch": 1.768018018018018,
+ "grad_norm": 0.7910571694374084,
+ "learning_rate": 3.6302239336858545e-05,
+ "loss": 0.3415,
+ "step": 1570
+ },
+ {
+ "epoch": 1.7792792792792793,
+ "grad_norm": 0.81830894947052,
+ "learning_rate": 3.6143458894413465e-05,
+ "loss": 0.3442,
+ "step": 1580
+ },
+ {
+ "epoch": 1.7905405405405406,
+ "grad_norm": 0.8659543395042419,
+ "learning_rate": 3.598411549734042e-05,
+ "loss": 0.3357,
+ "step": 1590
+ },
+ {
+ "epoch": 1.8018018018018018,
+ "grad_norm": 0.9850949645042419,
+ "learning_rate": 3.582421719548318e-05,
+ "loss": 0.3653,
+ "step": 1600
+ },
+ {
+ "epoch": 1.8018018018018018,
+ "eval_loss": 0.3447774648666382,
+ "eval_runtime": 8.1959,
+ "eval_samples_per_second": 45.633,
+ "eval_steps_per_second": 5.735,
+ "step": 1600
+ },
+ {
+ "epoch": 1.813063063063063,
+ "grad_norm": 0.6600885391235352,
+ "learning_rate": 3.56637720667186e-05,
+ "loss": 0.3736,
+ "step": 1610
+ },
+ {
+ "epoch": 1.8243243243243243,
+ "grad_norm": 0.5550006031990051,
+ "learning_rate": 3.550278821654866e-05,
+ "loss": 0.3275,
+ "step": 1620
+ },
+ {
+ "epoch": 1.8355855855855856,
+ "grad_norm": 0.7177895307540894,
+ "learning_rate": 3.5341273777690865e-05,
+ "loss": 0.3611,
+ "step": 1630
+ },
+ {
+ "epoch": 1.8468468468468469,
+ "grad_norm": 0.710928201675415,
+ "learning_rate": 3.5179236909667465e-05,
+ "loss": 0.3252,
+ "step": 1640
+ },
+ {
+ "epoch": 1.8581081081081081,
+ "grad_norm": 0.6372870206832886,
+ "learning_rate": 3.5016685798393244e-05,
+ "loss": 0.3394,
+ "step": 1650
+ },
+ {
+ "epoch": 1.8693693693693694,
+ "grad_norm": 0.7593337297439575,
+ "learning_rate": 3.485362865576194e-05,
+ "loss": 0.3233,
+ "step": 1660
+ },
+ {
+ "epoch": 1.8806306306306306,
+ "grad_norm": 0.6406942009925842,
+ "learning_rate": 3.4690073719231425e-05,
+ "loss": 0.382,
+ "step": 1670
+ },
+ {
+ "epoch": 1.8918918918918919,
+ "grad_norm": 0.6719651818275452,
+ "learning_rate": 3.452602925140751e-05,
+ "loss": 0.3762,
+ "step": 1680
+ },
+ {
+ "epoch": 1.9031531531531531,
+ "grad_norm": 0.7636570334434509,
+ "learning_rate": 3.436150353962659e-05,
+ "loss": 0.3233,
+ "step": 1690
+ },
+ {
+ "epoch": 1.9144144144144144,
+ "grad_norm": 0.789856493473053,
+ "learning_rate": 3.419650489553695e-05,
+ "loss": 0.3412,
+ "step": 1700
+ },
+ {
+ "epoch": 1.9144144144144144,
+ "eval_loss": 0.3434712886810303,
+ "eval_runtime": 8.2201,
+ "eval_samples_per_second": 45.498,
+ "eval_steps_per_second": 5.718,
+ "step": 1700
+ },
+ {
+ "epoch": 1.9256756756756757,
+ "grad_norm": 0.835012674331665,
+ "learning_rate": 3.403104165467883e-05,
+ "loss": 0.36,
+ "step": 1710
+ },
+ {
+ "epoch": 1.936936936936937,
+ "grad_norm": 0.9047138690948486,
+ "learning_rate": 3.386512217606339e-05,
+ "loss": 0.3209,
+ "step": 1720
+ },
+ {
+ "epoch": 1.9481981981981982,
+ "grad_norm": 0.8788958191871643,
+ "learning_rate": 3.36987548417504e-05,
+ "loss": 0.35,
+ "step": 1730
+ },
+ {
+ "epoch": 1.9594594594594594,
+ "grad_norm": 0.8558595776557922,
+ "learning_rate": 3.353194805642477e-05,
+ "loss": 0.3442,
+ "step": 1740
+ },
+ {
+ "epoch": 1.9707207207207207,
+ "grad_norm": 0.9103739857673645,
+ "learning_rate": 3.3364710246971934e-05,
+ "loss": 0.3479,
+ "step": 1750
+ },
+ {
+ "epoch": 1.981981981981982,
+ "grad_norm": 0.6725114583969116,
+ "learning_rate": 3.319704986205223e-05,
+ "loss": 0.3507,
+ "step": 1760
+ },
+ {
+ "epoch": 1.9932432432432432,
+ "grad_norm": 0.8124126195907593,
+ "learning_rate": 3.302897537167397e-05,
+ "loss": 0.322,
+ "step": 1770
+ },
+ {
+ "epoch": 2.0045045045045047,
+ "grad_norm": 0.811869740486145,
+ "learning_rate": 3.28604952667656e-05,
+ "loss": 0.2991,
+ "step": 1780
+ },
+ {
+ "epoch": 2.015765765765766,
+ "grad_norm": 0.7791336178779602,
+ "learning_rate": 3.2691618058746756e-05,
+ "loss": 0.285,
+ "step": 1790
+ },
+ {
+ "epoch": 2.027027027027027,
+ "grad_norm": 0.9384168386459351,
+ "learning_rate": 3.252235227909826e-05,
+ "loss": 0.2738,
+ "step": 1800
+ },
+ {
+ "epoch": 2.027027027027027,
+ "eval_loss": 0.34939834475517273,
+ "eval_runtime": 8.1935,
+ "eval_samples_per_second": 45.646,
+ "eval_steps_per_second": 5.736,
+ "step": 1800
+ },
+ {
+ "epoch": 2.0382882882882885,
+ "grad_norm": 1.0694797039031982,
+ "learning_rate": 3.2352706478931106e-05,
+ "loss": 0.3052,
+ "step": 1810
+ },
+ {
+ "epoch": 2.0495495495495497,
+ "grad_norm": 0.73499596118927,
+ "learning_rate": 3.2182689228554517e-05,
+ "loss": 0.291,
+ "step": 1820
+ },
+ {
+ "epoch": 2.060810810810811,
+ "grad_norm": 0.8585954904556274,
+ "learning_rate": 3.201230911704292e-05,
+ "loss": 0.2901,
+ "step": 1830
+ },
+ {
+ "epoch": 2.0720720720720722,
+ "grad_norm": 0.831569254398346,
+ "learning_rate": 3.1841574751802076e-05,
+ "loss": 0.296,
+ "step": 1840
+ },
+ {
+ "epoch": 2.0833333333333335,
+ "grad_norm": 0.6446948051452637,
+ "learning_rate": 3.1670494758134235e-05,
+ "loss": 0.3048,
+ "step": 1850
+ },
+ {
+ "epoch": 2.0945945945945947,
+ "grad_norm": 0.8153528571128845,
+ "learning_rate": 3.1499077778802385e-05,
+ "loss": 0.3232,
+ "step": 1860
+ },
+ {
+ "epoch": 2.105855855855856,
+ "grad_norm": 1.1492727994918823,
+ "learning_rate": 3.132733247359366e-05,
+ "loss": 0.2836,
+ "step": 1870
+ },
+ {
+ "epoch": 2.1171171171171173,
+ "grad_norm": 0.8934274911880493,
+ "learning_rate": 3.115526751888181e-05,
+ "loss": 0.288,
+ "step": 1880
+ },
+ {
+ "epoch": 2.1283783783783785,
+ "grad_norm": 0.7422814965248108,
+ "learning_rate": 3.098289160718895e-05,
+ "loss": 0.3112,
+ "step": 1890
+ },
+ {
+ "epoch": 2.1396396396396398,
+ "grad_norm": 0.7775539755821228,
+ "learning_rate": 3.081021344674632e-05,
+ "loss": 0.3159,
+ "step": 1900
+ },
+ {
+ "epoch": 2.1396396396396398,
+ "eval_loss": 0.3487659990787506,
+ "eval_runtime": 8.1976,
+ "eval_samples_per_second": 45.623,
+ "eval_steps_per_second": 5.733,
+ "step": 1900
+ },
+ {
+ "epoch": 2.150900900900901,
+ "grad_norm": 0.8478897213935852,
+ "learning_rate": 3.063724176105447e-05,
+ "loss": 0.2923,
+ "step": 1910
+ },
+ {
+ "epoch": 2.1621621621621623,
+ "grad_norm": 0.8476938009262085,
+ "learning_rate": 3.0463985288442475e-05,
+ "loss": 0.2931,
+ "step": 1920
+ },
+ {
+ "epoch": 2.1734234234234235,
+ "grad_norm": 0.9131262302398682,
+ "learning_rate": 3.0290452781626526e-05,
+ "loss": 0.2884,
+ "step": 1930
+ },
+ {
+ "epoch": 2.184684684684685,
+ "grad_norm": 0.80256187915802,
+ "learning_rate": 3.0116653007267753e-05,
+ "loss": 0.3101,
+ "step": 1940
+ },
+ {
+ "epoch": 2.195945945945946,
+ "grad_norm": 0.924358069896698,
+ "learning_rate": 2.9942594745529307e-05,
+ "loss": 0.2692,
+ "step": 1950
+ },
+ {
+ "epoch": 2.2072072072072073,
+ "grad_norm": 0.9482952952384949,
+ "learning_rate": 2.9768286789632844e-05,
+ "loss": 0.2642,
+ "step": 1960
+ },
+ {
+ "epoch": 2.2184684684684686,
+ "grad_norm": 0.960928738117218,
+ "learning_rate": 2.9593737945414264e-05,
+ "loss": 0.3233,
+ "step": 1970
+ },
+ {
+ "epoch": 2.22972972972973,
+ "grad_norm": 0.8202047348022461,
+ "learning_rate": 2.9418957030878874e-05,
+ "loss": 0.2886,
+ "step": 1980
+ },
+ {
+ "epoch": 2.240990990990991,
+ "grad_norm": 1.0298452377319336,
+ "learning_rate": 2.9243952875755904e-05,
+ "loss": 0.2879,
+ "step": 1990
+ },
+ {
+ "epoch": 2.2522522522522523,
+ "grad_norm": 0.8166371583938599,
+ "learning_rate": 2.9068734321052444e-05,
+ "loss": 0.2892,
+ "step": 2000
+ },
+ {
+ "epoch": 2.2522522522522523,
+ "eval_loss": 0.3520003855228424,
+ "eval_runtime": 8.2053,
+ "eval_samples_per_second": 45.58,
+ "eval_steps_per_second": 5.728,
+ "step": 2000
+ },
+ {
+ "epoch": 2.2522522522522523,
+ "step": 2000,
+ "total_flos": 3.569474683755561e+17,
+ "train_loss": 0.3791467320919037,
+ "train_runtime": 1418.2267,
+ "train_samples_per_second": 25.028,
+ "train_steps_per_second": 3.131
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 4440,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 100,
+ "total_flos": 3.569474683755561e+17,
+ "train_batch_size": 4,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/llama2_13b_peft/gsm8k/training_args.bin b/llama2_13b_peft/gsm8k/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..51c77a3c030ced75f9999421dad27a373031753b
--- /dev/null
+++ b/llama2_13b_peft/gsm8k/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3801de57613398afae1ae05ff343cf788e86f2ff899e2963fdf1ca9a1992669
+size 5176
diff --git a/llama2_13b_peft/gsm8k/training_eval_loss.png b/llama2_13b_peft/gsm8k/training_eval_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..f94eb4a3a1ed401e4372286ba9c377e4d5aeefe1
Binary files /dev/null and b/llama2_13b_peft/gsm8k/training_eval_loss.png differ
diff --git a/llama2_13b_peft/gsm8k/training_loss.png b/llama2_13b_peft/gsm8k/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..0adf56927d98c3c67617988c13decac4d3ca076d
Binary files /dev/null and b/llama2_13b_peft/gsm8k/training_loss.png differ
diff --git a/llama2_13b_peft/language_identification/README.md b/llama2_13b_peft/language_identification/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..251cec47cbec32e3da8bd3c543a6c475dc847cbc
--- /dev/null
+++ b/llama2_13b_peft/language_identification/README.md
@@ -0,0 +1,78 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: language_identification_no_sys
+ results: []
+---
+
+
+
+# language_identification_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the language_identification_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0978
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- total_train_batch_size: 24
+- total_eval_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2391 | 0.35 | 100 | 0.2734 |
+| 0.253 | 0.7 | 200 | 0.1845 |
+| 0.1018 | 1.06 | 300 | 0.1642 |
+| 0.0807 | 1.41 | 400 | 0.1606 |
+| 0.0721 | 1.76 | 500 | 0.1121 |
+| 0.0415 | 2.11 | 600 | 0.1096 |
+| 0.0278 | 2.46 | 700 | 0.1008 |
+| 0.0142 | 2.82 | 800 | 0.0910 |
+| 0.0042 | 3.17 | 900 | 0.1130 |
+| 0.0025 | 3.52 | 1000 | 0.0978 |
+| 0.0087 | 3.87 | 1100 | 0.1109 |
+| 0.0002 | 4.23 | 1200 | 0.1120 |
+| 0.0001 | 4.58 | 1300 | 0.1139 |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2
\ No newline at end of file
diff --git a/llama2_13b_peft/language_identification/adapter_config.json b/llama2_13b_peft/language_identification/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8256ef436f33ca62c7ed3430e6b10c021fd9858
--- /dev/null
+++ b/llama2_13b_peft/language_identification/adapter_config.json
@@ -0,0 +1,33 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 16,
+ "lora_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "down_proj",
+ "up_proj",
+ "v_proj",
+ "q_proj",
+ "o_proj",
+ "k_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/language_identification/adapter_model.safetensors b/llama2_13b_peft/language_identification/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e6211f7bd0411931110599d559ff0b51d7ea3bf5
--- /dev/null
+++ b/llama2_13b_peft/language_identification/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef24c1b0159dc6487e4656a0af599593f7ae1677ec5ce2d3e46df7aad16ef51
+size 125248064
diff --git a/llama2_13b_peft/language_identification/all_results.json b/llama2_13b_peft/language_identification/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..a71316e87ce0c57f6411a371a8426ade9f64fd95
--- /dev/null
+++ b/llama2_13b_peft/language_identification/all_results.json
@@ -0,0 +1,11 @@
+{
+ "epoch": 4.58,
+ "eval_loss": 0.09783289581537247,
+ "eval_runtime": 24.1896,
+ "eval_samples_per_second": 49.608,
+ "eval_steps_per_second": 2.067,
+ "train_loss": 0.10346865890422263,
+ "train_runtime": 2388.7689,
+ "train_samples_per_second": 14.233,
+ "train_steps_per_second": 0.594
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/language_identification/eval_results.json b/llama2_13b_peft/language_identification/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab1023eb7463772d626b7cbdbbe5048bc53c1081
--- /dev/null
+++ b/llama2_13b_peft/language_identification/eval_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 4.58,
+ "eval_loss": 0.09783289581537247,
+ "eval_runtime": 24.1896,
+ "eval_samples_per_second": 49.608,
+ "eval_steps_per_second": 2.067
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/language_identification/special_tokens_map.json b/llama2_13b_peft/language_identification/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/llama2_13b_peft/language_identification/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/llama2_13b_peft/language_identification/tokenizer.model b/llama2_13b_peft/language_identification/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/llama2_13b_peft/language_identification/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/llama2_13b_peft/language_identification/tokenizer_config.json b/llama2_13b_peft/language_identification/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a40266f39e5b5fed14de34710d35eb9e98d6bdad
--- /dev/null
+++ b/llama2_13b_peft/language_identification/tokenizer_config.json
@@ -0,0 +1,45 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "split_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false
+}
diff --git a/llama2_13b_peft/language_identification/train_results.json b/llama2_13b_peft/language_identification/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff0f5a09e5ce508de2db73d9553a35686dceb000
--- /dev/null
+++ b/llama2_13b_peft/language_identification/train_results.json
@@ -0,0 +1,7 @@
+{
+ "epoch": 4.58,
+ "train_loss": 0.10346865890422263,
+ "train_runtime": 2388.7689,
+ "train_samples_per_second": 14.233,
+ "train_steps_per_second": 0.594
+}
\ No newline at end of file
diff --git a/llama2_13b_peft/language_identification/trainer_log.jsonl b/llama2_13b_peft/language_identification/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..5b041425134064214d56c133f06e1fb4c7c6b565
--- /dev/null
+++ b/llama2_13b_peft/language_identification/trainer_log.jsonl
@@ -0,0 +1,145 @@
+{"current_steps": 10, "total_steps": 1420, "loss": 3.2947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.04, "percentage": 0.7, "elapsed_time": "0:00:16", "remaining_time": "0:38:45"}
+{"current_steps": 20, "total_steps": 1420, "loss": 0.4521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.07, "percentage": 1.41, "elapsed_time": "0:00:32", "remaining_time": "0:38:26"}
+{"current_steps": 30, "total_steps": 1420, "loss": 0.3511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004999370587356267, "epoch": 0.11, "percentage": 2.11, "elapsed_time": "0:00:51", "remaining_time": "0:39:55"}
+{"current_steps": 40, "total_steps": 1420, "loss": 0.3116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004997482666353287, "epoch": 0.14, "percentage": 2.82, "elapsed_time": "0:01:08", "remaining_time": "0:39:25"}
+{"current_steps": 50, "total_steps": 1420, "loss": 0.3047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000499433718761614, "epoch": 0.18, "percentage": 3.52, "elapsed_time": "0:01:27", "remaining_time": "0:40:11"}
+{"current_steps": 60, "total_steps": 1420, "loss": 0.3014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004989935734988098, "epoch": 0.21, "percentage": 4.23, "elapsed_time": "0:01:40", "remaining_time": "0:38:02"}
+{"current_steps": 70, "total_steps": 1420, "loss": 0.3067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004984280524733107, "epoch": 0.25, "percentage": 4.93, "elapsed_time": "0:01:56", "remaining_time": "0:37:27"}
+{"current_steps": 80, "total_steps": 1420, "loss": 0.2718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004977374404419837, "epoch": 0.28, "percentage": 5.63, "elapsed_time": "0:02:11", "remaining_time": "0:36:37"}
+{"current_steps": 90, "total_steps": 1420, "loss": 0.2911, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004969220851487844, "epoch": 0.32, "percentage": 6.34, "elapsed_time": "0:02:29", "remaining_time": "0:36:48"}
+{"current_steps": 100, "total_steps": 1420, "loss": 0.2391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004959823971496574, "epoch": 0.35, "percentage": 7.04, "elapsed_time": "0:02:52", "remaining_time": "0:37:50"}
+{"current_steps": 100, "total_steps": 1420, "loss": null, "eval_loss": 0.2733969986438751, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.35, "percentage": 7.04, "elapsed_time": "0:02:52", "remaining_time": "0:37:50"}
+{"current_steps": 110, "total_steps": 1420, "loss": 0.2392, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004949188496058089, "epoch": 0.39, "percentage": 7.75, "elapsed_time": "0:03:33", "remaining_time": "0:42:17"}
+{"current_steps": 120, "total_steps": 1420, "loss": 0.2487, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004937319780454559, "epoch": 0.42, "percentage": 8.45, "elapsed_time": "0:03:48", "remaining_time": "0:41:14"}
+{"current_steps": 130, "total_steps": 1420, "loss": 0.2517, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004924223800941717, "epoch": 0.46, "percentage": 9.15, "elapsed_time": "0:04:01", "remaining_time": "0:39:55"}
+{"current_steps": 140, "total_steps": 1420, "loss": 0.2427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004909907151739633, "epoch": 0.49, "percentage": 9.86, "elapsed_time": "0:04:20", "remaining_time": "0:39:37"}
+{"current_steps": 150, "total_steps": 1420, "loss": 0.2285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004894377041712326, "epoch": 0.53, "percentage": 10.56, "elapsed_time": "0:04:34", "remaining_time": "0:38:47"}
+{"current_steps": 160, "total_steps": 1420, "loss": 0.2427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004877641290737884, "epoch": 0.56, "percentage": 11.27, "elapsed_time": "0:04:48", "remaining_time": "0:37:49"}
+{"current_steps": 170, "total_steps": 1420, "loss": 0.2571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004859708325770919, "epoch": 0.6, "percentage": 11.97, "elapsed_time": "0:05:01", "remaining_time": "0:37:00"}
+{"current_steps": 180, "total_steps": 1420, "loss": 0.2053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004840587176599343, "epoch": 0.63, "percentage": 12.68, "elapsed_time": "0:05:15", "remaining_time": "0:36:10"}
+{"current_steps": 190, "total_steps": 1420, "loss": 0.196, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00048202874712975977, "epoch": 0.67, "percentage": 13.38, "elapsed_time": "0:05:28", "remaining_time": "0:35:24"}
+{"current_steps": 200, "total_steps": 1420, "loss": 0.253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004798819431378627, "epoch": 0.7, "percentage": 14.08, "elapsed_time": "0:05:46", "remaining_time": "0:35:12"}
+{"current_steps": 200, "total_steps": 1420, "loss": null, "eval_loss": 0.1845243126153946, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7, "percentage": 14.08, "elapsed_time": "0:05:46", "remaining_time": "0:35:12"}
+{"current_steps": 210, "total_steps": 1420, "loss": 0.2324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000477619386664704, "epoch": 0.74, "percentage": 14.79, "elapsed_time": "0:06:26", "remaining_time": "0:37:04"}
+{"current_steps": 220, "total_steps": 1420, "loss": 0.1872, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047524221697560476, "epoch": 0.77, "percentage": 15.49, "elapsed_time": "0:06:46", "remaining_time": "0:36:57"}
+{"current_steps": 230, "total_steps": 1420, "loss": 0.1989, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047275163104709196, "epoch": 0.81, "percentage": 16.2, "elapsed_time": "0:07:02", "remaining_time": "0:36:25"}
+{"current_steps": 240, "total_steps": 1420, "loss": 0.1772, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004701488829641845, "epoch": 0.85, "percentage": 16.9, "elapsed_time": "0:07:15", "remaining_time": "0:35:42"}
+{"current_steps": 250, "total_steps": 1420, "loss": 0.1787, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004674352832889239, "epoch": 0.88, "percentage": 17.61, "elapsed_time": "0:07:29", "remaining_time": "0:35:02"}
+{"current_steps": 260, "total_steps": 1420, "loss": 0.2275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004646121984004665, "epoch": 0.92, "percentage": 18.31, "elapsed_time": "0:07:42", "remaining_time": "0:34:25"}
+{"current_steps": 270, "total_steps": 1420, "loss": 0.1851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046168104980707104, "epoch": 0.95, "percentage": 19.01, "elapsed_time": "0:07:56", "remaining_time": "0:33:48"}
+{"current_steps": 280, "total_steps": 1420, "loss": 0.175, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045864331343032565, "epoch": 0.99, "percentage": 19.72, "elapsed_time": "0:08:11", "remaining_time": "0:33:20"}
+{"current_steps": 290, "total_steps": 1420, "loss": 0.1318, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00045550051886197754, "epoch": 1.02, "percentage": 20.42, "elapsed_time": "0:08:40", "remaining_time": "0:33:46"}
+{"current_steps": 300, "total_steps": 1420, "loss": 0.1018, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004522542485937369, "epoch": 1.06, "percentage": 21.13, "elapsed_time": "0:08:56", "remaining_time": "0:33:21"}
+{"current_steps": 300, "total_steps": 1420, "loss": null, "eval_loss": 0.16419845819473267, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.06, "percentage": 21.13, "elapsed_time": "0:08:56", "remaining_time": "0:33:21"}
+{"current_steps": 310, "total_steps": 1420, "loss": 0.1007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044890613722044524, "epoch": 1.09, "percentage": 21.83, "elapsed_time": "0:09:33", "remaining_time": "0:34:12"}
+{"current_steps": 320, "total_steps": 1420, "loss": 0.0995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004454578706170075, "epoch": 1.13, "percentage": 22.54, "elapsed_time": "0:09:48", "remaining_time": "0:33:41"}
+{"current_steps": 330, "total_steps": 1420, "loss": 0.1006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044191118508950277, "epoch": 1.16, "percentage": 23.24, "elapsed_time": "0:10:03", "remaining_time": "0:33:12"}
+{"current_steps": 340, "total_steps": 1420, "loss": 0.1178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00043826786650090276, "epoch": 1.2, "percentage": 23.94, "elapsed_time": "0:10:19", "remaining_time": "0:32:47"}
+{"current_steps": 350, "total_steps": 1420, "loss": 0.1043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004345297493718352, "epoch": 1.23, "percentage": 24.65, "elapsed_time": "0:10:33", "remaining_time": "0:32:16"}
+{"current_steps": 360, "total_steps": 1420, "loss": 0.1286, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004306987159568479, "epoch": 1.27, "percentage": 25.35, "elapsed_time": "0:10:53", "remaining_time": "0:32:03"}
+{"current_steps": 370, "total_steps": 1420, "loss": 0.1059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00042677669529663686, "epoch": 1.3, "percentage": 26.06, "elapsed_time": "0:11:16", "remaining_time": "0:31:59"}
+{"current_steps": 380, "total_steps": 1420, "loss": 0.1135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004227656622467162, "epoch": 1.34, "percentage": 26.76, "elapsed_time": "0:11:30", "remaining_time": "0:31:30"}
+{"current_steps": 390, "total_steps": 1420, "loss": 0.0773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00041866763648301864, "epoch": 1.37, "percentage": 27.46, "elapsed_time": "0:11:46", "remaining_time": "0:31:04"}
+{"current_steps": 400, "total_steps": 1420, "loss": 0.0807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004144846814849282, "epoch": 1.41, "percentage": 28.17, "elapsed_time": "0:11:59", "remaining_time": "0:30:35"}
+{"current_steps": 400, "total_steps": 1420, "loss": null, "eval_loss": 0.16061989963054657, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.41, "percentage": 28.17, "elapsed_time": "0:11:59", "remaining_time": "0:30:35"}
+{"current_steps": 410, "total_steps": 1420, "loss": 0.1182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000410218903496256, "epoch": 1.44, "percentage": 28.87, "elapsed_time": "0:12:39", "remaining_time": "0:31:11"}
+{"current_steps": 420, "total_steps": 1420, "loss": 0.0807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004058724504646834, "epoch": 1.48, "percentage": 29.58, "elapsed_time": "0:12:54", "remaining_time": "0:30:44"}
+{"current_steps": 430, "total_steps": 1420, "loss": 0.0807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000401447510960205, "epoch": 1.51, "percentage": 30.28, "elapsed_time": "0:13:11", "remaining_time": "0:30:21"}
+{"current_steps": 440, "total_steps": 1420, "loss": 0.0929, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003969463130731183, "epoch": 1.55, "percentage": 30.99, "elapsed_time": "0:13:24", "remaining_time": "0:29:52"}
+{"current_steps": 450, "total_steps": 1420, "loss": 0.0874, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000392371123292113, "epoch": 1.58, "percentage": 31.69, "elapsed_time": "0:13:38", "remaining_time": "0:29:23"}
+{"current_steps": 460, "total_steps": 1420, "loss": 0.0932, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003877242453630256, "epoch": 1.62, "percentage": 32.39, "elapsed_time": "0:13:57", "remaining_time": "0:29:07"}
+{"current_steps": 470, "total_steps": 1420, "loss": 0.0973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00038300801912883415, "epoch": 1.65, "percentage": 33.1, "elapsed_time": "0:14:13", "remaining_time": "0:28:44"}
+{"current_steps": 480, "total_steps": 1420, "loss": 0.0864, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037822481935147656, "epoch": 1.69, "percentage": 33.8, "elapsed_time": "0:14:29", "remaining_time": "0:28:23"}
+{"current_steps": 490, "total_steps": 1420, "loss": 0.1081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003733770545160867, "epoch": 1.73, "percentage": 34.51, "elapsed_time": "0:14:46", "remaining_time": "0:28:03"}
+{"current_steps": 500, "total_steps": 1420, "loss": 0.0721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00036846716561824967, "epoch": 1.76, "percentage": 35.21, "elapsed_time": "0:15:03", "remaining_time": "0:27:43"}
+{"current_steps": 500, "total_steps": 1420, "loss": null, "eval_loss": 0.11214859038591385, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.76, "percentage": 35.21, "elapsed_time": "0:15:03", "remaining_time": "0:27:43"}
+{"current_steps": 510, "total_steps": 1420, "loss": 0.0784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00036349762493488667, "epoch": 1.8, "percentage": 35.92, "elapsed_time": "0:15:41", "remaining_time": "0:28:00"}
+{"current_steps": 520, "total_steps": 1420, "loss": 0.0942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00035847093477938953, "epoch": 1.83, "percentage": 36.62, "elapsed_time": "0:15:55", "remaining_time": "0:27:33"}
+{"current_steps": 530, "total_steps": 1420, "loss": 0.0612, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003533896262416302, "epoch": 1.87, "percentage": 37.32, "elapsed_time": "0:16:13", "remaining_time": "0:27:15"}
+{"current_steps": 540, "total_steps": 1420, "loss": 0.0714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003482562579134809, "epoch": 1.9, "percentage": 38.03, "elapsed_time": "0:16:28", "remaining_time": "0:26:51"}
+{"current_steps": 550, "total_steps": 1420, "loss": 0.06, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003430734146004863, "epoch": 1.94, "percentage": 38.73, "elapsed_time": "0:16:41", "remaining_time": "0:26:23"}
+{"current_steps": 560, "total_steps": 1420, "loss": 0.0635, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003378437060203357, "epoch": 1.97, "percentage": 39.44, "elapsed_time": "0:17:02", "remaining_time": "0:26:09"}
+{"current_steps": 570, "total_steps": 1420, "loss": 0.0609, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00033256976548879183, "epoch": 2.01, "percentage": 40.14, "elapsed_time": "0:17:23", "remaining_time": "0:25:55"}
+{"current_steps": 580, "total_steps": 1420, "loss": 0.0235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00032725424859373687, "epoch": 2.04, "percentage": 40.85, "elapsed_time": "0:17:43", "remaining_time": "0:25:40"}
+{"current_steps": 590, "total_steps": 1420, "loss": 0.0212, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003218998318580043, "epoch": 2.08, "percentage": 41.55, "elapsed_time": "0:17:59", "remaining_time": "0:25:18"}
+{"current_steps": 600, "total_steps": 1420, "loss": 0.0415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003165092113916688, "epoch": 2.11, "percentage": 42.25, "elapsed_time": "0:18:11", "remaining_time": "0:24:51"}
+{"current_steps": 600, "total_steps": 1420, "loss": null, "eval_loss": 0.1096331924200058, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.11, "percentage": 42.25, "elapsed_time": "0:18:11", "remaining_time": "0:24:51"}
+{"current_steps": 610, "total_steps": 1420, "loss": 0.0315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003110851015344735, "epoch": 2.15, "percentage": 42.96, "elapsed_time": "0:18:47", "remaining_time": "0:24:56"}
+{"current_steps": 620, "total_steps": 1420, "loss": 0.0461, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003056302334890786, "epoch": 2.18, "percentage": 43.66, "elapsed_time": "0:19:03", "remaining_time": "0:24:35"}
+{"current_steps": 630, "total_steps": 1420, "loss": 0.0192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003001473539458182, "epoch": 2.22, "percentage": 44.37, "elapsed_time": "0:19:19", "remaining_time": "0:24:14"}
+{"current_steps": 640, "total_steps": 1420, "loss": 0.0304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002946392236996592, "epoch": 2.25, "percentage": 45.07, "elapsed_time": "0:19:32", "remaining_time": "0:23:49"}
+{"current_steps": 650, "total_steps": 1420, "loss": 0.0144, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028910861626005774, "epoch": 2.29, "percentage": 45.77, "elapsed_time": "0:19:47", "remaining_time": "0:23:27"}
+{"current_steps": 660, "total_steps": 1420, "loss": 0.0239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002835583164544139, "epoch": 2.32, "percentage": 46.48, "elapsed_time": "0:20:01", "remaining_time": "0:23:03"}
+{"current_steps": 670, "total_steps": 1420, "loss": 0.019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027799111902582696, "epoch": 2.36, "percentage": 47.18, "elapsed_time": "0:20:16", "remaining_time": "0:22:41"}
+{"current_steps": 680, "total_steps": 1420, "loss": 0.0314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002724098272258584, "epoch": 2.39, "percentage": 47.89, "elapsed_time": "0:20:35", "remaining_time": "0:22:24"}
+{"current_steps": 690, "total_steps": 1420, "loss": 0.0196, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026681725140300993, "epoch": 2.43, "percentage": 48.59, "elapsed_time": "0:20:52", "remaining_time": "0:22:04"}
+{"current_steps": 700, "total_steps": 1420, "loss": 0.0278, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026121620758762877, "epoch": 2.46, "percentage": 49.3, "elapsed_time": "0:21:06", "remaining_time": "0:21:43"}
+{"current_steps": 700, "total_steps": 1420, "loss": null, "eval_loss": 0.10080268979072571, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.46, "percentage": 49.3, "elapsed_time": "0:21:06", "remaining_time": "0:21:43"}
+{"current_steps": 710, "total_steps": 1420, "loss": 0.0176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025560951607395127, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "0:21:45", "remaining_time": "0:21:45"}
+{"current_steps": 720, "total_steps": 1420, "loss": 0.0245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 2.54, "percentage": 50.7, "elapsed_time": "0:22:03", "remaining_time": "0:21:26"}
+{"current_steps": 730, "total_steps": 1420, "loss": 0.0129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002443904839260488, "epoch": 2.57, "percentage": 51.41, "elapsed_time": "0:22:19", "remaining_time": "0:21:06"}
+{"current_steps": 740, "total_steps": 1420, "loss": 0.0248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023878379241237135, "epoch": 2.61, "percentage": 52.11, "elapsed_time": "0:22:35", "remaining_time": "0:20:45"}
+{"current_steps": 750, "total_steps": 1420, "loss": 0.0087, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002331827485969901, "epoch": 2.64, "percentage": 52.82, "elapsed_time": "0:22:53", "remaining_time": "0:20:27"}
+{"current_steps": 760, "total_steps": 1420, "loss": 0.0287, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022759017277414165, "epoch": 2.68, "percentage": 53.52, "elapsed_time": "0:23:11", "remaining_time": "0:20:08"}
+{"current_steps": 770, "total_steps": 1420, "loss": 0.0248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022200888097417305, "epoch": 2.71, "percentage": 54.23, "elapsed_time": "0:23:24", "remaining_time": "0:19:45"}
+{"current_steps": 780, "total_steps": 1420, "loss": 0.0213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002164416835455862, "epoch": 2.75, "percentage": 54.93, "elapsed_time": "0:23:36", "remaining_time": "0:19:22"}
+{"current_steps": 790, "total_steps": 1420, "loss": 0.0132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021089138373994224, "epoch": 2.78, "percentage": 55.63, "elapsed_time": "0:23:53", "remaining_time": "0:19:03"}
+{"current_steps": 800, "total_steps": 1420, "loss": 0.0142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020536077630034085, "epoch": 2.82, "percentage": 56.34, "elapsed_time": "0:24:15", "remaining_time": "0:18:48"}
+{"current_steps": 800, "total_steps": 1420, "loss": null, "eval_loss": 0.09096023440361023, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.82, "percentage": 56.34, "elapsed_time": "0:24:15", "remaining_time": "0:18:48"}
+{"current_steps": 810, "total_steps": 1420, "loss": 0.0152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019985264605418181, "epoch": 2.85, "percentage": 57.04, "elapsed_time": "0:24:52", "remaining_time": "0:18:44"}
+{"current_steps": 820, "total_steps": 1420, "loss": 0.0055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019436976651092142, "epoch": 2.89, "percentage": 57.75, "elapsed_time": "0:25:10", "remaining_time": "0:18:25"}
+{"current_steps": 830, "total_steps": 1420, "loss": 0.0245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018891489846552647, "epoch": 2.92, "percentage": 58.45, "elapsed_time": "0:25:24", "remaining_time": "0:18:04"}
+{"current_steps": 840, "total_steps": 1420, "loss": 0.0085, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018349078860833125, "epoch": 2.96, "percentage": 59.15, "elapsed_time": "0:25:40", "remaining_time": "0:17:43"}
+{"current_steps": 850, "total_steps": 1420, "loss": 0.0124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001781001681419957, "epoch": 2.99, "percentage": 59.86, "elapsed_time": "0:25:57", "remaining_time": "0:17:24"}
+{"current_steps": 860, "total_steps": 1420, "loss": 0.0087, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017274575140626317, "epoch": 3.03, "percentage": 60.56, "elapsed_time": "0:26:14", "remaining_time": "0:17:05"}
+{"current_steps": 870, "total_steps": 1420, "loss": 0.0053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016743023451120832, "epoch": 3.06, "percentage": 61.27, "elapsed_time": "0:26:28", "remaining_time": "0:16:43"}
+{"current_steps": 880, "total_steps": 1420, "loss": 0.0092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001621562939796643, "epoch": 3.1, "percentage": 61.97, "elapsed_time": "0:26:44", "remaining_time": "0:16:24"}
+{"current_steps": 890, "total_steps": 1420, "loss": 0.0019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015692658539951372, "epoch": 3.13, "percentage": 62.68, "elapsed_time": "0:26:56", "remaining_time": "0:16:02"}
+{"current_steps": 900, "total_steps": 1420, "loss": 0.0042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001517437420865191, "epoch": 3.17, "percentage": 63.38, "elapsed_time": "0:27:14", "remaining_time": "0:15:44"}
+{"current_steps": 900, "total_steps": 1420, "loss": null, "eval_loss": 0.11295218020677567, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.17, "percentage": 63.38, "elapsed_time": "0:27:14", "remaining_time": "0:15:44"}
+{"current_steps": 910, "total_steps": 1420, "loss": 0.0039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014661037375836988, "epoch": 3.2, "percentage": 64.08, "elapsed_time": "0:27:51", "remaining_time": "0:15:36"}
+{"current_steps": 920, "total_steps": 1420, "loss": 0.0147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014152906522061048, "epoch": 3.24, "percentage": 64.79, "elapsed_time": "0:28:03", "remaining_time": "0:15:15"}
+{"current_steps": 930, "total_steps": 1420, "loss": 0.0049, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013650237506511331, "epoch": 3.27, "percentage": 65.49, "elapsed_time": "0:28:28", "remaining_time": "0:15:00"}
+{"current_steps": 940, "total_steps": 1420, "loss": 0.0071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013153283438175034, "epoch": 3.31, "percentage": 66.2, "elapsed_time": "0:28:41", "remaining_time": "0:14:39"}
+{"current_steps": 950, "total_steps": 1420, "loss": 0.0009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012662294548391328, "epoch": 3.35, "percentage": 66.9, "elapsed_time": "0:28:56", "remaining_time": "0:14:19"}
+{"current_steps": 960, "total_steps": 1420, "loss": 0.0126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001217751806485235, "epoch": 3.38, "percentage": 67.61, "elapsed_time": "0:29:10", "remaining_time": "0:13:58"}
+{"current_steps": 970, "total_steps": 1420, "loss": 0.0062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011699198087116588, "epoch": 3.42, "percentage": 68.31, "elapsed_time": "0:29:26", "remaining_time": "0:13:39"}
+{"current_steps": 980, "total_steps": 1420, "loss": 0.0046, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001122757546369744, "epoch": 3.45, "percentage": 69.01, "elapsed_time": "0:29:46", "remaining_time": "0:13:22"}
+{"current_steps": 990, "total_steps": 1420, "loss": 0.003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010762887670788701, "epoch": 3.49, "percentage": 69.72, "elapsed_time": "0:30:00", "remaining_time": "0:13:02"}
+{"current_steps": 1000, "total_steps": 1420, "loss": 0.0025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010305368692688174, "epoch": 3.52, "percentage": 70.42, "elapsed_time": "0:30:15", "remaining_time": "0:12:42"}
+{"current_steps": 1000, "total_steps": 1420, "loss": null, "eval_loss": 0.09783289581537247, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.52, "percentage": 70.42, "elapsed_time": "0:30:15", "remaining_time": "0:12:42"}
+{"current_steps": 1010, "total_steps": 1420, "loss": 0.0023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.855248903979506e-05, "epoch": 3.56, "percentage": 71.13, "elapsed_time": "0:30:55", "remaining_time": "0:12:33"}
+{"current_steps": 1020, "total_steps": 1420, "loss": 0.0017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.412754953531663e-05, "epoch": 3.59, "percentage": 71.83, "elapsed_time": "0:31:09", "remaining_time": "0:12:12"}
+{"current_steps": 1030, "total_steps": 1420, "loss": 0.001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.978109650374397e-05, "epoch": 3.63, "percentage": 72.54, "elapsed_time": "0:31:22", "remaining_time": "0:11:52"}
+{"current_steps": 1040, "total_steps": 1420, "loss": 0.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.551531851507186e-05, "epoch": 3.66, "percentage": 73.24, "elapsed_time": "0:31:40", "remaining_time": "0:11:34"}
+{"current_steps": 1050, "total_steps": 1420, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.133236351698142e-05, "epoch": 3.7, "percentage": 73.94, "elapsed_time": "0:32:04", "remaining_time": "0:11:18"}
+{"current_steps": 1060, "total_steps": 1420, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.723433775328384e-05, "epoch": 3.73, "percentage": 74.65, "elapsed_time": "0:32:21", "remaining_time": "0:10:59"}
+{"current_steps": 1070, "total_steps": 1420, "loss": 0.0024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.322330470336314e-05, "epoch": 3.77, "percentage": 75.35, "elapsed_time": "0:32:37", "remaining_time": "0:10:40"}
+{"current_steps": 1080, "total_steps": 1420, "loss": 0.0012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.930128404315214e-05, "epoch": 3.8, "percentage": 76.06, "elapsed_time": "0:33:01", "remaining_time": "0:10:23"}
+{"current_steps": 1090, "total_steps": 1420, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.547025062816486e-05, "epoch": 3.84, "percentage": 76.76, "elapsed_time": "0:33:17", "remaining_time": "0:10:04"}
+{"current_steps": 1100, "total_steps": 1420, "loss": 0.0087, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.173213349909729e-05, "epoch": 3.87, "percentage": 77.46, "elapsed_time": "0:33:33", "remaining_time": "0:09:45"}
+{"current_steps": 1100, "total_steps": 1420, "loss": null, "eval_loss": 0.1108880341053009, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.87, "percentage": 77.46, "elapsed_time": "0:33:33", "remaining_time": "0:09:45"}
+{"current_steps": 1110, "total_steps": 1420, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.808881491049722e-05, "epoch": 3.91, "percentage": 78.17, "elapsed_time": "0:34:10", "remaining_time": "0:09:32"}
+{"current_steps": 1120, "total_steps": 1420, "loss": 0.0032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.454212938299255e-05, "epoch": 3.94, "percentage": 78.87, "elapsed_time": "0:34:24", "remaining_time": "0:09:12"}
+{"current_steps": 1130, "total_steps": 1420, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.109386277955477e-05, "epoch": 3.98, "percentage": 79.58, "elapsed_time": "0:34:39", "remaining_time": "0:08:53"}
+{"current_steps": 1140, "total_steps": 1420, "loss": 0.0054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7745751406263163e-05, "epoch": 4.01, "percentage": 80.28, "elapsed_time": "0:34:54", "remaining_time": "0:08:34"}
+{"current_steps": 1150, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4499481138022546e-05, "epoch": 4.05, "percentage": 80.99, "elapsed_time": "0:35:09", "remaining_time": "0:08:15"}
+{"current_steps": 1160, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.135668656967434e-05, "epoch": 4.08, "percentage": 81.69, "elapsed_time": "0:35:30", "remaining_time": "0:07:57"}
+{"current_steps": 1170, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.831895019292897e-05, "epoch": 4.12, "percentage": 82.39, "elapsed_time": "0:35:45", "remaining_time": "0:07:38"}
+{"current_steps": 1180, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5387801599533474e-05, "epoch": 4.15, "percentage": 83.1, "elapsed_time": "0:35:59", "remaining_time": "0:07:19"}
+{"current_steps": 1190, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2564716711076164e-05, "epoch": 4.19, "percentage": 83.8, "elapsed_time": "0:36:13", "remaining_time": "0:06:59"}
+{"current_steps": 1200, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.98511170358155e-05, "epoch": 4.23, "percentage": 84.51, "elapsed_time": "0:36:26", "remaining_time": "0:06:40"}
+{"current_steps": 1200, "total_steps": 1420, "loss": null, "eval_loss": 0.1119951605796814, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.23, "percentage": 84.51, "elapsed_time": "0:36:26", "remaining_time": "0:06:40"}
+{"current_steps": 1210, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7248368952908055e-05, "epoch": 4.26, "percentage": 85.21, "elapsed_time": "0:37:06", "remaining_time": "0:06:26"}
+{"current_steps": 1220, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4757783024395242e-05, "epoch": 4.3, "percentage": 85.92, "elapsed_time": "0:37:20", "remaining_time": "0:06:07"}
+{"current_steps": 1230, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2380613335296037e-05, "epoch": 4.33, "percentage": 86.62, "elapsed_time": "0:37:35", "remaining_time": "0:05:48"}
+{"current_steps": 1240, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0118056862137357e-05, "epoch": 4.37, "percentage": 87.32, "elapsed_time": "0:37:48", "remaining_time": "0:05:29"}
+{"current_steps": 1250, "total_steps": 1420, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.797125287024029e-05, "epoch": 4.4, "percentage": 88.03, "elapsed_time": "0:38:03", "remaining_time": "0:05:10"}
+{"current_steps": 1260, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.59412823400657e-05, "epoch": 4.44, "percentage": 88.73, "elapsed_time": "0:38:16", "remaining_time": "0:04:51"}
+{"current_steps": 1270, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4029167422908107e-05, "epoch": 4.47, "percentage": 89.44, "elapsed_time": "0:38:32", "remaining_time": "0:04:33"}
+{"current_steps": 1280, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2235870926211617e-05, "epoch": 4.51, "percentage": 90.14, "elapsed_time": "0:38:46", "remaining_time": "0:04:14"}
+{"current_steps": 1290, "total_steps": 1420, "loss": 0.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0562295828767388e-05, "epoch": 4.54, "percentage": 90.85, "elapsed_time": "0:39:02", "remaining_time": "0:03:56"}
+{"current_steps": 1300, "total_steps": 1420, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.00928482603669e-06, "epoch": 4.58, "percentage": 91.55, "elapsed_time": "0:39:16", "remaining_time": "0:03:37"}
+{"current_steps": 1300, "total_steps": 1420, "loss": null, "eval_loss": 0.1138623058795929, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.58, "percentage": 91.55, "elapsed_time": "0:39:16", "remaining_time": "0:03:37"}
+{"current_steps": 1300, "total_steps": 1420, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.58, "percentage": 91.55, "elapsed_time": "0:39:16", "remaining_time": "0:03:37"}
+{"current_steps": 50, "total_steps": 50, "loss": null, "eval_loss": 0.09783289581537247, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.58, "percentage": 100.0, "elapsed_time": "0:40:18", "remaining_time": "0:00:00"}
diff --git a/llama2_13b_peft/language_identification/trainer_state.json b/llama2_13b_peft/language_identification/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..60c1dadfb645a92367a813b55ae6264731c32b74
--- /dev/null
+++ b/llama2_13b_peft/language_identification/trainer_state.json
@@ -0,0 +1,1044 @@
+{
+ "best_metric": 0.09783289581537247,
+ "best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/language_identification_no_sys/checkpoint-1000",
+ "epoch": 4.577464788732394,
+ "eval_steps": 100,
+ "global_step": 1300,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.04,
+ "grad_norm": 2.212151288986206,
+ "learning_rate": 0.00025,
+ "loss": 3.2947,
+ "step": 10
+ },
+ {
+ "epoch": 0.07,
+ "grad_norm": 1.6673853397369385,
+ "learning_rate": 0.0005,
+ "loss": 0.4521,
+ "step": 20
+ },
+ {
+ "epoch": 0.11,
+ "grad_norm": 0.9916551113128662,
+ "learning_rate": 0.0004999370587356267,
+ "loss": 0.3511,
+ "step": 30
+ },
+ {
+ "epoch": 0.14,
+ "grad_norm": 1.0642786026000977,
+ "learning_rate": 0.0004997482666353287,
+ "loss": 0.3116,
+ "step": 40
+ },
+ {
+ "epoch": 0.18,
+ "grad_norm": 0.9541206955909729,
+ "learning_rate": 0.000499433718761614,
+ "loss": 0.3047,
+ "step": 50
+ },
+ {
+ "epoch": 0.21,
+ "grad_norm": 4.345221519470215,
+ "learning_rate": 0.0004989935734988098,
+ "loss": 0.3014,
+ "step": 60
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 1.1881306171417236,
+ "learning_rate": 0.0004984280524733107,
+ "loss": 0.3067,
+ "step": 70
+ },
+ {
+ "epoch": 0.28,
+ "grad_norm": 1.3669559955596924,
+ "learning_rate": 0.0004977374404419837,
+ "loss": 0.2718,
+ "step": 80
+ },
+ {
+ "epoch": 0.32,
+ "grad_norm": 0.8870218396186829,
+ "learning_rate": 0.0004969220851487844,
+ "loss": 0.2911,
+ "step": 90
+ },
+ {
+ "epoch": 0.35,
+ "grad_norm": 1.203173279762268,
+ "learning_rate": 0.0004959823971496574,
+ "loss": 0.2391,
+ "step": 100
+ },
+ {
+ "epoch": 0.35,
+ "eval_loss": 0.2733969986438751,
+ "eval_runtime": 24.2506,
+ "eval_samples_per_second": 49.483,
+ "eval_steps_per_second": 2.062,
+ "step": 100
+ },
+ {
+ "epoch": 0.39,
+ "grad_norm": 0.9478153586387634,
+ "learning_rate": 0.0004949188496058089,
+ "loss": 0.2392,
+ "step": 110
+ },
+ {
+ "epoch": 0.42,
+ "grad_norm": 1.0930349826812744,
+ "learning_rate": 0.0004937319780454559,
+ "loss": 0.2487,
+ "step": 120
+ },
+ {
+ "epoch": 0.46,
+ "grad_norm": 0.7419151067733765,
+ "learning_rate": 0.0004924223800941717,
+ "loss": 0.2517,
+ "step": 130
+ },
+ {
+ "epoch": 0.49,
+ "grad_norm": 1.363133430480957,
+ "learning_rate": 0.0004909907151739633,
+ "loss": 0.2427,
+ "step": 140
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 1.4389188289642334,
+ "learning_rate": 0.0004894377041712326,
+ "loss": 0.2285,
+ "step": 150
+ },
+ {
+ "epoch": 0.56,
+ "grad_norm": 0.647335410118103,
+ "learning_rate": 0.0004877641290737884,
+ "loss": 0.2427,
+ "step": 160
+ },
+ {
+ "epoch": 0.6,
+ "grad_norm": 0.9028637409210205,
+ "learning_rate": 0.0004859708325770919,
+ "loss": 0.2571,
+ "step": 170
+ },
+ {
+ "epoch": 0.63,
+ "grad_norm": 0.8122641444206238,
+ "learning_rate": 0.0004840587176599343,
+ "loss": 0.2053,
+ "step": 180
+ },
+ {
+ "epoch": 0.67,
+ "grad_norm": 0.7749279737472534,
+ "learning_rate": 0.00048202874712975977,
+ "loss": 0.196,
+ "step": 190
+ },
+ {
+ "epoch": 0.7,
+ "grad_norm": 2.3857262134552,
+ "learning_rate": 0.0004798819431378627,
+ "loss": 0.253,
+ "step": 200
+ },
+ {
+ "epoch": 0.7,
+ "eval_loss": 0.1845243126153946,
+ "eval_runtime": 24.3028,
+ "eval_samples_per_second": 49.377,
+ "eval_steps_per_second": 2.057,
+ "step": 200
+ },
+ {
+ "epoch": 0.74,
+ "grad_norm": 1.1752371788024902,
+ "learning_rate": 0.000477619386664704,
+ "loss": 0.2324,
+ "step": 210
+ },
+ {
+ "epoch": 0.77,
+ "grad_norm": 0.8575253486633301,
+ "learning_rate": 0.00047524221697560476,
+ "loss": 0.1872,
+ "step": 220
+ },
+ {
+ "epoch": 0.81,
+ "grad_norm": 1.3138912916183472,
+ "learning_rate": 0.00047275163104709196,
+ "loss": 0.1989,
+ "step": 230
+ },
+ {
+ "epoch": 0.85,
+ "grad_norm": 1.0306133031845093,
+ "learning_rate": 0.0004701488829641845,
+ "loss": 0.1772,
+ "step": 240
+ },
+ {
+ "epoch": 0.88,
+ "grad_norm": 1.6315710544586182,
+ "learning_rate": 0.0004674352832889239,
+ "loss": 0.1787,
+ "step": 250
+ },
+ {
+ "epoch": 0.92,
+ "grad_norm": 0.92226642370224,
+ "learning_rate": 0.0004646121984004665,
+ "loss": 0.2275,
+ "step": 260
+ },
+ {
+ "epoch": 0.95,
+ "grad_norm": 1.0631942749023438,
+ "learning_rate": 0.00046168104980707104,
+ "loss": 0.1851,
+ "step": 270
+ },
+ {
+ "epoch": 0.99,
+ "grad_norm": 1.0530717372894287,
+ "learning_rate": 0.00045864331343032565,
+ "loss": 0.175,
+ "step": 280
+ },
+ {
+ "epoch": 1.02,
+ "grad_norm": 1.407698631286621,
+ "learning_rate": 0.00045550051886197754,
+ "loss": 0.1318,
+ "step": 290
+ },
+ {
+ "epoch": 1.06,
+ "grad_norm": 0.49979475140571594,
+ "learning_rate": 0.0004522542485937369,
+ "loss": 0.1018,
+ "step": 300
+ },
+ {
+ "epoch": 1.06,
+ "eval_loss": 0.16419845819473267,
+ "eval_runtime": 24.2586,
+ "eval_samples_per_second": 49.467,
+ "eval_steps_per_second": 2.061,
+ "step": 300
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 1.2636889219284058,
+ "learning_rate": 0.00044890613722044524,
+ "loss": 0.1007,
+ "step": 310
+ },
+ {
+ "epoch": 1.13,
+ "grad_norm": 1.2611491680145264,
+ "learning_rate": 0.0004454578706170075,
+ "loss": 0.0995,
+ "step": 320
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 0.8966920375823975,
+ "learning_rate": 0.00044191118508950277,
+ "loss": 0.1006,
+ "step": 330
+ },
+ {
+ "epoch": 1.2,
+ "grad_norm": 0.42645829916000366,
+ "learning_rate": 0.00043826786650090276,
+ "loss": 0.1178,
+ "step": 340
+ },
+ {
+ "epoch": 1.23,
+ "grad_norm": 1.1280796527862549,
+ "learning_rate": 0.0004345297493718352,
+ "loss": 0.1043,
+ "step": 350
+ },
+ {
+ "epoch": 1.27,
+ "grad_norm": 1.548030972480774,
+ "learning_rate": 0.0004306987159568479,
+ "loss": 0.1286,
+ "step": 360
+ },
+ {
+ "epoch": 1.3,
+ "grad_norm": 0.8548606038093567,
+ "learning_rate": 0.00042677669529663686,
+ "loss": 0.1059,
+ "step": 370
+ },
+ {
+ "epoch": 1.34,
+ "grad_norm": 0.7643742561340332,
+ "learning_rate": 0.0004227656622467162,
+ "loss": 0.1135,
+ "step": 380
+ },
+ {
+ "epoch": 1.37,
+ "grad_norm": 0.5004750490188599,
+ "learning_rate": 0.00041866763648301864,
+ "loss": 0.0773,
+ "step": 390
+ },
+ {
+ "epoch": 1.41,
+ "grad_norm": 1.9643527269363403,
+ "learning_rate": 0.0004144846814849282,
+ "loss": 0.0807,
+ "step": 400
+ },
+ {
+ "epoch": 1.41,
+ "eval_loss": 0.16061989963054657,
+ "eval_runtime": 24.3028,
+ "eval_samples_per_second": 49.377,
+ "eval_steps_per_second": 2.057,
+ "step": 400
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 1.9150224924087524,
+ "learning_rate": 0.000410218903496256,
+ "loss": 0.1182,
+ "step": 410
+ },
+ {
+ "epoch": 1.48,
+ "grad_norm": 0.785086452960968,
+ "learning_rate": 0.0004058724504646834,
+ "loss": 0.0807,
+ "step": 420
+ },
+ {
+ "epoch": 1.51,
+ "grad_norm": 0.8900055885314941,
+ "learning_rate": 0.000401447510960205,
+ "loss": 0.0807,
+ "step": 430
+ },
+ {
+ "epoch": 1.55,
+ "grad_norm": 1.1275370121002197,
+ "learning_rate": 0.0003969463130731183,
+ "loss": 0.0929,
+ "step": 440
+ },
+ {
+ "epoch": 1.58,
+ "grad_norm": 0.9126042127609253,
+ "learning_rate": 0.000392371123292113,
+ "loss": 0.0874,
+ "step": 450
+ },
+ {
+ "epoch": 1.62,
+ "grad_norm": 0.9545108079910278,
+ "learning_rate": 0.0003877242453630256,
+ "loss": 0.0932,
+ "step": 460
+ },
+ {
+ "epoch": 1.65,
+ "grad_norm": 1.6134352684020996,
+ "learning_rate": 0.00038300801912883415,
+ "loss": 0.0973,
+ "step": 470
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 0.5426120162010193,
+ "learning_rate": 0.00037822481935147656,
+ "loss": 0.0864,
+ "step": 480
+ },
+ {
+ "epoch": 1.73,
+ "grad_norm": 1.534216046333313,
+ "learning_rate": 0.0003733770545160867,
+ "loss": 0.1081,
+ "step": 490
+ },
+ {
+ "epoch": 1.76,
+ "grad_norm": 1.4139891862869263,
+ "learning_rate": 0.00036846716561824967,
+ "loss": 0.0721,
+ "step": 500
+ },
+ {
+ "epoch": 1.76,
+ "eval_loss": 0.11214859038591385,
+ "eval_runtime": 24.3383,
+ "eval_samples_per_second": 49.305,
+ "eval_steps_per_second": 2.054,
+ "step": 500
+ },
+ {
+ "epoch": 1.8,
+ "grad_norm": 1.198859691619873,
+ "learning_rate": 0.00036349762493488667,
+ "loss": 0.0784,
+ "step": 510
+ },
+ {
+ "epoch": 1.83,
+ "grad_norm": 2.0099964141845703,
+ "learning_rate": 0.00035847093477938953,
+ "loss": 0.0942,
+ "step": 520
+ },
+ {
+ "epoch": 1.87,
+ "grad_norm": 1.5550956726074219,
+ "learning_rate": 0.0003533896262416302,
+ "loss": 0.0612,
+ "step": 530
+ },
+ {
+ "epoch": 1.9,
+ "grad_norm": 0.9073893427848816,
+ "learning_rate": 0.0003482562579134809,
+ "loss": 0.0714,
+ "step": 540
+ },
+ {
+ "epoch": 1.94,
+ "grad_norm": 0.8476139903068542,
+ "learning_rate": 0.0003430734146004863,
+ "loss": 0.06,
+ "step": 550
+ },
+ {
+ "epoch": 1.97,
+ "grad_norm": 0.3816647231578827,
+ "learning_rate": 0.0003378437060203357,
+ "loss": 0.0635,
+ "step": 560
+ },
+ {
+ "epoch": 2.01,
+ "grad_norm": 0.2557448446750641,
+ "learning_rate": 0.00033256976548879183,
+ "loss": 0.0609,
+ "step": 570
+ },
+ {
+ "epoch": 2.04,
+ "grad_norm": 1.3074804544448853,
+ "learning_rate": 0.00032725424859373687,
+ "loss": 0.0235,
+ "step": 580
+ },
+ {
+ "epoch": 2.08,
+ "grad_norm": 0.13390375673770905,
+ "learning_rate": 0.0003218998318580043,
+ "loss": 0.0212,
+ "step": 590
+ },
+ {
+ "epoch": 2.11,
+ "grad_norm": 0.15385352075099945,
+ "learning_rate": 0.0003165092113916688,
+ "loss": 0.0415,
+ "step": 600
+ },
+ {
+ "epoch": 2.11,
+ "eval_loss": 0.1096331924200058,
+ "eval_runtime": 24.2511,
+ "eval_samples_per_second": 49.482,
+ "eval_steps_per_second": 2.062,
+ "step": 600
+ },
+ {
+ "epoch": 2.15,
+ "grad_norm": 1.1615819931030273,
+ "learning_rate": 0.0003110851015344735,
+ "loss": 0.0315,
+ "step": 610
+ },
+ {
+ "epoch": 2.18,
+ "grad_norm": 0.7269354462623596,
+ "learning_rate": 0.0003056302334890786,
+ "loss": 0.0461,
+ "step": 620
+ },
+ {
+ "epoch": 2.22,
+ "grad_norm": 0.2715390920639038,
+ "learning_rate": 0.0003001473539458182,
+ "loss": 0.0192,
+ "step": 630
+ },
+ {
+ "epoch": 2.25,
+ "grad_norm": 0.33742788434028625,
+ "learning_rate": 0.0002946392236996592,
+ "loss": 0.0304,
+ "step": 640
+ },
+ {
+ "epoch": 2.29,
+ "grad_norm": 0.2518526017665863,
+ "learning_rate": 0.00028910861626005774,
+ "loss": 0.0144,
+ "step": 650
+ },
+ {
+ "epoch": 2.32,
+ "grad_norm": 1.1775550842285156,
+ "learning_rate": 0.0002835583164544139,
+ "loss": 0.0239,
+ "step": 660
+ },
+ {
+ "epoch": 2.36,
+ "grad_norm": 1.4929524660110474,
+ "learning_rate": 0.00027799111902582696,
+ "loss": 0.019,
+ "step": 670
+ },
+ {
+ "epoch": 2.39,
+ "grad_norm": 0.1920006275177002,
+ "learning_rate": 0.0002724098272258584,
+ "loss": 0.0314,
+ "step": 680
+ },
+ {
+ "epoch": 2.43,
+ "grad_norm": 0.5932295918464661,
+ "learning_rate": 0.00026681725140300993,
+ "loss": 0.0196,
+ "step": 690
+ },
+ {
+ "epoch": 2.46,
+ "grad_norm": 0.8955658078193665,
+ "learning_rate": 0.00026121620758762877,
+ "loss": 0.0278,
+ "step": 700
+ },
+ {
+ "epoch": 2.46,
+ "eval_loss": 0.10080268979072571,
+ "eval_runtime": 24.2686,
+ "eval_samples_per_second": 49.447,
+ "eval_steps_per_second": 2.06,
+ "step": 700
+ },
+ {
+ "epoch": 2.5,
+ "grad_norm": 0.32239094376564026,
+ "learning_rate": 0.00025560951607395127,
+ "loss": 0.0176,
+ "step": 710
+ },
+ {
+ "epoch": 2.54,
+ "grad_norm": 0.15149308741092682,
+ "learning_rate": 0.00025,
+ "loss": 0.0245,
+ "step": 720
+ },
+ {
+ "epoch": 2.57,
+ "grad_norm": 0.2539712190628052,
+ "learning_rate": 0.0002443904839260488,
+ "loss": 0.0129,
+ "step": 730
+ },
+ {
+ "epoch": 2.61,
+ "grad_norm": 0.15594834089279175,
+ "learning_rate": 0.00023878379241237135,
+ "loss": 0.0248,
+ "step": 740
+ },
+ {
+ "epoch": 2.64,
+ "grad_norm": 0.1686088889837265,
+ "learning_rate": 0.0002331827485969901,
+ "loss": 0.0087,
+ "step": 750
+ },
+ {
+ "epoch": 2.68,
+ "grad_norm": 0.5635623931884766,
+ "learning_rate": 0.00022759017277414165,
+ "loss": 0.0287,
+ "step": 760
+ },
+ {
+ "epoch": 2.71,
+ "grad_norm": 0.09592404216527939,
+ "learning_rate": 0.00022200888097417305,
+ "loss": 0.0248,
+ "step": 770
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 0.5159811973571777,
+ "learning_rate": 0.0002164416835455862,
+ "loss": 0.0213,
+ "step": 780
+ },
+ {
+ "epoch": 2.78,
+ "grad_norm": 0.067528136074543,
+ "learning_rate": 0.00021089138373994224,
+ "loss": 0.0132,
+ "step": 790
+ },
+ {
+ "epoch": 2.82,
+ "grad_norm": 0.3488612771034241,
+ "learning_rate": 0.00020536077630034085,
+ "loss": 0.0142,
+ "step": 800
+ },
+ {
+ "epoch": 2.82,
+ "eval_loss": 0.09096023440361023,
+ "eval_runtime": 24.2886,
+ "eval_samples_per_second": 49.406,
+ "eval_steps_per_second": 2.059,
+ "step": 800
+ },
+ {
+ "epoch": 2.85,
+ "grad_norm": 0.5690057873725891,
+ "learning_rate": 0.00019985264605418181,
+ "loss": 0.0152,
+ "step": 810
+ },
+ {
+ "epoch": 2.89,
+ "grad_norm": 0.028505289927124977,
+ "learning_rate": 0.00019436976651092142,
+ "loss": 0.0055,
+ "step": 820
+ },
+ {
+ "epoch": 2.92,
+ "grad_norm": 0.7032138109207153,
+ "learning_rate": 0.00018891489846552647,
+ "loss": 0.0245,
+ "step": 830
+ },
+ {
+ "epoch": 2.96,
+ "grad_norm": 0.09572404623031616,
+ "learning_rate": 0.00018349078860833125,
+ "loss": 0.0085,
+ "step": 840
+ },
+ {
+ "epoch": 2.99,
+ "grad_norm": 0.038319505751132965,
+ "learning_rate": 0.0001781001681419957,
+ "loss": 0.0124,
+ "step": 850
+ },
+ {
+ "epoch": 3.03,
+ "grad_norm": 0.017241811379790306,
+ "learning_rate": 0.00017274575140626317,
+ "loss": 0.0087,
+ "step": 860
+ },
+ {
+ "epoch": 3.06,
+ "grad_norm": 0.00901174359023571,
+ "learning_rate": 0.00016743023451120832,
+ "loss": 0.0053,
+ "step": 870
+ },
+ {
+ "epoch": 3.1,
+ "grad_norm": 0.08782738447189331,
+ "learning_rate": 0.0001621562939796643,
+ "loss": 0.0092,
+ "step": 880
+ },
+ {
+ "epoch": 3.13,
+ "grad_norm": 0.05415625125169754,
+ "learning_rate": 0.00015692658539951372,
+ "loss": 0.0019,
+ "step": 890
+ },
+ {
+ "epoch": 3.17,
+ "grad_norm": 1.1505556106567383,
+ "learning_rate": 0.0001517437420865191,
+ "loss": 0.0042,
+ "step": 900
+ },
+ {
+ "epoch": 3.17,
+ "eval_loss": 0.11295218020677567,
+ "eval_runtime": 24.2906,
+ "eval_samples_per_second": 49.402,
+ "eval_steps_per_second": 2.058,
+ "step": 900
+ },
+ {
+ "epoch": 3.2,
+ "grad_norm": 0.006730707362294197,
+ "learning_rate": 0.00014661037375836988,
+ "loss": 0.0039,
+ "step": 910
+ },
+ {
+ "epoch": 3.24,
+ "grad_norm": 0.053513217717409134,
+ "learning_rate": 0.00014152906522061048,
+ "loss": 0.0147,
+ "step": 920
+ },
+ {
+ "epoch": 3.27,
+ "grad_norm": 0.0446440726518631,
+ "learning_rate": 0.00013650237506511331,
+ "loss": 0.0049,
+ "step": 930
+ },
+ {
+ "epoch": 3.31,
+ "grad_norm": 0.007526729255914688,
+ "learning_rate": 0.00013153283438175034,
+ "loss": 0.0071,
+ "step": 940
+ },
+ {
+ "epoch": 3.35,
+ "grad_norm": 0.007718957960605621,
+ "learning_rate": 0.00012662294548391328,
+ "loss": 0.0009,
+ "step": 950
+ },
+ {
+ "epoch": 3.38,
+ "grad_norm": 0.7277163863182068,
+ "learning_rate": 0.0001217751806485235,
+ "loss": 0.0126,
+ "step": 960
+ },
+ {
+ "epoch": 3.42,
+ "grad_norm": 0.013046162202954292,
+ "learning_rate": 0.00011699198087116588,
+ "loss": 0.0062,
+ "step": 970
+ },
+ {
+ "epoch": 3.45,
+ "grad_norm": 0.01276946347206831,
+ "learning_rate": 0.0001122757546369744,
+ "loss": 0.0046,
+ "step": 980
+ },
+ {
+ "epoch": 3.49,
+ "grad_norm": 0.21583452820777893,
+ "learning_rate": 0.00010762887670788701,
+ "loss": 0.003,
+ "step": 990
+ },
+ {
+ "epoch": 3.52,
+ "grad_norm": 0.026241082698106766,
+ "learning_rate": 0.00010305368692688174,
+ "loss": 0.0025,
+ "step": 1000
+ },
+ {
+ "epoch": 3.52,
+ "eval_loss": 0.09783289581537247,
+ "eval_runtime": 24.315,
+ "eval_samples_per_second": 49.352,
+ "eval_steps_per_second": 2.056,
+ "step": 1000
+ },
+ {
+ "epoch": 3.56,
+ "grad_norm": 0.08409489691257477,
+ "learning_rate": 9.855248903979506e-05,
+ "loss": 0.0023,
+ "step": 1010
+ },
+ {
+ "epoch": 3.59,
+ "grad_norm": 0.30051106214523315,
+ "learning_rate": 9.412754953531663e-05,
+ "loss": 0.0017,
+ "step": 1020
+ },
+ {
+ "epoch": 3.63,
+ "grad_norm": 0.01539202407002449,
+ "learning_rate": 8.978109650374397e-05,
+ "loss": 0.001,
+ "step": 1030
+ },
+ {
+ "epoch": 3.66,
+ "grad_norm": 0.0011260408209636807,
+ "learning_rate": 8.551531851507186e-05,
+ "loss": 0.0015,
+ "step": 1040
+ },
+ {
+ "epoch": 3.7,
+ "grad_norm": 0.011008994653820992,
+ "learning_rate": 8.133236351698142e-05,
+ "loss": 0.0007,
+ "step": 1050
+ },
+ {
+ "epoch": 3.73,
+ "grad_norm": 0.01506808027625084,
+ "learning_rate": 7.723433775328384e-05,
+ "loss": 0.0004,
+ "step": 1060
+ },
+ {
+ "epoch": 3.77,
+ "grad_norm": 0.5517930388450623,
+ "learning_rate": 7.322330470336314e-05,
+ "loss": 0.0024,
+ "step": 1070
+ },
+ {
+ "epoch": 3.8,
+ "grad_norm": 0.15247488021850586,
+ "learning_rate": 6.930128404315214e-05,
+ "loss": 0.0012,
+ "step": 1080
+ },
+ {
+ "epoch": 3.84,
+ "grad_norm": 0.001158914645202458,
+ "learning_rate": 6.547025062816486e-05,
+ "loss": 0.0004,
+ "step": 1090
+ },
+ {
+ "epoch": 3.87,
+ "grad_norm": 0.002445521531626582,
+ "learning_rate": 6.173213349909729e-05,
+ "loss": 0.0087,
+ "step": 1100
+ },
+ {
+ "epoch": 3.87,
+ "eval_loss": 0.1108880341053009,
+ "eval_runtime": 24.301,
+ "eval_samples_per_second": 49.381,
+ "eval_steps_per_second": 2.058,
+ "step": 1100
+ },
+ {
+ "epoch": 3.91,
+ "grad_norm": 0.5591037273406982,
+ "learning_rate": 5.808881491049722e-05,
+ "loss": 0.0007,
+ "step": 1110
+ },
+ {
+ "epoch": 3.94,
+ "grad_norm": 0.01642187125980854,
+ "learning_rate": 5.454212938299255e-05,
+ "loss": 0.0032,
+ "step": 1120
+ },
+ {
+ "epoch": 3.98,
+ "grad_norm": 0.04142434522509575,
+ "learning_rate": 5.109386277955477e-05,
+ "loss": 0.0016,
+ "step": 1130
+ },
+ {
+ "epoch": 4.01,
+ "grad_norm": 0.004027165938168764,
+ "learning_rate": 4.7745751406263163e-05,
+ "loss": 0.0054,
+ "step": 1140
+ },
+ {
+ "epoch": 4.05,
+ "grad_norm": 0.0009935923153534532,
+ "learning_rate": 4.4499481138022546e-05,
+ "loss": 0.0001,
+ "step": 1150
+ },
+ {
+ "epoch": 4.08,
+ "grad_norm": 0.0011846484849229455,
+ "learning_rate": 4.135668656967434e-05,
+ "loss": 0.0002,
+ "step": 1160
+ },
+ {
+ "epoch": 4.12,
+ "grad_norm": 0.010172044858336449,
+ "learning_rate": 3.831895019292897e-05,
+ "loss": 0.0001,
+ "step": 1170
+ },
+ {
+ "epoch": 4.15,
+ "grad_norm": 0.0008480555843561888,
+ "learning_rate": 3.5387801599533474e-05,
+ "loss": 0.0001,
+ "step": 1180
+ },
+ {
+ "epoch": 4.19,
+ "grad_norm": 0.0006466006161645055,
+ "learning_rate": 3.2564716711076164e-05,
+ "loss": 0.0002,
+ "step": 1190
+ },
+ {
+ "epoch": 4.23,
+ "grad_norm": 0.003692232072353363,
+ "learning_rate": 2.98511170358155e-05,
+ "loss": 0.0002,
+ "step": 1200
+ },
+ {
+ "epoch": 4.23,
+ "eval_loss": 0.1119951605796814,
+ "eval_runtime": 24.2963,
+ "eval_samples_per_second": 49.39,
+ "eval_steps_per_second": 2.058,
+ "step": 1200
+ },
+ {
+ "epoch": 4.26,
+ "grad_norm": 0.014719746075570583,
+ "learning_rate": 2.7248368952908055e-05,
+ "loss": 0.0002,
+ "step": 1210
+ },
+ {
+ "epoch": 4.3,
+ "grad_norm": 0.0012403527507558465,
+ "learning_rate": 2.4757783024395242e-05,
+ "loss": 0.0002,
+ "step": 1220
+ },
+ {
+ "epoch": 4.33,
+ "grad_norm": 0.0006684574182145298,
+ "learning_rate": 2.2380613335296037e-05,
+ "loss": 0.0002,
+ "step": 1230
+ },
+ {
+ "epoch": 4.37,
+ "grad_norm": 0.0013737869448959827,
+ "learning_rate": 2.0118056862137357e-05,
+ "loss": 0.0002,
+ "step": 1240
+ },
+ {
+ "epoch": 4.4,
+ "grad_norm": 0.037718772888183594,
+ "learning_rate": 1.797125287024029e-05,
+ "loss": 0.0002,
+ "step": 1250
+ },
+ {
+ "epoch": 4.44,
+ "grad_norm": 0.0014982918510213494,
+ "learning_rate": 1.59412823400657e-05,
+ "loss": 0.0001,
+ "step": 1260
+ },
+ {
+ "epoch": 4.47,
+ "grad_norm": 0.0025713511276990175,
+ "learning_rate": 1.4029167422908107e-05,
+ "loss": 0.0001,
+ "step": 1270
+ },
+ {
+ "epoch": 4.51,
+ "grad_norm": 0.0010034763254225254,
+ "learning_rate": 1.2235870926211617e-05,
+ "loss": 0.0001,
+ "step": 1280
+ },
+ {
+ "epoch": 4.54,
+ "grad_norm": 0.053933627903461456,
+ "learning_rate": 1.0562295828767388e-05,
+ "loss": 0.0004,
+ "step": 1290
+ },
+ {
+ "epoch": 4.58,
+ "grad_norm": 0.0021008604671806097,
+ "learning_rate": 9.00928482603669e-06,
+ "loss": 0.0001,
+ "step": 1300
+ },
+ {
+ "epoch": 4.58,
+ "eval_loss": 0.1138623058795929,
+ "eval_runtime": 24.3162,
+ "eval_samples_per_second": 49.35,
+ "eval_steps_per_second": 2.056,
+ "step": 1300
+ },
+ {
+ "epoch": 4.58,
+ "step": 1300,
+ "total_flos": 8.824408957758996e+17,
+ "train_loss": 0.10346865890422263,
+ "train_runtime": 2388.7689,
+ "train_samples_per_second": 14.233,
+ "train_steps_per_second": 0.594
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 1420,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 500,
+ "total_flos": 8.824408957758996e+17,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/llama2_13b_peft/language_identification/training_args.bin b/llama2_13b_peft/language_identification/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b5d3b89781de39c70be60cc1b16a3c9f79c375ab
--- /dev/null
+++ b/llama2_13b_peft/language_identification/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5031b421dc96423f7d02d16051e98f33bbf995840fd303ac70dc2e97bdc8358c
+size 5112
diff --git a/llama2_13b_peft/language_identification/training_eval_loss.png b/llama2_13b_peft/language_identification/training_eval_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..b9758428ed9541348184f65f1154cbf2d904d7f2
Binary files /dev/null and b/llama2_13b_peft/language_identification/training_eval_loss.png differ
diff --git a/llama2_13b_peft/language_identification/training_loss.png b/llama2_13b_peft/language_identification/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..75274bc28f6860ce7926327b051ca2ed4ac0b09a
Binary files /dev/null and b/llama2_13b_peft/language_identification/training_loss.png differ