Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the Sky-T1 dataset.
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.999043062200957,
+    "total_flos": 665025606320128.0,
+    "train_loss": 0.19090694274710512,
+    "train_runtime": 9940.2778,
+    "train_samples_per_second": 1.681,
+    "train_steps_per_second": 0.018
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2050a0b2fbead862208eeb3a27a5c9e95ae0799c0f6af89c5a496308962d2f7f
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c5acbbc70872eb86e272ad8e68b7e96c44869752c30b655e5a2d5b98ac5da9
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589c1f8fca0c13bce320267a2aa2b4f741263c376518b5e68a7c9bd456d729da
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ae75750cf04d599ecccf80c052aa751c07cb1fcb01ed687a3f744371fc75af
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a132401f7278878a43e7c9a2e1b6c9df2b7488263a484046e6752031faad2425
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b5f08fa6b3dbebaf95fc5993a2f2620e12eb04fdd9d664405e22291a207f19
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.999043062200957,
+    "total_flos": 665025606320128.0,
+    "train_loss": 0.19090694274710512,
+    "train_runtime": 9940.2778,
+    "train_samples_per_second": 1.681,
+    "train_steps_per_second": 0.018
+}

trainer_log.jsonl

@@ -0,0 +1,193 @@
+{"current_steps": 1, "total_steps": 174, "loss": 0.7736, "lr": 1.111111111111111e-06, "epoch": 0.011483253588516746, "percentage": 0.57, "elapsed_time": "0:02:16", "remaining_time": "6:32:20"}
+{"current_steps": 2, "total_steps": 174, "loss": 0.8086, "lr": 2.222222222222222e-06, "epoch": 0.022966507177033493, "percentage": 1.15, "elapsed_time": "0:04:38", "remaining_time": "6:38:40"}
+{"current_steps": 3, "total_steps": 174, "loss": 0.8393, "lr": 3.3333333333333333e-06, "epoch": 0.03444976076555024, "percentage": 1.72, "elapsed_time": "0:06:40", "remaining_time": "6:20:00"}
+{"current_steps": 4, "total_steps": 174, "loss": 0.8137, "lr": 4.444444444444444e-06, "epoch": 0.045933014354066985, "percentage": 2.3, "elapsed_time": "0:08:56", "remaining_time": "6:20:00"}
+{"current_steps": 5, "total_steps": 174, "loss": 0.7843, "lr": 5.555555555555557e-06, "epoch": 0.05741626794258373, "percentage": 2.87, "elapsed_time": "0:10:57", "remaining_time": "6:10:24"}
+{"current_steps": 6, "total_steps": 174, "loss": 0.7326, "lr": 6.666666666666667e-06, "epoch": 0.06889952153110047, "percentage": 3.45, "elapsed_time": "0:12:56", "remaining_time": "6:02:21"}
+{"current_steps": 7, "total_steps": 174, "loss": 0.7357, "lr": 7.77777777777778e-06, "epoch": 0.08038277511961722, "percentage": 4.02, "elapsed_time": "0:15:09", "remaining_time": "6:01:28"}
+{"current_steps": 8, "total_steps": 174, "loss": 0.7291, "lr": 8.888888888888888e-06, "epoch": 0.09186602870813397, "percentage": 4.6, "elapsed_time": "0:17:10", "remaining_time": "5:56:32"}
+{"current_steps": 9, "total_steps": 174, "loss": 0.7269, "lr": 1e-05, "epoch": 0.10334928229665072, "percentage": 5.17, "elapsed_time": "0:19:24", "remaining_time": "5:55:48"}
+{"current_steps": 10, "total_steps": 174, "loss": 0.6371, "lr": 1.1111111111111113e-05, "epoch": 0.11483253588516747, "percentage": 5.75, "elapsed_time": "0:21:16", "remaining_time": "5:48:51"}
+{"current_steps": 11, "total_steps": 174, "loss": 0.6625, "lr": 1.2222222222222224e-05, "epoch": 0.12631578947368421, "percentage": 6.32, "elapsed_time": "0:23:18", "remaining_time": "5:45:16"}
+{"current_steps": 12, "total_steps": 174, "loss": 0.6528, "lr": 1.3333333333333333e-05, "epoch": 0.13779904306220095, "percentage": 6.9, "elapsed_time": "0:25:29", "remaining_time": "5:44:03"}
+{"current_steps": 13, "total_steps": 174, "loss": 0.6319, "lr": 1.4444444444444446e-05, "epoch": 0.1492822966507177, "percentage": 7.47, "elapsed_time": "0:27:34", "remaining_time": "5:41:30"}
+{"current_steps": 14, "total_steps": 174, "loss": 0.6174, "lr": 1.555555555555556e-05, "epoch": 0.16076555023923444, "percentage": 8.05, "elapsed_time": "0:30:01", "remaining_time": "5:43:06"}
+{"current_steps": 15, "total_steps": 174, "loss": 0.634, "lr": 1.6666666666666667e-05, "epoch": 0.1722488038277512, "percentage": 8.62, "elapsed_time": "0:32:21", "remaining_time": "5:42:58"}
+{"current_steps": 16, "total_steps": 174, "loss": 0.6115, "lr": 1.7777777777777777e-05, "epoch": 0.18373205741626794, "percentage": 9.2, "elapsed_time": "0:34:32", "remaining_time": "5:41:09"}
+{"current_steps": 17, "total_steps": 174, "loss": 0.575, "lr": 1.888888888888889e-05, "epoch": 0.19521531100478468, "percentage": 9.77, "elapsed_time": "0:36:46", "remaining_time": "5:39:33"}
+{"current_steps": 18, "total_steps": 174, "loss": 0.6074, "lr": 2e-05, "epoch": 0.20669856459330144, "percentage": 10.34, "elapsed_time": "0:39:11", "remaining_time": "5:39:35"}
+{"current_steps": 1, "total_steps": 174, "loss": 0.7736, "lr": 1.111111111111111e-06, "epoch": 0.011483253588516746, "percentage": 0.57, "elapsed_time": "0:02:15", "remaining_time": "6:32:03"}
+{"current_steps": 2, "total_steps": 174, "loss": 0.8086, "lr": 2.222222222222222e-06, "epoch": 0.022966507177033493, "percentage": 1.15, "elapsed_time": "0:04:37", "remaining_time": "6:38:26"}
+{"current_steps": 3, "total_steps": 174, "loss": 0.8392, "lr": 3.3333333333333333e-06, "epoch": 0.03444976076555024, "percentage": 1.72, "elapsed_time": "0:06:39", "remaining_time": "6:19:32"}
+{"current_steps": 4, "total_steps": 174, "loss": 0.8138, "lr": 4.444444444444444e-06, "epoch": 0.045933014354066985, "percentage": 2.3, "elapsed_time": "0:08:56", "remaining_time": "6:20:01"}
+{"current_steps": 5, "total_steps": 174, "loss": 0.7843, "lr": 5.555555555555557e-06, "epoch": 0.05741626794258373, "percentage": 2.87, "elapsed_time": "0:10:57", "remaining_time": "6:10:32"}
+{"current_steps": 6, "total_steps": 174, "loss": 0.7329, "lr": 6.666666666666667e-06, "epoch": 0.06889952153110047, "percentage": 3.45, "elapsed_time": "0:12:57", "remaining_time": "6:02:39"}
+{"current_steps": 7, "total_steps": 174, "loss": 0.7359, "lr": 7.77777777777778e-06, "epoch": 0.08038277511961722, "percentage": 4.02, "elapsed_time": "0:15:10", "remaining_time": "6:01:51"}
+{"current_steps": 8, "total_steps": 174, "loss": 0.7293, "lr": 8.888888888888888e-06, "epoch": 0.09186602870813397, "percentage": 4.6, "elapsed_time": "0:17:11", "remaining_time": "5:56:50"}
+{"current_steps": 9, "total_steps": 174, "loss": 0.7275, "lr": 1e-05, "epoch": 0.10334928229665072, "percentage": 5.17, "elapsed_time": "0:19:25", "remaining_time": "5:55:58"}
+{"current_steps": 10, "total_steps": 174, "loss": 0.6375, "lr": 1.1111111111111113e-05, "epoch": 0.11483253588516747, "percentage": 5.75, "elapsed_time": "0:21:16", "remaining_time": "5:48:59"}
+{"current_steps": 11, "total_steps": 174, "loss": 0.6625, "lr": 1.2222222222222224e-05, "epoch": 0.12631578947368421, "percentage": 6.32, "elapsed_time": "0:23:18", "remaining_time": "5:45:24"}
+{"current_steps": 12, "total_steps": 174, "loss": 0.6525, "lr": 1.3333333333333333e-05, "epoch": 0.13779904306220095, "percentage": 6.9, "elapsed_time": "0:25:29", "remaining_time": "5:44:09"}
+{"current_steps": 13, "total_steps": 174, "loss": 0.6317, "lr": 1.4444444444444446e-05, "epoch": 0.1492822966507177, "percentage": 7.47, "elapsed_time": "0:27:35", "remaining_time": "5:41:41"}
+{"current_steps": 14, "total_steps": 174, "loss": 0.6169, "lr": 1.555555555555556e-05, "epoch": 0.16076555023923444, "percentage": 8.05, "elapsed_time": "0:30:02", "remaining_time": "5:43:19"}
+{"current_steps": 15, "total_steps": 174, "loss": 0.634, "lr": 1.6666666666666667e-05, "epoch": 0.1722488038277512, "percentage": 8.62, "elapsed_time": "0:32:22", "remaining_time": "5:43:10"}
+{"current_steps": 16, "total_steps": 174, "loss": 0.6116, "lr": 1.7777777777777777e-05, "epoch": 0.18373205741626794, "percentage": 9.2, "elapsed_time": "0:34:33", "remaining_time": "5:41:20"}
+{"current_steps": 17, "total_steps": 174, "loss": 0.5749, "lr": 1.888888888888889e-05, "epoch": 0.19521531100478468, "percentage": 9.77, "elapsed_time": "0:36:47", "remaining_time": "5:39:47"}
+{"current_steps": 18, "total_steps": 174, "loss": 0.6072, "lr": 2e-05, "epoch": 0.20669856459330144, "percentage": 10.34, "elapsed_time": "0:39:12", "remaining_time": "5:39:49"}
+{"current_steps": 19, "total_steps": 174, "loss": 0.5816, "lr": 1.9997972289848505e-05, "epoch": 0.21818181818181817, "percentage": 10.92, "elapsed_time": "0:41:28", "remaining_time": "5:38:19"}
+{"current_steps": 20, "total_steps": 174, "loss": 0.5943, "lr": 1.9991889981715696e-05, "epoch": 0.22966507177033493, "percentage": 11.49, "elapsed_time": "0:43:49", "remaining_time": "5:37:29"}
+{"current_steps": 21, "total_steps": 174, "loss": 0.575, "lr": 1.9981755542233175e-05, "epoch": 0.24114832535885167, "percentage": 12.07, "elapsed_time": "0:46:14", "remaining_time": "5:36:52"}
+{"current_steps": 22, "total_steps": 174, "loss": 0.5681, "lr": 1.9967573081342103e-05, "epoch": 0.25263157894736843, "percentage": 12.64, "elapsed_time": "0:48:15", "remaining_time": "5:33:23"}
+{"current_steps": 23, "total_steps": 174, "loss": 0.5618, "lr": 1.9949348350626456e-05, "epoch": 0.2641148325358852, "percentage": 13.22, "elapsed_time": "0:50:30", "remaining_time": "5:31:33"}
+{"current_steps": 24, "total_steps": 174, "loss": 0.5716, "lr": 1.992708874098054e-05, "epoch": 0.2755980861244019, "percentage": 13.79, "elapsed_time": "0:52:53", "remaining_time": "5:30:33"}
+{"current_steps": 25, "total_steps": 174, "loss": 0.5297, "lr": 1.9900803279611643e-05, "epoch": 0.28708133971291866, "percentage": 14.37, "elapsed_time": "0:54:55", "remaining_time": "5:27:20"}
+{"current_steps": 26, "total_steps": 174, "loss": 0.5666, "lr": 1.9870502626379127e-05, "epoch": 0.2985645933014354, "percentage": 14.94, "elapsed_time": "0:56:57", "remaining_time": "5:24:12"}
+{"current_steps": 27, "total_steps": 174, "loss": 0.566, "lr": 1.983619906947144e-05, "epoch": 0.31004784688995213, "percentage": 15.52, "elapsed_time": "0:58:52", "remaining_time": "5:20:31"}
+{"current_steps": 28, "total_steps": 174, "loss": 0.5577, "lr": 1.979790652042268e-05, "epoch": 0.3215311004784689, "percentage": 16.09, "elapsed_time": "1:00:54", "remaining_time": "5:17:36"}
+{"current_steps": 29, "total_steps": 174, "loss": 0.5458, "lr": 1.975564050847094e-05, "epoch": 0.33301435406698565, "percentage": 16.67, "elapsed_time": "1:03:09", "remaining_time": "5:15:47"}
+{"current_steps": 30, "total_steps": 174, "loss": 0.5787, "lr": 1.9709418174260523e-05, "epoch": 0.3444976076555024, "percentage": 17.24, "elapsed_time": "1:05:35", "remaining_time": "5:14:52"}
+{"current_steps": 31, "total_steps": 174, "loss": 0.5403, "lr": 1.9659258262890683e-05, "epoch": 0.3559808612440191, "percentage": 17.82, "elapsed_time": "1:07:50", "remaining_time": "5:12:56"}
+{"current_steps": 32, "total_steps": 174, "loss": 0.5492, "lr": 1.9605181116313725e-05, "epoch": 0.3674641148325359, "percentage": 18.39, "elapsed_time": "1:10:10", "remaining_time": "5:11:24"}
+{"current_steps": 33, "total_steps": 174, "loss": 0.5476, "lr": 1.954720866508546e-05, "epoch": 0.37894736842105264, "percentage": 18.97, "elapsed_time": "1:12:25", "remaining_time": "5:09:25"}
+{"current_steps": 34, "total_steps": 174, "loss": 0.5408, "lr": 1.9485364419471454e-05, "epoch": 0.39043062200956935, "percentage": 19.54, "elapsed_time": "1:14:27", "remaining_time": "5:06:35"}
+{"current_steps": 35, "total_steps": 174, "loss": 0.5641, "lr": 1.9419673459912652e-05, "epoch": 0.4019138755980861, "percentage": 20.11, "elapsed_time": "1:16:47", "remaining_time": "5:04:59"}
+{"current_steps": 36, "total_steps": 174, "loss": 0.5344, "lr": 1.9350162426854152e-05, "epoch": 0.4133971291866029, "percentage": 20.69, "elapsed_time": "1:19:13", "remaining_time": "5:03:40"}
+{"current_steps": 37, "total_steps": 174, "loss": 0.5271, "lr": 1.927685950994143e-05, "epoch": 0.42488038277511964, "percentage": 21.26, "elapsed_time": "1:21:20", "remaining_time": "5:01:09"}
+{"current_steps": 38, "total_steps": 174, "loss": 0.5352, "lr": 1.9199794436588244e-05, "epoch": 0.43636363636363634, "percentage": 21.84, "elapsed_time": "1:23:47", "remaining_time": "4:59:54"}
+{"current_steps": 39, "total_steps": 174, "loss": 0.5478, "lr": 1.91189984599209e-05, "epoch": 0.4478468899521531, "percentage": 22.41, "elapsed_time": "1:26:06", "remaining_time": "4:58:02"}
+{"current_steps": 40, "total_steps": 174, "loss": 0.5072, "lr": 1.9034504346103825e-05, "epoch": 0.45933014354066987, "percentage": 22.99, "elapsed_time": "1:28:17", "remaining_time": "4:55:46"}
+{"current_steps": 41, "total_steps": 174, "loss": 0.504, "lr": 1.8946346361051474e-05, "epoch": 0.47081339712918663, "percentage": 23.56, "elapsed_time": "1:30:25", "remaining_time": "4:53:19"}
+{"current_steps": 42, "total_steps": 174, "loss": 0.5447, "lr": 1.8854560256532098e-05, "epoch": 0.48229665071770333, "percentage": 24.14, "elapsed_time": "1:33:09", "remaining_time": "4:52:46"}
+{"current_steps": 43, "total_steps": 174, "loss": 0.5217, "lr": 1.875918325566888e-05, "epoch": 0.4937799043062201, "percentage": 24.71, "elapsed_time": "1:35:14", "remaining_time": "4:50:10"}
+{"current_steps": 44, "total_steps": 174, "loss": 0.5311, "lr": 1.866025403784439e-05, "epoch": 0.5052631578947369, "percentage": 25.29, "elapsed_time": "1:37:45", "remaining_time": "4:48:48"}
+{"current_steps": 45, "total_steps": 174, "loss": 0.5305, "lr": 1.8557812723014476e-05, "epoch": 0.5167464114832536, "percentage": 25.86, "elapsed_time": "1:40:06", "remaining_time": "4:46:58"}
+{"current_steps": 46, "total_steps": 174, "loss": 0.5425, "lr": 1.845190085543795e-05, "epoch": 0.5282296650717704, "percentage": 26.44, "elapsed_time": "1:42:15", "remaining_time": "4:44:32"}
+{"current_steps": 47, "total_steps": 174, "loss": 0.5122, "lr": 1.8342561386828613e-05, "epoch": 0.539712918660287, "percentage": 27.01, "elapsed_time": "1:44:31", "remaining_time": "4:42:25"}
+{"current_steps": 48, "total_steps": 174, "loss": 0.4986, "lr": 1.8229838658936566e-05, "epoch": 0.5511961722488038, "percentage": 27.59, "elapsed_time": "1:46:51", "remaining_time": "4:40:31"}
+{"current_steps": 49, "total_steps": 174, "loss": 0.5448, "lr": 1.811377838556573e-05, "epoch": 0.5626794258373206, "percentage": 28.16, "elapsed_time": "1:49:05", "remaining_time": "4:38:18"}
+{"current_steps": 50, "total_steps": 174, "loss": 0.522, "lr": 1.7994427634035016e-05, "epoch": 0.5741626794258373, "percentage": 28.74, "elapsed_time": "1:51:18", "remaining_time": "4:36:02"}
+{"current_steps": 51, "total_steps": 174, "loss": 0.5182, "lr": 1.7871834806090502e-05, "epoch": 0.5856459330143541, "percentage": 29.31, "elapsed_time": "1:54:52", "remaining_time": "4:37:02"}
+{"current_steps": 52, "total_steps": 174, "loss": 0.5173, "lr": 1.7746049618276545e-05, "epoch": 0.5971291866028708, "percentage": 29.89, "elapsed_time": "1:57:06", "remaining_time": "4:34:44"}
+{"current_steps": 53, "total_steps": 174, "loss": 0.5267, "lr": 1.761712308177359e-05, "epoch": 0.6086124401913876, "percentage": 30.46, "elapsed_time": "1:59:23", "remaining_time": "4:32:33"}
+{"current_steps": 54, "total_steps": 174, "loss": 0.5243, "lr": 1.7485107481711014e-05, "epoch": 0.6200956937799043, "percentage": 31.03, "elapsed_time": "2:01:51", "remaining_time": "4:30:47"}
+{"current_steps": 55, "total_steps": 174, "loss": 0.5193, "lr": 1.7350056355963287e-05, "epoch": 0.631578947368421, "percentage": 31.61, "elapsed_time": "2:03:35", "remaining_time": "4:27:24"}
+{"current_steps": 56, "total_steps": 174, "loss": 0.5029, "lr": 1.7212024473438145e-05, "epoch": 0.6430622009569378, "percentage": 32.18, "elapsed_time": "2:06:06", "remaining_time": "4:25:44"}
+{"current_steps": 57, "total_steps": 174, "loss": 0.5131, "lr": 1.7071067811865477e-05, "epoch": 0.6545454545454545, "percentage": 32.76, "elapsed_time": "2:08:25", "remaining_time": "4:23:35"}
+{"current_steps": 58, "total_steps": 174, "loss": 0.4912, "lr": 1.6927243535095995e-05, "epoch": 0.6660287081339713, "percentage": 33.33, "elapsed_time": "2:10:45", "remaining_time": "4:21:30"}
+{"current_steps": 59, "total_steps": 174, "loss": 0.5124, "lr": 1.678060996991891e-05, "epoch": 0.6775119617224881, "percentage": 33.91, "elapsed_time": "2:12:42", "remaining_time": "4:18:40"}
+{"current_steps": 60, "total_steps": 174, "loss": 0.5132, "lr": 1.6631226582407954e-05, "epoch": 0.6889952153110048, "percentage": 34.48, "elapsed_time": "2:15:15", "remaining_time": "4:16:59"}
+{"current_steps": 61, "total_steps": 174, "loss": 0.5119, "lr": 1.647915395380539e-05, "epoch": 0.7004784688995215, "percentage": 35.06, "elapsed_time": "2:17:25", "remaining_time": "4:14:34"}
+{"current_steps": 62, "total_steps": 174, "loss": 0.5055, "lr": 1.6324453755953772e-05, "epoch": 0.7119617224880382, "percentage": 35.63, "elapsed_time": "2:19:31", "remaining_time": "4:12:02"}
+{"current_steps": 63, "total_steps": 174, "loss": 0.5216, "lr": 1.6167188726285433e-05, "epoch": 0.723444976076555, "percentage": 36.21, "elapsed_time": "2:21:38", "remaining_time": "4:09:33"}
+{"current_steps": 64, "total_steps": 174, "loss": 0.5087, "lr": 1.600742264237979e-05, "epoch": 0.7349282296650718, "percentage": 36.78, "elapsed_time": "2:23:40", "remaining_time": "4:06:56"}
+{"current_steps": 65, "total_steps": 174, "loss": 0.5093, "lr": 1.584522029609889e-05, "epoch": 0.7464114832535885, "percentage": 37.36, "elapsed_time": "2:25:54", "remaining_time": "4:04:40"}
+{"current_steps": 66, "total_steps": 174, "loss": 0.4954, "lr": 1.568064746731156e-05, "epoch": 0.7578947368421053, "percentage": 37.93, "elapsed_time": "2:27:58", "remaining_time": "4:02:08"}
+{"current_steps": 67, "total_steps": 174, "loss": 0.4881, "lr": 1.551377089721692e-05, "epoch": 0.769377990430622, "percentage": 38.51, "elapsed_time": "2:30:25", "remaining_time": "4:00:13"}
+{"current_steps": 68, "total_steps": 174, "loss": 0.4741, "lr": 1.5344658261278013e-05, "epoch": 0.7808612440191387, "percentage": 39.08, "elapsed_time": "2:32:17", "remaining_time": "3:57:24"}
+{"current_steps": 69, "total_steps": 174, "loss": 0.5133, "lr": 1.5173378141776569e-05, "epoch": 0.7923444976076555, "percentage": 39.66, "elapsed_time": "2:34:25", "remaining_time": "3:54:59"}
+{"current_steps": 70, "total_steps": 174, "loss": 0.4843, "lr": 1.5000000000000002e-05, "epoch": 0.8038277511961722, "percentage": 40.23, "elapsed_time": "2:36:24", "remaining_time": "3:52:22"}
+{"current_steps": 71, "total_steps": 174, "loss": 0.4956, "lr": 1.4824594148071936e-05, "epoch": 0.815311004784689, "percentage": 40.8, "elapsed_time": "2:38:33", "remaining_time": "3:50:00"}
+{"current_steps": 72, "total_steps": 174, "loss": 0.5161, "lr": 1.4647231720437687e-05, "epoch": 0.8267942583732057, "percentage": 41.38, "elapsed_time": "2:40:47", "remaining_time": "3:47:47"}
+{"current_steps": 73, "total_steps": 174, "loss": 0.4991, "lr": 1.4467984645016259e-05, "epoch": 0.8382775119617225, "percentage": 41.95, "elapsed_time": "2:42:58", "remaining_time": "3:45:29"}
+{"current_steps": 74, "total_steps": 174, "loss": 0.4991, "lr": 1.4286925614030542e-05, "epoch": 0.8497607655502393, "percentage": 42.53, "elapsed_time": "2:45:11", "remaining_time": "3:43:14"}
+{"current_steps": 75, "total_steps": 174, "loss": 0.4778, "lr": 1.410412805452757e-05, "epoch": 0.861244019138756, "percentage": 43.1, "elapsed_time": "2:47:03", "remaining_time": "3:40:30"}
+{"current_steps": 76, "total_steps": 174, "loss": 0.5201, "lr": 1.3919666098600753e-05, "epoch": 0.8727272727272727, "percentage": 43.68, "elapsed_time": "2:49:23", "remaining_time": "3:38:25"}
+{"current_steps": 77, "total_steps": 174, "loss": 0.4943, "lr": 1.3733614553326211e-05, "epoch": 0.8842105263157894, "percentage": 44.25, "elapsed_time": "2:51:36", "remaining_time": "3:36:10"}
+{"current_steps": 78, "total_steps": 174, "loss": 0.5022, "lr": 1.3546048870425356e-05, "epoch": 0.8956937799043062, "percentage": 44.83, "elapsed_time": "2:53:53", "remaining_time": "3:34:01"}
+{"current_steps": 79, "total_steps": 174, "loss": 0.482, "lr": 1.335704511566605e-05, "epoch": 0.907177033492823, "percentage": 45.4, "elapsed_time": "2:56:10", "remaining_time": "3:31:51"}
+{"current_steps": 80, "total_steps": 174, "loss": 0.4803, "lr": 1.3166679938014728e-05, "epoch": 0.9186602870813397, "percentage": 45.98, "elapsed_time": "2:58:31", "remaining_time": "3:29:46"}
+{"current_steps": 81, "total_steps": 174, "loss": 0.4895, "lr": 1.297503053855203e-05, "epoch": 0.9301435406698565, "percentage": 46.55, "elapsed_time": "3:00:41", "remaining_time": "3:27:27"}
+{"current_steps": 82, "total_steps": 174, "loss": 0.5031, "lr": 1.2782174639164528e-05, "epoch": 0.9416267942583733, "percentage": 47.13, "elapsed_time": "3:03:08", "remaining_time": "3:25:28"}
+{"current_steps": 83, "total_steps": 174, "loss": 0.4931, "lr": 1.2588190451025209e-05, "epoch": 0.9531100478468899, "percentage": 47.7, "elapsed_time": "3:05:35", "remaining_time": "3:23:28"}
+{"current_steps": 84, "total_steps": 174, "loss": 0.4923, "lr": 1.2393156642875579e-05, "epoch": 0.9645933014354067, "percentage": 48.28, "elapsed_time": "3:08:09", "remaining_time": "3:21:35"}
+{"current_steps": 85, "total_steps": 174, "loss": 0.5252, "lr": 1.2197152309122173e-05, "epoch": 0.9760765550239234, "percentage": 48.85, "elapsed_time": "3:10:11", "remaining_time": "3:19:08"}
+{"current_steps": 86, "total_steps": 174, "loss": 0.4903, "lr": 1.2000256937760446e-05, "epoch": 0.9875598086124402, "percentage": 49.43, "elapsed_time": "3:12:23", "remaining_time": "3:16:51"}
+{"current_steps": 87, "total_steps": 174, "loss": 0.4879, "lr": 1.180255037813906e-05, "epoch": 0.999043062200957, "percentage": 50.0, "elapsed_time": "3:14:28", "remaining_time": "3:14:28"}
+{"current_steps": 88, "total_steps": 174, "loss": 0.7722, "lr": 1.1604112808577603e-05, "epoch": 1.0105263157894737, "percentage": 50.57, "elapsed_time": "3:16:44", "remaining_time": "3:12:15"}
+{"current_steps": 89, "total_steps": 174, "loss": 0.4322, "lr": 1.1405024703850929e-05, "epoch": 1.0220095693779905, "percentage": 51.15, "elapsed_time": "3:18:38", "remaining_time": "3:09:43"}
+{"current_steps": 90, "total_steps": 174, "loss": 0.4452, "lr": 1.1205366802553231e-05, "epoch": 1.0334928229665072, "percentage": 51.72, "elapsed_time": "3:20:46", "remaining_time": "3:07:23"}
+{"current_steps": 91, "total_steps": 174, "loss": 0.4676, "lr": 1.1005220074355172e-05, "epoch": 1.044976076555024, "percentage": 52.3, "elapsed_time": "3:23:18", "remaining_time": "3:05:25"}
+{"current_steps": 92, "total_steps": 174, "loss": 0.4573, "lr": 1.0804665687167262e-05, "epoch": 1.0564593301435408, "percentage": 52.87, "elapsed_time": "3:25:39", "remaining_time": "3:03:17"}
+{"current_steps": 93, "total_steps": 174, "loss": 0.4608, "lr": 1.0603784974222862e-05, "epoch": 1.0679425837320573, "percentage": 53.45, "elapsed_time": "3:28:10", "remaining_time": "3:01:18"}
+{"current_steps": 94, "total_steps": 174, "loss": 0.4511, "lr": 1.0402659401094154e-05, "epoch": 1.079425837320574, "percentage": 54.02, "elapsed_time": "3:30:16", "remaining_time": "2:58:57"}
+{"current_steps": 95, "total_steps": 174, "loss": 0.4757, "lr": 1.0201370532654404e-05, "epoch": 1.0909090909090908, "percentage": 54.6, "elapsed_time": "3:32:43", "remaining_time": "2:56:53"}
+{"current_steps": 96, "total_steps": 174, "loss": 0.4764, "lr": 1e-05, "epoch": 1.1023923444976076, "percentage": 55.17, "elapsed_time": "3:34:53", "remaining_time": "2:54:36"}
+{"current_steps": 97, "total_steps": 174, "loss": 0.4183, "lr": 9.7986294673456e-06, "epoch": 1.1138755980861244, "percentage": 55.75, "elapsed_time": "3:37:08", "remaining_time": "2:52:22"}
+{"current_steps": 98, "total_steps": 174, "loss": 0.4677, "lr": 9.597340598905851e-06, "epoch": 1.1253588516746411, "percentage": 56.32, "elapsed_time": "3:39:31", "remaining_time": "2:50:14"}
+{"current_steps": 99, "total_steps": 174, "loss": 0.4345, "lr": 9.39621502577714e-06, "epoch": 1.1368421052631579, "percentage": 56.9, "elapsed_time": "3:42:14", "remaining_time": "2:48:21"}
+{"current_steps": 100, "total_steps": 174, "loss": 0.456, "lr": 9.195334312832742e-06, "epoch": 1.1483253588516746, "percentage": 57.47, "elapsed_time": "3:44:23", "remaining_time": "2:46:02"}
+{"current_steps": 101, "total_steps": 174, "loss": 0.4653, "lr": 8.994779925644832e-06, "epoch": 1.1607655502392344, "percentage": 58.05, "elapsed_time": "0:02:10", "remaining_time": "0:01:34"}
+{"current_steps": 102, "total_steps": 174, "loss": 0.4663, "lr": 8.79463319744677e-06, "epoch": 1.1722488038277512, "percentage": 58.62, "elapsed_time": "0:04:20", "remaining_time": "0:03:03"}
+{"current_steps": 103, "total_steps": 174, "loss": 0.4598, "lr": 8.594975296149076e-06, "epoch": 1.183732057416268, "percentage": 59.2, "elapsed_time": "0:06:48", "remaining_time": "0:04:41"}
+{"current_steps": 104, "total_steps": 174, "loss": 0.4603, "lr": 8.395887191422397e-06, "epoch": 1.1952153110047847, "percentage": 59.77, "elapsed_time": "0:09:07", "remaining_time": "0:06:08"}
+{"current_steps": 105, "total_steps": 174, "loss": 0.4691, "lr": 8.197449621860944e-06, "epoch": 1.2066985645933015, "percentage": 60.34, "elapsed_time": "0:11:12", "remaining_time": "0:07:21"}
+{"current_steps": 106, "total_steps": 174, "loss": 0.4363, "lr": 7.999743062239557e-06, "epoch": 1.2181818181818183, "percentage": 60.92, "elapsed_time": "0:13:44", "remaining_time": "0:08:49"}
+{"current_steps": 107, "total_steps": 174, "loss": 0.4507, "lr": 7.802847690877832e-06, "epoch": 1.229665071770335, "percentage": 61.49, "elapsed_time": "0:15:51", "remaining_time": "0:09:55"}
+{"current_steps": 108, "total_steps": 174, "loss": 0.4537, "lr": 7.606843357124426e-06, "epoch": 1.2411483253588518, "percentage": 62.07, "elapsed_time": "0:17:56", "remaining_time": "0:10:57"}
+{"current_steps": 109, "total_steps": 174, "loss": 0.4358, "lr": 7.411809548974792e-06, "epoch": 1.2526315789473683, "percentage": 62.64, "elapsed_time": "0:19:56", "remaining_time": "0:11:53"}
+{"current_steps": 110, "total_steps": 174, "loss": 0.4394, "lr": 7.217825360835475e-06, "epoch": 1.2641148325358853, "percentage": 63.22, "elapsed_time": "0:21:51", "remaining_time": "0:12:43"}
+{"current_steps": 111, "total_steps": 174, "loss": 0.4375, "lr": 7.024969461447973e-06, "epoch": 1.2755980861244018, "percentage": 63.79, "elapsed_time": "0:23:56", "remaining_time": "0:13:35"}
+{"current_steps": 112, "total_steps": 174, "loss": 0.4508, "lr": 6.833320061985278e-06, "epoch": 1.2870813397129186, "percentage": 64.37, "elapsed_time": "0:25:58", "remaining_time": "0:14:22"}
+{"current_steps": 113, "total_steps": 174, "loss": 0.4608, "lr": 6.6429548843339554e-06, "epoch": 1.2985645933014354, "percentage": 64.94, "elapsed_time": "0:28:18", "remaining_time": "0:15:16"}
+{"current_steps": 114, "total_steps": 174, "loss": 0.4451, "lr": 6.453951129574644e-06, "epoch": 1.3100478468899521, "percentage": 65.52, "elapsed_time": "0:30:42", "remaining_time": "0:16:09"}
+{"current_steps": 115, "total_steps": 174, "loss": 0.4378, "lr": 6.266385446673791e-06, "epoch": 1.321531100478469, "percentage": 66.09, "elapsed_time": "0:32:41", "remaining_time": "0:16:46"}
+{"current_steps": 116, "total_steps": 174, "loss": 0.4443, "lr": 6.080333901399252e-06, "epoch": 1.3330143540669857, "percentage": 66.67, "elapsed_time": "0:34:45", "remaining_time": "0:17:22"}
+{"current_steps": 117, "total_steps": 174, "loss": 0.4565, "lr": 5.895871945472434e-06, "epoch": 1.3444976076555024, "percentage": 67.24, "elapsed_time": "0:36:49", "remaining_time": "0:17:56"}
+{"current_steps": 118, "total_steps": 174, "loss": 0.4305, "lr": 5.713074385969457e-06, "epoch": 1.3559808612440192, "percentage": 67.82, "elapsed_time": "0:39:07", "remaining_time": "0:18:34"}
+{"current_steps": 119, "total_steps": 174, "loss": 0.4472, "lr": 5.532015354983742e-06, "epoch": 1.367464114832536, "percentage": 68.39, "elapsed_time": "0:41:09", "remaining_time": "0:19:01"}
+{"current_steps": 120, "total_steps": 174, "loss": 0.4548, "lr": 5.352768279562315e-06, "epoch": 1.3789473684210527, "percentage": 68.97, "elapsed_time": "0:43:38", "remaining_time": "0:19:38"}
+{"current_steps": 121, "total_steps": 174, "loss": 0.4401, "lr": 5.175405851928068e-06, "epoch": 1.3904306220095695, "percentage": 69.54, "elapsed_time": "0:45:47", "remaining_time": "0:20:03"}
+{"current_steps": 122, "total_steps": 174, "loss": 0.4624, "lr": 5.000000000000003e-06, "epoch": 1.401913875598086, "percentage": 70.11, "elapsed_time": "0:47:48", "remaining_time": "0:20:22"}
+{"current_steps": 123, "total_steps": 174, "loss": 0.4388, "lr": 4.826621858223431e-06, "epoch": 1.413397129186603, "percentage": 70.69, "elapsed_time": "0:49:49", "remaining_time": "0:20:39"}
+{"current_steps": 124, "total_steps": 174, "loss": 0.4546, "lr": 4.655341738721989e-06, "epoch": 1.4248803827751195, "percentage": 71.26, "elapsed_time": "0:52:12", "remaining_time": "0:21:03"}
+{"current_steps": 125, "total_steps": 174, "loss": 0.4561, "lr": 4.486229102783084e-06, "epoch": 1.4363636363636363, "percentage": 71.84, "elapsed_time": "0:54:08", "remaining_time": "0:21:13"}
+{"current_steps": 126, "total_steps": 174, "loss": 0.4445, "lr": 4.319352532688444e-06, "epoch": 1.447846889952153, "percentage": 72.41, "elapsed_time": "0:56:15", "remaining_time": "0:21:25"}
+{"current_steps": 127, "total_steps": 174, "loss": 0.4821, "lr": 4.154779703901114e-06, "epoch": 1.4593301435406698, "percentage": 72.99, "elapsed_time": "0:58:16", "remaining_time": "0:21:33"}
+{"current_steps": 128, "total_steps": 174, "loss": 0.4571, "lr": 3.99257735762021e-06, "epoch": 1.4708133971291866, "percentage": 73.56, "elapsed_time": "1:00:30", "remaining_time": "0:21:44"}
+{"current_steps": 129, "total_steps": 174, "loss": 0.4514, "lr": 3.832811273714569e-06, "epoch": 1.4822966507177033, "percentage": 74.14, "elapsed_time": "1:02:57", "remaining_time": "0:21:57"}
+{"current_steps": 130, "total_steps": 174, "loss": 0.4405, "lr": 3.6755462440462288e-06, "epoch": 1.49377990430622, "percentage": 74.71, "elapsed_time": "1:04:58", "remaining_time": "0:21:59"}
+{"current_steps": 131, "total_steps": 174, "loss": 0.4676, "lr": 3.5208460461946136e-06, "epoch": 1.5052631578947369, "percentage": 75.29, "elapsed_time": "1:07:17", "remaining_time": "0:22:05"}
+{"current_steps": 132, "total_steps": 174, "loss": 0.4422, "lr": 3.3687734175920505e-06, "epoch": 1.5167464114832536, "percentage": 75.86, "elapsed_time": "1:09:20", "remaining_time": "0:22:03"}
+{"current_steps": 133, "total_steps": 174, "loss": 0.4287, "lr": 3.2193900300810908e-06, "epoch": 1.5282296650717704, "percentage": 76.44, "elapsed_time": "1:11:24", "remaining_time": "0:22:00"}
+{"current_steps": 134, "total_steps": 174, "loss": 0.4107, "lr": 3.0727564649040066e-06, "epoch": 1.5397129186602871, "percentage": 77.01, "elapsed_time": "1:13:51", "remaining_time": "0:22:02"}
+{"current_steps": 135, "total_steps": 174, "loss": 0.4542, "lr": 2.9289321881345257e-06, "epoch": 1.5511961722488037, "percentage": 77.59, "elapsed_time": "1:15:42", "remaining_time": "0:21:52"}
+{"current_steps": 136, "total_steps": 174, "loss": 0.4471, "lr": 2.7879755265618558e-06, "epoch": 1.5626794258373207, "percentage": 78.16, "elapsed_time": "1:17:47", "remaining_time": "0:21:44"}
+{"current_steps": 137, "total_steps": 174, "loss": 0.4452, "lr": 2.6499436440367165e-06, "epoch": 1.5741626794258372, "percentage": 78.74, "elapsed_time": "1:20:09", "remaining_time": "0:21:38"}
+{"current_steps": 138, "total_steps": 174, "loss": 0.4369, "lr": 2.514892518288988e-06, "epoch": 1.5856459330143542, "percentage": 79.31, "elapsed_time": "1:22:23", "remaining_time": "0:21:29"}
+{"current_steps": 139, "total_steps": 174, "loss": 0.4419, "lr": 2.382876918226409e-06, "epoch": 1.5971291866028707, "percentage": 79.89, "elapsed_time": "1:24:26", "remaining_time": "0:21:15"}
+{"current_steps": 140, "total_steps": 174, "loss": 0.4455, "lr": 2.2539503817234553e-06, "epoch": 1.6086124401913877, "percentage": 80.46, "elapsed_time": "1:26:29", "remaining_time": "0:21:00"}
+{"current_steps": 141, "total_steps": 174, "loss": 0.4511, "lr": 2.1281651939094996e-06, "epoch": 1.6200956937799043, "percentage": 81.03, "elapsed_time": "1:28:51", "remaining_time": "0:20:47"}
+{"current_steps": 142, "total_steps": 174, "loss": 0.4452, "lr": 2.0055723659649907e-06, "epoch": 1.631578947368421, "percentage": 81.61, "elapsed_time": "1:30:51", "remaining_time": "0:20:28"}
+{"current_steps": 143, "total_steps": 174, "loss": 0.4596, "lr": 1.8862216144342692e-06, "epoch": 1.6430622009569378, "percentage": 82.18, "elapsed_time": "1:33:15", "remaining_time": "0:20:13"}
+{"current_steps": 144, "total_steps": 174, "loss": 0.4721, "lr": 1.7701613410634367e-06, "epoch": 1.6545454545454545, "percentage": 82.76, "elapsed_time": "1:35:42", "remaining_time": "0:19:56"}
+{"current_steps": 145, "total_steps": 174, "loss": 0.4669, "lr": 1.6574386131713872e-06, "epoch": 1.6660287081339713, "percentage": 83.33, "elapsed_time": "1:38:16", "remaining_time": "0:19:39"}
+{"current_steps": 146, "total_steps": 174, "loss": 0.484, "lr": 1.5480991445620541e-06, "epoch": 1.677511961722488, "percentage": 83.91, "elapsed_time": "1:40:38", "remaining_time": "0:19:17"}
+{"current_steps": 147, "total_steps": 174, "loss": 0.4429, "lr": 1.4421872769855262e-06, "epoch": 1.6889952153110048, "percentage": 84.48, "elapsed_time": "1:42:39", "remaining_time": "0:18:51"}
+{"current_steps": 148, "total_steps": 174, "loss": 0.4636, "lr": 1.339745962155613e-06, "epoch": 1.7004784688995214, "percentage": 85.06, "elapsed_time": "1:45:14", "remaining_time": "0:18:29"}
+{"current_steps": 149, "total_steps": 174, "loss": 0.4015, "lr": 1.2408167443311215e-06, "epoch": 1.7119617224880384, "percentage": 85.63, "elapsed_time": "1:47:14", "remaining_time": "0:17:59"}
+{"current_steps": 150, "total_steps": 174, "loss": 0.4508, "lr": 1.1454397434679022e-06, "epoch": 1.723444976076555, "percentage": 86.21, "elapsed_time": "1:49:30", "remaining_time": "0:17:31"}
+{"current_steps": 151, "total_steps": 174, "loss": 0.4316, "lr": 1.0536536389485275e-06, "epoch": 1.7349282296650719, "percentage": 86.78, "elapsed_time": "1:53:11", "remaining_time": "0:17:14"}
+{"current_steps": 152, "total_steps": 174, "loss": 0.4347, "lr": 9.65495653896179e-07, "epoch": 1.7464114832535884, "percentage": 87.36, "elapsed_time": "1:55:24", "remaining_time": "0:16:42"}
+{"current_steps": 153, "total_steps": 174, "loss": 0.4579, "lr": 8.810015400790994e-07, "epoch": 1.7578947368421054, "percentage": 87.93, "elapsed_time": "1:57:47", "remaining_time": "0:16:10"}
+{"current_steps": 154, "total_steps": 174, "loss": 0.4148, "lr": 8.002055634117578e-07, "epoch": 1.769377990430622, "percentage": 88.51, "elapsed_time": "1:59:55", "remaining_time": "0:15:34"}
+{"current_steps": 155, "total_steps": 174, "loss": 0.4443, "lr": 7.231404900585714e-07, "epoch": 1.7808612440191387, "percentage": 89.08, "elapsed_time": "2:01:46", "remaining_time": "0:14:55"}
+{"current_steps": 156, "total_steps": 174, "loss": 0.4583, "lr": 6.498375731458529e-07, "epoch": 1.7923444976076555, "percentage": 89.66, "elapsed_time": "2:03:55", "remaining_time": "0:14:17"}
+{"current_steps": 157, "total_steps": 174, "loss": 0.4448, "lr": 5.803265400873514e-07, "epoch": 1.8038277511961722, "percentage": 90.23, "elapsed_time": "2:06:16", "remaining_time": "0:13:40"}
+{"current_steps": 158, "total_steps": 174, "loss": 0.4488, "lr": 5.146355805285452e-07, "epoch": 1.815311004784689, "percentage": 90.8, "elapsed_time": "2:08:55", "remaining_time": "0:13:03"}
+{"current_steps": 159, "total_steps": 174, "loss": 0.4448, "lr": 4.5279133491454406e-07, "epoch": 1.8267942583732057, "percentage": 91.38, "elapsed_time": "2:11:08", "remaining_time": "0:12:22"}
+{"current_steps": 160, "total_steps": 174, "loss": 0.4608, "lr": 3.9481888368627764e-07, "epoch": 1.8382775119617225, "percentage": 91.95, "elapsed_time": "2:13:33", "remaining_time": "0:11:41"}
+{"current_steps": 161, "total_steps": 174, "loss": 0.4344, "lr": 3.4074173710931804e-07, "epoch": 1.8497607655502393, "percentage": 92.53, "elapsed_time": "2:15:46", "remaining_time": "0:10:57"}
+{"current_steps": 162, "total_steps": 174, "loss": 0.4483, "lr": 2.905818257394799e-07, "epoch": 1.861244019138756, "percentage": 93.1, "elapsed_time": "2:18:05", "remaining_time": "0:10:13"}
+{"current_steps": 163, "total_steps": 174, "loss": 0.4689, "lr": 2.4435949152906144e-07, "epoch": 1.8727272727272726, "percentage": 93.68, "elapsed_time": "2:20:04", "remaining_time": "0:09:27"}
+{"current_steps": 164, "total_steps": 174, "loss": 0.4479, "lr": 2.0209347957732328e-07, "epoch": 1.8842105263157896, "percentage": 94.25, "elapsed_time": "2:22:06", "remaining_time": "0:08:39"}
+{"current_steps": 165, "total_steps": 174, "loss": 0.4329, "lr": 1.6380093052856482e-07, "epoch": 1.895693779904306, "percentage": 94.83, "elapsed_time": "2:24:01", "remaining_time": "0:07:51"}
+{"current_steps": 166, "total_steps": 174, "loss": 0.4493, "lr": 1.2949737362087156e-07, "epoch": 1.907177033492823, "percentage": 95.4, "elapsed_time": "2:26:34", "remaining_time": "0:07:03"}
+{"current_steps": 167, "total_steps": 174, "loss": 0.445, "lr": 9.919672038835926e-08, "epoch": 1.9186602870813396, "percentage": 95.98, "elapsed_time": "2:28:41", "remaining_time": "0:06:13"}
+{"current_steps": 168, "total_steps": 174, "loss": 0.4704, "lr": 7.291125901946027e-08, "epoch": 1.9301435406698566, "percentage": 96.55, "elapsed_time": "2:30:34", "remaining_time": "0:05:22"}
+{"current_steps": 169, "total_steps": 174, "loss": 0.4601, "lr": 5.0651649373544276e-08, "epoch": 1.9416267942583731, "percentage": 97.13, "elapsed_time": "2:32:50", "remaining_time": "0:04:31"}
+{"current_steps": 170, "total_steps": 174, "loss": 0.4416, "lr": 3.242691865790071e-08, "epoch": 1.95311004784689, "percentage": 97.7, "elapsed_time": "2:35:11", "remaining_time": "0:03:39"}
+{"current_steps": 171, "total_steps": 174, "loss": 0.4389, "lr": 1.824445776682504e-08, "epoch": 1.9645933014354067, "percentage": 98.28, "elapsed_time": "2:37:40", "remaining_time": "0:02:45"}
+{"current_steps": 172, "total_steps": 174, "loss": 0.4549, "lr": 8.110018284304132e-09, "epoch": 1.9760765550239234, "percentage": 98.85, "elapsed_time": "2:39:45", "remaining_time": "0:01:51"}
+{"current_steps": 173, "total_steps": 174, "loss": 0.4451, "lr": 2.0277101514987184e-09, "epoch": 1.9875598086124402, "percentage": 99.43, "elapsed_time": "2:41:48", "remaining_time": "0:00:56"}
+{"current_steps": 174, "total_steps": 174, "loss": 0.4523, "lr": 0.0, "epoch": 1.999043062200957, "percentage": 100.0, "elapsed_time": "2:44:17", "remaining_time": "0:00:00"}
+{"current_steps": 174, "total_steps": 174, "epoch": 1.999043062200957, "percentage": 100.0, "elapsed_time": "2:45:38", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1260 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.999043062200957,
+  "eval_steps": 500,
+  "global_step": 174,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 2.804490089416504,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.7736,
+      "step": 1
+    },
+    {
+      "epoch": 0.022966507177033493,
+      "grad_norm": 2.74699068069458,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.8086,
+      "step": 2
+    },
+    {
+      "epoch": 0.03444976076555024,
+      "grad_norm": 2.9466397762298584,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8392,
+      "step": 3
+    },
+    {
+      "epoch": 0.045933014354066985,
+      "grad_norm": 2.555311679840088,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.8138,
+      "step": 4
+    },
+    {
+      "epoch": 0.05741626794258373,
+      "grad_norm": 1.9726232290267944,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.7843,
+      "step": 5
+    },
+    {
+      "epoch": 0.06889952153110047,
+      "grad_norm": 3.302605628967285,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7329,
+      "step": 6
+    },
+    {
+      "epoch": 0.08038277511961722,
+      "grad_norm": 1.8911763429641724,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.7359,
+      "step": 7
+    },
+    {
+      "epoch": 0.09186602870813397,
+      "grad_norm": 1.9695310592651367,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.7293,
+      "step": 8
+    },
+    {
+      "epoch": 0.10334928229665072,
+      "grad_norm": 1.4005483388900757,
+      "learning_rate": 1e-05,
+      "loss": 0.7275,
+      "step": 9
+    },
+    {
+      "epoch": 0.11483253588516747,
+      "grad_norm": 1.3015406131744385,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.6375,
+      "step": 10
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 1.205918788909912,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 0.6625,
+      "step": 11
+    },
+    {
+      "epoch": 0.13779904306220095,
+      "grad_norm": 0.8213034868240356,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6525,
+      "step": 12
+    },
+    {
+      "epoch": 0.1492822966507177,
+      "grad_norm": 1.1025549173355103,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 0.6317,
+      "step": 13
+    },
+    {
+      "epoch": 0.16076555023923444,
+      "grad_norm": 0.956466794013977,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.6169,
+      "step": 14
+    },
+    {
+      "epoch": 0.1722488038277512,
+      "grad_norm": 1.0524718761444092,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.634,
+      "step": 15
+    },
+    {
+      "epoch": 0.18373205741626794,
+      "grad_norm": 0.7834458351135254,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.6116,
+      "step": 16
+    },
+    {
+      "epoch": 0.19521531100478468,
+      "grad_norm": 0.7513645887374878,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.5749,
+      "step": 17
+    },
+    {
+      "epoch": 0.20669856459330144,
+      "grad_norm": 0.7897821664810181,
+      "learning_rate": 2e-05,
+      "loss": 0.6072,
+      "step": 18
+    },
+    {
+      "epoch": 0.21818181818181817,
+      "grad_norm": 0.5807076096534729,
+      "learning_rate": 1.9997972289848505e-05,
+      "loss": 0.5816,
+      "step": 19
+    },
+    {
+      "epoch": 0.22966507177033493,
+      "grad_norm": 0.663065493106842,
+      "learning_rate": 1.9991889981715696e-05,
+      "loss": 0.5943,
+      "step": 20
+    },
+    {
+      "epoch": 0.24114832535885167,
+      "grad_norm": 0.5980852246284485,
+      "learning_rate": 1.9981755542233175e-05,
+      "loss": 0.575,
+      "step": 21
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.6174298524856567,
+      "learning_rate": 1.9967573081342103e-05,
+      "loss": 0.5681,
+      "step": 22
+    },
+    {
+      "epoch": 0.2641148325358852,
+      "grad_norm": 0.519263744354248,
+      "learning_rate": 1.9949348350626456e-05,
+      "loss": 0.5618,
+      "step": 23
+    },
+    {
+      "epoch": 0.2755980861244019,
+      "grad_norm": 0.5192844867706299,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 0.5716,
+      "step": 24
+    },
+    {
+      "epoch": 0.28708133971291866,
+      "grad_norm": 0.5204177498817444,
+      "learning_rate": 1.9900803279611643e-05,
+      "loss": 0.5297,
+      "step": 25
+    },
+    {
+      "epoch": 0.2985645933014354,
+      "grad_norm": 0.43173807859420776,
+      "learning_rate": 1.9870502626379127e-05,
+      "loss": 0.5666,
+      "step": 26
+    },
+    {
+      "epoch": 0.31004784688995213,
+      "grad_norm": 0.47530868649482727,
+      "learning_rate": 1.983619906947144e-05,
+      "loss": 0.566,
+      "step": 27
+    },
+    {
+      "epoch": 0.3215311004784689,
+      "grad_norm": 0.43519994616508484,
+      "learning_rate": 1.979790652042268e-05,
+      "loss": 0.5577,
+      "step": 28
+    },
+    {
+      "epoch": 0.33301435406698565,
+      "grad_norm": 0.43898147344589233,
+      "learning_rate": 1.975564050847094e-05,
+      "loss": 0.5458,
+      "step": 29
+    },
+    {
+      "epoch": 0.3444976076555024,
+      "grad_norm": 0.38831689953804016,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.5787,
+      "step": 30
+    },
+    {
+      "epoch": 0.3559808612440191,
+      "grad_norm": 0.38646361231803894,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.5403,
+      "step": 31
+    },
+    {
+      "epoch": 0.3674641148325359,
+      "grad_norm": 0.3714185655117035,
+      "learning_rate": 1.9605181116313725e-05,
+      "loss": 0.5492,
+      "step": 32
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 0.3823264539241791,
+      "learning_rate": 1.954720866508546e-05,
+      "loss": 0.5476,
+      "step": 33
+    },
+    {
+      "epoch": 0.39043062200956935,
+      "grad_norm": 0.33007943630218506,
+      "learning_rate": 1.9485364419471454e-05,
+      "loss": 0.5408,
+      "step": 34
+    },
+    {
+      "epoch": 0.4019138755980861,
+      "grad_norm": 0.39259204268455505,
+      "learning_rate": 1.9419673459912652e-05,
+      "loss": 0.5641,
+      "step": 35
+    },
+    {
+      "epoch": 0.4133971291866029,
+      "grad_norm": 0.3294496536254883,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 0.5344,
+      "step": 36
+    },
+    {
+      "epoch": 0.42488038277511964,
+      "grad_norm": 0.3135583698749542,
+      "learning_rate": 1.927685950994143e-05,
+      "loss": 0.5271,
+      "step": 37
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.33793437480926514,
+      "learning_rate": 1.9199794436588244e-05,
+      "loss": 0.5352,
+      "step": 38
+    },
+    {
+      "epoch": 0.4478468899521531,
+      "grad_norm": 0.3562823534011841,
+      "learning_rate": 1.91189984599209e-05,
+      "loss": 0.5478,
+      "step": 39
+    },
+    {
+      "epoch": 0.45933014354066987,
+      "grad_norm": 0.3568083643913269,
+      "learning_rate": 1.9034504346103825e-05,
+      "loss": 0.5072,
+      "step": 40
+    },
+    {
+      "epoch": 0.47081339712918663,
+      "grad_norm": 0.34692370891571045,
+      "learning_rate": 1.8946346361051474e-05,
+      "loss": 0.504,
+      "step": 41
+    },
+    {
+      "epoch": 0.48229665071770333,
+      "grad_norm": 0.35962024331092834,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.5447,
+      "step": 42
+    },
+    {
+      "epoch": 0.4937799043062201,
+      "grad_norm": 0.37867891788482666,
+      "learning_rate": 1.875918325566888e-05,
+      "loss": 0.5217,
+      "step": 43
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.3821343779563904,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.5311,
+      "step": 44
+    },
+    {
+      "epoch": 0.5167464114832536,
+      "grad_norm": 0.36335083842277527,
+      "learning_rate": 1.8557812723014476e-05,
+      "loss": 0.5305,
+      "step": 45
+    },
+    {
+      "epoch": 0.5282296650717704,
+      "grad_norm": 0.33280235528945923,
+      "learning_rate": 1.845190085543795e-05,
+      "loss": 0.5425,
+      "step": 46
+    },
+    {
+      "epoch": 0.539712918660287,
+      "grad_norm": 0.36008763313293457,
+      "learning_rate": 1.8342561386828613e-05,
+      "loss": 0.5122,
+      "step": 47
+    },
+    {
+      "epoch": 0.5511961722488038,
+      "grad_norm": 0.36620059609413147,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.4986,
+      "step": 48
+    },
+    {
+      "epoch": 0.5626794258373206,
+      "grad_norm": 9.159019470214844,
+      "learning_rate": 1.811377838556573e-05,
+      "loss": 0.5448,
+      "step": 49
+    },
+    {
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.47111213207244873,
+      "learning_rate": 1.7994427634035016e-05,
+      "loss": 0.522,
+      "step": 50
+    },
+    {
+      "epoch": 0.5856459330143541,
+      "grad_norm": 0.34213587641716003,
+      "learning_rate": 1.7871834806090502e-05,
+      "loss": 0.5182,
+      "step": 51
+    },
+    {
+      "epoch": 0.5971291866028708,
+      "grad_norm": 0.3735521137714386,
+      "learning_rate": 1.7746049618276545e-05,
+      "loss": 0.5173,
+      "step": 52
+    },
+    {
+      "epoch": 0.6086124401913876,
+      "grad_norm": 0.3792261481285095,
+      "learning_rate": 1.761712308177359e-05,
+      "loss": 0.5267,
+      "step": 53
+    },
+    {
+      "epoch": 0.6200956937799043,
+      "grad_norm": 0.31414318084716797,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.5243,
+      "step": 54
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.3608068525791168,
+      "learning_rate": 1.7350056355963287e-05,
+      "loss": 0.5193,
+      "step": 55
+    },
+    {
+      "epoch": 0.6430622009569378,
+      "grad_norm": 0.31694212555885315,
+      "learning_rate": 1.7212024473438145e-05,
+      "loss": 0.5029,
+      "step": 56
+    },
+    {
+      "epoch": 0.6545454545454545,
+      "grad_norm": 0.2968662679195404,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.5131,
+      "step": 57
+    },
+    {
+      "epoch": 0.6660287081339713,
+      "grad_norm": 0.3195832073688507,
+      "learning_rate": 1.6927243535095995e-05,
+      "loss": 0.4912,
+      "step": 58
+    },
+    {
+      "epoch": 0.6775119617224881,
+      "grad_norm": 0.34518277645111084,
+      "learning_rate": 1.678060996991891e-05,
+      "loss": 0.5124,
+      "step": 59
+    },
+    {
+      "epoch": 0.6889952153110048,
+      "grad_norm": 0.285602867603302,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 0.5132,
+      "step": 60
+    },
+    {
+      "epoch": 0.7004784688995215,
+      "grad_norm": 0.3201611638069153,
+      "learning_rate": 1.647915395380539e-05,
+      "loss": 0.5119,
+      "step": 61
+    },
+    {
+      "epoch": 0.7119617224880382,
+      "grad_norm": 0.3024705946445465,
+      "learning_rate": 1.6324453755953772e-05,
+      "loss": 0.5055,
+      "step": 62
+    },
+    {
+      "epoch": 0.723444976076555,
+      "grad_norm": 0.32308679819107056,
+      "learning_rate": 1.6167188726285433e-05,
+      "loss": 0.5216,
+      "step": 63
+    },
+    {
+      "epoch": 0.7349282296650718,
+      "grad_norm": 0.278341680765152,
+      "learning_rate": 1.600742264237979e-05,
+      "loss": 0.5087,
+      "step": 64
+    },
+    {
+      "epoch": 0.7464114832535885,
+      "grad_norm": 0.43393227458000183,
+      "learning_rate": 1.584522029609889e-05,
+      "loss": 0.5093,
+      "step": 65
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2864857316017151,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.4954,
+      "step": 66
+    },
+    {
+      "epoch": 0.769377990430622,
+      "grad_norm": 0.2618401348590851,
+      "learning_rate": 1.551377089721692e-05,
+      "loss": 0.4881,
+      "step": 67
+    },
+    {
+      "epoch": 0.7808612440191387,
+      "grad_norm": 0.2827475666999817,
+      "learning_rate": 1.5344658261278013e-05,
+      "loss": 0.4741,
+      "step": 68
+    },
+    {
+      "epoch": 0.7923444976076555,
+      "grad_norm": 0.28884321451187134,
+      "learning_rate": 1.5173378141776569e-05,
+      "loss": 0.5133,
+      "step": 69
+    },
+    {
+      "epoch": 0.8038277511961722,
+      "grad_norm": 0.2944667935371399,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4843,
+      "step": 70
+    },
+    {
+      "epoch": 0.815311004784689,
+      "grad_norm": 0.301776647567749,
+      "learning_rate": 1.4824594148071936e-05,
+      "loss": 0.4956,
+      "step": 71
+    },
+    {
+      "epoch": 0.8267942583732057,
+      "grad_norm": 0.31137344241142273,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 0.5161,
+      "step": 72
+    },
+    {
+      "epoch": 0.8382775119617225,
+      "grad_norm": 0.28323987126350403,
+      "learning_rate": 1.4467984645016259e-05,
+      "loss": 0.4991,
+      "step": 73
+    },
+    {
+      "epoch": 0.8497607655502393,
+      "grad_norm": 0.31255266070365906,
+      "learning_rate": 1.4286925614030542e-05,
+      "loss": 0.4991,
+      "step": 74
+    },
+    {
+      "epoch": 0.861244019138756,
+      "grad_norm": 0.31073659658432007,
+      "learning_rate": 1.410412805452757e-05,
+      "loss": 0.4778,
+      "step": 75
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.30535194277763367,
+      "learning_rate": 1.3919666098600753e-05,
+      "loss": 0.5201,
+      "step": 76
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.3717443346977234,
+      "learning_rate": 1.3733614553326211e-05,
+      "loss": 0.4943,
+      "step": 77
+    },
+    {
+      "epoch": 0.8956937799043062,
+      "grad_norm": 0.26282674074172974,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.5022,
+      "step": 78
+    },
+    {
+      "epoch": 0.907177033492823,
+      "grad_norm": 0.2955797612667084,
+      "learning_rate": 1.335704511566605e-05,
+      "loss": 0.482,
+      "step": 79
+    },
+    {
+      "epoch": 0.9186602870813397,
+      "grad_norm": 0.30926328897476196,
+      "learning_rate": 1.3166679938014728e-05,
+      "loss": 0.4803,
+      "step": 80
+    },
+    {
+      "epoch": 0.9301435406698565,
+      "grad_norm": 0.2495397925376892,
+      "learning_rate": 1.297503053855203e-05,
+      "loss": 0.4895,
+      "step": 81
+    },
+    {
+      "epoch": 0.9416267942583733,
+      "grad_norm": 0.299214631319046,
+      "learning_rate": 1.2782174639164528e-05,
+      "loss": 0.5031,
+      "step": 82
+    },
+    {
+      "epoch": 0.9531100478468899,
+      "grad_norm": 0.26720190048217773,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.4931,
+      "step": 83
+    },
+    {
+      "epoch": 0.9645933014354067,
+      "grad_norm": 0.28564536571502686,
+      "learning_rate": 1.2393156642875579e-05,
+      "loss": 0.4923,
+      "step": 84
+    },
+    {
+      "epoch": 0.9760765550239234,
+      "grad_norm": 0.26890474557876587,
+      "learning_rate": 1.2197152309122173e-05,
+      "loss": 0.5252,
+      "step": 85
+    },
+    {
+      "epoch": 0.9875598086124402,
+      "grad_norm": 0.28297609090805054,
+      "learning_rate": 1.2000256937760446e-05,
+      "loss": 0.4903,
+      "step": 86
+    },
+    {
+      "epoch": 0.999043062200957,
+      "grad_norm": 0.26182886958122253,
+      "learning_rate": 1.180255037813906e-05,
+      "loss": 0.4879,
+      "step": 87
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 0.7859248518943787,
+      "learning_rate": 1.1604112808577603e-05,
+      "loss": 0.7722,
+      "step": 88
+    },
+    {
+      "epoch": 1.0220095693779905,
+      "grad_norm": 0.3331013023853302,
+      "learning_rate": 1.1405024703850929e-05,
+      "loss": 0.4322,
+      "step": 89
+    },
+    {
+      "epoch": 1.0334928229665072,
+      "grad_norm": 0.7180531620979309,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 0.4452,
+      "step": 90
+    },
+    {
+      "epoch": 1.044976076555024,
+      "grad_norm": 0.3440372049808502,
+      "learning_rate": 1.1005220074355172e-05,
+      "loss": 0.4676,
+      "step": 91
+    },
+    {
+      "epoch": 1.0564593301435408,
+      "grad_norm": 0.31776347756385803,
+      "learning_rate": 1.0804665687167262e-05,
+      "loss": 0.4573,
+      "step": 92
+    },
+    {
+      "epoch": 1.0679425837320573,
+      "grad_norm": 0.39098435640335083,
+      "learning_rate": 1.0603784974222862e-05,
+      "loss": 0.4608,
+      "step": 93
+    },
+    {
+      "epoch": 1.079425837320574,
+      "grad_norm": 0.29146501421928406,
+      "learning_rate": 1.0402659401094154e-05,
+      "loss": 0.4511,
+      "step": 94
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.3079903721809387,
+      "learning_rate": 1.0201370532654404e-05,
+      "loss": 0.4757,
+      "step": 95
+    },
+    {
+      "epoch": 1.1023923444976076,
+      "grad_norm": 0.32171630859375,
+      "learning_rate": 1e-05,
+      "loss": 0.4764,
+      "step": 96
+    },
+    {
+      "epoch": 1.1138755980861244,
+      "grad_norm": 0.2739886939525604,
+      "learning_rate": 9.7986294673456e-06,
+      "loss": 0.4183,
+      "step": 97
+    },
+    {
+      "epoch": 1.1253588516746411,
+      "grad_norm": 0.31871333718299866,
+      "learning_rate": 9.597340598905851e-06,
+      "loss": 0.4677,
+      "step": 98
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 0.28314825892448425,
+      "learning_rate": 9.39621502577714e-06,
+      "loss": 0.4345,
+      "step": 99
+    },
+    {
+      "epoch": 1.1483253588516746,
+      "grad_norm": 0.2956909239292145,
+      "learning_rate": 9.195334312832742e-06,
+      "loss": 0.456,
+      "step": 100
+    },
+    {
+      "epoch": 1.1607655502392344,
+      "grad_norm": 0.3102877140045166,
+      "learning_rate": 8.994779925644832e-06,
+      "loss": 0.4653,
+      "step": 101
+    },
+    {
+      "epoch": 1.1722488038277512,
+      "grad_norm": 0.2631514072418213,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 0.4663,
+      "step": 102
+    },
+    {
+      "epoch": 1.183732057416268,
+      "grad_norm": 0.2780362665653229,
+      "learning_rate": 8.594975296149076e-06,
+      "loss": 0.4598,
+      "step": 103
+    },
+    {
+      "epoch": 1.1952153110047847,
+      "grad_norm": 0.30441659688949585,
+      "learning_rate": 8.395887191422397e-06,
+      "loss": 0.4603,
+      "step": 104
+    },
+    {
+      "epoch": 1.2066985645933015,
+      "grad_norm": 0.31006890535354614,
+      "learning_rate": 8.197449621860944e-06,
+      "loss": 0.4691,
+      "step": 105
+    },
+    {
+      "epoch": 1.2181818181818183,
+      "grad_norm": 0.24229736626148224,
+      "learning_rate": 7.999743062239557e-06,
+      "loss": 0.4363,
+      "step": 106
+    },
+    {
+      "epoch": 1.229665071770335,
+      "grad_norm": 0.28089576959609985,
+      "learning_rate": 7.802847690877832e-06,
+      "loss": 0.4507,
+      "step": 107
+    },
+    {
+      "epoch": 1.2411483253588518,
+      "grad_norm": 0.2989681661128998,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 0.4537,
+      "step": 108
+    },
+    {
+      "epoch": 1.2526315789473683,
+      "grad_norm": 0.25250881910324097,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.4358,
+      "step": 109
+    },
+    {
+      "epoch": 1.2641148325358853,
+      "grad_norm": 0.2874893546104431,
+      "learning_rate": 7.217825360835475e-06,
+      "loss": 0.4394,
+      "step": 110
+    },
+    {
+      "epoch": 1.2755980861244018,
+      "grad_norm": 0.25158512592315674,
+      "learning_rate": 7.024969461447973e-06,
+      "loss": 0.4375,
+      "step": 111
+    },
+    {
+      "epoch": 1.2870813397129186,
+      "grad_norm": 0.27635353803634644,
+      "learning_rate": 6.833320061985278e-06,
+      "loss": 0.4508,
+      "step": 112
+    },
+    {
+      "epoch": 1.2985645933014354,
+      "grad_norm": 0.2624880373477936,
+      "learning_rate": 6.6429548843339554e-06,
+      "loss": 0.4608,
+      "step": 113
+    },
+    {
+      "epoch": 1.3100478468899521,
+      "grad_norm": 0.2889038026332855,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.4451,
+      "step": 114
+    },
+    {
+      "epoch": 1.321531100478469,
+      "grad_norm": 0.24713511765003204,
+      "learning_rate": 6.266385446673791e-06,
+      "loss": 0.4378,
+      "step": 115
+    },
+    {
+      "epoch": 1.3330143540669857,
+      "grad_norm": 0.26973429322242737,
+      "learning_rate": 6.080333901399252e-06,
+      "loss": 0.4443,
+      "step": 116
+    },
+    {
+      "epoch": 1.3444976076555024,
+      "grad_norm": 0.2887195348739624,
+      "learning_rate": 5.895871945472434e-06,
+      "loss": 0.4565,
+      "step": 117
+    },
+    {
+      "epoch": 1.3559808612440192,
+      "grad_norm": 0.2864110469818115,
+      "learning_rate": 5.713074385969457e-06,
+      "loss": 0.4305,
+      "step": 118
+    },
+    {
+      "epoch": 1.367464114832536,
+      "grad_norm": 0.2510843873023987,
+      "learning_rate": 5.532015354983742e-06,
+      "loss": 0.4472,
+      "step": 119
+    },
+    {
+      "epoch": 1.3789473684210527,
+      "grad_norm": 0.27841120958328247,
+      "learning_rate": 5.352768279562315e-06,
+      "loss": 0.4548,
+      "step": 120
+    },
+    {
+      "epoch": 1.3904306220095695,
+      "grad_norm": 0.253780722618103,
+      "learning_rate": 5.175405851928068e-06,
+      "loss": 0.4401,
+      "step": 121
+    },
+    {
+      "epoch": 1.401913875598086,
+      "grad_norm": 0.2693757116794586,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4624,
+      "step": 122
+    },
+    {
+      "epoch": 1.413397129186603,
+      "grad_norm": 0.2563832104206085,
+      "learning_rate": 4.826621858223431e-06,
+      "loss": 0.4388,
+      "step": 123
+    },
+    {
+      "epoch": 1.4248803827751195,
+      "grad_norm": 0.305113285779953,
+      "learning_rate": 4.655341738721989e-06,
+      "loss": 0.4546,
+      "step": 124
+    },
+    {
+      "epoch": 1.4363636363636363,
+      "grad_norm": 0.2533874213695526,
+      "learning_rate": 4.486229102783084e-06,
+      "loss": 0.4561,
+      "step": 125
+    },
+    {
+      "epoch": 1.447846889952153,
+      "grad_norm": 0.2530078589916229,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 0.4445,
+      "step": 126
+    },
+    {
+      "epoch": 1.4593301435406698,
+      "grad_norm": 0.28587111830711365,
+      "learning_rate": 4.154779703901114e-06,
+      "loss": 0.4821,
+      "step": 127
+    },
+    {
+      "epoch": 1.4708133971291866,
+      "grad_norm": 0.26422637701034546,
+      "learning_rate": 3.99257735762021e-06,
+      "loss": 0.4571,
+      "step": 128
+    },
+    {
+      "epoch": 1.4822966507177033,
+      "grad_norm": 0.279634028673172,
+      "learning_rate": 3.832811273714569e-06,
+      "loss": 0.4514,
+      "step": 129
+    },
+    {
+      "epoch": 1.49377990430622,
+      "grad_norm": 0.24408729374408722,
+      "learning_rate": 3.6755462440462288e-06,
+      "loss": 0.4405,
+      "step": 130
+    },
+    {
+      "epoch": 1.5052631578947369,
+      "grad_norm": 0.277403324842453,
+      "learning_rate": 3.5208460461946136e-06,
+      "loss": 0.4676,
+      "step": 131
+    },
+    {
+      "epoch": 1.5167464114832536,
+      "grad_norm": 0.2653951048851013,
+      "learning_rate": 3.3687734175920505e-06,
+      "loss": 0.4422,
+      "step": 132
+    },
+    {
+      "epoch": 1.5282296650717704,
+      "grad_norm": 0.2684209644794464,
+      "learning_rate": 3.2193900300810908e-06,
+      "loss": 0.4287,
+      "step": 133
+    },
+    {
+      "epoch": 1.5397129186602871,
+      "grad_norm": 0.25018298625946045,
+      "learning_rate": 3.0727564649040066e-06,
+      "loss": 0.4107,
+      "step": 134
+    },
+    {
+      "epoch": 1.5511961722488037,
+      "grad_norm": 0.25643426179885864,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.4542,
+      "step": 135
+    },
+    {
+      "epoch": 1.5626794258373207,
+      "grad_norm": 0.2723328173160553,
+      "learning_rate": 2.7879755265618558e-06,
+      "loss": 0.4471,
+      "step": 136
+    },
+    {
+      "epoch": 1.5741626794258372,
+      "grad_norm": 0.25238141417503357,
+      "learning_rate": 2.6499436440367165e-06,
+      "loss": 0.4452,
+      "step": 137
+    },
+    {
+      "epoch": 1.5856459330143542,
+      "grad_norm": 0.25168266892433167,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.4369,
+      "step": 138
+    },
+    {
+      "epoch": 1.5971291866028707,
+      "grad_norm": 0.34418055415153503,
+      "learning_rate": 2.382876918226409e-06,
+      "loss": 0.4419,
+      "step": 139
+    },
+    {
+      "epoch": 1.6086124401913877,
+      "grad_norm": 0.2500324547290802,
+      "learning_rate": 2.2539503817234553e-06,
+      "loss": 0.4455,
+      "step": 140
+    },
+    {
+      "epoch": 1.6200956937799043,
+      "grad_norm": 0.2515903115272522,
+      "learning_rate": 2.1281651939094996e-06,
+      "loss": 0.4511,
+      "step": 141
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.24545879662036896,
+      "learning_rate": 2.0055723659649907e-06,
+      "loss": 0.4452,
+      "step": 142
+    },
+    {
+      "epoch": 1.6430622009569378,
+      "grad_norm": 0.277642160654068,
+      "learning_rate": 1.8862216144342692e-06,
+      "loss": 0.4596,
+      "step": 143
+    },
+    {
+      "epoch": 1.6545454545454545,
+      "grad_norm": 0.2690809965133667,
+      "learning_rate": 1.7701613410634367e-06,
+      "loss": 0.4721,
+      "step": 144
+    },
+    {
+      "epoch": 1.6660287081339713,
+      "grad_norm": 0.2773820459842682,
+      "learning_rate": 1.6574386131713872e-06,
+      "loss": 0.4669,
+      "step": 145
+    },
+    {
+      "epoch": 1.677511961722488,
+      "grad_norm": 0.2979687452316284,
+      "learning_rate": 1.5480991445620541e-06,
+      "loss": 0.484,
+      "step": 146
+    },
+    {
+      "epoch": 1.6889952153110048,
+      "grad_norm": 0.2545396685600281,
+      "learning_rate": 1.4421872769855262e-06,
+      "loss": 0.4429,
+      "step": 147
+    },
+    {
+      "epoch": 1.7004784688995214,
+      "grad_norm": 0.2929985523223877,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.4636,
+      "step": 148
+    },
+    {
+      "epoch": 1.7119617224880384,
+      "grad_norm": 0.27831029891967773,
+      "learning_rate": 1.2408167443311215e-06,
+      "loss": 0.4015,
+      "step": 149
+    },
+    {
+      "epoch": 1.723444976076555,
+      "grad_norm": 0.2582859694957733,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 0.4508,
+      "step": 150
+    },
+    {
+      "epoch": 1.7349282296650719,
+      "grad_norm": 0.27638334035873413,
+      "learning_rate": 1.0536536389485275e-06,
+      "loss": 0.4316,
+      "step": 151
+    },
+    {
+      "epoch": 1.7464114832535884,
+      "grad_norm": 0.2702406942844391,
+      "learning_rate": 9.65495653896179e-07,
+      "loss": 0.4347,
+      "step": 152
+    },
+    {
+      "epoch": 1.7578947368421054,
+      "grad_norm": 0.286505788564682,
+      "learning_rate": 8.810015400790994e-07,
+      "loss": 0.4579,
+      "step": 153
+    },
+    {
+      "epoch": 1.769377990430622,
+      "grad_norm": 0.23764821887016296,
+      "learning_rate": 8.002055634117578e-07,
+      "loss": 0.4148,
+      "step": 154
+    },
+    {
+      "epoch": 1.7808612440191387,
+      "grad_norm": 0.2822108268737793,
+      "learning_rate": 7.231404900585714e-07,
+      "loss": 0.4443,
+      "step": 155
+    },
+    {
+      "epoch": 1.7923444976076555,
+      "grad_norm": 0.24537336826324463,
+      "learning_rate": 6.498375731458529e-07,
+      "loss": 0.4583,
+      "step": 156
+    },
+    {
+      "epoch": 1.8038277511961722,
+      "grad_norm": 0.2529117465019226,
+      "learning_rate": 5.803265400873514e-07,
+      "loss": 0.4448,
+      "step": 157
+    },
+    {
+      "epoch": 1.815311004784689,
+      "grad_norm": 0.2595837712287903,
+      "learning_rate": 5.146355805285452e-07,
+      "loss": 0.4488,
+      "step": 158
+    },
+    {
+      "epoch": 1.8267942583732057,
+      "grad_norm": 0.27293673157691956,
+      "learning_rate": 4.5279133491454406e-07,
+      "loss": 0.4448,
+      "step": 159
+    },
+    {
+      "epoch": 1.8382775119617225,
+      "grad_norm": 0.27972596883773804,
+      "learning_rate": 3.9481888368627764e-07,
+      "loss": 0.4608,
+      "step": 160
+    },
+    {
+      "epoch": 1.8497607655502393,
+      "grad_norm": 0.384954571723938,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.4344,
+      "step": 161
+    },
+    {
+      "epoch": 1.861244019138756,
+      "grad_norm": 0.2894757390022278,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 0.4483,
+      "step": 162
+    },
+    {
+      "epoch": 1.8727272727272726,
+      "grad_norm": 0.31389251351356506,
+      "learning_rate": 2.4435949152906144e-07,
+      "loss": 0.4689,
+      "step": 163
+    },
+    {
+      "epoch": 1.8842105263157896,
+      "grad_norm": 0.2728366255760193,
+      "learning_rate": 2.0209347957732328e-07,
+      "loss": 0.4479,
+      "step": 164
+    },
+    {
+      "epoch": 1.895693779904306,
+      "grad_norm": 0.28522682189941406,
+      "learning_rate": 1.6380093052856482e-07,
+      "loss": 0.4329,
+      "step": 165
+    },
+    {
+      "epoch": 1.907177033492823,
+      "grad_norm": 0.31500834226608276,
+      "learning_rate": 1.2949737362087156e-07,
+      "loss": 0.4493,
+      "step": 166
+    },
+    {
+      "epoch": 1.9186602870813396,
+      "grad_norm": 0.28287577629089355,
+      "learning_rate": 9.919672038835926e-08,
+      "loss": 0.445,
+      "step": 167
+    },
+    {
+      "epoch": 1.9301435406698566,
+      "grad_norm": 0.2714127004146576,
+      "learning_rate": 7.291125901946027e-08,
+      "loss": 0.4704,
+      "step": 168
+    },
+    {
+      "epoch": 1.9416267942583731,
+      "grad_norm": 0.2918432950973511,
+      "learning_rate": 5.0651649373544276e-08,
+      "loss": 0.4601,
+      "step": 169
+    },
+    {
+      "epoch": 1.95311004784689,
+      "grad_norm": 0.2897633910179138,
+      "learning_rate": 3.242691865790071e-08,
+      "loss": 0.4416,
+      "step": 170
+    },
+    {
+      "epoch": 1.9645933014354067,
+      "grad_norm": 0.24492616951465607,
+      "learning_rate": 1.824445776682504e-08,
+      "loss": 0.4389,
+      "step": 171
+    },
+    {
+      "epoch": 1.9760765550239234,
+      "grad_norm": 0.3015381693840027,
+      "learning_rate": 8.110018284304132e-09,
+      "loss": 0.4549,
+      "step": 172
+    },
+    {
+      "epoch": 1.9875598086124402,
+      "grad_norm": 0.26895269751548767,
+      "learning_rate": 2.0277101514987184e-09,
+      "loss": 0.4451,
+      "step": 173
+    },
+    {
+      "epoch": 1.999043062200957,
+      "grad_norm": 0.25817951560020447,
+      "learning_rate": 0.0,
+      "loss": 0.4523,
+      "step": 174
+    },
+    {
+      "epoch": 1.999043062200957,
+      "step": 174,
+      "total_flos": 665025606320128.0,
+      "train_loss": 0.19090694274710512,
+      "train_runtime": 9940.2778,
+      "train_samples_per_second": 1.681,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 174,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 665025606320128.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89404f223832017751a1fd55e5e97166a4caaf2ec23fcc5d39c88c37c5cc1e3b
+size 7544