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": 1.9976019184652278,
+    "total_flos": 537505164820480.0,
+    "train_loss": 0.11768974435444061,
+    "train_runtime": 6440.6597,
+    "train_samples_per_second": 3.106,
+    "train_steps_per_second": 0.032
+}

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:b3756e0c553ccedb403362935e661ddbc9cc1127ffe479c842fc60d1eb039cf9
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200c1e830a291dda776a0c54a6cde753a5a77ee1276b7288ad32b0bb467ca42f
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c0d06358c8538136a8174dcf8867aec3629069a40f89d5635c781abca3c36e
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1fb8e61cf843266182d301b533baed7b29475a8e41b1a4c1d12f774f0119d0
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50811873773a752cba64ce1e81d21d9a65132c2e8fc8ec8b2fc94025d5bc95ad
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11dd3ffeb387869c895ffb439324dc3d169c3e6b7f422c56900d399d643f3175
+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": 1.9976019184652278,
+    "total_flos": 537505164820480.0,
+    "train_loss": 0.11768974435444061,
+    "train_runtime": 6440.6597,
+    "train_samples_per_second": 3.106,
+    "train_steps_per_second": 0.032
+}

trainer_log.jsonl

@@ -0,0 +1,257 @@
+{"current_steps": 1, "total_steps": 208, "loss": 0.7616, "lr": 9.523809523809525e-07, "epoch": 0.009592326139088728, "percentage": 0.48, "elapsed_time": "0:01:46", "remaining_time": "6:07:27"}
+{"current_steps": 2, "total_steps": 208, "loss": 0.8093, "lr": 1.904761904761905e-06, "epoch": 0.019184652278177457, "percentage": 0.96, "elapsed_time": "0:03:24", "remaining_time": "5:50:41"}
+{"current_steps": 3, "total_steps": 208, "loss": 0.8114, "lr": 2.8571428571428573e-06, "epoch": 0.02877697841726619, "percentage": 1.44, "elapsed_time": "0:05:07", "remaining_time": "5:49:44"}
+{"current_steps": 4, "total_steps": 208, "loss": 0.7994, "lr": 3.80952380952381e-06, "epoch": 0.03836930455635491, "percentage": 1.92, "elapsed_time": "0:07:03", "remaining_time": "6:00:01"}
+{"current_steps": 5, "total_steps": 208, "loss": 0.7662, "lr": 4.761904761904762e-06, "epoch": 0.047961630695443645, "percentage": 2.4, "elapsed_time": "0:08:33", "remaining_time": "5:47:31"}
+{"current_steps": 6, "total_steps": 208, "loss": 0.7797, "lr": 5.7142857142857145e-06, "epoch": 0.05755395683453238, "percentage": 2.88, "elapsed_time": "0:10:43", "remaining_time": "6:01:19"}
+{"current_steps": 7, "total_steps": 208, "loss": 0.7279, "lr": 6.666666666666667e-06, "epoch": 0.0671462829736211, "percentage": 3.37, "elapsed_time": "0:12:19", "remaining_time": "5:53:46"}
+{"current_steps": 8, "total_steps": 208, "loss": 0.7203, "lr": 7.61904761904762e-06, "epoch": 0.07673860911270983, "percentage": 3.85, "elapsed_time": "0:13:43", "remaining_time": "5:43:04"}
+{"current_steps": 9, "total_steps": 208, "loss": 0.733, "lr": 8.571428571428571e-06, "epoch": 0.08633093525179857, "percentage": 4.33, "elapsed_time": "0:15:35", "remaining_time": "5:44:55"}
+{"current_steps": 10, "total_steps": 208, "loss": 0.6486, "lr": 9.523809523809525e-06, "epoch": 0.09592326139088729, "percentage": 4.81, "elapsed_time": "0:17:22", "remaining_time": "5:44:08"}
+{"current_steps": 11, "total_steps": 208, "loss": 0.6576, "lr": 1.0476190476190477e-05, "epoch": 0.10551558752997602, "percentage": 5.29, "elapsed_time": "0:19:06", "remaining_time": "5:42:10"}
+{"current_steps": 12, "total_steps": 208, "loss": 0.6284, "lr": 1.1428571428571429e-05, "epoch": 0.11510791366906475, "percentage": 5.77, "elapsed_time": "0:20:48", "remaining_time": "5:39:52"}
+{"current_steps": 13, "total_steps": 208, "loss": 0.649, "lr": 1.2380952380952383e-05, "epoch": 0.12470023980815348, "percentage": 6.25, "elapsed_time": "0:22:51", "remaining_time": "5:42:55"}
+{"current_steps": 14, "total_steps": 208, "loss": 0.6369, "lr": 1.3333333333333333e-05, "epoch": 0.1342925659472422, "percentage": 6.73, "elapsed_time": "0:24:42", "remaining_time": "5:42:26"}
+{"current_steps": 15, "total_steps": 208, "loss": 0.6114, "lr": 1.4285714285714287e-05, "epoch": 0.14388489208633093, "percentage": 7.21, "elapsed_time": "0:26:21", "remaining_time": "5:39:04"}
+{"current_steps": 16, "total_steps": 208, "loss": 0.6142, "lr": 1.523809523809524e-05, "epoch": 0.15347721822541965, "percentage": 7.69, "elapsed_time": "0:28:18", "remaining_time": "5:39:46"}
+{"current_steps": 17, "total_steps": 208, "loss": 0.5983, "lr": 1.6190476190476193e-05, "epoch": 0.1630695443645084, "percentage": 8.17, "elapsed_time": "0:29:52", "remaining_time": "5:35:44"}
+{"current_steps": 18, "total_steps": 208, "loss": 0.585, "lr": 1.7142857142857142e-05, "epoch": 0.17266187050359713, "percentage": 8.65, "elapsed_time": "0:31:15", "remaining_time": "5:29:56"}
+{"current_steps": 19, "total_steps": 208, "loss": 0.6167, "lr": 1.8095238095238097e-05, "epoch": 0.18225419664268586, "percentage": 9.13, "elapsed_time": "0:32:57", "remaining_time": "5:27:54"}
+{"current_steps": 20, "total_steps": 208, "loss": 0.561, "lr": 1.904761904761905e-05, "epoch": 0.19184652278177458, "percentage": 9.62, "elapsed_time": "0:34:49", "remaining_time": "5:27:20"}
+{"current_steps": 21, "total_steps": 208, "loss": 0.5779, "lr": 2e-05, "epoch": 0.2014388489208633, "percentage": 10.1, "elapsed_time": "0:36:44", "remaining_time": "5:27:06"}
+{"current_steps": 22, "total_steps": 208, "loss": 0.5944, "lr": 1.9998588839790777e-05, "epoch": 0.21103117505995203, "percentage": 10.58, "elapsed_time": "0:38:51", "remaining_time": "5:28:27"}
+{"current_steps": 23, "total_steps": 208, "loss": 0.5512, "lr": 1.999435575743774e-05, "epoch": 0.22062350119904076, "percentage": 11.06, "elapsed_time": "0:40:42", "remaining_time": "5:27:23"}
+{"current_steps": 24, "total_steps": 208, "loss": 0.5776, "lr": 1.9987301947652354e-05, "epoch": 0.2302158273381295, "percentage": 11.54, "elapsed_time": "0:42:45", "remaining_time": "5:27:46"}
+{"current_steps": 25, "total_steps": 208, "loss": 0.5843, "lr": 1.9977429401245764e-05, "epoch": 0.23980815347721823, "percentage": 12.02, "elapsed_time": "0:44:40", "remaining_time": "5:26:59"}
+{"current_steps": 26, "total_steps": 208, "loss": 0.5571, "lr": 1.9964740904566903e-05, "epoch": 0.24940047961630696, "percentage": 12.5, "elapsed_time": "0:46:29", "remaining_time": "5:25:23"}
+{"current_steps": 27, "total_steps": 208, "loss": 0.5383, "lr": 1.9949240038716092e-05, "epoch": 0.2589928057553957, "percentage": 12.98, "elapsed_time": "0:48:01", "remaining_time": "5:21:56"}
+{"current_steps": 28, "total_steps": 208, "loss": 0.5437, "lr": 1.9930931178534353e-05, "epoch": 0.2685851318944844, "percentage": 13.46, "elapsed_time": "0:49:31", "remaining_time": "5:18:21"}
+{"current_steps": 29, "total_steps": 208, "loss": 0.5392, "lr": 1.9909819491368677e-05, "epoch": 0.27817745803357313, "percentage": 13.94, "elapsed_time": "0:51:03", "remaining_time": "5:15:06"}
+{"current_steps": 30, "total_steps": 208, "loss": 0.5536, "lr": 1.988591093561364e-05, "epoch": 0.28776978417266186, "percentage": 14.42, "elapsed_time": "0:52:38", "remaining_time": "5:12:21"}
+{"current_steps": 31, "total_steps": 208, "loss": 0.5515, "lr": 1.985921225902975e-05, "epoch": 0.2973621103117506, "percentage": 14.9, "elapsed_time": "0:54:27", "remaining_time": "5:10:57"}
+{"current_steps": 32, "total_steps": 208, "loss": 0.527, "lr": 1.982973099683902e-05, "epoch": 0.3069544364508393, "percentage": 15.38, "elapsed_time": "0:56:04", "remaining_time": "5:08:25"}
+{"current_steps": 33, "total_steps": 208, "loss": 0.5314, "lr": 1.9797475469598267e-05, "epoch": 0.31654676258992803, "percentage": 15.87, "elapsed_time": "0:58:09", "remaining_time": "5:08:27"}
+{"current_steps": 34, "total_steps": 208, "loss": 0.5265, "lr": 1.9762454780850807e-05, "epoch": 0.3261390887290168, "percentage": 16.35, "elapsed_time": "0:59:36", "remaining_time": "5:05:01"}
+{"current_steps": 35, "total_steps": 208, "loss": 0.5424, "lr": 1.972467881455713e-05, "epoch": 0.33573141486810554, "percentage": 16.83, "elapsed_time": "1:01:38", "remaining_time": "5:04:38"}
+{"current_steps": 36, "total_steps": 208, "loss": 0.5316, "lr": 1.968415823230534e-05, "epoch": 0.34532374100719426, "percentage": 17.31, "elapsed_time": "1:03:10", "remaining_time": "5:01:50"}
+{"current_steps": 37, "total_steps": 208, "loss": 0.5077, "lr": 1.96409044703021e-05, "epoch": 0.354916067146283, "percentage": 17.79, "elapsed_time": "1:05:02", "remaining_time": "5:00:36"}
+{"current_steps": 38, "total_steps": 208, "loss": 0.5526, "lr": 1.9594929736144978e-05, "epoch": 0.3645083932853717, "percentage": 18.27, "elapsed_time": "1:06:33", "remaining_time": "4:57:44"}
+{"current_steps": 39, "total_steps": 208, "loss": 0.5157, "lr": 1.9546247005377065e-05, "epoch": 0.37410071942446044, "percentage": 18.75, "elapsed_time": "1:08:20", "remaining_time": "4:56:07"}
+{"current_steps": 40, "total_steps": 208, "loss": 0.5015, "lr": 1.9494870017824877e-05, "epoch": 0.38369304556354916, "percentage": 19.23, "elapsed_time": "1:10:02", "remaining_time": "4:54:09"}
+{"current_steps": 41, "total_steps": 208, "loss": 0.4995, "lr": 1.9440813273720504e-05, "epoch": 0.3932853717026379, "percentage": 19.71, "elapsed_time": "1:11:36", "remaining_time": "4:51:41"}
+{"current_steps": 42, "total_steps": 208, "loss": 0.49, "lr": 1.938409202960922e-05, "epoch": 0.4028776978417266, "percentage": 20.19, "elapsed_time": "1:13:18", "remaining_time": "4:49:45"}
+{"current_steps": 43, "total_steps": 208, "loss": 0.5277, "lr": 1.932472229404356e-05, "epoch": 0.41247002398081534, "percentage": 20.67, "elapsed_time": "1:15:00", "remaining_time": "4:47:47"}
+{"current_steps": 44, "total_steps": 208, "loss": 0.5318, "lr": 1.9262720823065217e-05, "epoch": 0.42206235011990406, "percentage": 21.15, "elapsed_time": "1:16:56", "remaining_time": "4:46:47"}
+{"current_steps": 45, "total_steps": 208, "loss": 0.5101, "lr": 1.9198105115475946e-05, "epoch": 0.4316546762589928, "percentage": 21.63, "elapsed_time": "1:18:32", "remaining_time": "4:44:30"}
+{"current_steps": 46, "total_steps": 208, "loss": 0.5197, "lr": 1.9130893407898834e-05, "epoch": 0.4412470023980815, "percentage": 22.12, "elapsed_time": "1:20:18", "remaining_time": "4:42:48"}
+{"current_steps": 47, "total_steps": 208, "loss": 0.5029, "lr": 1.9061104669631343e-05, "epoch": 0.45083932853717024, "percentage": 22.6, "elapsed_time": "1:22:07", "remaining_time": "4:41:19"}
+{"current_steps": 48, "total_steps": 208, "loss": 0.5247, "lr": 1.8988758597291577e-05, "epoch": 0.460431654676259, "percentage": 23.08, "elapsed_time": "1:23:53", "remaining_time": "4:39:39"}
+{"current_steps": 49, "total_steps": 208, "loss": 0.4924, "lr": 1.8913875609259246e-05, "epoch": 0.47002398081534774, "percentage": 23.56, "elapsed_time": "1:25:48", "remaining_time": "4:38:24"}
+{"current_steps": 50, "total_steps": 208, "loss": 0.508, "lr": 1.8836476839912967e-05, "epoch": 0.47961630695443647, "percentage": 24.04, "elapsed_time": "1:27:27", "remaining_time": "4:36:23"}
+{"current_steps": 51, "total_steps": 208, "loss": 0.5216, "lr": 1.8756584133665447e-05, "epoch": 0.4892086330935252, "percentage": 24.52, "elapsed_time": "1:30:24", "remaining_time": "4:38:19"}
+{"current_steps": 52, "total_steps": 208, "loss": 0.52, "lr": 1.86742200387983e-05, "epoch": 0.4988009592326139, "percentage": 25.0, "elapsed_time": "1:32:11", "remaining_time": "4:36:34"}
+{"current_steps": 53, "total_steps": 208, "loss": 0.4673, "lr": 1.8589407801098192e-05, "epoch": 0.5083932853717026, "percentage": 25.48, "elapsed_time": "1:33:55", "remaining_time": "4:34:41"}
+{"current_steps": 54, "total_steps": 208, "loss": 0.5069, "lr": 1.8502171357296144e-05, "epoch": 0.5179856115107914, "percentage": 25.96, "elapsed_time": "1:35:42", "remaining_time": "4:32:55"}
+{"current_steps": 55, "total_steps": 208, "loss": 0.5195, "lr": 1.8412535328311813e-05, "epoch": 0.5275779376498801, "percentage": 26.44, "elapsed_time": "1:37:27", "remaining_time": "4:31:06"}
+{"current_steps": 56, "total_steps": 208, "loss": 0.486, "lr": 1.8320525012304685e-05, "epoch": 0.5371702637889688, "percentage": 26.92, "elapsed_time": "1:39:13", "remaining_time": "4:29:20"}
+{"current_steps": 57, "total_steps": 208, "loss": 0.4916, "lr": 1.8226166377534113e-05, "epoch": 0.5467625899280576, "percentage": 27.4, "elapsed_time": "1:41:02", "remaining_time": "4:27:39"}
+{"current_steps": 58, "total_steps": 208, "loss": 0.5225, "lr": 1.8129486055030255e-05, "epoch": 0.5563549160671463, "percentage": 27.88, "elapsed_time": "1:43:00", "remaining_time": "4:26:23"}
+{"current_steps": 59, "total_steps": 208, "loss": 0.4606, "lr": 1.8030511331077945e-05, "epoch": 0.565947242206235, "percentage": 28.37, "elapsed_time": "1:44:41", "remaining_time": "4:24:23"}
+{"current_steps": 60, "total_steps": 208, "loss": 0.4934, "lr": 1.7929270139515606e-05, "epoch": 0.5755395683453237, "percentage": 28.85, "elapsed_time": "1:46:36", "remaining_time": "4:22:58"}
+{"current_steps": 61, "total_steps": 208, "loss": 0.4739, "lr": 1.782579105385145e-05, "epoch": 0.5851318944844125, "percentage": 29.33, "elapsed_time": "1:47:44", "remaining_time": "4:19:38"}
+{"current_steps": 62, "total_steps": 208, "loss": 0.5169, "lr": 1.772010327919912e-05, "epoch": 0.5947242206235012, "percentage": 29.81, "elapsed_time": "1:50:01", "remaining_time": "4:19:05"}
+{"current_steps": 63, "total_steps": 208, "loss": 0.5037, "lr": 1.761223664403505e-05, "epoch": 0.60431654676259, "percentage": 30.29, "elapsed_time": "1:52:06", "remaining_time": "4:18:00"}
+{"current_steps": 64, "total_steps": 208, "loss": 0.4946, "lr": 1.7502221591779932e-05, "epoch": 0.6139088729016786, "percentage": 30.77, "elapsed_time": "1:53:55", "remaining_time": "4:16:20"}
+{"current_steps": 65, "total_steps": 208, "loss": 0.5111, "lr": 1.7390089172206594e-05, "epoch": 0.6235011990407674, "percentage": 31.25, "elapsed_time": "1:55:53", "remaining_time": "4:14:57"}
+{"current_steps": 66, "total_steps": 208, "loss": 0.5044, "lr": 1.727587103267677e-05, "epoch": 0.6330935251798561, "percentage": 31.73, "elapsed_time": "1:57:29", "remaining_time": "4:12:46"}
+{"current_steps": 67, "total_steps": 208, "loss": 0.5399, "lr": 1.7159599409209194e-05, "epoch": 0.6426858513189448, "percentage": 32.21, "elapsed_time": "1:59:24", "remaining_time": "4:11:17"}
+{"current_steps": 51, "total_steps": 208, "loss": 0.5216, "lr": 1.8756584133665447e-05, "epoch": 0.4892086330935252, "percentage": 24.52, "elapsed_time": "0:01:41", "remaining_time": "0:05:12"}
+{"current_steps": 52, "total_steps": 208, "loss": 0.52, "lr": 1.86742200387983e-05, "epoch": 0.4988009592326139, "percentage": 25.0, "elapsed_time": "0:03:27", "remaining_time": "0:10:23"}
+{"current_steps": 53, "total_steps": 208, "loss": 0.4674, "lr": 1.8589407801098192e-05, "epoch": 0.5083932853717026, "percentage": 25.48, "elapsed_time": "0:05:10", "remaining_time": "0:15:09"}
+{"current_steps": 54, "total_steps": 208, "loss": 0.507, "lr": 1.8502171357296144e-05, "epoch": 0.5179856115107914, "percentage": 25.96, "elapsed_time": "0:06:55", "remaining_time": "0:19:45"}
+{"current_steps": 55, "total_steps": 208, "loss": 0.5194, "lr": 1.8412535328311813e-05, "epoch": 0.5275779376498801, "percentage": 26.44, "elapsed_time": "0:08:39", "remaining_time": "0:24:04"}
+{"current_steps": 56, "total_steps": 208, "loss": 0.486, "lr": 1.8320525012304685e-05, "epoch": 0.5371702637889688, "percentage": 26.92, "elapsed_time": "0:10:24", "remaining_time": "0:28:14"}
+{"current_steps": 57, "total_steps": 208, "loss": 0.4917, "lr": 1.8226166377534113e-05, "epoch": 0.5467625899280576, "percentage": 27.4, "elapsed_time": "0:12:11", "remaining_time": "0:32:17"}
+{"current_steps": 58, "total_steps": 208, "loss": 0.5226, "lr": 1.8129486055030255e-05, "epoch": 0.5563549160671463, "percentage": 27.88, "elapsed_time": "0:14:07", "remaining_time": "0:36:32"}
+{"current_steps": 59, "total_steps": 208, "loss": 0.4607, "lr": 1.8030511331077945e-05, "epoch": 0.565947242206235, "percentage": 28.37, "elapsed_time": "0:15:47", "remaining_time": "0:39:51"}
+{"current_steps": 60, "total_steps": 208, "loss": 0.4935, "lr": 1.7929270139515606e-05, "epoch": 0.5755395683453237, "percentage": 28.85, "elapsed_time": "0:17:40", "remaining_time": "0:43:36"}
+{"current_steps": 61, "total_steps": 208, "loss": 0.4741, "lr": 1.782579105385145e-05, "epoch": 0.5851318944844125, "percentage": 29.33, "elapsed_time": "0:18:47", "remaining_time": "0:45:16"}
+{"current_steps": 62, "total_steps": 208, "loss": 0.5172, "lr": 1.772010327919912e-05, "epoch": 0.5947242206235012, "percentage": 29.81, "elapsed_time": "0:21:03", "remaining_time": "0:49:34"}
+{"current_steps": 63, "total_steps": 208, "loss": 0.5039, "lr": 1.761223664403505e-05, "epoch": 0.60431654676259, "percentage": 30.29, "elapsed_time": "0:23:06", "remaining_time": "0:53:11"}
+{"current_steps": 64, "total_steps": 208, "loss": 0.4952, "lr": 1.7502221591779932e-05, "epoch": 0.6139088729016786, "percentage": 30.77, "elapsed_time": "0:24:55", "remaining_time": "0:56:04"}
+{"current_steps": 65, "total_steps": 208, "loss": 0.5115, "lr": 1.7390089172206594e-05, "epoch": 0.6235011990407674, "percentage": 31.25, "elapsed_time": "0:26:51", "remaining_time": "0:59:04"}
+{"current_steps": 66, "total_steps": 208, "loss": 0.5046, "lr": 1.727587103267677e-05, "epoch": 0.6330935251798561, "percentage": 31.73, "elapsed_time": "0:28:25", "remaining_time": "1:01:08"}
+{"current_steps": 67, "total_steps": 208, "loss": 0.5404, "lr": 1.7159599409209194e-05, "epoch": 0.6426858513189448, "percentage": 32.21, "elapsed_time": "0:30:19", "remaining_time": "1:03:48"}
+{"current_steps": 68, "total_steps": 208, "loss": 0.4542, "lr": 1.704130711738157e-05, "epoch": 0.6522781774580336, "percentage": 32.69, "elapsed_time": "0:31:30", "remaining_time": "1:04:53"}
+{"current_steps": 69, "total_steps": 208, "loss": 0.4984, "lr": 1.692102754306895e-05, "epoch": 0.6618705035971223, "percentage": 33.17, "elapsed_time": "0:33:30", "remaining_time": "1:07:30"}
+{"current_steps": 70, "total_steps": 208, "loss": 0.4983, "lr": 1.6798794633021192e-05, "epoch": 0.6714628297362111, "percentage": 33.65, "elapsed_time": "0:35:36", "remaining_time": "1:10:12"}
+{"current_steps": 71, "total_steps": 208, "loss": 0.5032, "lr": 1.667464288528207e-05, "epoch": 0.6810551558752997, "percentage": 34.13, "elapsed_time": "0:37:19", "remaining_time": "1:12:01"}
+{"current_steps": 72, "total_steps": 208, "loss": 0.4894, "lr": 1.6548607339452853e-05, "epoch": 0.6906474820143885, "percentage": 34.62, "elapsed_time": "0:39:12", "remaining_time": "1:14:03"}
+{"current_steps": 73, "total_steps": 208, "loss": 0.4888, "lr": 1.6420723566802982e-05, "epoch": 0.7002398081534772, "percentage": 35.1, "elapsed_time": "0:40:52", "remaining_time": "1:15:35"}
+{"current_steps": 74, "total_steps": 208, "loss": 0.4992, "lr": 1.6291027660230735e-05, "epoch": 0.709832134292566, "percentage": 35.58, "elapsed_time": "0:42:27", "remaining_time": "1:16:52"}
+{"current_steps": 75, "total_steps": 208, "loss": 0.4777, "lr": 1.6159556224076637e-05, "epoch": 0.7194244604316546, "percentage": 36.06, "elapsed_time": "0:44:11", "remaining_time": "1:18:22"}
+{"current_steps": 76, "total_steps": 208, "loss": 0.5104, "lr": 1.6026346363792565e-05, "epoch": 0.7290167865707434, "percentage": 36.54, "elapsed_time": "0:46:17", "remaining_time": "1:20:24"}
+{"current_steps": 77, "total_steps": 208, "loss": 0.5115, "lr": 1.5891435675469376e-05, "epoch": 0.7386091127098321, "percentage": 37.02, "elapsed_time": "0:48:05", "remaining_time": "1:21:48"}
+{"current_steps": 78, "total_steps": 208, "loss": 0.5104, "lr": 1.57548622352261e-05, "epoch": 0.7482014388489209, "percentage": 37.5, "elapsed_time": "0:49:42", "remaining_time": "1:22:51"}
+{"current_steps": 79, "total_steps": 208, "loss": 0.4944, "lr": 1.561666458846365e-05, "epoch": 0.7577937649880095, "percentage": 37.98, "elapsed_time": "0:51:53", "remaining_time": "1:24:44"}
+{"current_steps": 80, "total_steps": 208, "loss": 0.5092, "lr": 1.5476881738986037e-05, "epoch": 0.7673860911270983, "percentage": 38.46, "elapsed_time": "0:53:42", "remaining_time": "1:25:56"}
+{"current_steps": 81, "total_steps": 208, "loss": 0.4602, "lr": 1.5335553137992286e-05, "epoch": 0.7769784172661871, "percentage": 38.94, "elapsed_time": "0:55:14", "remaining_time": "1:26:37"}
+{"current_steps": 82, "total_steps": 208, "loss": 0.4818, "lr": 1.519271867294203e-05, "epoch": 0.7865707434052758, "percentage": 39.42, "elapsed_time": "0:57:16", "remaining_time": "1:28:00"}
+{"current_steps": 83, "total_steps": 208, "loss": 0.5304, "lr": 1.504841865629799e-05, "epoch": 0.7961630695443646, "percentage": 39.9, "elapsed_time": "0:59:13", "remaining_time": "1:29:11"}
+{"current_steps": 84, "total_steps": 208, "loss": 0.5299, "lr": 1.490269381414849e-05, "epoch": 0.8057553956834532, "percentage": 40.38, "elapsed_time": "1:00:53", "remaining_time": "1:29:52"}
+{"current_steps": 85, "total_steps": 208, "loss": 0.4781, "lr": 1.4755585274713289e-05, "epoch": 0.815347721822542, "percentage": 40.87, "elapsed_time": "1:02:45", "remaining_time": "1:30:48"}
+{"current_steps": 86, "total_steps": 208, "loss": 0.4576, "lr": 1.4607134556735836e-05, "epoch": 0.8249400479616307, "percentage": 41.35, "elapsed_time": "1:04:13", "remaining_time": "1:31:06"}
+{"current_steps": 87, "total_steps": 208, "loss": 0.5182, "lr": 1.4457383557765385e-05, "epoch": 0.8345323741007195, "percentage": 41.83, "elapsed_time": "1:06:00", "remaining_time": "1:31:47"}
+{"current_steps": 88, "total_steps": 208, "loss": 0.4952, "lr": 1.4306374542332141e-05, "epoch": 0.8441247002398081, "percentage": 42.31, "elapsed_time": "1:07:36", "remaining_time": "1:32:11"}
+{"current_steps": 89, "total_steps": 208, "loss": 0.4836, "lr": 1.4154150130018867e-05, "epoch": 0.8537170263788969, "percentage": 42.79, "elapsed_time": "1:09:13", "remaining_time": "1:32:33"}
+{"current_steps": 90, "total_steps": 208, "loss": 0.5144, "lr": 1.4000753283432267e-05, "epoch": 0.8633093525179856, "percentage": 43.27, "elapsed_time": "1:11:07", "remaining_time": "1:33:14"}
+{"current_steps": 91, "total_steps": 208, "loss": 0.5008, "lr": 1.3846227296077568e-05, "epoch": 0.8729016786570744, "percentage": 43.75, "elapsed_time": "1:12:52", "remaining_time": "1:33:42"}
+{"current_steps": 92, "total_steps": 208, "loss": 0.4742, "lr": 1.3690615780139703e-05, "epoch": 0.882494004796163, "percentage": 44.23, "elapsed_time": "1:14:28", "remaining_time": "1:33:53"}
+{"current_steps": 93, "total_steps": 208, "loss": 0.4993, "lr": 1.3533962654174542e-05, "epoch": 0.8920863309352518, "percentage": 44.71, "elapsed_time": "1:16:19", "remaining_time": "1:34:22"}
+{"current_steps": 94, "total_steps": 208, "loss": 0.4823, "lr": 1.337631213071369e-05, "epoch": 0.9016786570743405, "percentage": 45.19, "elapsed_time": "1:17:59", "remaining_time": "1:34:34"}
+{"current_steps": 95, "total_steps": 208, "loss": 0.4882, "lr": 1.321770870378628e-05, "epoch": 0.9112709832134293, "percentage": 45.67, "elapsed_time": "1:19:44", "remaining_time": "1:34:51"}
+{"current_steps": 96, "total_steps": 208, "loss": 0.4882, "lr": 1.3058197136361344e-05, "epoch": 0.920863309352518, "percentage": 46.15, "elapsed_time": "1:21:41", "remaining_time": "1:35:18"}
+{"current_steps": 97, "total_steps": 208, "loss": 0.4943, "lr": 1.2897822447714247e-05, "epoch": 0.9304556354916067, "percentage": 46.63, "elapsed_time": "1:23:13", "remaining_time": "1:35:14"}
+{"current_steps": 98, "total_steps": 208, "loss": 0.4723, "lr": 1.2736629900720832e-05, "epoch": 0.9400479616306955, "percentage": 47.12, "elapsed_time": "1:25:03", "remaining_time": "1:35:28"}
+{"current_steps": 99, "total_steps": 208, "loss": 0.4867, "lr": 1.257466498908276e-05, "epoch": 0.9496402877697842, "percentage": 47.6, "elapsed_time": "1:26:49", "remaining_time": "1:35:35"}
+{"current_steps": 100, "total_steps": 208, "loss": 0.5095, "lr": 1.2411973424487751e-05, "epoch": 0.9592326139088729, "percentage": 48.08, "elapsed_time": "1:28:19", "remaining_time": "1:35:23"}
+{"current_steps": 101, "total_steps": 208, "loss": 0.494, "lr": 1.2248601123708279e-05, "epoch": 0.9688249400479616, "percentage": 48.56, "elapsed_time": "1:31:16", "remaining_time": "1:36:42"}
+{"current_steps": 102, "total_steps": 208, "loss": 0.4916, "lr": 1.2084594195642367e-05, "epoch": 0.9784172661870504, "percentage": 49.04, "elapsed_time": "1:33:17", "remaining_time": "1:36:57"}
+{"current_steps": 103, "total_steps": 208, "loss": 0.491, "lr": 1.1919998928300203e-05, "epoch": 0.988009592326139, "percentage": 49.52, "elapsed_time": "1:35:15", "remaining_time": "1:37:06"}
+{"current_steps": 104, "total_steps": 208, "loss": 0.515, "lr": 1.1754861775740163e-05, "epoch": 0.9976019184652278, "percentage": 50.0, "elapsed_time": "1:37:08", "remaining_time": "1:37:08"}
+{"current_steps": 105, "total_steps": 208, "loss": 0.7678, "lr": 1.1589229344958e-05, "epoch": 1.0071942446043165, "percentage": 50.48, "elapsed_time": "1:38:52", "remaining_time": "1:36:59"}
+{"current_steps": 106, "total_steps": 208, "loss": 0.369, "lr": 1.1423148382732854e-05, "epoch": 1.0167865707434052, "percentage": 50.96, "elapsed_time": "1:40:20", "remaining_time": "1:36:32"}
+{"current_steps": 107, "total_steps": 208, "loss": 0.4232, "lr": 1.1256665762433798e-05, "epoch": 1.026378896882494, "percentage": 51.44, "elapsed_time": "1:41:52", "remaining_time": "1:36:10"}
+{"current_steps": 108, "total_steps": 208, "loss": 0.4268, "lr": 1.1089828470790694e-05, "epoch": 1.0359712230215827, "percentage": 51.92, "elapsed_time": "1:43:28", "remaining_time": "1:35:48"}
+{"current_steps": 109, "total_steps": 208, "loss": 0.4918, "lr": 1.092268359463302e-05, "epoch": 1.0455635491606714, "percentage": 52.4, "elapsed_time": "1:45:17", "remaining_time": "1:35:37"}
+{"current_steps": 110, "total_steps": 208, "loss": 0.4358, "lr": 1.0755278307600459e-05, "epoch": 1.0551558752997603, "percentage": 52.88, "elapsed_time": "1:47:00", "remaining_time": "1:35:19"}
+{"current_steps": 111, "total_steps": 208, "loss": 0.4003, "lr": 1.058765985682898e-05, "epoch": 1.064748201438849, "percentage": 53.37, "elapsed_time": "1:48:40", "remaining_time": "1:34:58"}
+{"current_steps": 112, "total_steps": 208, "loss": 0.3958, "lr": 1.0419875549616196e-05, "epoch": 1.0743405275779376, "percentage": 53.85, "elapsed_time": "1:50:30", "remaining_time": "1:34:43"}
+{"current_steps": 113, "total_steps": 208, "loss": 0.4657, "lr": 1.0251972740069724e-05, "epoch": 1.0839328537170263, "percentage": 54.33, "elapsed_time": "1:52:28", "remaining_time": "1:34:33"}
+{"current_steps": 114, "total_steps": 208, "loss": 0.4065, "lr": 1.0083998815742335e-05, "epoch": 1.0935251798561152, "percentage": 54.81, "elapsed_time": "1:54:14", "remaining_time": "1:34:11"}
+{"current_steps": 115, "total_steps": 208, "loss": 0.3775, "lr": 9.916001184257668e-06, "epoch": 1.1031175059952039, "percentage": 55.29, "elapsed_time": "1:55:28", "remaining_time": "1:33:23"}
+{"current_steps": 116, "total_steps": 208, "loss": 0.4429, "lr": 9.748027259930276e-06, "epoch": 1.1127098321342925, "percentage": 55.77, "elapsed_time": "1:57:24", "remaining_time": "1:33:07"}
+{"current_steps": 117, "total_steps": 208, "loss": 0.4807, "lr": 9.580124450383804e-06, "epoch": 1.1223021582733812, "percentage": 56.25, "elapsed_time": "1:59:27", "remaining_time": "1:32:54"}
+{"current_steps": 118, "total_steps": 208, "loss": 0.4069, "lr": 9.412340143171025e-06, "epoch": 1.13189448441247, "percentage": 56.73, "elapsed_time": "2:01:01", "remaining_time": "1:32:18"}
+{"current_steps": 119, "total_steps": 208, "loss": 0.4236, "lr": 9.244721692399545e-06, "epoch": 1.1414868105515588, "percentage": 57.21, "elapsed_time": "2:02:52", "remaining_time": "1:31:53"}
+{"current_steps": 120, "total_steps": 208, "loss": 0.4153, "lr": 9.07731640536698e-06, "epoch": 1.1510791366906474, "percentage": 57.69, "elapsed_time": "2:04:23", "remaining_time": "1:31:13"}
+{"current_steps": 121, "total_steps": 208, "loss": 0.4089, "lr": 8.910171529209306e-06, "epoch": 1.160671462829736, "percentage": 58.17, "elapsed_time": "2:06:10", "remaining_time": "1:30:43"}
+{"current_steps": 122, "total_steps": 208, "loss": 0.4567, "lr": 8.743334237566202e-06, "epoch": 1.170263788968825, "percentage": 58.65, "elapsed_time": "2:07:45", "remaining_time": "1:30:03"}
+{"current_steps": 123, "total_steps": 208, "loss": 0.4158, "lr": 8.576851617267151e-06, "epoch": 1.1798561151079137, "percentage": 59.13, "elapsed_time": "2:09:30", "remaining_time": "1:29:29"}
+{"current_steps": 124, "total_steps": 208, "loss": 0.4203, "lr": 8.410770655042003e-06, "epoch": 1.1894484412470023, "percentage": 59.62, "elapsed_time": "2:11:02", "remaining_time": "1:28:46"}
+{"current_steps": 125, "total_steps": 208, "loss": 0.4632, "lr": 8.24513822425984e-06, "epoch": 1.1990407673860912, "percentage": 60.1, "elapsed_time": "2:12:54", "remaining_time": "1:28:15"}
+{"current_steps": 126, "total_steps": 208, "loss": 0.4108, "lr": 8.0800010716998e-06, "epoch": 1.20863309352518, "percentage": 60.58, "elapsed_time": "2:14:45", "remaining_time": "1:27:42"}
+{"current_steps": 127, "total_steps": 208, "loss": 0.4008, "lr": 7.915405804357632e-06, "epoch": 1.2182254196642686, "percentage": 61.06, "elapsed_time": "2:16:25", "remaining_time": "1:27:00"}
+{"current_steps": 128, "total_steps": 208, "loss": 0.4096, "lr": 7.751398876291725e-06, "epoch": 1.2278177458033572, "percentage": 61.54, "elapsed_time": "2:17:50", "remaining_time": "1:26:09"}
+{"current_steps": 129, "total_steps": 208, "loss": 0.4696, "lr": 7.58802657551225e-06, "epoch": 1.2374100719424461, "percentage": 62.02, "elapsed_time": "2:19:46", "remaining_time": "1:25:36"}
+{"current_steps": 130, "total_steps": 208, "loss": 0.4096, "lr": 7.425335010917244e-06, "epoch": 1.2470023980815348, "percentage": 62.5, "elapsed_time": "2:21:37", "remaining_time": "1:24:58"}
+{"current_steps": 131, "total_steps": 208, "loss": 0.5086, "lr": 7.263370099279173e-06, "epoch": 1.2565947242206235, "percentage": 62.98, "elapsed_time": "2:23:45", "remaining_time": "1:24:30"}
+{"current_steps": 132, "total_steps": 208, "loss": 0.3724, "lr": 7.102177552285753e-06, "epoch": 1.2661870503597124, "percentage": 63.46, "elapsed_time": "2:25:05", "remaining_time": "1:23:32"}
+{"current_steps": 133, "total_steps": 208, "loss": 0.4146, "lr": 6.9418028636386595e-06, "epoch": 1.275779376498801, "percentage": 63.94, "elapsed_time": "2:26:33", "remaining_time": "1:22:38"}
+{"current_steps": 134, "total_steps": 208, "loss": 0.426, "lr": 6.7822912962137225e-06, "epoch": 1.2853717026378897, "percentage": 64.42, "elapsed_time": "2:28:20", "remaining_time": "1:21:55"}
+{"current_steps": 135, "total_steps": 208, "loss": 0.4367, "lr": 6.623687869286314e-06, "epoch": 1.2949640287769784, "percentage": 64.9, "elapsed_time": "2:30:10", "remaining_time": "1:21:12"}
+{"current_steps": 136, "total_steps": 208, "loss": 0.4187, "lr": 6.466037345825462e-06, "epoch": 1.304556354916067, "percentage": 65.38, "elapsed_time": "2:32:02", "remaining_time": "1:20:29"}
+{"current_steps": 137, "total_steps": 208, "loss": 0.419, "lr": 6.3093842198603014e-06, "epoch": 1.314148681055156, "percentage": 65.87, "elapsed_time": "2:33:50", "remaining_time": "1:19:43"}
+{"current_steps": 138, "total_steps": 208, "loss": 0.4023, "lr": 6.153772703922434e-06, "epoch": 1.3237410071942446, "percentage": 66.35, "elapsed_time": "2:35:16", "remaining_time": "1:18:45"}
+{"current_steps": 139, "total_steps": 208, "loss": 0.4144, "lr": 5.999246716567737e-06, "epoch": 1.3333333333333333, "percentage": 66.83, "elapsed_time": "2:37:08", "remaining_time": "1:18:00"}
+{"current_steps": 140, "total_steps": 208, "loss": 0.4116, "lr": 5.845849869981137e-06, "epoch": 1.3429256594724222, "percentage": 67.31, "elapsed_time": "2:38:48", "remaining_time": "1:17:08"}
+{"current_steps": 141, "total_steps": 208, "loss": 0.3824, "lr": 5.693625457667862e-06, "epoch": 1.3525179856115108, "percentage": 67.79, "elapsed_time": "2:40:22", "remaining_time": "1:16:12"}
+{"current_steps": 142, "total_steps": 208, "loss": 0.4488, "lr": 5.542616442234618e-06, "epoch": 1.3621103117505995, "percentage": 68.27, "elapsed_time": "2:42:19", "remaining_time": "1:15:26"}
+{"current_steps": 143, "total_steps": 208, "loss": 0.4348, "lr": 5.392865443264164e-06, "epoch": 1.3717026378896882, "percentage": 68.75, "elapsed_time": "2:44:09", "remaining_time": "1:14:36"}
+{"current_steps": 144, "total_steps": 208, "loss": 0.4364, "lr": 5.244414725286717e-06, "epoch": 1.381294964028777, "percentage": 69.23, "elapsed_time": "2:46:02", "remaining_time": "1:13:47"}
+{"current_steps": 145, "total_steps": 208, "loss": 0.4401, "lr": 5.097306185851515e-06, "epoch": 1.3908872901678657, "percentage": 69.71, "elapsed_time": "2:47:49", "remaining_time": "1:12:54"}
+{"current_steps": 146, "total_steps": 208, "loss": 0.4094, "lr": 4.951581343702014e-06, "epoch": 1.4004796163069544, "percentage": 70.19, "elapsed_time": "2:49:38", "remaining_time": "1:12:02"}
+{"current_steps": 147, "total_steps": 208, "loss": 0.4293, "lr": 4.807281327057972e-06, "epoch": 1.4100719424460433, "percentage": 70.67, "elapsed_time": "2:51:23", "remaining_time": "1:11:07"}
+{"current_steps": 148, "total_steps": 208, "loss": 0.3955, "lr": 4.664446862007718e-06, "epoch": 1.419664268585132, "percentage": 71.15, "elapsed_time": "2:53:14", "remaining_time": "1:10:14"}
+{"current_steps": 149, "total_steps": 208, "loss": 0.4822, "lr": 4.523118261013969e-06, "epoch": 1.4292565947242206, "percentage": 71.63, "elapsed_time": "2:54:55", "remaining_time": "1:09:15"}
+{"current_steps": 150, "total_steps": 208, "loss": 0.4023, "lr": 4.383335411536357e-06, "epoch": 1.4388489208633093, "percentage": 72.12, "elapsed_time": "2:56:27", "remaining_time": "1:08:13"}
+{"current_steps": 151, "total_steps": 208, "loss": 0.4231, "lr": 4.245137764773899e-06, "epoch": 1.448441247002398, "percentage": 72.6, "elapsed_time": "2:59:36", "remaining_time": "1:07:48"}
+{"current_steps": 152, "total_steps": 208, "loss": 0.4024, "lr": 4.108564324530626e-06, "epoch": 1.4580335731414868, "percentage": 73.08, "elapsed_time": "3:01:10", "remaining_time": "1:06:44"}
+{"current_steps": 153, "total_steps": 208, "loss": 0.4622, "lr": 3.973653636207437e-06, "epoch": 1.4676258992805755, "percentage": 73.56, "elapsed_time": "3:03:03", "remaining_time": "1:05:48"}
+{"current_steps": 154, "total_steps": 208, "loss": 0.388, "lr": 3.840443775923365e-06, "epoch": 1.4772182254196642, "percentage": 74.04, "elapsed_time": "3:04:45", "remaining_time": "1:04:47"}
+{"current_steps": 155, "total_steps": 208, "loss": 0.4194, "lr": 3.70897233976927e-06, "epoch": 1.486810551558753, "percentage": 74.52, "elapsed_time": "3:06:17", "remaining_time": "1:03:42"}
+{"current_steps": 156, "total_steps": 208, "loss": 0.4246, "lr": 3.5792764331970187e-06, "epoch": 1.4964028776978417, "percentage": 75.0, "elapsed_time": "3:08:09", "remaining_time": "1:02:43"}
+{"current_steps": 157, "total_steps": 208, "loss": 0.3984, "lr": 3.4513926605471504e-06, "epoch": 1.5059952038369304, "percentage": 75.48, "elapsed_time": "3:09:30", "remaining_time": "1:01:33"}
+{"current_steps": 158, "total_steps": 208, "loss": 0.3675, "lr": 3.3253571147179333e-06, "epoch": 1.515587529976019, "percentage": 75.96, "elapsed_time": "3:11:32", "remaining_time": "1:00:36"}
+{"current_steps": 159, "total_steps": 208, "loss": 0.4977, "lr": 3.2012053669788136e-06, "epoch": 1.5251798561151078, "percentage": 76.44, "elapsed_time": "3:13:30", "remaining_time": "0:59:38"}
+{"current_steps": 160, "total_steps": 208, "loss": 0.4778, "lr": 3.0789724569310532e-06, "epoch": 1.5347721822541966, "percentage": 76.92, "elapsed_time": "3:15:41", "remaining_time": "0:58:42"}
+{"current_steps": 161, "total_steps": 208, "loss": 0.3675, "lr": 2.9586928826184323e-06, "epoch": 1.5443645083932853, "percentage": 77.4, "elapsed_time": "3:17:30", "remaining_time": "0:57:39"}
+{"current_steps": 162, "total_steps": 208, "loss": 0.457, "lr": 2.8404005907908083e-06, "epoch": 1.5539568345323742, "percentage": 77.88, "elapsed_time": "3:19:38", "remaining_time": "0:56:41"}
+{"current_steps": 163, "total_steps": 208, "loss": 0.4238, "lr": 2.724128967323234e-06, "epoch": 1.5635491606714629, "percentage": 78.37, "elapsed_time": "3:21:16", "remaining_time": "0:55:34"}
+{"current_steps": 164, "total_steps": 208, "loss": 0.4673, "lr": 2.6099108277934105e-06, "epoch": 1.5731414868105515, "percentage": 78.85, "elapsed_time": "3:23:29", "remaining_time": "0:54:35"}
+{"current_steps": 165, "total_steps": 208, "loss": 0.4199, "lr": 2.4977784082200728e-06, "epoch": 1.5827338129496402, "percentage": 79.33, "elapsed_time": "3:25:08", "remaining_time": "0:53:27"}
+{"current_steps": 166, "total_steps": 208, "loss": 0.4244, "lr": 2.3877633559649505e-06, "epoch": 1.5923261390887289, "percentage": 79.81, "elapsed_time": "3:26:48", "remaining_time": "0:52:19"}
+{"current_steps": 167, "total_steps": 208, "loss": 0.4078, "lr": 2.2798967208008806e-06, "epoch": 1.6019184652278178, "percentage": 80.29, "elapsed_time": "3:28:16", "remaining_time": "0:51:07"}
+{"current_steps": 168, "total_steps": 208, "loss": 0.4389, "lr": 2.1742089461485504e-06, "epoch": 1.6115107913669064, "percentage": 80.77, "elapsed_time": "3:29:49", "remaining_time": "0:49:57"}
+{"current_steps": 169, "total_steps": 208, "loss": 0.4174, "lr": 2.0707298604843964e-06, "epoch": 1.6211031175059953, "percentage": 81.25, "elapsed_time": "3:31:46", "remaining_time": "0:48:52"}
+{"current_steps": 170, "total_steps": 208, "loss": 0.4078, "lr": 1.9694886689220592e-06, "epoch": 1.630695443645084, "percentage": 81.73, "elapsed_time": "3:33:19", "remaining_time": "0:47:40"}
+{"current_steps": 171, "total_steps": 208, "loss": 0.4606, "lr": 1.870513944969743e-06, "epoch": 1.6402877697841727, "percentage": 82.21, "elapsed_time": "3:35:22", "remaining_time": "0:46:36"}
+{"current_steps": 172, "total_steps": 208, "loss": 0.4026, "lr": 1.773833622465888e-06, "epoch": 1.6498800959232613, "percentage": 82.69, "elapsed_time": "3:36:48", "remaining_time": "0:45:22"}
+{"current_steps": 173, "total_steps": 208, "loss": 0.4181, "lr": 1.6794749876953187e-06, "epoch": 1.65947242206235, "percentage": 83.17, "elapsed_time": "3:38:29", "remaining_time": "0:44:12"}
+{"current_steps": 174, "total_steps": 208, "loss": 0.4696, "lr": 1.587464671688187e-06, "epoch": 1.6690647482014387, "percentage": 83.65, "elapsed_time": "3:40:17", "remaining_time": "0:43:02"}
+{"current_steps": 175, "total_steps": 208, "loss": 0.419, "lr": 1.4978286427038602e-06, "epoch": 1.6786570743405276, "percentage": 84.13, "elapsed_time": "3:41:49", "remaining_time": "0:41:49"}
+{"current_steps": 176, "total_steps": 208, "loss": 0.3954, "lr": 1.4105921989018112e-06, "epoch": 1.6882494004796165, "percentage": 84.62, "elapsed_time": "3:43:36", "remaining_time": "0:40:39"}
+{"current_steps": 177, "total_steps": 208, "loss": 0.448, "lr": 1.325779961201703e-06, "epoch": 1.6978417266187051, "percentage": 85.1, "elapsed_time": "3:45:25", "remaining_time": "0:39:28"}
+{"current_steps": 178, "total_steps": 208, "loss": 0.3593, "lr": 1.2434158663345553e-06, "epoch": 1.7074340527577938, "percentage": 85.58, "elapsed_time": "3:47:21", "remaining_time": "0:38:19"}
+{"current_steps": 179, "total_steps": 208, "loss": 0.4474, "lr": 1.1635231600870334e-06, "epoch": 1.7170263788968825, "percentage": 86.06, "elapsed_time": "3:48:51", "remaining_time": "0:37:04"}
+{"current_steps": 180, "total_steps": 208, "loss": 0.3887, "lr": 1.086124390740757e-06, "epoch": 1.7266187050359711, "percentage": 86.54, "elapsed_time": "3:50:36", "remaining_time": "0:35:52"}
+{"current_steps": 181, "total_steps": 208, "loss": 0.4204, "lr": 1.0112414027084262e-06, "epoch": 1.7362110311750598, "percentage": 87.02, "elapsed_time": "3:52:02", "remaining_time": "0:34:36"}
+{"current_steps": 151, "total_steps": 208, "loss": 0.4106, "lr": 4.245137764773899e-06, "epoch": 1.4508393285371701, "percentage": 72.6, "elapsed_time": "0:01:52", "remaining_time": "0:00:42"}
+{"current_steps": 152, "total_steps": 208, "loss": 0.4179, "lr": 4.108564324530626e-06, "epoch": 1.460431654676259, "percentage": 73.08, "elapsed_time": "0:03:35", "remaining_time": "0:01:19"}
+{"current_steps": 153, "total_steps": 208, "loss": 0.4202, "lr": 3.973653636207437e-06, "epoch": 1.4700239808153477, "percentage": 73.56, "elapsed_time": "0:05:21", "remaining_time": "0:01:55"}
+{"current_steps": 154, "total_steps": 208, "loss": 0.445, "lr": 3.840443775923365e-06, "epoch": 1.4796163069544366, "percentage": 74.04, "elapsed_time": "0:07:07", "remaining_time": "0:02:30"}
+{"current_steps": 155, "total_steps": 208, "loss": 0.417, "lr": 3.70897233976927e-06, "epoch": 1.4892086330935252, "percentage": 74.52, "elapsed_time": "0:08:49", "remaining_time": "0:03:01"}
+{"current_steps": 156, "total_steps": 208, "loss": 0.3848, "lr": 3.5792764331970187e-06, "epoch": 1.498800959232614, "percentage": 75.0, "elapsed_time": "0:10:26", "remaining_time": "0:03:28"}
+{"current_steps": 157, "total_steps": 208, "loss": 0.4239, "lr": 3.4513926605471504e-06, "epoch": 1.5083932853717026, "percentage": 75.48, "elapsed_time": "0:12:17", "remaining_time": "0:03:59"}
+{"current_steps": 158, "total_steps": 208, "loss": 0.4283, "lr": 3.3253571147179333e-06, "epoch": 1.5179856115107913, "percentage": 75.96, "elapsed_time": "0:14:14", "remaining_time": "0:04:30"}
+{"current_steps": 159, "total_steps": 208, "loss": 0.4337, "lr": 3.2012053669788136e-06, "epoch": 1.5275779376498801, "percentage": 76.44, "elapsed_time": "0:16:11", "remaining_time": "0:04:59"}
+{"current_steps": 160, "total_steps": 208, "loss": 0.4561, "lr": 3.0789724569310532e-06, "epoch": 1.5371702637889688, "percentage": 76.92, "elapsed_time": "0:18:27", "remaining_time": "0:05:32"}
+{"current_steps": 161, "total_steps": 208, "loss": 0.4186, "lr": 2.9586928826184323e-06, "epoch": 1.5467625899280577, "percentage": 77.4, "elapsed_time": "0:20:21", "remaining_time": "0:05:56"}
+{"current_steps": 162, "total_steps": 208, "loss": 0.4269, "lr": 2.8404005907908083e-06, "epoch": 1.5563549160671464, "percentage": 77.88, "elapsed_time": "0:22:17", "remaining_time": "0:06:19"}
+{"current_steps": 163, "total_steps": 208, "loss": 0.4438, "lr": 2.724128967323234e-06, "epoch": 1.565947242206235, "percentage": 78.37, "elapsed_time": "0:24:17", "remaining_time": "0:06:42"}
+{"current_steps": 164, "total_steps": 208, "loss": 0.4366, "lr": 2.6099108277934105e-06, "epoch": 1.5755395683453237, "percentage": 78.85, "elapsed_time": "0:26:16", "remaining_time": "0:07:03"}
+{"current_steps": 165, "total_steps": 208, "loss": 0.418, "lr": 2.4977784082200728e-06, "epoch": 1.5851318944844124, "percentage": 79.33, "elapsed_time": "0:27:57", "remaining_time": "0:07:17"}
+{"current_steps": 166, "total_steps": 208, "loss": 0.4286, "lr": 2.3877633559649505e-06, "epoch": 1.594724220623501, "percentage": 79.81, "elapsed_time": "0:29:32", "remaining_time": "0:07:28"}
+{"current_steps": 167, "total_steps": 208, "loss": 0.4065, "lr": 2.2798967208008806e-06, "epoch": 1.60431654676259, "percentage": 80.29, "elapsed_time": "0:31:00", "remaining_time": "0:07:36"}
+{"current_steps": 168, "total_steps": 208, "loss": 0.4223, "lr": 2.1742089461485504e-06, "epoch": 1.6139088729016786, "percentage": 80.77, "elapsed_time": "0:32:43", "remaining_time": "0:07:47"}
+{"current_steps": 169, "total_steps": 208, "loss": 0.4268, "lr": 2.0707298604843964e-06, "epoch": 1.6235011990407675, "percentage": 81.25, "elapsed_time": "0:34:40", "remaining_time": "0:08:00"}
+{"current_steps": 170, "total_steps": 208, "loss": 0.4283, "lr": 1.9694886689220592e-06, "epoch": 1.6330935251798562, "percentage": 81.73, "elapsed_time": "0:36:20", "remaining_time": "0:08:07"}
+{"current_steps": 171, "total_steps": 208, "loss": 0.4306, "lr": 1.870513944969743e-06, "epoch": 1.6426858513189448, "percentage": 82.21, "elapsed_time": "0:38:19", "remaining_time": "0:08:17"}
+{"current_steps": 172, "total_steps": 208, "loss": 0.4026, "lr": 1.773833622465888e-06, "epoch": 1.6522781774580335, "percentage": 82.69, "elapsed_time": "0:39:44", "remaining_time": "0:08:19"}
+{"current_steps": 173, "total_steps": 208, "loss": 0.4487, "lr": 1.6794749876953187e-06, "epoch": 1.6618705035971222, "percentage": 83.17, "elapsed_time": "0:41:31", "remaining_time": "0:08:24"}
+{"current_steps": 174, "total_steps": 208, "loss": 0.4163, "lr": 1.587464671688187e-06, "epoch": 1.671462829736211, "percentage": 83.65, "elapsed_time": "0:43:07", "remaining_time": "0:08:25"}
+{"current_steps": 175, "total_steps": 208, "loss": 0.4302, "lr": 1.4978286427038602e-06, "epoch": 1.6810551558752997, "percentage": 84.13, "elapsed_time": "0:44:48", "remaining_time": "0:08:27"}
+{"current_steps": 176, "total_steps": 208, "loss": 0.4173, "lr": 1.4105921989018112e-06, "epoch": 1.6906474820143886, "percentage": 84.62, "elapsed_time": "0:46:47", "remaining_time": "0:08:30"}
+{"current_steps": 177, "total_steps": 208, "loss": 0.4112, "lr": 1.325779961201703e-06, "epoch": 1.7002398081534773, "percentage": 85.1, "elapsed_time": "0:48:31", "remaining_time": "0:08:29"}
+{"current_steps": 178, "total_steps": 208, "loss": 0.4059, "lr": 1.2434158663345553e-06, "epoch": 1.709832134292566, "percentage": 85.58, "elapsed_time": "0:50:25", "remaining_time": "0:08:29"}
+{"current_steps": 179, "total_steps": 208, "loss": 0.4323, "lr": 1.1635231600870334e-06, "epoch": 1.7194244604316546, "percentage": 86.06, "elapsed_time": "0:51:53", "remaining_time": "0:08:24"}
+{"current_steps": 180, "total_steps": 208, "loss": 0.4115, "lr": 1.086124390740757e-06, "epoch": 1.7290167865707433, "percentage": 86.54, "elapsed_time": "0:53:55", "remaining_time": "0:08:23"}
+{"current_steps": 181, "total_steps": 208, "loss": 0.4159, "lr": 1.0112414027084262e-06, "epoch": 1.738609112709832, "percentage": 87.02, "elapsed_time": "0:55:25", "remaining_time": "0:08:15"}
+{"current_steps": 182, "total_steps": 208, "loss": 0.4363, "lr": 9.388953303686587e-07, "epoch": 1.7482014388489209, "percentage": 87.5, "elapsed_time": "0:57:20", "remaining_time": "0:08:11"}
+{"current_steps": 183, "total_steps": 208, "loss": 0.4019, "lr": 8.691065921011687e-07, "epoch": 1.7577937649880095, "percentage": 87.98, "elapsed_time": "0:58:45", "remaining_time": "0:08:01"}
+{"current_steps": 184, "total_steps": 208, "loss": 0.415, "lr": 8.018948845240538e-07, "epoch": 1.7673860911270984, "percentage": 88.46, "elapsed_time": "1:00:36", "remaining_time": "0:07:54"}
+{"current_steps": 185, "total_steps": 208, "loss": 0.4187, "lr": 7.372791769347843e-07, "epoch": 1.776978417266187, "percentage": 88.94, "elapsed_time": "1:02:15", "remaining_time": "0:07:44"}
+{"current_steps": 186, "total_steps": 208, "loss": 0.3999, "lr": 6.752777059564431e-07, "epoch": 1.7865707434052758, "percentage": 89.42, "elapsed_time": "1:03:49", "remaining_time": "0:07:32"}
+{"current_steps": 187, "total_steps": 208, "loss": 0.4122, "lr": 6.159079703907823e-07, "epoch": 1.7961630695443644, "percentage": 89.9, "elapsed_time": "1:06:02", "remaining_time": "0:07:24"}
+{"current_steps": 188, "total_steps": 208, "loss": 0.3995, "lr": 5.591867262794969e-07, "epoch": 1.8057553956834531, "percentage": 90.38, "elapsed_time": "1:07:31", "remaining_time": "0:07:11"}
+{"current_steps": 189, "total_steps": 208, "loss": 0.4226, "lr": 5.051299821751254e-07, "epoch": 1.815347721822542, "percentage": 90.87, "elapsed_time": "1:09:28", "remaining_time": "0:06:59"}
+{"current_steps": 190, "total_steps": 208, "loss": 0.4082, "lr": 4.537529946229369e-07, "epoch": 1.8249400479616307, "percentage": 91.35, "elapsed_time": "1:11:23", "remaining_time": "0:06:45"}
+{"current_steps": 191, "total_steps": 208, "loss": 0.4066, "lr": 4.0507026385502747e-07, "epoch": 1.8345323741007196, "percentage": 91.83, "elapsed_time": "1:12:58", "remaining_time": "0:06:29"}
+{"current_steps": 192, "total_steps": 208, "loss": 0.4452, "lr": 3.5909552969790376e-07, "epoch": 1.8441247002398082, "percentage": 92.31, "elapsed_time": "1:14:43", "remaining_time": "0:06:13"}
+{"current_steps": 193, "total_steps": 208, "loss": 0.4295, "lr": 3.158417676946635e-07, "epoch": 1.853717026378897, "percentage": 92.79, "elapsed_time": "1:16:31", "remaining_time": "0:05:56"}
+{"current_steps": 194, "total_steps": 208, "loss": 0.4265, "lr": 2.753211854428728e-07, "epoch": 1.8633093525179856, "percentage": 93.27, "elapsed_time": "1:18:09", "remaining_time": "0:05:38"}
+{"current_steps": 195, "total_steps": 208, "loss": 0.451, "lr": 2.375452191491967e-07, "epoch": 1.8729016786570742, "percentage": 93.75, "elapsed_time": "1:20:29", "remaining_time": "0:05:21"}
+{"current_steps": 196, "total_steps": 208, "loss": 0.4096, "lr": 2.0252453040173646e-07, "epoch": 1.882494004796163, "percentage": 94.23, "elapsed_time": "1:22:26", "remaining_time": "0:05:02"}
+{"current_steps": 197, "total_steps": 208, "loss": 0.3775, "lr": 1.7026900316098217e-07, "epoch": 1.8920863309352518, "percentage": 94.71, "elapsed_time": "1:23:53", "remaining_time": "0:04:41"}
+{"current_steps": 198, "total_steps": 208, "loss": 0.4398, "lr": 1.407877409702496e-07, "epoch": 1.9016786570743405, "percentage": 95.19, "elapsed_time": "1:25:21", "remaining_time": "0:04:18"}
+{"current_steps": 199, "total_steps": 208, "loss": 0.4296, "lr": 1.1408906438636236e-07, "epoch": 1.9112709832134294, "percentage": 95.67, "elapsed_time": "1:27:08", "remaining_time": "0:03:56"}
+{"current_steps": 200, "total_steps": 208, "loss": 0.4384, "lr": 9.018050863132566e-08, "epoch": 1.920863309352518, "percentage": 96.15, "elapsed_time": "1:29:08", "remaining_time": "0:03:33"}
+{"current_steps": 201, "total_steps": 208, "loss": 0.4164, "lr": 6.906882146565097e-08, "epoch": 1.9304556354916067, "percentage": 96.63, "elapsed_time": "1:32:19", "remaining_time": "0:03:12"}
+{"current_steps": 202, "total_steps": 208, "loss": 0.4191, "lr": 5.0759961283911584e-08, "epoch": 1.9400479616306954, "percentage": 97.12, "elapsed_time": "1:34:01", "remaining_time": "0:02:47"}
+{"current_steps": 203, "total_steps": 208, "loss": 0.4142, "lr": 3.525909543310002e-08, "epoch": 1.949640287769784, "percentage": 97.6, "elapsed_time": "1:35:49", "remaining_time": "0:02:21"}
+{"current_steps": 204, "total_steps": 208, "loss": 0.4255, "lr": 2.257059875423795e-08, "epoch": 1.959232613908873, "percentage": 98.08, "elapsed_time": "1:37:53", "remaining_time": "0:01:55"}
+{"current_steps": 205, "total_steps": 208, "loss": 0.4466, "lr": 1.2698052347649426e-08, "epoch": 1.9688249400479616, "percentage": 98.56, "elapsed_time": "1:39:54", "remaining_time": "0:01:27"}
+{"current_steps": 206, "total_steps": 208, "loss": 0.3985, "lr": 5.644242562264923e-09, "epoch": 1.9784172661870505, "percentage": 99.04, "elapsed_time": "1:41:48", "remaining_time": "0:00:59"}
+{"current_steps": 207, "total_steps": 208, "loss": 0.441, "lr": 1.4111602092226062e-09, "epoch": 1.9880095923261392, "percentage": 99.52, "elapsed_time": "1:44:03", "remaining_time": "0:00:30"}
+{"current_steps": 208, "total_steps": 208, "loss": 0.4339, "lr": 0.0, "epoch": 1.9976019184652278, "percentage": 100.0, "elapsed_time": "1:45:59", "remaining_time": "0:00:00"}
+{"current_steps": 208, "total_steps": 208, "epoch": 1.9976019184652278, "percentage": 100.0, "elapsed_time": "1:47:19", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1498 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9976019184652278,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009592326139088728,
+      "grad_norm": 2.9696555137634277,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 0.7616,
+      "step": 1
+    },
+    {
+      "epoch": 0.019184652278177457,
+      "grad_norm": 2.9819626808166504,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 0.8093,
+      "step": 2
+    },
+    {
+      "epoch": 0.02877697841726619,
+      "grad_norm": 2.8761885166168213,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.8114,
+      "step": 3
+    },
+    {
+      "epoch": 0.03836930455635491,
+      "grad_norm": 2.6478004455566406,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 0.7994,
+      "step": 4
+    },
+    {
+      "epoch": 0.047961630695443645,
+      "grad_norm": 2.2247092723846436,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.7662,
+      "step": 5
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 2.1519033908843994,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.7797,
+      "step": 6
+    },
+    {
+      "epoch": 0.0671462829736211,
+      "grad_norm": 1.6199476718902588,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7279,
+      "step": 7
+    },
+    {
+      "epoch": 0.07673860911270983,
+      "grad_norm": 1.9333553314208984,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 0.7203,
+      "step": 8
+    },
+    {
+      "epoch": 0.08633093525179857,
+      "grad_norm": 1.8156510591506958,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.733,
+      "step": 9
+    },
+    {
+      "epoch": 0.09592326139088729,
+      "grad_norm": 1.3204002380371094,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.6486,
+      "step": 10
+    },
+    {
+      "epoch": 0.10551558752997602,
+      "grad_norm": 1.4889897108078003,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 0.6576,
+      "step": 11
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 0.9800885915756226,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.6284,
+      "step": 12
+    },
+    {
+      "epoch": 0.12470023980815348,
+      "grad_norm": 0.8177942633628845,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 0.649,
+      "step": 13
+    },
+    {
+      "epoch": 0.1342925659472422,
+      "grad_norm": 1.1905466318130493,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6369,
+      "step": 14
+    },
+    {
+      "epoch": 0.14388489208633093,
+      "grad_norm": 1.0374023914337158,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.6114,
+      "step": 15
+    },
+    {
+      "epoch": 0.15347721822541965,
+      "grad_norm": 1.0067347288131714,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 0.6142,
+      "step": 16
+    },
+    {
+      "epoch": 0.1630695443645084,
+      "grad_norm": 0.7811371088027954,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.5983,
+      "step": 17
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 0.8175334334373474,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.585,
+      "step": 18
+    },
+    {
+      "epoch": 0.18225419664268586,
+      "grad_norm": 0.8208688497543335,
+      "learning_rate": 1.8095238095238097e-05,
+      "loss": 0.6167,
+      "step": 19
+    },
+    {
+      "epoch": 0.19184652278177458,
+      "grad_norm": 0.6435378789901733,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.561,
+      "step": 20
+    },
+    {
+      "epoch": 0.2014388489208633,
+      "grad_norm": 0.6469037532806396,
+      "learning_rate": 2e-05,
+      "loss": 0.5779,
+      "step": 21
+    },
+    {
+      "epoch": 0.21103117505995203,
+      "grad_norm": 0.712081253528595,
+      "learning_rate": 1.9998588839790777e-05,
+      "loss": 0.5944,
+      "step": 22
+    },
+    {
+      "epoch": 0.22062350119904076,
+      "grad_norm": 0.4959125220775604,
+      "learning_rate": 1.999435575743774e-05,
+      "loss": 0.5512,
+      "step": 23
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 0.5561655759811401,
+      "learning_rate": 1.9987301947652354e-05,
+      "loss": 0.5776,
+      "step": 24
+    },
+    {
+      "epoch": 0.23980815347721823,
+      "grad_norm": 0.5795208215713501,
+      "learning_rate": 1.9977429401245764e-05,
+      "loss": 0.5843,
+      "step": 25
+    },
+    {
+      "epoch": 0.24940047961630696,
+      "grad_norm": 0.5561151504516602,
+      "learning_rate": 1.9964740904566903e-05,
+      "loss": 0.5571,
+      "step": 26
+    },
+    {
+      "epoch": 0.2589928057553957,
+      "grad_norm": 0.47304224967956543,
+      "learning_rate": 1.9949240038716092e-05,
+      "loss": 0.5383,
+      "step": 27
+    },
+    {
+      "epoch": 0.2685851318944844,
+      "grad_norm": 0.530933141708374,
+      "learning_rate": 1.9930931178534353e-05,
+      "loss": 0.5437,
+      "step": 28
+    },
+    {
+      "epoch": 0.27817745803357313,
+      "grad_norm": 0.501769483089447,
+      "learning_rate": 1.9909819491368677e-05,
+      "loss": 0.5392,
+      "step": 29
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.4704575836658478,
+      "learning_rate": 1.988591093561364e-05,
+      "loss": 0.5536,
+      "step": 30
+    },
+    {
+      "epoch": 0.2973621103117506,
+      "grad_norm": 0.4151773750782013,
+      "learning_rate": 1.985921225902975e-05,
+      "loss": 0.5515,
+      "step": 31
+    },
+    {
+      "epoch": 0.3069544364508393,
+      "grad_norm": 0.36268681287765503,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 0.527,
+      "step": 32
+    },
+    {
+      "epoch": 0.31654676258992803,
+      "grad_norm": 0.42509084939956665,
+      "learning_rate": 1.9797475469598267e-05,
+      "loss": 0.5314,
+      "step": 33
+    },
+    {
+      "epoch": 0.3261390887290168,
+      "grad_norm": 0.41967424750328064,
+      "learning_rate": 1.9762454780850807e-05,
+      "loss": 0.5265,
+      "step": 34
+    },
+    {
+      "epoch": 0.33573141486810554,
+      "grad_norm": 0.3834385871887207,
+      "learning_rate": 1.972467881455713e-05,
+      "loss": 0.5424,
+      "step": 35
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 0.38314002752304077,
+      "learning_rate": 1.968415823230534e-05,
+      "loss": 0.5316,
+      "step": 36
+    },
+    {
+      "epoch": 0.354916067146283,
+      "grad_norm": 0.37963882088661194,
+      "learning_rate": 1.96409044703021e-05,
+      "loss": 0.5077,
+      "step": 37
+    },
+    {
+      "epoch": 0.3645083932853717,
+      "grad_norm": 0.42077991366386414,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.5526,
+      "step": 38
+    },
+    {
+      "epoch": 0.37410071942446044,
+      "grad_norm": 0.38076290488243103,
+      "learning_rate": 1.9546247005377065e-05,
+      "loss": 0.5157,
+      "step": 39
+    },
+    {
+      "epoch": 0.38369304556354916,
+      "grad_norm": 0.3871311843395233,
+      "learning_rate": 1.9494870017824877e-05,
+      "loss": 0.5015,
+      "step": 40
+    },
+    {
+      "epoch": 0.3932853717026379,
+      "grad_norm": 0.4013996124267578,
+      "learning_rate": 1.9440813273720504e-05,
+      "loss": 0.4995,
+      "step": 41
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 0.42125990986824036,
+      "learning_rate": 1.938409202960922e-05,
+      "loss": 0.49,
+      "step": 42
+    },
+    {
+      "epoch": 0.41247002398081534,
+      "grad_norm": 0.39803189039230347,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 0.5277,
+      "step": 43
+    },
+    {
+      "epoch": 0.42206235011990406,
+      "grad_norm": 0.3990386724472046,
+      "learning_rate": 1.9262720823065217e-05,
+      "loss": 0.5318,
+      "step": 44
+    },
+    {
+      "epoch": 0.4316546762589928,
+      "grad_norm": 0.36926716566085815,
+      "learning_rate": 1.9198105115475946e-05,
+      "loss": 0.5101,
+      "step": 45
+    },
+    {
+      "epoch": 0.4412470023980815,
+      "grad_norm": 0.4282250702381134,
+      "learning_rate": 1.9130893407898834e-05,
+      "loss": 0.5197,
+      "step": 46
+    },
+    {
+      "epoch": 0.45083932853717024,
+      "grad_norm": 0.3543744385242462,
+      "learning_rate": 1.9061104669631343e-05,
+      "loss": 0.5029,
+      "step": 47
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 0.3961417078971863,
+      "learning_rate": 1.8988758597291577e-05,
+      "loss": 0.5247,
+      "step": 48
+    },
+    {
+      "epoch": 0.47002398081534774,
+      "grad_norm": 0.3576875627040863,
+      "learning_rate": 1.8913875609259246e-05,
+      "loss": 0.4924,
+      "step": 49
+    },
+    {
+      "epoch": 0.47961630695443647,
+      "grad_norm": 0.39000141620635986,
+      "learning_rate": 1.8836476839912967e-05,
+      "loss": 0.508,
+      "step": 50
+    },
+    {
+      "epoch": 0.4892086330935252,
+      "grad_norm": 0.3909335136413574,
+      "learning_rate": 1.8756584133665447e-05,
+      "loss": 0.5216,
+      "step": 51
+    },
+    {
+      "epoch": 0.4988009592326139,
+      "grad_norm": 0.39766091108322144,
+      "learning_rate": 1.86742200387983e-05,
+      "loss": 0.52,
+      "step": 52
+    },
+    {
+      "epoch": 0.5083932853717026,
+      "grad_norm": 0.34101566672325134,
+      "learning_rate": 1.8589407801098192e-05,
+      "loss": 0.4674,
+      "step": 53
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 0.43114396929740906,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 0.507,
+      "step": 54
+    },
+    {
+      "epoch": 0.5275779376498801,
+      "grad_norm": 0.38922569155693054,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.5194,
+      "step": 55
+    },
+    {
+      "epoch": 0.5371702637889688,
+      "grad_norm": 0.3502518832683563,
+      "learning_rate": 1.8320525012304685e-05,
+      "loss": 0.486,
+      "step": 56
+    },
+    {
+      "epoch": 0.5467625899280576,
+      "grad_norm": 0.3923037648200989,
+      "learning_rate": 1.8226166377534113e-05,
+      "loss": 0.4917,
+      "step": 57
+    },
+    {
+      "epoch": 0.5563549160671463,
+      "grad_norm": 0.3637664318084717,
+      "learning_rate": 1.8129486055030255e-05,
+      "loss": 0.5226,
+      "step": 58
+    },
+    {
+      "epoch": 0.565947242206235,
+      "grad_norm": 0.401072233915329,
+      "learning_rate": 1.8030511331077945e-05,
+      "loss": 0.4607,
+      "step": 59
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.3727758824825287,
+      "learning_rate": 1.7929270139515606e-05,
+      "loss": 0.4935,
+      "step": 60
+    },
+    {
+      "epoch": 0.5851318944844125,
+      "grad_norm": 0.41193482279777527,
+      "learning_rate": 1.782579105385145e-05,
+      "loss": 0.4741,
+      "step": 61
+    },
+    {
+      "epoch": 0.5947242206235012,
+      "grad_norm": 0.3923046588897705,
+      "learning_rate": 1.772010327919912e-05,
+      "loss": 0.5172,
+      "step": 62
+    },
+    {
+      "epoch": 0.60431654676259,
+      "grad_norm": 0.3971167802810669,
+      "learning_rate": 1.761223664403505e-05,
+      "loss": 0.5039,
+      "step": 63
+    },
+    {
+      "epoch": 0.6139088729016786,
+      "grad_norm": 0.3540147840976715,
+      "learning_rate": 1.7502221591779932e-05,
+      "loss": 0.4952,
+      "step": 64
+    },
+    {
+      "epoch": 0.6235011990407674,
+      "grad_norm": 0.40841755270957947,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.5115,
+      "step": 65
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 0.37069812417030334,
+      "learning_rate": 1.727587103267677e-05,
+      "loss": 0.5046,
+      "step": 66
+    },
+    {
+      "epoch": 0.6426858513189448,
+      "grad_norm": 0.40236225724220276,
+      "learning_rate": 1.7159599409209194e-05,
+      "loss": 0.5404,
+      "step": 67
+    },
+    {
+      "epoch": 0.6522781774580336,
+      "grad_norm": 0.4000904858112335,
+      "learning_rate": 1.704130711738157e-05,
+      "loss": 0.4542,
+      "step": 68
+    },
+    {
+      "epoch": 0.6618705035971223,
+      "grad_norm": 0.38863110542297363,
+      "learning_rate": 1.692102754306895e-05,
+      "loss": 0.4984,
+      "step": 69
+    },
+    {
+      "epoch": 0.6714628297362111,
+      "grad_norm": 0.4343845844268799,
+      "learning_rate": 1.6798794633021192e-05,
+      "loss": 0.4983,
+      "step": 70
+    },
+    {
+      "epoch": 0.6810551558752997,
+      "grad_norm": 0.41532468795776367,
+      "learning_rate": 1.667464288528207e-05,
+      "loss": 0.5032,
+      "step": 71
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.383349746465683,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.4894,
+      "step": 72
+    },
+    {
+      "epoch": 0.7002398081534772,
+      "grad_norm": 0.42376449704170227,
+      "learning_rate": 1.6420723566802982e-05,
+      "loss": 0.4888,
+      "step": 73
+    },
+    {
+      "epoch": 0.709832134292566,
+      "grad_norm": 0.37497472763061523,
+      "learning_rate": 1.6291027660230735e-05,
+      "loss": 0.4992,
+      "step": 74
+    },
+    {
+      "epoch": 0.7194244604316546,
+      "grad_norm": 0.37608063220977783,
+      "learning_rate": 1.6159556224076637e-05,
+      "loss": 0.4777,
+      "step": 75
+    },
+    {
+      "epoch": 0.7290167865707434,
+      "grad_norm": 0.3530066907405853,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 0.5104,
+      "step": 76
+    },
+    {
+      "epoch": 0.7386091127098321,
+      "grad_norm": 0.3600369691848755,
+      "learning_rate": 1.5891435675469376e-05,
+      "loss": 0.5115,
+      "step": 77
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 0.3592014014720917,
+      "learning_rate": 1.57548622352261e-05,
+      "loss": 0.5104,
+      "step": 78
+    },
+    {
+      "epoch": 0.7577937649880095,
+      "grad_norm": 0.4462052881717682,
+      "learning_rate": 1.561666458846365e-05,
+      "loss": 0.4944,
+      "step": 79
+    },
+    {
+      "epoch": 0.7673860911270983,
+      "grad_norm": 0.396361768245697,
+      "learning_rate": 1.5476881738986037e-05,
+      "loss": 0.5092,
+      "step": 80
+    },
+    {
+      "epoch": 0.7769784172661871,
+      "grad_norm": 0.34244418144226074,
+      "learning_rate": 1.5335553137992286e-05,
+      "loss": 0.4602,
+      "step": 81
+    },
+    {
+      "epoch": 0.7865707434052758,
+      "grad_norm": 0.46860936284065247,
+      "learning_rate": 1.519271867294203e-05,
+      "loss": 0.4818,
+      "step": 82
+    },
+    {
+      "epoch": 0.7961630695443646,
+      "grad_norm": 0.3834230899810791,
+      "learning_rate": 1.504841865629799e-05,
+      "loss": 0.5304,
+      "step": 83
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.3659767210483551,
+      "learning_rate": 1.490269381414849e-05,
+      "loss": 0.5299,
+      "step": 84
+    },
+    {
+      "epoch": 0.815347721822542,
+      "grad_norm": 0.32778194546699524,
+      "learning_rate": 1.4755585274713289e-05,
+      "loss": 0.4781,
+      "step": 85
+    },
+    {
+      "epoch": 0.8249400479616307,
+      "grad_norm": 0.31894972920417786,
+      "learning_rate": 1.4607134556735836e-05,
+      "loss": 0.4576,
+      "step": 86
+    },
+    {
+      "epoch": 0.8345323741007195,
+      "grad_norm": 0.39927753806114197,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.5182,
+      "step": 87
+    },
+    {
+      "epoch": 0.8441247002398081,
+      "grad_norm": 0.3539075553417206,
+      "learning_rate": 1.4306374542332141e-05,
+      "loss": 0.4952,
+      "step": 88
+    },
+    {
+      "epoch": 0.8537170263788969,
+      "grad_norm": 0.35559773445129395,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.4836,
+      "step": 89
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.39313530921936035,
+      "learning_rate": 1.4000753283432267e-05,
+      "loss": 0.5144,
+      "step": 90
+    },
+    {
+      "epoch": 0.8729016786570744,
+      "grad_norm": 0.35766634345054626,
+      "learning_rate": 1.3846227296077568e-05,
+      "loss": 0.5008,
+      "step": 91
+    },
+    {
+      "epoch": 0.882494004796163,
+      "grad_norm": 0.3517184853553772,
+      "learning_rate": 1.3690615780139703e-05,
+      "loss": 0.4742,
+      "step": 92
+    },
+    {
+      "epoch": 0.8920863309352518,
+      "grad_norm": 0.3641684055328369,
+      "learning_rate": 1.3533962654174542e-05,
+      "loss": 0.4993,
+      "step": 93
+    },
+    {
+      "epoch": 0.9016786570743405,
+      "grad_norm": 0.3608703911304474,
+      "learning_rate": 1.337631213071369e-05,
+      "loss": 0.4823,
+      "step": 94
+    },
+    {
+      "epoch": 0.9112709832134293,
+      "grad_norm": 0.359666109085083,
+      "learning_rate": 1.321770870378628e-05,
+      "loss": 0.4882,
+      "step": 95
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.364860862493515,
+      "learning_rate": 1.3058197136361344e-05,
+      "loss": 0.4882,
+      "step": 96
+    },
+    {
+      "epoch": 0.9304556354916067,
+      "grad_norm": 0.39230814576148987,
+      "learning_rate": 1.2897822447714247e-05,
+      "loss": 0.4943,
+      "step": 97
+    },
+    {
+      "epoch": 0.9400479616306955,
+      "grad_norm": 0.3717727065086365,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.4723,
+      "step": 98
+    },
+    {
+      "epoch": 0.9496402877697842,
+      "grad_norm": 0.4326834976673126,
+      "learning_rate": 1.257466498908276e-05,
+      "loss": 0.4867,
+      "step": 99
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "grad_norm": 0.3796863853931427,
+      "learning_rate": 1.2411973424487751e-05,
+      "loss": 0.5095,
+      "step": 100
+    },
+    {
+      "epoch": 0.9688249400479616,
+      "grad_norm": 0.4415254592895508,
+      "learning_rate": 1.2248601123708279e-05,
+      "loss": 0.494,
+      "step": 101
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.34461161494255066,
+      "learning_rate": 1.2084594195642367e-05,
+      "loss": 0.4916,
+      "step": 102
+    },
+    {
+      "epoch": 0.988009592326139,
+      "grad_norm": 0.43720710277557373,
+      "learning_rate": 1.1919998928300203e-05,
+      "loss": 0.491,
+      "step": 103
+    },
+    {
+      "epoch": 0.9976019184652278,
+      "grad_norm": 0.39884787797927856,
+      "learning_rate": 1.1754861775740163e-05,
+      "loss": 0.515,
+      "step": 104
+    },
+    {
+      "epoch": 1.0071942446043165,
+      "grad_norm": 0.8768265247344971,
+      "learning_rate": 1.1589229344958e-05,
+      "loss": 0.7678,
+      "step": 105
+    },
+    {
+      "epoch": 1.0167865707434052,
+      "grad_norm": 0.46353015303611755,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.369,
+      "step": 106
+    },
+    {
+      "epoch": 1.026378896882494,
+      "grad_norm": 0.6758041381835938,
+      "learning_rate": 1.1256665762433798e-05,
+      "loss": 0.4232,
+      "step": 107
+    },
+    {
+      "epoch": 1.0359712230215827,
+      "grad_norm": 0.5311920046806335,
+      "learning_rate": 1.1089828470790694e-05,
+      "loss": 0.4268,
+      "step": 108
+    },
+    {
+      "epoch": 1.0455635491606714,
+      "grad_norm": 0.6828810572624207,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.4918,
+      "step": 109
+    },
+    {
+      "epoch": 1.0551558752997603,
+      "grad_norm": 0.6523643136024475,
+      "learning_rate": 1.0755278307600459e-05,
+      "loss": 0.4358,
+      "step": 110
+    },
+    {
+      "epoch": 1.064748201438849,
+      "grad_norm": 0.5224204063415527,
+      "learning_rate": 1.058765985682898e-05,
+      "loss": 0.4003,
+      "step": 111
+    },
+    {
+      "epoch": 1.0743405275779376,
+      "grad_norm": 0.5372710227966309,
+      "learning_rate": 1.0419875549616196e-05,
+      "loss": 0.3958,
+      "step": 112
+    },
+    {
+      "epoch": 1.0839328537170263,
+      "grad_norm": 0.6062539219856262,
+      "learning_rate": 1.0251972740069724e-05,
+      "loss": 0.4657,
+      "step": 113
+    },
+    {
+      "epoch": 1.0935251798561152,
+      "grad_norm": 0.4233975410461426,
+      "learning_rate": 1.0083998815742335e-05,
+      "loss": 0.4065,
+      "step": 114
+    },
+    {
+      "epoch": 1.1031175059952039,
+      "grad_norm": 0.4593757688999176,
+      "learning_rate": 9.916001184257668e-06,
+      "loss": 0.3775,
+      "step": 115
+    },
+    {
+      "epoch": 1.1127098321342925,
+      "grad_norm": 0.5032916069030762,
+      "learning_rate": 9.748027259930276e-06,
+      "loss": 0.4429,
+      "step": 116
+    },
+    {
+      "epoch": 1.1223021582733812,
+      "grad_norm": 0.4631021022796631,
+      "learning_rate": 9.580124450383804e-06,
+      "loss": 0.4807,
+      "step": 117
+    },
+    {
+      "epoch": 1.13189448441247,
+      "grad_norm": 0.4672567546367645,
+      "learning_rate": 9.412340143171025e-06,
+      "loss": 0.4069,
+      "step": 118
+    },
+    {
+      "epoch": 1.1414868105515588,
+      "grad_norm": 0.5399085283279419,
+      "learning_rate": 9.244721692399545e-06,
+      "loss": 0.4236,
+      "step": 119
+    },
+    {
+      "epoch": 1.1510791366906474,
+      "grad_norm": 0.4115072786808014,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.4153,
+      "step": 120
+    },
+    {
+      "epoch": 1.160671462829736,
+      "grad_norm": 0.4668033719062805,
+      "learning_rate": 8.910171529209306e-06,
+      "loss": 0.4089,
+      "step": 121
+    },
+    {
+      "epoch": 1.170263788968825,
+      "grad_norm": 0.4309557378292084,
+      "learning_rate": 8.743334237566202e-06,
+      "loss": 0.4567,
+      "step": 122
+    },
+    {
+      "epoch": 1.1798561151079137,
+      "grad_norm": 0.3743434250354767,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.4158,
+      "step": 123
+    },
+    {
+      "epoch": 1.1894484412470023,
+      "grad_norm": 0.3974321484565735,
+      "learning_rate": 8.410770655042003e-06,
+      "loss": 0.4203,
+      "step": 124
+    },
+    {
+      "epoch": 1.1990407673860912,
+      "grad_norm": 0.47186291217803955,
+      "learning_rate": 8.24513822425984e-06,
+      "loss": 0.4632,
+      "step": 125
+    },
+    {
+      "epoch": 1.20863309352518,
+      "grad_norm": 0.3651352524757385,
+      "learning_rate": 8.0800010716998e-06,
+      "loss": 0.4108,
+      "step": 126
+    },
+    {
+      "epoch": 1.2182254196642686,
+      "grad_norm": 0.39271947741508484,
+      "learning_rate": 7.915405804357632e-06,
+      "loss": 0.4008,
+      "step": 127
+    },
+    {
+      "epoch": 1.2278177458033572,
+      "grad_norm": 0.39792487025260925,
+      "learning_rate": 7.751398876291725e-06,
+      "loss": 0.4096,
+      "step": 128
+    },
+    {
+      "epoch": 1.2374100719424461,
+      "grad_norm": 0.42248499393463135,
+      "learning_rate": 7.58802657551225e-06,
+      "loss": 0.4696,
+      "step": 129
+    },
+    {
+      "epoch": 1.2470023980815348,
+      "grad_norm": 0.4151700735092163,
+      "learning_rate": 7.425335010917244e-06,
+      "loss": 0.4096,
+      "step": 130
+    },
+    {
+      "epoch": 1.2565947242206235,
+      "grad_norm": 0.44272318482398987,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.5086,
+      "step": 131
+    },
+    {
+      "epoch": 1.2661870503597124,
+      "grad_norm": 0.3492010533809662,
+      "learning_rate": 7.102177552285753e-06,
+      "loss": 0.3724,
+      "step": 132
+    },
+    {
+      "epoch": 1.275779376498801,
+      "grad_norm": 0.40979301929473877,
+      "learning_rate": 6.9418028636386595e-06,
+      "loss": 0.4146,
+      "step": 133
+    },
+    {
+      "epoch": 1.2853717026378897,
+      "grad_norm": 0.3699316382408142,
+      "learning_rate": 6.7822912962137225e-06,
+      "loss": 0.426,
+      "step": 134
+    },
+    {
+      "epoch": 1.2949640287769784,
+      "grad_norm": 0.4194217324256897,
+      "learning_rate": 6.623687869286314e-06,
+      "loss": 0.4367,
+      "step": 135
+    },
+    {
+      "epoch": 1.304556354916067,
+      "grad_norm": 0.39025217294692993,
+      "learning_rate": 6.466037345825462e-06,
+      "loss": 0.4187,
+      "step": 136
+    },
+    {
+      "epoch": 1.314148681055156,
+      "grad_norm": 0.37933436036109924,
+      "learning_rate": 6.3093842198603014e-06,
+      "loss": 0.419,
+      "step": 137
+    },
+    {
+      "epoch": 1.3237410071942446,
+      "grad_norm": 0.4016135036945343,
+      "learning_rate": 6.153772703922434e-06,
+      "loss": 0.4023,
+      "step": 138
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.380022794008255,
+      "learning_rate": 5.999246716567737e-06,
+      "loss": 0.4144,
+      "step": 139
+    },
+    {
+      "epoch": 1.3429256594724222,
+      "grad_norm": 0.43621206283569336,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.4116,
+      "step": 140
+    },
+    {
+      "epoch": 1.3525179856115108,
+      "grad_norm": 0.3471137583255768,
+      "learning_rate": 5.693625457667862e-06,
+      "loss": 0.3824,
+      "step": 141
+    },
+    {
+      "epoch": 1.3621103117505995,
+      "grad_norm": 0.41573986411094666,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.4488,
+      "step": 142
+    },
+    {
+      "epoch": 1.3717026378896882,
+      "grad_norm": 0.3361431062221527,
+      "learning_rate": 5.392865443264164e-06,
+      "loss": 0.4348,
+      "step": 143
+    },
+    {
+      "epoch": 1.381294964028777,
+      "grad_norm": 0.3979591429233551,
+      "learning_rate": 5.244414725286717e-06,
+      "loss": 0.4364,
+      "step": 144
+    },
+    {
+      "epoch": 1.3908872901678657,
+      "grad_norm": 0.371258944272995,
+      "learning_rate": 5.097306185851515e-06,
+      "loss": 0.4401,
+      "step": 145
+    },
+    {
+      "epoch": 1.4004796163069544,
+      "grad_norm": 0.3614884316921234,
+      "learning_rate": 4.951581343702014e-06,
+      "loss": 0.4094,
+      "step": 146
+    },
+    {
+      "epoch": 1.4100719424460433,
+      "grad_norm": 0.3901156783103943,
+      "learning_rate": 4.807281327057972e-06,
+      "loss": 0.4293,
+      "step": 147
+    },
+    {
+      "epoch": 1.419664268585132,
+      "grad_norm": 0.3403017520904541,
+      "learning_rate": 4.664446862007718e-06,
+      "loss": 0.3955,
+      "step": 148
+    },
+    {
+      "epoch": 1.4292565947242206,
+      "grad_norm": 0.43209612369537354,
+      "learning_rate": 4.523118261013969e-06,
+      "loss": 0.4822,
+      "step": 149
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 0.37548181414604187,
+      "learning_rate": 4.383335411536357e-06,
+      "loss": 0.4023,
+      "step": 150
+    },
+    {
+      "epoch": 1.4508393285371701,
+      "grad_norm": 0.39062410593032837,
+      "learning_rate": 4.245137764773899e-06,
+      "loss": 0.4106,
+      "step": 151
+    },
+    {
+      "epoch": 1.460431654676259,
+      "grad_norm": 0.4019917845726013,
+      "learning_rate": 4.108564324530626e-06,
+      "loss": 0.4179,
+      "step": 152
+    },
+    {
+      "epoch": 1.4700239808153477,
+      "grad_norm": 0.33987224102020264,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.4202,
+      "step": 153
+    },
+    {
+      "epoch": 1.4796163069544366,
+      "grad_norm": 0.43186017870903015,
+      "learning_rate": 3.840443775923365e-06,
+      "loss": 0.445,
+      "step": 154
+    },
+    {
+      "epoch": 1.4892086330935252,
+      "grad_norm": 0.3407555818557739,
+      "learning_rate": 3.70897233976927e-06,
+      "loss": 0.417,
+      "step": 155
+    },
+    {
+      "epoch": 1.498800959232614,
+      "grad_norm": 0.4105745553970337,
+      "learning_rate": 3.5792764331970187e-06,
+      "loss": 0.3848,
+      "step": 156
+    },
+    {
+      "epoch": 1.5083932853717026,
+      "grad_norm": 0.3866329491138458,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.4239,
+      "step": 157
+    },
+    {
+      "epoch": 1.5179856115107913,
+      "grad_norm": 0.3923889398574829,
+      "learning_rate": 3.3253571147179333e-06,
+      "loss": 0.4283,
+      "step": 158
+    },
+    {
+      "epoch": 1.5275779376498801,
+      "grad_norm": 0.3712652325630188,
+      "learning_rate": 3.2012053669788136e-06,
+      "loss": 0.4337,
+      "step": 159
+    },
+    {
+      "epoch": 1.5371702637889688,
+      "grad_norm": 0.3875731825828552,
+      "learning_rate": 3.0789724569310532e-06,
+      "loss": 0.4561,
+      "step": 160
+    },
+    {
+      "epoch": 1.5467625899280577,
+      "grad_norm": 0.40692004561424255,
+      "learning_rate": 2.9586928826184323e-06,
+      "loss": 0.4186,
+      "step": 161
+    },
+    {
+      "epoch": 1.5563549160671464,
+      "grad_norm": 0.3391355276107788,
+      "learning_rate": 2.8404005907908083e-06,
+      "loss": 0.4269,
+      "step": 162
+    },
+    {
+      "epoch": 1.565947242206235,
+      "grad_norm": 0.38804173469543457,
+      "learning_rate": 2.724128967323234e-06,
+      "loss": 0.4438,
+      "step": 163
+    },
+    {
+      "epoch": 1.5755395683453237,
+      "grad_norm": 0.40315940976142883,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.4366,
+      "step": 164
+    },
+    {
+      "epoch": 1.5851318944844124,
+      "grad_norm": 0.39368948340415955,
+      "learning_rate": 2.4977784082200728e-06,
+      "loss": 0.418,
+      "step": 165
+    },
+    {
+      "epoch": 1.594724220623501,
+      "grad_norm": 0.3897246718406677,
+      "learning_rate": 2.3877633559649505e-06,
+      "loss": 0.4286,
+      "step": 166
+    },
+    {
+      "epoch": 1.60431654676259,
+      "grad_norm": 0.3813110291957855,
+      "learning_rate": 2.2798967208008806e-06,
+      "loss": 0.4065,
+      "step": 167
+    },
+    {
+      "epoch": 1.6139088729016786,
+      "grad_norm": 0.3794170022010803,
+      "learning_rate": 2.1742089461485504e-06,
+      "loss": 0.4223,
+      "step": 168
+    },
+    {
+      "epoch": 1.6235011990407675,
+      "grad_norm": 0.3752288818359375,
+      "learning_rate": 2.0707298604843964e-06,
+      "loss": 0.4268,
+      "step": 169
+    },
+    {
+      "epoch": 1.6330935251798562,
+      "grad_norm": 0.3563545346260071,
+      "learning_rate": 1.9694886689220592e-06,
+      "loss": 0.4283,
+      "step": 170
+    },
+    {
+      "epoch": 1.6426858513189448,
+      "grad_norm": 0.3818962275981903,
+      "learning_rate": 1.870513944969743e-06,
+      "loss": 0.4306,
+      "step": 171
+    },
+    {
+      "epoch": 1.6522781774580335,
+      "grad_norm": 0.3251638412475586,
+      "learning_rate": 1.773833622465888e-06,
+      "loss": 0.4026,
+      "step": 172
+    },
+    {
+      "epoch": 1.6618705035971222,
+      "grad_norm": 0.3651812970638275,
+      "learning_rate": 1.6794749876953187e-06,
+      "loss": 0.4487,
+      "step": 173
+    },
+    {
+      "epoch": 1.671462829736211,
+      "grad_norm": 0.38173985481262207,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.4163,
+      "step": 174
+    },
+    {
+      "epoch": 1.6810551558752997,
+      "grad_norm": 0.42386284470558167,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.4302,
+      "step": 175
+    },
+    {
+      "epoch": 1.6906474820143886,
+      "grad_norm": 0.3804621994495392,
+      "learning_rate": 1.4105921989018112e-06,
+      "loss": 0.4173,
+      "step": 176
+    },
+    {
+      "epoch": 1.7002398081534773,
+      "grad_norm": 0.3547152280807495,
+      "learning_rate": 1.325779961201703e-06,
+      "loss": 0.4112,
+      "step": 177
+    },
+    {
+      "epoch": 1.709832134292566,
+      "grad_norm": 0.369701087474823,
+      "learning_rate": 1.2434158663345553e-06,
+      "loss": 0.4059,
+      "step": 178
+    },
+    {
+      "epoch": 1.7194244604316546,
+      "grad_norm": 0.3956952691078186,
+      "learning_rate": 1.1635231600870334e-06,
+      "loss": 0.4323,
+      "step": 179
+    },
+    {
+      "epoch": 1.7290167865707433,
+      "grad_norm": 0.3940920829772949,
+      "learning_rate": 1.086124390740757e-06,
+      "loss": 0.4115,
+      "step": 180
+    },
+    {
+      "epoch": 1.738609112709832,
+      "grad_norm": 0.3364342451095581,
+      "learning_rate": 1.0112414027084262e-06,
+      "loss": 0.4159,
+      "step": 181
+    },
+    {
+      "epoch": 1.7482014388489209,
+      "grad_norm": 0.4342215061187744,
+      "learning_rate": 9.388953303686587e-07,
+      "loss": 0.4363,
+      "step": 182
+    },
+    {
+      "epoch": 1.7577937649880095,
+      "grad_norm": 0.37105199694633484,
+      "learning_rate": 8.691065921011687e-07,
+      "loss": 0.4019,
+      "step": 183
+    },
+    {
+      "epoch": 1.7673860911270984,
+      "grad_norm": 0.45095208287239075,
+      "learning_rate": 8.018948845240538e-07,
+      "loss": 0.415,
+      "step": 184
+    },
+    {
+      "epoch": 1.776978417266187,
+      "grad_norm": 0.36239635944366455,
+      "learning_rate": 7.372791769347843e-07,
+      "loss": 0.4187,
+      "step": 185
+    },
+    {
+      "epoch": 1.7865707434052758,
+      "grad_norm": 0.4184933304786682,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.3999,
+      "step": 186
+    },
+    {
+      "epoch": 1.7961630695443644,
+      "grad_norm": 0.3767246603965759,
+      "learning_rate": 6.159079703907823e-07,
+      "loss": 0.4122,
+      "step": 187
+    },
+    {
+      "epoch": 1.8057553956834531,
+      "grad_norm": 0.42145809531211853,
+      "learning_rate": 5.591867262794969e-07,
+      "loss": 0.3995,
+      "step": 188
+    },
+    {
+      "epoch": 1.815347721822542,
+      "grad_norm": 0.4406041204929352,
+      "learning_rate": 5.051299821751254e-07,
+      "loss": 0.4226,
+      "step": 189
+    },
+    {
+      "epoch": 1.8249400479616307,
+      "grad_norm": 0.43930745124816895,
+      "learning_rate": 4.537529946229369e-07,
+      "loss": 0.4082,
+      "step": 190
+    },
+    {
+      "epoch": 1.8345323741007196,
+      "grad_norm": 0.40434902906417847,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.4066,
+      "step": 191
+    },
+    {
+      "epoch": 1.8441247002398082,
+      "grad_norm": 0.4053698480129242,
+      "learning_rate": 3.5909552969790376e-07,
+      "loss": 0.4452,
+      "step": 192
+    },
+    {
+      "epoch": 1.853717026378897,
+      "grad_norm": 0.4088927209377289,
+      "learning_rate": 3.158417676946635e-07,
+      "loss": 0.4295,
+      "step": 193
+    },
+    {
+      "epoch": 1.8633093525179856,
+      "grad_norm": 0.3584789037704468,
+      "learning_rate": 2.753211854428728e-07,
+      "loss": 0.4265,
+      "step": 194
+    },
+    {
+      "epoch": 1.8729016786570742,
+      "grad_norm": 0.40616756677627563,
+      "learning_rate": 2.375452191491967e-07,
+      "loss": 0.451,
+      "step": 195
+    },
+    {
+      "epoch": 1.882494004796163,
+      "grad_norm": 0.471882700920105,
+      "learning_rate": 2.0252453040173646e-07,
+      "loss": 0.4096,
+      "step": 196
+    },
+    {
+      "epoch": 1.8920863309352518,
+      "grad_norm": 0.37745100259780884,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.3775,
+      "step": 197
+    },
+    {
+      "epoch": 1.9016786570743405,
+      "grad_norm": 0.4699881672859192,
+      "learning_rate": 1.407877409702496e-07,
+      "loss": 0.4398,
+      "step": 198
+    },
+    {
+      "epoch": 1.9112709832134294,
+      "grad_norm": 0.3633701801300049,
+      "learning_rate": 1.1408906438636236e-07,
+      "loss": 0.4296,
+      "step": 199
+    },
+    {
+      "epoch": 1.920863309352518,
+      "grad_norm": 0.39742547273635864,
+      "learning_rate": 9.018050863132566e-08,
+      "loss": 0.4384,
+      "step": 200
+    },
+    {
+      "epoch": 1.9304556354916067,
+      "grad_norm": 0.3783310651779175,
+      "learning_rate": 6.906882146565097e-08,
+      "loss": 0.4164,
+      "step": 201
+    },
+    {
+      "epoch": 1.9400479616306954,
+      "grad_norm": 0.3894818127155304,
+      "learning_rate": 5.0759961283911584e-08,
+      "loss": 0.4191,
+      "step": 202
+    },
+    {
+      "epoch": 1.949640287769784,
+      "grad_norm": 0.3850553631782532,
+      "learning_rate": 3.525909543310002e-08,
+      "loss": 0.4142,
+      "step": 203
+    },
+    {
+      "epoch": 1.959232613908873,
+      "grad_norm": 0.3297866880893707,
+      "learning_rate": 2.257059875423795e-08,
+      "loss": 0.4255,
+      "step": 204
+    },
+    {
+      "epoch": 1.9688249400479616,
+      "grad_norm": 0.379538893699646,
+      "learning_rate": 1.2698052347649426e-08,
+      "loss": 0.4466,
+      "step": 205
+    },
+    {
+      "epoch": 1.9784172661870505,
+      "grad_norm": 0.34772875905036926,
+      "learning_rate": 5.644242562264923e-09,
+      "loss": 0.3985,
+      "step": 206
+    },
+    {
+      "epoch": 1.9880095923261392,
+      "grad_norm": 0.35218551754951477,
+      "learning_rate": 1.4111602092226062e-09,
+      "loss": 0.441,
+      "step": 207
+    },
+    {
+      "epoch": 1.9976019184652278,
+      "grad_norm": 0.37045979499816895,
+      "learning_rate": 0.0,
+      "loss": 0.4339,
+      "step": 208
+    },
+    {
+      "epoch": 1.9976019184652278,
+      "step": 208,
+      "total_flos": 537505164820480.0,
+      "train_loss": 0.11768974435444061,
+      "train_runtime": 6440.6597,
+      "train_samples_per_second": 3.106,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 208,
+  "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": 537505164820480.0,
+  "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:e7c9ea3da879dc55a30e98a1a7bbf55530ba1da1f0a22d105bc2ed5e6634df01
+size 7544