Add files using upload-large-folder tool

.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 +1,65 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: agenttuning_v4_15k_tag4
+  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. -->
+
+# agenttuning_v4_15k_tag4
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the agenttuning_v4_15k_tag4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4219
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 4
+- 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
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3968        | 0.3937 | 100  | 0.4446          |
+| 0.3873        | 0.7874 | 200  | 0.4238          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- 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 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.4219117760658264,
+    "eval_runtime": 1.1998,
+    "eval_samples_per_second": 1.667,
+    "eval_steps_per_second": 0.833,
+    "total_flos": 24382439424000.0,
+    "train_loss": 0.4321931260307943,
+    "train_runtime": 1177.8664,
+    "train_samples_per_second": 0.86,
+    "train_steps_per_second": 0.216
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.4219117760658264,
+    "eval_runtime": 1.1998,
+    "eval_samples_per_second": 1.667,
+    "eval_steps_per_second": 0.833
+}

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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac25dbb9374ce56b3af350186369bac9b3a16401e3a4b4153bf237b18a2aded
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf064cc46d07b41f7458936808312badbb40bf97d6714537c76f430e2065c57a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7201ae00429ef1b7c8e3357fd7117f246a4a99b163d483733b5b48f1245b6d
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bffef522ba21e02c93488a7bd9c05e9736ad5fbb671c351b0a4a109a706eb40f
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.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": "<|im_end|>",
+    "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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 24382439424000.0,
+    "train_loss": 0.4321931260307943,
+    "train_runtime": 1177.8664,
+    "train_samples_per_second": 0.86,
+    "train_steps_per_second": 0.216
+}

trainer_log.jsonl

@@ -0,0 +1,257 @@
+{"current_steps": 1, "total_steps": 254, "loss": 1.0172, "lr": 4.9998087784700426e-06, "epoch": 0.003937007874015748, "percentage": 0.39, "elapsed_time": "0:00:05", "remaining_time": "0:24:38"}
+{"current_steps": 2, "total_steps": 254, "loss": 0.9352, "lr": 4.999235143132708e-06, "epoch": 0.007874015748031496, "percentage": 0.79, "elapsed_time": "0:00:11", "remaining_time": "0:24:15"}
+{"current_steps": 3, "total_steps": 254, "loss": 0.8516, "lr": 4.998279181741138e-06, "epoch": 0.011811023622047244, "percentage": 1.18, "elapsed_time": "0:00:15", "remaining_time": "0:22:17"}
+{"current_steps": 4, "total_steps": 254, "loss": 0.7877, "lr": 4.996941040535654e-06, "epoch": 0.015748031496062992, "percentage": 1.57, "elapsed_time": "0:00:20", "remaining_time": "0:21:17"}
+{"current_steps": 5, "total_steps": 254, "loss": 0.6726, "lr": 4.99522092422138e-06, "epoch": 0.01968503937007874, "percentage": 1.97, "elapsed_time": "0:00:24", "remaining_time": "0:20:39"}
+{"current_steps": 6, "total_steps": 254, "loss": 0.6184, "lr": 4.993119095936937e-06, "epoch": 0.023622047244094488, "percentage": 2.36, "elapsed_time": "0:00:29", "remaining_time": "0:20:13"}
+{"current_steps": 7, "total_steps": 254, "loss": 0.7206, "lr": 4.9906358772141805e-06, "epoch": 0.027559055118110236, "percentage": 2.76, "elapsed_time": "0:00:33", "remaining_time": "0:19:56"}
+{"current_steps": 8, "total_steps": 254, "loss": 0.5616, "lr": 4.987771647929017e-06, "epoch": 0.031496062992125984, "percentage": 3.15, "elapsed_time": "0:00:38", "remaining_time": "0:19:40"}
+{"current_steps": 9, "total_steps": 254, "loss": 0.5068, "lr": 4.984526846243291e-06, "epoch": 0.03543307086614173, "percentage": 3.54, "elapsed_time": "0:00:42", "remaining_time": "0:19:26"}
+{"current_steps": 10, "total_steps": 254, "loss": 0.6207, "lr": 4.980901968537758e-06, "epoch": 0.03937007874015748, "percentage": 3.94, "elapsed_time": "0:00:47", "remaining_time": "0:19:15"}
+{"current_steps": 11, "total_steps": 254, "loss": 0.5879, "lr": 4.9768975693361456e-06, "epoch": 0.04330708661417323, "percentage": 4.33, "elapsed_time": "0:00:51", "remaining_time": "0:19:05"}
+{"current_steps": 12, "total_steps": 254, "loss": 0.5368, "lr": 4.972514261220327e-06, "epoch": 0.047244094488188976, "percentage": 4.72, "elapsed_time": "0:00:56", "remaining_time": "0:18:56"}
+{"current_steps": 13, "total_steps": 254, "loss": 0.5044, "lr": 4.967752714736611e-06, "epoch": 0.051181102362204724, "percentage": 5.12, "elapsed_time": "0:01:00", "remaining_time": "0:18:48"}
+{"current_steps": 14, "total_steps": 254, "loss": 0.5477, "lr": 4.962613658293158e-06, "epoch": 0.05511811023622047, "percentage": 5.51, "elapsed_time": "0:01:05", "remaining_time": "0:18:40"}
+{"current_steps": 15, "total_steps": 254, "loss": 0.5093, "lr": 4.95709787804856e-06, "epoch": 0.05905511811023622, "percentage": 5.91, "elapsed_time": "0:01:09", "remaining_time": "0:18:33"}
+{"current_steps": 16, "total_steps": 254, "loss": 0.5062, "lr": 4.9512062177915634e-06, "epoch": 0.06299212598425197, "percentage": 6.3, "elapsed_time": "0:01:14", "remaining_time": "0:18:26"}
+{"current_steps": 17, "total_steps": 254, "loss": 0.5541, "lr": 4.9449395788120014e-06, "epoch": 0.06692913385826772, "percentage": 6.69, "elapsed_time": "0:01:18", "remaining_time": "0:18:20"}
+{"current_steps": 18, "total_steps": 254, "loss": 0.505, "lr": 4.938298919762907e-06, "epoch": 0.07086614173228346, "percentage": 7.09, "elapsed_time": "0:01:23", "remaining_time": "0:18:13"}
+{"current_steps": 19, "total_steps": 254, "loss": 0.4907, "lr": 4.931285256513868e-06, "epoch": 0.07480314960629922, "percentage": 7.48, "elapsed_time": "0:01:27", "remaining_time": "0:18:07"}
+{"current_steps": 20, "total_steps": 254, "loss": 0.4991, "lr": 4.923899661995617e-06, "epoch": 0.07874015748031496, "percentage": 7.87, "elapsed_time": "0:01:32", "remaining_time": "0:18:01"}
+{"current_steps": 21, "total_steps": 254, "loss": 0.478, "lr": 4.916143266035901e-06, "epoch": 0.08267716535433071, "percentage": 8.27, "elapsed_time": "0:01:36", "remaining_time": "0:17:55"}
+{"current_steps": 22, "total_steps": 254, "loss": 0.4678, "lr": 4.908017255186644e-06, "epoch": 0.08661417322834646, "percentage": 8.66, "elapsed_time": "0:01:41", "remaining_time": "0:17:50"}
+{"current_steps": 23, "total_steps": 254, "loss": 0.4581, "lr": 4.899522872542424e-06, "epoch": 0.09055118110236221, "percentage": 9.06, "elapsed_time": "0:01:45", "remaining_time": "0:17:44"}
+{"current_steps": 24, "total_steps": 254, "loss": 0.4757, "lr": 4.8906614175503196e-06, "epoch": 0.09448818897637795, "percentage": 9.45, "elapsed_time": "0:01:50", "remaining_time": "0:17:38"}
+{"current_steps": 25, "total_steps": 254, "loss": 0.5344, "lr": 4.8814342458111145e-06, "epoch": 0.0984251968503937, "percentage": 9.84, "elapsed_time": "0:01:55", "remaining_time": "0:17:33"}
+{"current_steps": 26, "total_steps": 254, "loss": 0.4379, "lr": 4.871842768871928e-06, "epoch": 0.10236220472440945, "percentage": 10.24, "elapsed_time": "0:01:59", "remaining_time": "0:17:28"}
+{"current_steps": 27, "total_steps": 254, "loss": 0.5005, "lr": 4.861888454010275e-06, "epoch": 0.1062992125984252, "percentage": 10.63, "elapsed_time": "0:02:04", "remaining_time": "0:17:23"}
+{"current_steps": 28, "total_steps": 254, "loss": 0.4295, "lr": 4.85157282400961e-06, "epoch": 0.11023622047244094, "percentage": 11.02, "elapsed_time": "0:02:08", "remaining_time": "0:17:18"}
+{"current_steps": 29, "total_steps": 254, "loss": 0.449, "lr": 4.8408974569263734e-06, "epoch": 0.1141732283464567, "percentage": 11.42, "elapsed_time": "0:02:13", "remaining_time": "0:17:12"}
+{"current_steps": 30, "total_steps": 254, "loss": 0.4881, "lr": 4.829863985848587e-06, "epoch": 0.11811023622047244, "percentage": 11.81, "elapsed_time": "0:02:17", "remaining_time": "0:17:07"}
+{"current_steps": 31, "total_steps": 254, "loss": 0.444, "lr": 4.818474098646026e-06, "epoch": 0.1220472440944882, "percentage": 12.2, "elapsed_time": "0:02:22", "remaining_time": "0:17:02"}
+{"current_steps": 32, "total_steps": 254, "loss": 0.4314, "lr": 4.806729537712017e-06, "epoch": 0.12598425196850394, "percentage": 12.6, "elapsed_time": "0:02:26", "remaining_time": "0:16:57"}
+{"current_steps": 33, "total_steps": 254, "loss": 0.4464, "lr": 4.794632099696888e-06, "epoch": 0.12992125984251968, "percentage": 12.99, "elapsed_time": "0:02:31", "remaining_time": "0:16:52"}
+{"current_steps": 34, "total_steps": 254, "loss": 0.4896, "lr": 4.7821836352331235e-06, "epoch": 0.13385826771653545, "percentage": 13.39, "elapsed_time": "0:02:35", "remaining_time": "0:16:47"}
+{"current_steps": 35, "total_steps": 254, "loss": 0.4331, "lr": 4.76938604865226e-06, "epoch": 0.1377952755905512, "percentage": 13.78, "elapsed_time": "0:02:40", "remaining_time": "0:16:42"}
+{"current_steps": 36, "total_steps": 254, "loss": 0.4213, "lr": 4.7562412976935655e-06, "epoch": 0.14173228346456693, "percentage": 14.17, "elapsed_time": "0:02:44", "remaining_time": "0:16:38"}
+{"current_steps": 37, "total_steps": 254, "loss": 0.4098, "lr": 4.742751393204553e-06, "epoch": 0.14566929133858267, "percentage": 14.57, "elapsed_time": "0:02:49", "remaining_time": "0:16:33"}
+{"current_steps": 38, "total_steps": 254, "loss": 0.5072, "lr": 4.728918398833361e-06, "epoch": 0.14960629921259844, "percentage": 14.96, "elapsed_time": "0:02:53", "remaining_time": "0:16:28"}
+{"current_steps": 39, "total_steps": 254, "loss": 0.4477, "lr": 4.714744430713068e-06, "epoch": 0.15354330708661418, "percentage": 15.35, "elapsed_time": "0:02:58", "remaining_time": "0:16:23"}
+{"current_steps": 40, "total_steps": 254, "loss": 0.4629, "lr": 4.700231657137971e-06, "epoch": 0.15748031496062992, "percentage": 15.75, "elapsed_time": "0:03:03", "remaining_time": "0:16:19"}
+{"current_steps": 41, "total_steps": 254, "loss": 0.4574, "lr": 4.685382298231882e-06, "epoch": 0.16141732283464566, "percentage": 16.14, "elapsed_time": "0:03:07", "remaining_time": "0:16:14"}
+{"current_steps": 42, "total_steps": 254, "loss": 0.3994, "lr": 4.670198625608504e-06, "epoch": 0.16535433070866143, "percentage": 16.54, "elapsed_time": "0:03:12", "remaining_time": "0:16:09"}
+{"current_steps": 43, "total_steps": 254, "loss": 0.4548, "lr": 4.6546829620239265e-06, "epoch": 0.16929133858267717, "percentage": 16.93, "elapsed_time": "0:03:16", "remaining_time": "0:16:04"}
+{"current_steps": 44, "total_steps": 254, "loss": 0.4359, "lr": 4.63883768102129e-06, "epoch": 0.1732283464566929, "percentage": 17.32, "elapsed_time": "0:03:21", "remaining_time": "0:15:59"}
+{"current_steps": 45, "total_steps": 254, "loss": 0.4226, "lr": 4.622665206567698e-06, "epoch": 0.17716535433070865, "percentage": 17.72, "elapsed_time": "0:03:25", "remaining_time": "0:15:54"}
+{"current_steps": 46, "total_steps": 254, "loss": 0.3893, "lr": 4.606168012683394e-06, "epoch": 0.18110236220472442, "percentage": 18.11, "elapsed_time": "0:03:30", "remaining_time": "0:15:50"}
+{"current_steps": 47, "total_steps": 254, "loss": 0.4619, "lr": 4.589348623063304e-06, "epoch": 0.18503937007874016, "percentage": 18.5, "elapsed_time": "0:03:34", "remaining_time": "0:15:45"}
+{"current_steps": 48, "total_steps": 254, "loss": 0.4376, "lr": 4.5722096106909595e-06, "epoch": 0.1889763779527559, "percentage": 18.9, "elapsed_time": "0:03:39", "remaining_time": "0:15:40"}
+{"current_steps": 49, "total_steps": 254, "loss": 0.4622, "lr": 4.5547535974448966e-06, "epoch": 0.19291338582677164, "percentage": 19.29, "elapsed_time": "0:03:43", "remaining_time": "0:15:36"}
+{"current_steps": 50, "total_steps": 254, "loss": 0.4368, "lr": 4.536983253697561e-06, "epoch": 0.1968503937007874, "percentage": 19.69, "elapsed_time": "0:03:48", "remaining_time": "0:15:31"}
+{"current_steps": 51, "total_steps": 254, "loss": 0.4798, "lr": 4.518901297906811e-06, "epoch": 0.20078740157480315, "percentage": 20.08, "elapsed_time": "0:03:52", "remaining_time": "0:15:26"}
+{"current_steps": 52, "total_steps": 254, "loss": 0.4713, "lr": 4.500510496200043e-06, "epoch": 0.2047244094488189, "percentage": 20.47, "elapsed_time": "0:03:57", "remaining_time": "0:15:21"}
+{"current_steps": 53, "total_steps": 254, "loss": 0.4172, "lr": 4.481813661951052e-06, "epoch": 0.20866141732283464, "percentage": 20.87, "elapsed_time": "0:04:01", "remaining_time": "0:15:17"}
+{"current_steps": 54, "total_steps": 254, "loss": 0.4068, "lr": 4.462813655349637e-06, "epoch": 0.2125984251968504, "percentage": 21.26, "elapsed_time": "0:04:06", "remaining_time": "0:15:12"}
+{"current_steps": 55, "total_steps": 254, "loss": 0.4348, "lr": 4.4435133829640645e-06, "epoch": 0.21653543307086615, "percentage": 21.65, "elapsed_time": "0:04:10", "remaining_time": "0:15:07"}
+{"current_steps": 56, "total_steps": 254, "loss": 0.4596, "lr": 4.423915797296426e-06, "epoch": 0.2204724409448819, "percentage": 22.05, "elapsed_time": "0:04:15", "remaining_time": "0:15:03"}
+{"current_steps": 57, "total_steps": 254, "loss": 0.4159, "lr": 4.4040238963309705e-06, "epoch": 0.22440944881889763, "percentage": 22.44, "elapsed_time": "0:04:19", "remaining_time": "0:14:58"}
+{"current_steps": 58, "total_steps": 254, "loss": 0.4373, "lr": 4.383840723075488e-06, "epoch": 0.2283464566929134, "percentage": 22.83, "elapsed_time": "0:04:24", "remaining_time": "0:14:53"}
+{"current_steps": 59, "total_steps": 254, "loss": 0.422, "lr": 4.363369365095798e-06, "epoch": 0.23228346456692914, "percentage": 23.23, "elapsed_time": "0:04:28", "remaining_time": "0:14:49"}
+{"current_steps": 60, "total_steps": 254, "loss": 0.4129, "lr": 4.34261295404341e-06, "epoch": 0.23622047244094488, "percentage": 23.62, "elapsed_time": "0:04:33", "remaining_time": "0:14:44"}
+{"current_steps": 61, "total_steps": 254, "loss": 0.419, "lr": 4.321574665176469e-06, "epoch": 0.24015748031496062, "percentage": 24.02, "elapsed_time": "0:04:38", "remaining_time": "0:14:39"}
+{"current_steps": 62, "total_steps": 254, "loss": 0.4363, "lr": 4.300257716874001e-06, "epoch": 0.2440944881889764, "percentage": 24.41, "elapsed_time": "0:04:42", "remaining_time": "0:14:35"}
+{"current_steps": 63, "total_steps": 254, "loss": 0.457, "lr": 4.278665370143583e-06, "epoch": 0.24803149606299213, "percentage": 24.8, "elapsed_time": "0:04:47", "remaining_time": "0:14:30"}
+{"current_steps": 64, "total_steps": 254, "loss": 0.4253, "lr": 4.2568009281224755e-06, "epoch": 0.25196850393700787, "percentage": 25.2, "elapsed_time": "0:04:51", "remaining_time": "0:14:25"}
+{"current_steps": 65, "total_steps": 254, "loss": 0.3958, "lr": 4.234667735572323e-06, "epoch": 0.2559055118110236, "percentage": 25.59, "elapsed_time": "0:04:56", "remaining_time": "0:14:21"}
+{"current_steps": 66, "total_steps": 254, "loss": 0.4035, "lr": 4.2122691783674786e-06, "epoch": 0.25984251968503935, "percentage": 25.98, "elapsed_time": "0:05:00", "remaining_time": "0:14:16"}
+{"current_steps": 67, "total_steps": 254, "loss": 0.4039, "lr": 4.1896086829770445e-06, "epoch": 0.2637795275590551, "percentage": 26.38, "elapsed_time": "0:05:05", "remaining_time": "0:14:11"}
+{"current_steps": 68, "total_steps": 254, "loss": 0.4316, "lr": 4.166689715940699e-06, "epoch": 0.2677165354330709, "percentage": 26.77, "elapsed_time": "0:05:09", "remaining_time": "0:14:07"}
+{"current_steps": 69, "total_steps": 254, "loss": 0.3887, "lr": 4.143515783338395e-06, "epoch": 0.27165354330708663, "percentage": 27.17, "elapsed_time": "0:05:14", "remaining_time": "0:14:02"}
+{"current_steps": 70, "total_steps": 254, "loss": 0.4218, "lr": 4.120090430254013e-06, "epoch": 0.2755905511811024, "percentage": 27.56, "elapsed_time": "0:05:18", "remaining_time": "0:13:57"}
+{"current_steps": 71, "total_steps": 254, "loss": 0.4333, "lr": 4.096417240233036e-06, "epoch": 0.2795275590551181, "percentage": 27.95, "elapsed_time": "0:05:23", "remaining_time": "0:13:53"}
+{"current_steps": 72, "total_steps": 254, "loss": 0.4474, "lr": 4.072499834734357e-06, "epoch": 0.28346456692913385, "percentage": 28.35, "elapsed_time": "0:05:27", "remaining_time": "0:13:48"}
+{"current_steps": 73, "total_steps": 254, "loss": 0.4568, "lr": 4.048341872576272e-06, "epoch": 0.2874015748031496, "percentage": 28.74, "elapsed_time": "0:05:32", "remaining_time": "0:13:44"}
+{"current_steps": 74, "total_steps": 254, "loss": 0.4408, "lr": 4.02394704937677e-06, "epoch": 0.29133858267716534, "percentage": 29.13, "elapsed_time": "0:05:36", "remaining_time": "0:13:39"}
+{"current_steps": 75, "total_steps": 254, "loss": 0.426, "lr": 3.999319096988183e-06, "epoch": 0.2952755905511811, "percentage": 29.53, "elapsed_time": "0:05:41", "remaining_time": "0:13:34"}
+{"current_steps": 76, "total_steps": 254, "loss": 0.4336, "lr": 3.974461782926299e-06, "epoch": 0.2992125984251969, "percentage": 29.92, "elapsed_time": "0:05:46", "remaining_time": "0:13:30"}
+{"current_steps": 77, "total_steps": 254, "loss": 0.4657, "lr": 3.949378909794019e-06, "epoch": 0.3031496062992126, "percentage": 30.31, "elapsed_time": "0:05:50", "remaining_time": "0:13:25"}
+{"current_steps": 78, "total_steps": 254, "loss": 0.4671, "lr": 3.924074314699643e-06, "epoch": 0.30708661417322836, "percentage": 30.71, "elapsed_time": "0:05:55", "remaining_time": "0:13:21"}
+{"current_steps": 79, "total_steps": 254, "loss": 0.4413, "lr": 3.898551868669883e-06, "epoch": 0.3110236220472441, "percentage": 31.1, "elapsed_time": "0:05:59", "remaining_time": "0:13:16"}
+{"current_steps": 80, "total_steps": 254, "loss": 0.4998, "lr": 3.872815476057682e-06, "epoch": 0.31496062992125984, "percentage": 31.5, "elapsed_time": "0:06:04", "remaining_time": "0:13:12"}
+{"current_steps": 81, "total_steps": 254, "loss": 0.4479, "lr": 3.846869073944934e-06, "epoch": 0.3188976377952756, "percentage": 31.89, "elapsed_time": "0:06:08", "remaining_time": "0:13:07"}
+{"current_steps": 82, "total_steps": 254, "loss": 0.4489, "lr": 3.820716631540209e-06, "epoch": 0.3228346456692913, "percentage": 32.28, "elapsed_time": "0:06:13", "remaining_time": "0:13:02"}
+{"current_steps": 83, "total_steps": 254, "loss": 0.3866, "lr": 3.7943621495715455e-06, "epoch": 0.32677165354330706, "percentage": 32.68, "elapsed_time": "0:06:17", "remaining_time": "0:12:58"}
+{"current_steps": 84, "total_steps": 254, "loss": 0.3934, "lr": 3.7678096596744328e-06, "epoch": 0.33070866141732286, "percentage": 33.07, "elapsed_time": "0:06:22", "remaining_time": "0:12:53"}
+{"current_steps": 85, "total_steps": 254, "loss": 0.4133, "lr": 3.7410632237750662e-06, "epoch": 0.3346456692913386, "percentage": 33.46, "elapsed_time": "0:06:26", "remaining_time": "0:12:49"}
+{"current_steps": 86, "total_steps": 254, "loss": 0.4512, "lr": 3.7141269334689593e-06, "epoch": 0.33858267716535434, "percentage": 33.86, "elapsed_time": "0:06:31", "remaining_time": "0:12:44"}
+{"current_steps": 87, "total_steps": 254, "loss": 0.42, "lr": 3.687004909395029e-06, "epoch": 0.3425196850393701, "percentage": 34.25, "elapsed_time": "0:06:35", "remaining_time": "0:12:39"}
+{"current_steps": 88, "total_steps": 254, "loss": 0.4001, "lr": 3.659701300605224e-06, "epoch": 0.3464566929133858, "percentage": 34.65, "elapsed_time": "0:06:40", "remaining_time": "0:12:35"}
+{"current_steps": 89, "total_steps": 254, "loss": 0.4396, "lr": 3.6322202839298225e-06, "epoch": 0.35039370078740156, "percentage": 35.04, "elapsed_time": "0:06:44", "remaining_time": "0:12:30"}
+{"current_steps": 90, "total_steps": 254, "loss": 0.3909, "lr": 3.604566063338467e-06, "epoch": 0.3543307086614173, "percentage": 35.43, "elapsed_time": "0:06:49", "remaining_time": "0:12:26"}
+{"current_steps": 91, "total_steps": 254, "loss": 0.3977, "lr": 3.5767428692970557e-06, "epoch": 0.35826771653543305, "percentage": 35.83, "elapsed_time": "0:06:54", "remaining_time": "0:12:21"}
+{"current_steps": 92, "total_steps": 254, "loss": 0.3806, "lr": 3.5487549581205727e-06, "epoch": 0.36220472440944884, "percentage": 36.22, "elapsed_time": "0:06:58", "remaining_time": "0:12:17"}
+{"current_steps": 93, "total_steps": 254, "loss": 0.4175, "lr": 3.520606611321976e-06, "epoch": 0.3661417322834646, "percentage": 36.61, "elapsed_time": "0:07:03", "remaining_time": "0:12:12"}
+{"current_steps": 94, "total_steps": 254, "loss": 0.433, "lr": 3.4923021349572183e-06, "epoch": 0.3700787401574803, "percentage": 37.01, "elapsed_time": "0:07:07", "remaining_time": "0:12:07"}
+{"current_steps": 95, "total_steps": 254, "loss": 0.3999, "lr": 3.463845858966519e-06, "epoch": 0.37401574803149606, "percentage": 37.4, "elapsed_time": "0:07:12", "remaining_time": "0:12:03"}
+{"current_steps": 96, "total_steps": 254, "loss": 0.5329, "lr": 3.4352421365119837e-06, "epoch": 0.3779527559055118, "percentage": 37.8, "elapsed_time": "0:07:16", "remaining_time": "0:11:58"}
+{"current_steps": 97, "total_steps": 254, "loss": 0.4608, "lr": 3.4064953433116675e-06, "epoch": 0.38188976377952755, "percentage": 38.19, "elapsed_time": "0:07:21", "remaining_time": "0:11:54"}
+{"current_steps": 98, "total_steps": 254, "loss": 0.3644, "lr": 3.3776098769701944e-06, "epoch": 0.3858267716535433, "percentage": 38.58, "elapsed_time": "0:07:25", "remaining_time": "0:11:49"}
+{"current_steps": 99, "total_steps": 254, "loss": 0.4215, "lr": 3.3485901563060168e-06, "epoch": 0.38976377952755903, "percentage": 38.98, "elapsed_time": "0:07:30", "remaining_time": "0:11:45"}
+{"current_steps": 100, "total_steps": 254, "loss": 0.3968, "lr": 3.319440620675442e-06, "epoch": 0.3937007874015748, "percentage": 39.37, "elapsed_time": "0:07:34", "remaining_time": "0:11:40"}
+{"current_steps": 100, "total_steps": 254, "eval_loss": 0.44460952281951904, "epoch": 0.3937007874015748, "percentage": 39.37, "elapsed_time": "0:07:36", "remaining_time": "0:11:42"}
+{"current_steps": 101, "total_steps": 254, "loss": 0.4121, "lr": 3.2901657292935113e-06, "epoch": 0.39763779527559057, "percentage": 39.76, "elapsed_time": "0:07:40", "remaining_time": "0:11:37"}
+{"current_steps": 102, "total_steps": 254, "loss": 0.3994, "lr": 3.2607699605518408e-06, "epoch": 0.4015748031496063, "percentage": 40.16, "elapsed_time": "0:07:45", "remaining_time": "0:11:33"}
+{"current_steps": 103, "total_steps": 254, "loss": 0.3921, "lr": 3.231257811333528e-06, "epoch": 0.40551181102362205, "percentage": 40.55, "elapsed_time": "0:07:49", "remaining_time": "0:11:28"}
+{"current_steps": 104, "total_steps": 254, "loss": 0.3882, "lr": 3.201633796325233e-06, "epoch": 0.4094488188976378, "percentage": 40.94, "elapsed_time": "0:07:54", "remaining_time": "0:11:23"}
+{"current_steps": 105, "total_steps": 254, "loss": 0.4121, "lr": 3.171902447326536e-06, "epoch": 0.41338582677165353, "percentage": 41.34, "elapsed_time": "0:07:58", "remaining_time": "0:11:19"}
+{"current_steps": 106, "total_steps": 254, "loss": 0.3974, "lr": 3.1420683125566703e-06, "epoch": 0.41732283464566927, "percentage": 41.73, "elapsed_time": "0:08:03", "remaining_time": "0:11:14"}
+{"current_steps": 107, "total_steps": 254, "loss": 0.4014, "lr": 3.112135955958754e-06, "epoch": 0.421259842519685, "percentage": 42.13, "elapsed_time": "0:08:07", "remaining_time": "0:11:10"}
+{"current_steps": 108, "total_steps": 254, "loss": 0.3901, "lr": 3.082109956501604e-06, "epoch": 0.4251968503937008, "percentage": 42.52, "elapsed_time": "0:08:12", "remaining_time": "0:11:05"}
+{"current_steps": 109, "total_steps": 254, "loss": 0.4022, "lr": 3.0519949074792652e-06, "epoch": 0.42913385826771655, "percentage": 42.91, "elapsed_time": "0:08:16", "remaining_time": "0:11:00"}
+{"current_steps": 110, "total_steps": 254, "loss": 0.4293, "lr": 3.0217954158083384e-06, "epoch": 0.4330708661417323, "percentage": 43.31, "elapsed_time": "0:08:21", "remaining_time": "0:10:56"}
+{"current_steps": 111, "total_steps": 254, "loss": 0.4276, "lr": 2.9915161013232218e-06, "epoch": 0.43700787401574803, "percentage": 43.7, "elapsed_time": "0:08:25", "remaining_time": "0:10:51"}
+{"current_steps": 112, "total_steps": 254, "loss": 0.4257, "lr": 2.96116159606939e-06, "epoch": 0.4409448818897638, "percentage": 44.09, "elapsed_time": "0:08:30", "remaining_time": "0:10:47"}
+{"current_steps": 113, "total_steps": 254, "loss": 0.4234, "lr": 2.930736543594792e-06, "epoch": 0.4448818897637795, "percentage": 44.49, "elapsed_time": "0:08:34", "remaining_time": "0:10:42"}
+{"current_steps": 114, "total_steps": 254, "loss": 0.4273, "lr": 2.9002455982394946e-06, "epoch": 0.44881889763779526, "percentage": 44.88, "elapsed_time": "0:08:39", "remaining_time": "0:10:37"}
+{"current_steps": 115, "total_steps": 254, "loss": 0.3724, "lr": 2.869693424423673e-06, "epoch": 0.452755905511811, "percentage": 45.28, "elapsed_time": "0:08:43", "remaining_time": "0:10:33"}
+{"current_steps": 116, "total_steps": 254, "loss": 0.4263, "lr": 2.839084695934064e-06, "epoch": 0.4566929133858268, "percentage": 45.67, "elapsed_time": "0:08:48", "remaining_time": "0:10:28"}
+{"current_steps": 117, "total_steps": 254, "loss": 0.3942, "lr": 2.8084240952089824e-06, "epoch": 0.46062992125984253, "percentage": 46.06, "elapsed_time": "0:08:52", "remaining_time": "0:10:24"}
+{"current_steps": 118, "total_steps": 254, "loss": 0.4194, "lr": 2.777716312622012e-06, "epoch": 0.4645669291338583, "percentage": 46.46, "elapsed_time": "0:08:57", "remaining_time": "0:10:19"}
+{"current_steps": 119, "total_steps": 254, "loss": 0.4208, "lr": 2.746966045764486e-06, "epoch": 0.468503937007874, "percentage": 46.85, "elapsed_time": "0:09:02", "remaining_time": "0:10:14"}
+{"current_steps": 120, "total_steps": 254, "loss": 0.3695, "lr": 2.7161779987268643e-06, "epoch": 0.47244094488188976, "percentage": 47.24, "elapsed_time": "0:09:06", "remaining_time": "0:10:10"}
+{"current_steps": 121, "total_steps": 254, "loss": 0.4045, "lr": 2.6853568813791158e-06, "epoch": 0.4763779527559055, "percentage": 47.64, "elapsed_time": "0:09:11", "remaining_time": "0:10:05"}
+{"current_steps": 122, "total_steps": 254, "loss": 0.3857, "lr": 2.654507408650211e-06, "epoch": 0.48031496062992124, "percentage": 48.03, "elapsed_time": "0:09:15", "remaining_time": "0:10:01"}
+{"current_steps": 123, "total_steps": 254, "loss": 0.3801, "lr": 2.623634299806848e-06, "epoch": 0.484251968503937, "percentage": 48.43, "elapsed_time": "0:09:20", "remaining_time": "0:09:56"}
+{"current_steps": 124, "total_steps": 254, "loss": 0.4161, "lr": 2.592742277731513e-06, "epoch": 0.4881889763779528, "percentage": 48.82, "elapsed_time": "0:09:24", "remaining_time": "0:09:51"}
+{"current_steps": 125, "total_steps": 254, "loss": 0.3918, "lr": 2.5618360681999876e-06, "epoch": 0.4921259842519685, "percentage": 49.21, "elapsed_time": "0:09:29", "remaining_time": "0:09:47"}
+{"current_steps": 126, "total_steps": 254, "loss": 0.4008, "lr": 2.5309203991584076e-06, "epoch": 0.49606299212598426, "percentage": 49.61, "elapsed_time": "0:09:33", "remaining_time": "0:09:42"}
+{"current_steps": 127, "total_steps": 254, "loss": 0.3788, "lr": 2.5e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:09:38", "remaining_time": "0:09:38"}
+{"current_steps": 128, "total_steps": 254, "loss": 0.4851, "lr": 2.4690796008415928e-06, "epoch": 0.5039370078740157, "percentage": 50.39, "elapsed_time": "0:09:42", "remaining_time": "0:09:33"}
+{"current_steps": 129, "total_steps": 254, "loss": 0.4291, "lr": 2.438163931800013e-06, "epoch": 0.5078740157480315, "percentage": 50.79, "elapsed_time": "0:09:47", "remaining_time": "0:09:29"}
+{"current_steps": 130, "total_steps": 254, "loss": 0.3957, "lr": 2.4072577222684874e-06, "epoch": 0.5118110236220472, "percentage": 51.18, "elapsed_time": "0:09:51", "remaining_time": "0:09:24"}
+{"current_steps": 131, "total_steps": 254, "loss": 0.399, "lr": 2.376365700193153e-06, "epoch": 0.515748031496063, "percentage": 51.57, "elapsed_time": "0:09:56", "remaining_time": "0:09:19"}
+{"current_steps": 132, "total_steps": 254, "loss": 0.4387, "lr": 2.3454925913497905e-06, "epoch": 0.5196850393700787, "percentage": 51.97, "elapsed_time": "0:10:00", "remaining_time": "0:09:15"}
+{"current_steps": 133, "total_steps": 254, "loss": 0.3818, "lr": 2.314643118620885e-06, "epoch": 0.5236220472440944, "percentage": 52.36, "elapsed_time": "0:10:05", "remaining_time": "0:09:10"}
+{"current_steps": 134, "total_steps": 254, "loss": 0.3848, "lr": 2.2838220012731365e-06, "epoch": 0.5275590551181102, "percentage": 52.76, "elapsed_time": "0:10:09", "remaining_time": "0:09:06"}
+{"current_steps": 135, "total_steps": 254, "loss": 0.4537, "lr": 2.2530339542355145e-06, "epoch": 0.531496062992126, "percentage": 53.15, "elapsed_time": "0:10:14", "remaining_time": "0:09:01"}
+{"current_steps": 136, "total_steps": 254, "loss": 0.4299, "lr": 2.222283687377989e-06, "epoch": 0.5354330708661418, "percentage": 53.54, "elapsed_time": "0:10:18", "remaining_time": "0:08:56"}
+{"current_steps": 137, "total_steps": 254, "loss": 0.3917, "lr": 2.1915759047910176e-06, "epoch": 0.5393700787401575, "percentage": 53.94, "elapsed_time": "0:10:23", "remaining_time": "0:08:52"}
+{"current_steps": 138, "total_steps": 254, "loss": 0.419, "lr": 2.160915304065936e-06, "epoch": 0.5433070866141733, "percentage": 54.33, "elapsed_time": "0:10:27", "remaining_time": "0:08:47"}
+{"current_steps": 139, "total_steps": 254, "loss": 0.3893, "lr": 2.1303065755763276e-06, "epoch": 0.547244094488189, "percentage": 54.72, "elapsed_time": "0:10:32", "remaining_time": "0:08:43"}
+{"current_steps": 140, "total_steps": 254, "loss": 0.4037, "lr": 2.0997544017605063e-06, "epoch": 0.5511811023622047, "percentage": 55.12, "elapsed_time": "0:10:36", "remaining_time": "0:08:38"}
+{"current_steps": 141, "total_steps": 254, "loss": 0.3921, "lr": 2.069263456405209e-06, "epoch": 0.5551181102362205, "percentage": 55.51, "elapsed_time": "0:10:41", "remaining_time": "0:08:34"}
+{"current_steps": 142, "total_steps": 254, "loss": 0.4272, "lr": 2.0388384039306105e-06, "epoch": 0.5590551181102362, "percentage": 55.91, "elapsed_time": "0:10:46", "remaining_time": "0:08:29"}
+{"current_steps": 143, "total_steps": 254, "loss": 0.397, "lr": 2.008483898676779e-06, "epoch": 0.562992125984252, "percentage": 56.3, "elapsed_time": "0:10:50", "remaining_time": "0:08:24"}
+{"current_steps": 144, "total_steps": 254, "loss": 0.4044, "lr": 1.9782045841916625e-06, "epoch": 0.5669291338582677, "percentage": 56.69, "elapsed_time": "0:10:55", "remaining_time": "0:08:20"}
+{"current_steps": 145, "total_steps": 254, "loss": 0.4037, "lr": 1.948005092520735e-06, "epoch": 0.5708661417322834, "percentage": 57.09, "elapsed_time": "0:10:59", "remaining_time": "0:08:15"}
+{"current_steps": 146, "total_steps": 254, "loss": 0.4305, "lr": 1.917890043498397e-06, "epoch": 0.5748031496062992, "percentage": 57.48, "elapsed_time": "0:11:04", "remaining_time": "0:08:11"}
+{"current_steps": 147, "total_steps": 254, "loss": 0.3745, "lr": 1.8878640440412473e-06, "epoch": 0.5787401574803149, "percentage": 57.87, "elapsed_time": "0:11:08", "remaining_time": "0:08:06"}
+{"current_steps": 148, "total_steps": 254, "loss": 0.3798, "lr": 1.8579316874433306e-06, "epoch": 0.5826771653543307, "percentage": 58.27, "elapsed_time": "0:11:13", "remaining_time": "0:08:02"}
+{"current_steps": 149, "total_steps": 254, "loss": 0.389, "lr": 1.8280975526734657e-06, "epoch": 0.5866141732283464, "percentage": 58.66, "elapsed_time": "0:11:17", "remaining_time": "0:07:57"}
+{"current_steps": 150, "total_steps": 254, "loss": 0.4377, "lr": 1.7983662036747682e-06, "epoch": 0.5905511811023622, "percentage": 59.06, "elapsed_time": "0:11:22", "remaining_time": "0:07:52"}
+{"current_steps": 151, "total_steps": 254, "loss": 0.4328, "lr": 1.7687421886664725e-06, "epoch": 0.594488188976378, "percentage": 59.45, "elapsed_time": "0:11:26", "remaining_time": "0:07:48"}
+{"current_steps": 152, "total_steps": 254, "loss": 0.3874, "lr": 1.7392300394481599e-06, "epoch": 0.5984251968503937, "percentage": 59.84, "elapsed_time": "0:11:31", "remaining_time": "0:07:43"}
+{"current_steps": 153, "total_steps": 254, "loss": 0.4296, "lr": 1.7098342707064885e-06, "epoch": 0.6023622047244095, "percentage": 60.24, "elapsed_time": "0:11:35", "remaining_time": "0:07:39"}
+{"current_steps": 154, "total_steps": 254, "loss": 0.4319, "lr": 1.680559379324558e-06, "epoch": 0.6062992125984252, "percentage": 60.63, "elapsed_time": "0:11:40", "remaining_time": "0:07:34"}
+{"current_steps": 155, "total_steps": 254, "loss": 0.4253, "lr": 1.6514098436939834e-06, "epoch": 0.610236220472441, "percentage": 61.02, "elapsed_time": "0:11:44", "remaining_time": "0:07:30"}
+{"current_steps": 156, "total_steps": 254, "loss": 0.41, "lr": 1.6223901230298062e-06, "epoch": 0.6141732283464567, "percentage": 61.42, "elapsed_time": "0:11:49", "remaining_time": "0:07:25"}
+{"current_steps": 157, "total_steps": 254, "loss": 0.3984, "lr": 1.5935046566883327e-06, "epoch": 0.6181102362204725, "percentage": 61.81, "elapsed_time": "0:11:53", "remaining_time": "0:07:21"}
+{"current_steps": 158, "total_steps": 254, "loss": 0.3675, "lr": 1.5647578634880174e-06, "epoch": 0.6220472440944882, "percentage": 62.2, "elapsed_time": "0:11:58", "remaining_time": "0:07:16"}
+{"current_steps": 159, "total_steps": 254, "loss": 0.3902, "lr": 1.5361541410334817e-06, "epoch": 0.6259842519685039, "percentage": 62.6, "elapsed_time": "0:12:03", "remaining_time": "0:07:11"}
+{"current_steps": 160, "total_steps": 254, "loss": 0.3719, "lr": 1.5076978650427825e-06, "epoch": 0.6299212598425197, "percentage": 62.99, "elapsed_time": "0:12:07", "remaining_time": "0:07:07"}
+{"current_steps": 161, "total_steps": 254, "loss": 0.387, "lr": 1.4793933886780244e-06, "epoch": 0.6338582677165354, "percentage": 63.39, "elapsed_time": "0:12:12", "remaining_time": "0:07:02"}
+{"current_steps": 162, "total_steps": 254, "loss": 0.3464, "lr": 1.451245041879428e-06, "epoch": 0.6377952755905512, "percentage": 63.78, "elapsed_time": "0:12:16", "remaining_time": "0:06:58"}
+{"current_steps": 163, "total_steps": 254, "loss": 0.4082, "lr": 1.4232571307029458e-06, "epoch": 0.6417322834645669, "percentage": 64.17, "elapsed_time": "0:12:21", "remaining_time": "0:06:53"}
+{"current_steps": 164, "total_steps": 254, "loss": 0.4097, "lr": 1.3954339366615335e-06, "epoch": 0.6456692913385826, "percentage": 64.57, "elapsed_time": "0:12:25", "remaining_time": "0:06:49"}
+{"current_steps": 165, "total_steps": 254, "loss": 0.3858, "lr": 1.367779716070179e-06, "epoch": 0.6496062992125984, "percentage": 64.96, "elapsed_time": "0:12:30", "remaining_time": "0:06:44"}
+{"current_steps": 166, "total_steps": 254, "loss": 0.3941, "lr": 1.340298699394777e-06, "epoch": 0.6535433070866141, "percentage": 65.35, "elapsed_time": "0:12:34", "remaining_time": "0:06:40"}
+{"current_steps": 167, "total_steps": 254, "loss": 0.3887, "lr": 1.3129950906049716e-06, "epoch": 0.65748031496063, "percentage": 65.75, "elapsed_time": "0:12:39", "remaining_time": "0:06:35"}
+{"current_steps": 168, "total_steps": 254, "loss": 0.3814, "lr": 1.285873066531041e-06, "epoch": 0.6614173228346457, "percentage": 66.14, "elapsed_time": "0:12:43", "remaining_time": "0:06:30"}
+{"current_steps": 169, "total_steps": 254, "loss": 0.3818, "lr": 1.2589367762249346e-06, "epoch": 0.6653543307086615, "percentage": 66.54, "elapsed_time": "0:12:48", "remaining_time": "0:06:26"}
+{"current_steps": 170, "total_steps": 254, "loss": 0.4148, "lr": 1.2321903403255672e-06, "epoch": 0.6692913385826772, "percentage": 66.93, "elapsed_time": "0:12:52", "remaining_time": "0:06:21"}
+{"current_steps": 171, "total_steps": 254, "loss": 0.4152, "lr": 1.2056378504284551e-06, "epoch": 0.6732283464566929, "percentage": 67.32, "elapsed_time": "0:12:57", "remaining_time": "0:06:17"}
+{"current_steps": 172, "total_steps": 254, "loss": 0.3826, "lr": 1.1792833684597908e-06, "epoch": 0.6771653543307087, "percentage": 67.72, "elapsed_time": "0:13:01", "remaining_time": "0:06:12"}
+{"current_steps": 173, "total_steps": 254, "loss": 0.3981, "lr": 1.153130926055066e-06, "epoch": 0.6811023622047244, "percentage": 68.11, "elapsed_time": "0:13:06", "remaining_time": "0:06:08"}
+{"current_steps": 174, "total_steps": 254, "loss": 0.4269, "lr": 1.1271845239423196e-06, "epoch": 0.6850393700787402, "percentage": 68.5, "elapsed_time": "0:13:10", "remaining_time": "0:06:03"}
+{"current_steps": 175, "total_steps": 254, "loss": 0.4193, "lr": 1.1014481313301173e-06, "epoch": 0.6889763779527559, "percentage": 68.9, "elapsed_time": "0:13:15", "remaining_time": "0:05:59"}
+{"current_steps": 176, "total_steps": 254, "loss": 0.4016, "lr": 1.0759256853003577e-06, "epoch": 0.6929133858267716, "percentage": 69.29, "elapsed_time": "0:13:19", "remaining_time": "0:05:54"}
+{"current_steps": 177, "total_steps": 254, "loss": 0.4018, "lr": 1.0506210902059815e-06, "epoch": 0.6968503937007874, "percentage": 69.69, "elapsed_time": "0:13:24", "remaining_time": "0:05:49"}
+{"current_steps": 178, "total_steps": 254, "loss": 0.4192, "lr": 1.0255382170737016e-06, "epoch": 0.7007874015748031, "percentage": 70.08, "elapsed_time": "0:13:28", "remaining_time": "0:05:45"}
+{"current_steps": 179, "total_steps": 254, "loss": 0.38, "lr": 1.000680903011818e-06, "epoch": 0.7047244094488189, "percentage": 70.47, "elapsed_time": "0:13:33", "remaining_time": "0:05:40"}
+{"current_steps": 180, "total_steps": 254, "loss": 0.4397, "lr": 9.760529506232306e-07, "epoch": 0.7086614173228346, "percentage": 70.87, "elapsed_time": "0:13:37", "remaining_time": "0:05:36"}
+{"current_steps": 181, "total_steps": 254, "loss": 0.3696, "lr": 9.516581274237288e-07, "epoch": 0.7125984251968503, "percentage": 71.26, "elapsed_time": "0:13:42", "remaining_time": "0:05:31"}
+{"current_steps": 182, "total_steps": 254, "loss": 0.4376, "lr": 9.275001652656445e-07, "epoch": 0.7165354330708661, "percentage": 71.65, "elapsed_time": "0:13:46", "remaining_time": "0:05:27"}
+{"current_steps": 183, "total_steps": 254, "loss": 0.3983, "lr": 9.035827597669636e-07, "epoch": 0.7204724409448819, "percentage": 72.05, "elapsed_time": "0:13:51", "remaining_time": "0:05:22"}
+{"current_steps": 184, "total_steps": 254, "loss": 0.4211, "lr": 8.799095697459869e-07, "epoch": 0.7244094488188977, "percentage": 72.44, "elapsed_time": "0:13:55", "remaining_time": "0:05:18"}
+{"current_steps": 185, "total_steps": 254, "loss": 0.3867, "lr": 8.564842166616047e-07, "epoch": 0.7283464566929134, "percentage": 72.83, "elapsed_time": "0:14:00", "remaining_time": "0:05:13"}
+{"current_steps": 186, "total_steps": 254, "loss": 0.4111, "lr": 8.333102840593016e-07, "epoch": 0.7322834645669292, "percentage": 73.23, "elapsed_time": "0:14:05", "remaining_time": "0:05:08"}
+{"current_steps": 187, "total_steps": 254, "loss": 0.4344, "lr": 8.103913170229566e-07, "epoch": 0.7362204724409449, "percentage": 73.62, "elapsed_time": "0:14:09", "remaining_time": "0:05:04"}
+{"current_steps": 188, "total_steps": 254, "loss": 0.4086, "lr": 7.877308216325222e-07, "epoch": 0.7401574803149606, "percentage": 74.02, "elapsed_time": "0:14:14", "remaining_time": "0:04:59"}
+{"current_steps": 189, "total_steps": 254, "loss": 0.4111, "lr": 7.653322644276778e-07, "epoch": 0.7440944881889764, "percentage": 74.41, "elapsed_time": "0:14:18", "remaining_time": "0:04:55"}
+{"current_steps": 190, "total_steps": 254, "loss": 0.4075, "lr": 7.43199071877525e-07, "epoch": 0.7480314960629921, "percentage": 74.8, "elapsed_time": "0:14:23", "remaining_time": "0:04:50"}
+{"current_steps": 191, "total_steps": 254, "loss": 0.407, "lr": 7.213346298564169e-07, "epoch": 0.7519685039370079, "percentage": 75.2, "elapsed_time": "0:14:27", "remaining_time": "0:04:46"}
+{"current_steps": 192, "total_steps": 254, "loss": 0.3934, "lr": 6.997422831259992e-07, "epoch": 0.7559055118110236, "percentage": 75.59, "elapsed_time": "0:14:32", "remaining_time": "0:04:41"}
+{"current_steps": 193, "total_steps": 254, "loss": 0.3718, "lr": 6.784253348235323e-07, "epoch": 0.7598425196850394, "percentage": 75.98, "elapsed_time": "0:14:36", "remaining_time": "0:04:37"}
+{"current_steps": 194, "total_steps": 254, "loss": 0.3919, "lr": 6.573870459565907e-07, "epoch": 0.7637795275590551, "percentage": 76.38, "elapsed_time": "0:14:41", "remaining_time": "0:04:32"}
+{"current_steps": 195, "total_steps": 254, "loss": 0.4167, "lr": 6.366306349042034e-07, "epoch": 0.7677165354330708, "percentage": 76.77, "elapsed_time": "0:14:45", "remaining_time": "0:04:27"}
+{"current_steps": 196, "total_steps": 254, "loss": 0.5578, "lr": 6.161592769245115e-07, "epoch": 0.7716535433070866, "percentage": 77.17, "elapsed_time": "0:14:50", "remaining_time": "0:04:23"}
+{"current_steps": 197, "total_steps": 254, "loss": 0.3596, "lr": 5.959761036690307e-07, "epoch": 0.7755905511811023, "percentage": 77.56, "elapsed_time": "0:14:54", "remaining_time": "0:04:18"}
+{"current_steps": 198, "total_steps": 254, "loss": 0.4179, "lr": 5.760842027035762e-07, "epoch": 0.7795275590551181, "percentage": 77.95, "elapsed_time": "0:14:59", "remaining_time": "0:04:14"}
+{"current_steps": 199, "total_steps": 254, "loss": 0.3809, "lr": 5.564866170359351e-07, "epoch": 0.7834645669291339, "percentage": 78.35, "elapsed_time": "0:15:03", "remaining_time": "0:04:09"}
+{"current_steps": 200, "total_steps": 254, "loss": 0.3873, "lr": 5.371863446503628e-07, "epoch": 0.7874015748031497, "percentage": 78.74, "elapsed_time": "0:15:08", "remaining_time": "0:04:05"}
+{"current_steps": 200, "total_steps": 254, "eval_loss": 0.4238421320915222, "epoch": 0.7874015748031497, "percentage": 78.74, "elapsed_time": "0:15:09", "remaining_time": "0:04:05"}
+{"current_steps": 201, "total_steps": 254, "loss": 0.3982, "lr": 5.181863380489485e-07, "epoch": 0.7913385826771654, "percentage": 79.13, "elapsed_time": "0:15:13", "remaining_time": "0:04:01"}
+{"current_steps": 202, "total_steps": 254, "loss": 0.4038, "lr": 4.994895037999573e-07, "epoch": 0.7952755905511811, "percentage": 79.53, "elapsed_time": "0:15:18", "remaining_time": "0:03:56"}
+{"current_steps": 203, "total_steps": 254, "loss": 0.4041, "lr": 4.810987020931907e-07, "epoch": 0.7992125984251969, "percentage": 79.92, "elapsed_time": "0:15:23", "remaining_time": "0:03:51"}
+{"current_steps": 204, "total_steps": 254, "loss": 0.3767, "lr": 4.6301674630243934e-07, "epoch": 0.8031496062992126, "percentage": 80.31, "elapsed_time": "0:15:27", "remaining_time": "0:03:47"}
+{"current_steps": 205, "total_steps": 254, "loss": 0.4103, "lr": 4.452464025551037e-07, "epoch": 0.8070866141732284, "percentage": 80.71, "elapsed_time": "0:15:32", "remaining_time": "0:03:42"}
+{"current_steps": 206, "total_steps": 254, "loss": 0.4024, "lr": 4.277903893090407e-07, "epoch": 0.8110236220472441, "percentage": 81.1, "elapsed_time": "0:15:36", "remaining_time": "0:03:38"}
+{"current_steps": 207, "total_steps": 254, "loss": 0.4274, "lr": 4.106513769366965e-07, "epoch": 0.8149606299212598, "percentage": 81.5, "elapsed_time": "0:15:41", "remaining_time": "0:03:33"}
+{"current_steps": 208, "total_steps": 254, "loss": 0.3904, "lr": 3.938319873166066e-07, "epoch": 0.8188976377952756, "percentage": 81.89, "elapsed_time": "0:15:45", "remaining_time": "0:03:29"}
+{"current_steps": 209, "total_steps": 254, "loss": 0.4096, "lr": 3.773347934323035e-07, "epoch": 0.8228346456692913, "percentage": 82.28, "elapsed_time": "0:15:50", "remaining_time": "0:03:24"}
+{"current_steps": 210, "total_steps": 254, "loss": 0.3846, "lr": 3.611623189787103e-07, "epoch": 0.8267716535433071, "percentage": 82.68, "elapsed_time": "0:15:54", "remaining_time": "0:03:20"}
+{"current_steps": 211, "total_steps": 254, "loss": 0.4084, "lr": 3.453170379760745e-07, "epoch": 0.8307086614173228, "percentage": 83.07, "elapsed_time": "0:15:59", "remaining_time": "0:03:15"}
+{"current_steps": 212, "total_steps": 254, "loss": 0.4596, "lr": 3.298013743914957e-07, "epoch": 0.8346456692913385, "percentage": 83.46, "elapsed_time": "0:16:03", "remaining_time": "0:03:10"}
+{"current_steps": 213, "total_steps": 254, "loss": 0.388, "lr": 3.1461770176811845e-07, "epoch": 0.8385826771653543, "percentage": 83.86, "elapsed_time": "0:16:08", "remaining_time": "0:03:06"}
+{"current_steps": 214, "total_steps": 254, "loss": 0.4241, "lr": 2.997683428620296e-07, "epoch": 0.84251968503937, "percentage": 84.25, "elapsed_time": "0:16:12", "remaining_time": "0:03:01"}
+{"current_steps": 215, "total_steps": 254, "loss": 0.4003, "lr": 2.852555692869319e-07, "epoch": 0.8464566929133859, "percentage": 84.65, "elapsed_time": "0:16:17", "remaining_time": "0:02:57"}
+{"current_steps": 216, "total_steps": 254, "loss": 0.3926, "lr": 2.7108160116663896e-07, "epoch": 0.8503937007874016, "percentage": 85.04, "elapsed_time": "0:16:21", "remaining_time": "0:02:52"}
+{"current_steps": 217, "total_steps": 254, "loss": 0.3846, "lr": 2.5724860679544745e-07, "epoch": 0.8543307086614174, "percentage": 85.43, "elapsed_time": "0:16:26", "remaining_time": "0:02:48"}
+{"current_steps": 218, "total_steps": 254, "loss": 0.4081, "lr": 2.437587023064342e-07, "epoch": 0.8582677165354331, "percentage": 85.83, "elapsed_time": "0:16:30", "remaining_time": "0:02:43"}
+{"current_steps": 219, "total_steps": 254, "loss": 0.4031, "lr": 2.306139513477404e-07, "epoch": 0.8622047244094488, "percentage": 86.22, "elapsed_time": "0:16:35", "remaining_time": "0:02:39"}
+{"current_steps": 220, "total_steps": 254, "loss": 0.415, "lr": 2.1781636476687713e-07, "epoch": 0.8661417322834646, "percentage": 86.61, "elapsed_time": "0:16:39", "remaining_time": "0:02:34"}
+{"current_steps": 221, "total_steps": 254, "loss": 0.4806, "lr": 2.0536790030311227e-07, "epoch": 0.8700787401574803, "percentage": 87.01, "elapsed_time": "0:16:44", "remaining_time": "0:02:29"}
+{"current_steps": 222, "total_steps": 254, "loss": 0.397, "lr": 1.9327046228798357e-07, "epoch": 0.8740157480314961, "percentage": 87.4, "elapsed_time": "0:16:48", "remaining_time": "0:02:25"}
+{"current_steps": 223, "total_steps": 254, "loss": 0.4075, "lr": 1.8152590135397413e-07, "epoch": 0.8779527559055118, "percentage": 87.8, "elapsed_time": "0:16:53", "remaining_time": "0:02:20"}
+{"current_steps": 224, "total_steps": 254, "loss": 0.3905, "lr": 1.7013601415141384e-07, "epoch": 0.8818897637795275, "percentage": 88.19, "elapsed_time": "0:16:57", "remaining_time": "0:02:16"}
+{"current_steps": 225, "total_steps": 254, "loss": 0.528, "lr": 1.5910254307362704e-07, "epoch": 0.8858267716535433, "percentage": 88.58, "elapsed_time": "0:17:02", "remaining_time": "0:02:11"}
+{"current_steps": 226, "total_steps": 254, "loss": 0.4163, "lr": 1.4842717599039048e-07, "epoch": 0.889763779527559, "percentage": 88.98, "elapsed_time": "0:17:06", "remaining_time": "0:02:07"}
+{"current_steps": 227, "total_steps": 254, "loss": 0.4116, "lr": 1.381115459897253e-07, "epoch": 0.8937007874015748, "percentage": 89.37, "elapsed_time": "0:17:11", "remaining_time": "0:02:02"}
+{"current_steps": 228, "total_steps": 254, "loss": 0.3909, "lr": 1.2815723112807264e-07, "epoch": 0.8976377952755905, "percentage": 89.76, "elapsed_time": "0:17:16", "remaining_time": "0:01:58"}
+{"current_steps": 229, "total_steps": 254, "loss": 0.4236, "lr": 1.1856575418888571e-07, "epoch": 0.9015748031496063, "percentage": 90.16, "elapsed_time": "0:17:20", "remaining_time": "0:01:53"}
+{"current_steps": 230, "total_steps": 254, "loss": 0.4055, "lr": 1.0933858244968148e-07, "epoch": 0.905511811023622, "percentage": 90.55, "elapsed_time": "0:17:25", "remaining_time": "0:01:49"}
+{"current_steps": 231, "total_steps": 254, "loss": 0.3908, "lr": 1.0047712745757693e-07, "epoch": 0.9094488188976378, "percentage": 90.94, "elapsed_time": "0:17:29", "remaining_time": "0:01:44"}
+{"current_steps": 232, "total_steps": 254, "loss": 0.3581, "lr": 9.198274481335728e-08, "epoch": 0.9133858267716536, "percentage": 91.34, "elapsed_time": "0:17:34", "remaining_time": "0:01:39"}
+{"current_steps": 233, "total_steps": 254, "loss": 0.4035, "lr": 8.385673396409915e-08, "epoch": 0.9173228346456693, "percentage": 91.73, "elapsed_time": "0:17:38", "remaining_time": "0:01:35"}
+{"current_steps": 234, "total_steps": 254, "loss": 0.3957, "lr": 7.610033800438343e-08, "epoch": 0.9212598425196851, "percentage": 92.13, "elapsed_time": "0:17:43", "remaining_time": "0:01:30"}
+{"current_steps": 235, "total_steps": 254, "loss": 0.3973, "lr": 6.871474348613267e-08, "epoch": 0.9251968503937008, "percentage": 92.52, "elapsed_time": "0:17:47", "remaining_time": "0:01:26"}
+{"current_steps": 236, "total_steps": 254, "loss": 0.3762, "lr": 6.170108023709349e-08, "epoch": 0.9291338582677166, "percentage": 92.91, "elapsed_time": "0:17:52", "remaining_time": "0:01:21"}
+{"current_steps": 237, "total_steps": 254, "loss": 0.4001, "lr": 5.506042118799904e-08, "epoch": 0.9330708661417323, "percentage": 93.31, "elapsed_time": "0:17:56", "remaining_time": "0:01:17"}
+{"current_steps": 238, "total_steps": 254, "loss": 0.4175, "lr": 4.8793782208436667e-08, "epoch": 0.937007874015748, "percentage": 93.7, "elapsed_time": "0:18:01", "remaining_time": "0:01:12"}
+{"current_steps": 239, "total_steps": 254, "loss": 0.4012, "lr": 4.2902121951440834e-08, "epoch": 0.9409448818897638, "percentage": 94.09, "elapsed_time": "0:18:05", "remaining_time": "0:01:08"}
+{"current_steps": 240, "total_steps": 254, "loss": 0.4177, "lr": 3.73863417068418e-08, "epoch": 0.9448818897637795, "percentage": 94.49, "elapsed_time": "0:18:10", "remaining_time": "0:01:03"}
+{"current_steps": 241, "total_steps": 254, "loss": 0.3921, "lr": 3.2247285263389824e-08, "epoch": 0.9488188976377953, "percentage": 94.88, "elapsed_time": "0:18:14", "remaining_time": "0:00:59"}
+{"current_steps": 242, "total_steps": 254, "loss": 0.3802, "lr": 2.7485738779673143e-08, "epoch": 0.952755905511811, "percentage": 95.28, "elapsed_time": "0:18:19", "remaining_time": "0:00:54"}
+{"current_steps": 243, "total_steps": 254, "loss": 0.3954, "lr": 2.310243066385498e-08, "epoch": 0.9566929133858267, "percentage": 95.67, "elapsed_time": "0:18:23", "remaining_time": "0:00:49"}
+{"current_steps": 244, "total_steps": 254, "loss": 0.3732, "lr": 1.9098031462242704e-08, "epoch": 0.9606299212598425, "percentage": 96.06, "elapsed_time": "0:18:28", "remaining_time": "0:00:45"}
+{"current_steps": 245, "total_steps": 254, "loss": 0.3943, "lr": 1.5473153756709048e-08, "epoch": 0.9645669291338582, "percentage": 96.46, "elapsed_time": "0:18:32", "remaining_time": "0:00:40"}
+{"current_steps": 246, "total_steps": 254, "loss": 0.3921, "lr": 1.2228352070983719e-08, "epoch": 0.968503937007874, "percentage": 96.85, "elapsed_time": "0:18:37", "remaining_time": "0:00:36"}
+{"current_steps": 247, "total_steps": 254, "loss": 0.3856, "lr": 9.364122785820162e-09, "epoch": 0.9724409448818898, "percentage": 97.24, "elapsed_time": "0:18:42", "remaining_time": "0:00:31"}
+{"current_steps": 248, "total_steps": 254, "loss": 0.4032, "lr": 6.880904063063243e-09, "epoch": 0.9763779527559056, "percentage": 97.64, "elapsed_time": "0:18:46", "remaining_time": "0:00:27"}
+{"current_steps": 249, "total_steps": 254, "loss": 0.4013, "lr": 4.779075778620079e-09, "epoch": 0.9803149606299213, "percentage": 98.03, "elapsed_time": "0:18:51", "remaining_time": "0:00:22"}
+{"current_steps": 250, "total_steps": 254, "loss": 0.3861, "lr": 3.0589594643468114e-09, "epoch": 0.984251968503937, "percentage": 98.43, "elapsed_time": "0:18:55", "remaining_time": "0:00:18"}
+{"current_steps": 251, "total_steps": 254, "loss": 0.3643, "lr": 1.7208182588618338e-09, "epoch": 0.9881889763779528, "percentage": 98.82, "elapsed_time": "0:19:00", "remaining_time": "0:00:13"}
+{"current_steps": 252, "total_steps": 254, "loss": 0.392, "lr": 7.648568672921631e-10, "epoch": 0.9921259842519685, "percentage": 99.21, "elapsed_time": "0:19:04", "remaining_time": "0:00:09"}
+{"current_steps": 253, "total_steps": 254, "loss": 0.3861, "lr": 1.9122152995765252e-10, "epoch": 0.9960629921259843, "percentage": 99.61, "elapsed_time": "0:19:09", "remaining_time": "0:00:04"}
+{"current_steps": 254, "total_steps": 254, "loss": 0.3538, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:19:13", "remaining_time": "0:00:00"}
+{"current_steps": 254, "total_steps": 254, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:19:37", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1836 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 254,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003937007874015748,
+      "grad_norm": 5.873804846579428,
+      "learning_rate": 4.9998087784700426e-06,
+      "loss": 1.0172,
+      "step": 1
+    },
+    {
+      "epoch": 0.007874015748031496,
+      "grad_norm": 5.2042709874473365,
+      "learning_rate": 4.999235143132708e-06,
+      "loss": 0.9352,
+      "step": 2
+    },
+    {
+      "epoch": 0.011811023622047244,
+      "grad_norm": 3.390348716317633,
+      "learning_rate": 4.998279181741138e-06,
+      "loss": 0.8516,
+      "step": 3
+    },
+    {
+      "epoch": 0.015748031496062992,
+      "grad_norm": 2.9381260902548,
+      "learning_rate": 4.996941040535654e-06,
+      "loss": 0.7877,
+      "step": 4
+    },
+    {
+      "epoch": 0.01968503937007874,
+      "grad_norm": 2.1648279111709083,
+      "learning_rate": 4.99522092422138e-06,
+      "loss": 0.6726,
+      "step": 5
+    },
+    {
+      "epoch": 0.023622047244094488,
+      "grad_norm": 2.2738099366452844,
+      "learning_rate": 4.993119095936937e-06,
+      "loss": 0.6184,
+      "step": 6
+    },
+    {
+      "epoch": 0.027559055118110236,
+      "grad_norm": 4.021794506930905,
+      "learning_rate": 4.9906358772141805e-06,
+      "loss": 0.7206,
+      "step": 7
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "grad_norm": 1.6520175708626668,
+      "learning_rate": 4.987771647929017e-06,
+      "loss": 0.5616,
+      "step": 8
+    },
+    {
+      "epoch": 0.03543307086614173,
+      "grad_norm": 1.6578193570079638,
+      "learning_rate": 4.984526846243291e-06,
+      "loss": 0.5068,
+      "step": 9
+    },
+    {
+      "epoch": 0.03937007874015748,
+      "grad_norm": 1.7040371781178054,
+      "learning_rate": 4.980901968537758e-06,
+      "loss": 0.6207,
+      "step": 10
+    },
+    {
+      "epoch": 0.04330708661417323,
+      "grad_norm": 1.463249248885123,
+      "learning_rate": 4.9768975693361456e-06,
+      "loss": 0.5879,
+      "step": 11
+    },
+    {
+      "epoch": 0.047244094488188976,
+      "grad_norm": 1.4213629856781884,
+      "learning_rate": 4.972514261220327e-06,
+      "loss": 0.5368,
+      "step": 12
+    },
+    {
+      "epoch": 0.051181102362204724,
+      "grad_norm": 1.2467768795933698,
+      "learning_rate": 4.967752714736611e-06,
+      "loss": 0.5044,
+      "step": 13
+    },
+    {
+      "epoch": 0.05511811023622047,
+      "grad_norm": 1.3981232734055578,
+      "learning_rate": 4.962613658293158e-06,
+      "loss": 0.5477,
+      "step": 14
+    },
+    {
+      "epoch": 0.05905511811023622,
+      "grad_norm": 1.2149834075245458,
+      "learning_rate": 4.95709787804856e-06,
+      "loss": 0.5093,
+      "step": 15
+    },
+    {
+      "epoch": 0.06299212598425197,
+      "grad_norm": 1.2185569711465276,
+      "learning_rate": 4.9512062177915634e-06,
+      "loss": 0.5062,
+      "step": 16
+    },
+    {
+      "epoch": 0.06692913385826772,
+      "grad_norm": 1.1984492073043462,
+      "learning_rate": 4.9449395788120014e-06,
+      "loss": 0.5541,
+      "step": 17
+    },
+    {
+      "epoch": 0.07086614173228346,
+      "grad_norm": 1.2172219157907191,
+      "learning_rate": 4.938298919762907e-06,
+      "loss": 0.505,
+      "step": 18
+    },
+    {
+      "epoch": 0.07480314960629922,
+      "grad_norm": 1.184029446063265,
+      "learning_rate": 4.931285256513868e-06,
+      "loss": 0.4907,
+      "step": 19
+    },
+    {
+      "epoch": 0.07874015748031496,
+      "grad_norm": 1.160881791638922,
+      "learning_rate": 4.923899661995617e-06,
+      "loss": 0.4991,
+      "step": 20
+    },
+    {
+      "epoch": 0.08267716535433071,
+      "grad_norm": 1.0729841153262496,
+      "learning_rate": 4.916143266035901e-06,
+      "loss": 0.478,
+      "step": 21
+    },
+    {
+      "epoch": 0.08661417322834646,
+      "grad_norm": 1.1237104358980416,
+      "learning_rate": 4.908017255186644e-06,
+      "loss": 0.4678,
+      "step": 22
+    },
+    {
+      "epoch": 0.09055118110236221,
+      "grad_norm": 1.1714884658251425,
+      "learning_rate": 4.899522872542424e-06,
+      "loss": 0.4581,
+      "step": 23
+    },
+    {
+      "epoch": 0.09448818897637795,
+      "grad_norm": 1.22504208732838,
+      "learning_rate": 4.8906614175503196e-06,
+      "loss": 0.4757,
+      "step": 24
+    },
+    {
+      "epoch": 0.0984251968503937,
+      "grad_norm": 1.2486433851150303,
+      "learning_rate": 4.8814342458111145e-06,
+      "loss": 0.5344,
+      "step": 25
+    },
+    {
+      "epoch": 0.10236220472440945,
+      "grad_norm": 1.0443053546369905,
+      "learning_rate": 4.871842768871928e-06,
+      "loss": 0.4379,
+      "step": 26
+    },
+    {
+      "epoch": 0.1062992125984252,
+      "grad_norm": 1.1103752119253238,
+      "learning_rate": 4.861888454010275e-06,
+      "loss": 0.5005,
+      "step": 27
+    },
+    {
+      "epoch": 0.11023622047244094,
+      "grad_norm": 1.0235779793250492,
+      "learning_rate": 4.85157282400961e-06,
+      "loss": 0.4295,
+      "step": 28
+    },
+    {
+      "epoch": 0.1141732283464567,
+      "grad_norm": 1.113368510105623,
+      "learning_rate": 4.8408974569263734e-06,
+      "loss": 0.449,
+      "step": 29
+    },
+    {
+      "epoch": 0.11811023622047244,
+      "grad_norm": 1.2631464174916769,
+      "learning_rate": 4.829863985848587e-06,
+      "loss": 0.4881,
+      "step": 30
+    },
+    {
+      "epoch": 0.1220472440944882,
+      "grad_norm": 1.011586340941771,
+      "learning_rate": 4.818474098646026e-06,
+      "loss": 0.444,
+      "step": 31
+    },
+    {
+      "epoch": 0.12598425196850394,
+      "grad_norm": 1.1043675539930584,
+      "learning_rate": 4.806729537712017e-06,
+      "loss": 0.4314,
+      "step": 32
+    },
+    {
+      "epoch": 0.12992125984251968,
+      "grad_norm": 1.1033617525958317,
+      "learning_rate": 4.794632099696888e-06,
+      "loss": 0.4464,
+      "step": 33
+    },
+    {
+      "epoch": 0.13385826771653545,
+      "grad_norm": 1.172028152688878,
+      "learning_rate": 4.7821836352331235e-06,
+      "loss": 0.4896,
+      "step": 34
+    },
+    {
+      "epoch": 0.1377952755905512,
+      "grad_norm": 1.0665501835038442,
+      "learning_rate": 4.76938604865226e-06,
+      "loss": 0.4331,
+      "step": 35
+    },
+    {
+      "epoch": 0.14173228346456693,
+      "grad_norm": 1.0610256879973345,
+      "learning_rate": 4.7562412976935655e-06,
+      "loss": 0.4213,
+      "step": 36
+    },
+    {
+      "epoch": 0.14566929133858267,
+      "grad_norm": 1.0636766303151017,
+      "learning_rate": 4.742751393204553e-06,
+      "loss": 0.4098,
+      "step": 37
+    },
+    {
+      "epoch": 0.14960629921259844,
+      "grad_norm": 1.4383447218617336,
+      "learning_rate": 4.728918398833361e-06,
+      "loss": 0.5072,
+      "step": 38
+    },
+    {
+      "epoch": 0.15354330708661418,
+      "grad_norm": 1.2512278699579351,
+      "learning_rate": 4.714744430713068e-06,
+      "loss": 0.4477,
+      "step": 39
+    },
+    {
+      "epoch": 0.15748031496062992,
+      "grad_norm": 1.3915872161869538,
+      "learning_rate": 4.700231657137971e-06,
+      "loss": 0.4629,
+      "step": 40
+    },
+    {
+      "epoch": 0.16141732283464566,
+      "grad_norm": 1.1196547761955367,
+      "learning_rate": 4.685382298231882e-06,
+      "loss": 0.4574,
+      "step": 41
+    },
+    {
+      "epoch": 0.16535433070866143,
+      "grad_norm": 0.9621465791157945,
+      "learning_rate": 4.670198625608504e-06,
+      "loss": 0.3994,
+      "step": 42
+    },
+    {
+      "epoch": 0.16929133858267717,
+      "grad_norm": 1.019167544797294,
+      "learning_rate": 4.6546829620239265e-06,
+      "loss": 0.4548,
+      "step": 43
+    },
+    {
+      "epoch": 0.1732283464566929,
+      "grad_norm": 1.048140822937445,
+      "learning_rate": 4.63883768102129e-06,
+      "loss": 0.4359,
+      "step": 44
+    },
+    {
+      "epoch": 0.17716535433070865,
+      "grad_norm": 1.0298215981603185,
+      "learning_rate": 4.622665206567698e-06,
+      "loss": 0.4226,
+      "step": 45
+    },
+    {
+      "epoch": 0.18110236220472442,
+      "grad_norm": 1.5929424660653073,
+      "learning_rate": 4.606168012683394e-06,
+      "loss": 0.3893,
+      "step": 46
+    },
+    {
+      "epoch": 0.18503937007874016,
+      "grad_norm": 1.0842378837160482,
+      "learning_rate": 4.589348623063304e-06,
+      "loss": 0.4619,
+      "step": 47
+    },
+    {
+      "epoch": 0.1889763779527559,
+      "grad_norm": 1.0734217019914694,
+      "learning_rate": 4.5722096106909595e-06,
+      "loss": 0.4376,
+      "step": 48
+    },
+    {
+      "epoch": 0.19291338582677164,
+      "grad_norm": 0.9928372077591855,
+      "learning_rate": 4.5547535974448966e-06,
+      "loss": 0.4622,
+      "step": 49
+    },
+    {
+      "epoch": 0.1968503937007874,
+      "grad_norm": 1.2160080442574632,
+      "learning_rate": 4.536983253697561e-06,
+      "loss": 0.4368,
+      "step": 50
+    },
+    {
+      "epoch": 0.20078740157480315,
+      "grad_norm": 1.4068590327992998,
+      "learning_rate": 4.518901297906811e-06,
+      "loss": 0.4798,
+      "step": 51
+    },
+    {
+      "epoch": 0.2047244094488189,
+      "grad_norm": 1.2511773908437078,
+      "learning_rate": 4.500510496200043e-06,
+      "loss": 0.4713,
+      "step": 52
+    },
+    {
+      "epoch": 0.20866141732283464,
+      "grad_norm": 1.1424129628130344,
+      "learning_rate": 4.481813661951052e-06,
+      "loss": 0.4172,
+      "step": 53
+    },
+    {
+      "epoch": 0.2125984251968504,
+      "grad_norm": 1.0365301297747087,
+      "learning_rate": 4.462813655349637e-06,
+      "loss": 0.4068,
+      "step": 54
+    },
+    {
+      "epoch": 0.21653543307086615,
+      "grad_norm": 0.9975137171849471,
+      "learning_rate": 4.4435133829640645e-06,
+      "loss": 0.4348,
+      "step": 55
+    },
+    {
+      "epoch": 0.2204724409448819,
+      "grad_norm": 1.0959231402817728,
+      "learning_rate": 4.423915797296426e-06,
+      "loss": 0.4596,
+      "step": 56
+    },
+    {
+      "epoch": 0.22440944881889763,
+      "grad_norm": 1.0926803298999197,
+      "learning_rate": 4.4040238963309705e-06,
+      "loss": 0.4159,
+      "step": 57
+    },
+    {
+      "epoch": 0.2283464566929134,
+      "grad_norm": 1.03872741860108,
+      "learning_rate": 4.383840723075488e-06,
+      "loss": 0.4373,
+      "step": 58
+    },
+    {
+      "epoch": 0.23228346456692914,
+      "grad_norm": 1.0219361031311929,
+      "learning_rate": 4.363369365095798e-06,
+      "loss": 0.422,
+      "step": 59
+    },
+    {
+      "epoch": 0.23622047244094488,
+      "grad_norm": 0.9945849996271041,
+      "learning_rate": 4.34261295404341e-06,
+      "loss": 0.4129,
+      "step": 60
+    },
+    {
+      "epoch": 0.24015748031496062,
+      "grad_norm": 1.0091651461825784,
+      "learning_rate": 4.321574665176469e-06,
+      "loss": 0.419,
+      "step": 61
+    },
+    {
+      "epoch": 0.2440944881889764,
+      "grad_norm": 1.993372160075214,
+      "learning_rate": 4.300257716874001e-06,
+      "loss": 0.4363,
+      "step": 62
+    },
+    {
+      "epoch": 0.24803149606299213,
+      "grad_norm": 1.4354274506289624,
+      "learning_rate": 4.278665370143583e-06,
+      "loss": 0.457,
+      "step": 63
+    },
+    {
+      "epoch": 0.25196850393700787,
+      "grad_norm": 1.022359726362657,
+      "learning_rate": 4.2568009281224755e-06,
+      "loss": 0.4253,
+      "step": 64
+    },
+    {
+      "epoch": 0.2559055118110236,
+      "grad_norm": 0.9488379406030556,
+      "learning_rate": 4.234667735572323e-06,
+      "loss": 0.3958,
+      "step": 65
+    },
+    {
+      "epoch": 0.25984251968503935,
+      "grad_norm": 1.006467444909438,
+      "learning_rate": 4.2122691783674786e-06,
+      "loss": 0.4035,
+      "step": 66
+    },
+    {
+      "epoch": 0.2637795275590551,
+      "grad_norm": 1.016611971280268,
+      "learning_rate": 4.1896086829770445e-06,
+      "loss": 0.4039,
+      "step": 67
+    },
+    {
+      "epoch": 0.2677165354330709,
+      "grad_norm": 0.9998847612313827,
+      "learning_rate": 4.166689715940699e-06,
+      "loss": 0.4316,
+      "step": 68
+    },
+    {
+      "epoch": 0.27165354330708663,
+      "grad_norm": 0.9680966479148795,
+      "learning_rate": 4.143515783338395e-06,
+      "loss": 0.3887,
+      "step": 69
+    },
+    {
+      "epoch": 0.2755905511811024,
+      "grad_norm": 1.138199382913498,
+      "learning_rate": 4.120090430254013e-06,
+      "loss": 0.4218,
+      "step": 70
+    },
+    {
+      "epoch": 0.2795275590551181,
+      "grad_norm": 0.9922584296591679,
+      "learning_rate": 4.096417240233036e-06,
+      "loss": 0.4333,
+      "step": 71
+    },
+    {
+      "epoch": 0.28346456692913385,
+      "grad_norm": 1.0488951878944524,
+      "learning_rate": 4.072499834734357e-06,
+      "loss": 0.4474,
+      "step": 72
+    },
+    {
+      "epoch": 0.2874015748031496,
+      "grad_norm": 1.1597434560011772,
+      "learning_rate": 4.048341872576272e-06,
+      "loss": 0.4568,
+      "step": 73
+    },
+    {
+      "epoch": 0.29133858267716534,
+      "grad_norm": 1.4145899921242377,
+      "learning_rate": 4.02394704937677e-06,
+      "loss": 0.4408,
+      "step": 74
+    },
+    {
+      "epoch": 0.2952755905511811,
+      "grad_norm": 1.11863952480103,
+      "learning_rate": 3.999319096988183e-06,
+      "loss": 0.426,
+      "step": 75
+    },
+    {
+      "epoch": 0.2992125984251969,
+      "grad_norm": 1.2510722033722184,
+      "learning_rate": 3.974461782926299e-06,
+      "loss": 0.4336,
+      "step": 76
+    },
+    {
+      "epoch": 0.3031496062992126,
+      "grad_norm": 1.1187937772924657,
+      "learning_rate": 3.949378909794019e-06,
+      "loss": 0.4657,
+      "step": 77
+    },
+    {
+      "epoch": 0.30708661417322836,
+      "grad_norm": 1.1621647075599861,
+      "learning_rate": 3.924074314699643e-06,
+      "loss": 0.4671,
+      "step": 78
+    },
+    {
+      "epoch": 0.3110236220472441,
+      "grad_norm": 1.0356693075714127,
+      "learning_rate": 3.898551868669883e-06,
+      "loss": 0.4413,
+      "step": 79
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 1.228396694869618,
+      "learning_rate": 3.872815476057682e-06,
+      "loss": 0.4998,
+      "step": 80
+    },
+    {
+      "epoch": 0.3188976377952756,
+      "grad_norm": 1.214547046907022,
+      "learning_rate": 3.846869073944934e-06,
+      "loss": 0.4479,
+      "step": 81
+    },
+    {
+      "epoch": 0.3228346456692913,
+      "grad_norm": 1.122139004611209,
+      "learning_rate": 3.820716631540209e-06,
+      "loss": 0.4489,
+      "step": 82
+    },
+    {
+      "epoch": 0.32677165354330706,
+      "grad_norm": 1.031397903055992,
+      "learning_rate": 3.7943621495715455e-06,
+      "loss": 0.3866,
+      "step": 83
+    },
+    {
+      "epoch": 0.33070866141732286,
+      "grad_norm": 1.0432163033350288,
+      "learning_rate": 3.7678096596744328e-06,
+      "loss": 0.3934,
+      "step": 84
+    },
+    {
+      "epoch": 0.3346456692913386,
+      "grad_norm": 1.0500988402669522,
+      "learning_rate": 3.7410632237750662e-06,
+      "loss": 0.4133,
+      "step": 85
+    },
+    {
+      "epoch": 0.33858267716535434,
+      "grad_norm": 1.048705127091615,
+      "learning_rate": 3.7141269334689593e-06,
+      "loss": 0.4512,
+      "step": 86
+    },
+    {
+      "epoch": 0.3425196850393701,
+      "grad_norm": 0.9934988547952023,
+      "learning_rate": 3.687004909395029e-06,
+      "loss": 0.42,
+      "step": 87
+    },
+    {
+      "epoch": 0.3464566929133858,
+      "grad_norm": 0.9059475756625358,
+      "learning_rate": 3.659701300605224e-06,
+      "loss": 0.4001,
+      "step": 88
+    },
+    {
+      "epoch": 0.35039370078740156,
+      "grad_norm": 1.059585193037618,
+      "learning_rate": 3.6322202839298225e-06,
+      "loss": 0.4396,
+      "step": 89
+    },
+    {
+      "epoch": 0.3543307086614173,
+      "grad_norm": 1.000812722778205,
+      "learning_rate": 3.604566063338467e-06,
+      "loss": 0.3909,
+      "step": 90
+    },
+    {
+      "epoch": 0.35826771653543305,
+      "grad_norm": 1.0747314104145869,
+      "learning_rate": 3.5767428692970557e-06,
+      "loss": 0.3977,
+      "step": 91
+    },
+    {
+      "epoch": 0.36220472440944884,
+      "grad_norm": 0.9558836147441773,
+      "learning_rate": 3.5487549581205727e-06,
+      "loss": 0.3806,
+      "step": 92
+    },
+    {
+      "epoch": 0.3661417322834646,
+      "grad_norm": 0.9624078529182881,
+      "learning_rate": 3.520606611321976e-06,
+      "loss": 0.4175,
+      "step": 93
+    },
+    {
+      "epoch": 0.3700787401574803,
+      "grad_norm": 1.1363052012358694,
+      "learning_rate": 3.4923021349572183e-06,
+      "loss": 0.433,
+      "step": 94
+    },
+    {
+      "epoch": 0.37401574803149606,
+      "grad_norm": 1.076326779706891,
+      "learning_rate": 3.463845858966519e-06,
+      "loss": 0.3999,
+      "step": 95
+    },
+    {
+      "epoch": 0.3779527559055118,
+      "grad_norm": 5.119275193374418,
+      "learning_rate": 3.4352421365119837e-06,
+      "loss": 0.5329,
+      "step": 96
+    },
+    {
+      "epoch": 0.38188976377952755,
+      "grad_norm": 1.0195800992378443,
+      "learning_rate": 3.4064953433116675e-06,
+      "loss": 0.4608,
+      "step": 97
+    },
+    {
+      "epoch": 0.3858267716535433,
+      "grad_norm": 1.0583470233318997,
+      "learning_rate": 3.3776098769701944e-06,
+      "loss": 0.3644,
+      "step": 98
+    },
+    {
+      "epoch": 0.38976377952755903,
+      "grad_norm": 1.0166339717862853,
+      "learning_rate": 3.3485901563060168e-06,
+      "loss": 0.4215,
+      "step": 99
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "grad_norm": 1.0710102574752174,
+      "learning_rate": 3.319440620675442e-06,
+      "loss": 0.3968,
+      "step": 100
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "eval_loss": 0.44460952281951904,
+      "eval_runtime": 1.2192,
+      "eval_samples_per_second": 1.64,
+      "eval_steps_per_second": 0.82,
+      "step": 100
+    },
+    {
+      "epoch": 0.39763779527559057,
+      "grad_norm": 0.962473511631262,
+      "learning_rate": 3.2901657292935113e-06,
+      "loss": 0.4121,
+      "step": 101
+    },
+    {
+      "epoch": 0.4015748031496063,
+      "grad_norm": 0.9950023377796029,
+      "learning_rate": 3.2607699605518408e-06,
+      "loss": 0.3994,
+      "step": 102
+    },
+    {
+      "epoch": 0.40551181102362205,
+      "grad_norm": 1.0086934594089152,
+      "learning_rate": 3.231257811333528e-06,
+      "loss": 0.3921,
+      "step": 103
+    },
+    {
+      "epoch": 0.4094488188976378,
+      "grad_norm": 1.1457799763092185,
+      "learning_rate": 3.201633796325233e-06,
+      "loss": 0.3882,
+      "step": 104
+    },
+    {
+      "epoch": 0.41338582677165353,
+      "grad_norm": 2.3990157074386804,
+      "learning_rate": 3.171902447326536e-06,
+      "loss": 0.4121,
+      "step": 105
+    },
+    {
+      "epoch": 0.41732283464566927,
+      "grad_norm": 0.9400962201275679,
+      "learning_rate": 3.1420683125566703e-06,
+      "loss": 0.3974,
+      "step": 106
+    },
+    {
+      "epoch": 0.421259842519685,
+      "grad_norm": 0.9904108564393783,
+      "learning_rate": 3.112135955958754e-06,
+      "loss": 0.4014,
+      "step": 107
+    },
+    {
+      "epoch": 0.4251968503937008,
+      "grad_norm": 0.9854879620790317,
+      "learning_rate": 3.082109956501604e-06,
+      "loss": 0.3901,
+      "step": 108
+    },
+    {
+      "epoch": 0.42913385826771655,
+      "grad_norm": 1.088129332484552,
+      "learning_rate": 3.0519949074792652e-06,
+      "loss": 0.4022,
+      "step": 109
+    },
+    {
+      "epoch": 0.4330708661417323,
+      "grad_norm": 1.1803090625263783,
+      "learning_rate": 3.0217954158083384e-06,
+      "loss": 0.4293,
+      "step": 110
+    },
+    {
+      "epoch": 0.43700787401574803,
+      "grad_norm": 1.0433571004667173,
+      "learning_rate": 2.9915161013232218e-06,
+      "loss": 0.4276,
+      "step": 111
+    },
+    {
+      "epoch": 0.4409448818897638,
+      "grad_norm": 0.9917794966216765,
+      "learning_rate": 2.96116159606939e-06,
+      "loss": 0.4257,
+      "step": 112
+    },
+    {
+      "epoch": 0.4448818897637795,
+      "grad_norm": 1.054385000200268,
+      "learning_rate": 2.930736543594792e-06,
+      "loss": 0.4234,
+      "step": 113
+    },
+    {
+      "epoch": 0.44881889763779526,
+      "grad_norm": 0.9785870823505299,
+      "learning_rate": 2.9002455982394946e-06,
+      "loss": 0.4273,
+      "step": 114
+    },
+    {
+      "epoch": 0.452755905511811,
+      "grad_norm": 0.8952926063292104,
+      "learning_rate": 2.869693424423673e-06,
+      "loss": 0.3724,
+      "step": 115
+    },
+    {
+      "epoch": 0.4566929133858268,
+      "grad_norm": 1.014118393532633,
+      "learning_rate": 2.839084695934064e-06,
+      "loss": 0.4263,
+      "step": 116
+    },
+    {
+      "epoch": 0.46062992125984253,
+      "grad_norm": 0.99351875053989,
+      "learning_rate": 2.8084240952089824e-06,
+      "loss": 0.3942,
+      "step": 117
+    },
+    {
+      "epoch": 0.4645669291338583,
+      "grad_norm": 1.0385080724422786,
+      "learning_rate": 2.777716312622012e-06,
+      "loss": 0.4194,
+      "step": 118
+    },
+    {
+      "epoch": 0.468503937007874,
+      "grad_norm": 1.1320559550106792,
+      "learning_rate": 2.746966045764486e-06,
+      "loss": 0.4208,
+      "step": 119
+    },
+    {
+      "epoch": 0.47244094488188976,
+      "grad_norm": 1.0491722352340833,
+      "learning_rate": 2.7161779987268643e-06,
+      "loss": 0.3695,
+      "step": 120
+    },
+    {
+      "epoch": 0.4763779527559055,
+      "grad_norm": 0.9649223954046474,
+      "learning_rate": 2.6853568813791158e-06,
+      "loss": 0.4045,
+      "step": 121
+    },
+    {
+      "epoch": 0.48031496062992124,
+      "grad_norm": 0.9516476303449647,
+      "learning_rate": 2.654507408650211e-06,
+      "loss": 0.3857,
+      "step": 122
+    },
+    {
+      "epoch": 0.484251968503937,
+      "grad_norm": 1.0367511707313501,
+      "learning_rate": 2.623634299806848e-06,
+      "loss": 0.3801,
+      "step": 123
+    },
+    {
+      "epoch": 0.4881889763779528,
+      "grad_norm": 1.1223454232753762,
+      "learning_rate": 2.592742277731513e-06,
+      "loss": 0.4161,
+      "step": 124
+    },
+    {
+      "epoch": 0.4921259842519685,
+      "grad_norm": 1.0671868289947815,
+      "learning_rate": 2.5618360681999876e-06,
+      "loss": 0.3918,
+      "step": 125
+    },
+    {
+      "epoch": 0.49606299212598426,
+      "grad_norm": 0.983759274846438,
+      "learning_rate": 2.5309203991584076e-06,
+      "loss": 0.4008,
+      "step": 126
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.057514658356971,
+      "learning_rate": 2.5e-06,
+      "loss": 0.3788,
+      "step": 127
+    },
+    {
+      "epoch": 0.5039370078740157,
+      "grad_norm": 1.7537239911348215,
+      "learning_rate": 2.4690796008415928e-06,
+      "loss": 0.4851,
+      "step": 128
+    },
+    {
+      "epoch": 0.5078740157480315,
+      "grad_norm": 1.070523800173482,
+      "learning_rate": 2.438163931800013e-06,
+      "loss": 0.4291,
+      "step": 129
+    },
+    {
+      "epoch": 0.5118110236220472,
+      "grad_norm": 1.0985673544522587,
+      "learning_rate": 2.4072577222684874e-06,
+      "loss": 0.3957,
+      "step": 130
+    },
+    {
+      "epoch": 0.515748031496063,
+      "grad_norm": 0.9993518995354568,
+      "learning_rate": 2.376365700193153e-06,
+      "loss": 0.399,
+      "step": 131
+    },
+    {
+      "epoch": 0.5196850393700787,
+      "grad_norm": 1.1709380042197546,
+      "learning_rate": 2.3454925913497905e-06,
+      "loss": 0.4387,
+      "step": 132
+    },
+    {
+      "epoch": 0.5236220472440944,
+      "grad_norm": 1.0309363835656318,
+      "learning_rate": 2.314643118620885e-06,
+      "loss": 0.3818,
+      "step": 133
+    },
+    {
+      "epoch": 0.5275590551181102,
+      "grad_norm": 0.9829983734086418,
+      "learning_rate": 2.2838220012731365e-06,
+      "loss": 0.3848,
+      "step": 134
+    },
+    {
+      "epoch": 0.531496062992126,
+      "grad_norm": 1.261699271850856,
+      "learning_rate": 2.2530339542355145e-06,
+      "loss": 0.4537,
+      "step": 135
+    },
+    {
+      "epoch": 0.5354330708661418,
+      "grad_norm": 0.9544294714655335,
+      "learning_rate": 2.222283687377989e-06,
+      "loss": 0.4299,
+      "step": 136
+    },
+    {
+      "epoch": 0.5393700787401575,
+      "grad_norm": 1.0393372453085847,
+      "learning_rate": 2.1915759047910176e-06,
+      "loss": 0.3917,
+      "step": 137
+    },
+    {
+      "epoch": 0.5433070866141733,
+      "grad_norm": 1.0493660578238762,
+      "learning_rate": 2.160915304065936e-06,
+      "loss": 0.419,
+      "step": 138
+    },
+    {
+      "epoch": 0.547244094488189,
+      "grad_norm": 1.0380968790138452,
+      "learning_rate": 2.1303065755763276e-06,
+      "loss": 0.3893,
+      "step": 139
+    },
+    {
+      "epoch": 0.5511811023622047,
+      "grad_norm": 1.136522941504433,
+      "learning_rate": 2.0997544017605063e-06,
+      "loss": 0.4037,
+      "step": 140
+    },
+    {
+      "epoch": 0.5551181102362205,
+      "grad_norm": 1.0592000221324607,
+      "learning_rate": 2.069263456405209e-06,
+      "loss": 0.3921,
+      "step": 141
+    },
+    {
+      "epoch": 0.5590551181102362,
+      "grad_norm": 1.4756981498096395,
+      "learning_rate": 2.0388384039306105e-06,
+      "loss": 0.4272,
+      "step": 142
+    },
+    {
+      "epoch": 0.562992125984252,
+      "grad_norm": 1.0318207072284824,
+      "learning_rate": 2.008483898676779e-06,
+      "loss": 0.397,
+      "step": 143
+    },
+    {
+      "epoch": 0.5669291338582677,
+      "grad_norm": 1.0606125754651898,
+      "learning_rate": 1.9782045841916625e-06,
+      "loss": 0.4044,
+      "step": 144
+    },
+    {
+      "epoch": 0.5708661417322834,
+      "grad_norm": 1.2068610411413117,
+      "learning_rate": 1.948005092520735e-06,
+      "loss": 0.4037,
+      "step": 145
+    },
+    {
+      "epoch": 0.5748031496062992,
+      "grad_norm": 1.0342511943098542,
+      "learning_rate": 1.917890043498397e-06,
+      "loss": 0.4305,
+      "step": 146
+    },
+    {
+      "epoch": 0.5787401574803149,
+      "grad_norm": 0.9770540004821476,
+      "learning_rate": 1.8878640440412473e-06,
+      "loss": 0.3745,
+      "step": 147
+    },
+    {
+      "epoch": 0.5826771653543307,
+      "grad_norm": 0.9321080738471358,
+      "learning_rate": 1.8579316874433306e-06,
+      "loss": 0.3798,
+      "step": 148
+    },
+    {
+      "epoch": 0.5866141732283464,
+      "grad_norm": 1.0498741948941261,
+      "learning_rate": 1.8280975526734657e-06,
+      "loss": 0.389,
+      "step": 149
+    },
+    {
+      "epoch": 0.5905511811023622,
+      "grad_norm": 1.052521398787742,
+      "learning_rate": 1.7983662036747682e-06,
+      "loss": 0.4377,
+      "step": 150
+    },
+    {
+      "epoch": 0.594488188976378,
+      "grad_norm": 1.0508018534881387,
+      "learning_rate": 1.7687421886664725e-06,
+      "loss": 0.4328,
+      "step": 151
+    },
+    {
+      "epoch": 0.5984251968503937,
+      "grad_norm": 0.9184488408479479,
+      "learning_rate": 1.7392300394481599e-06,
+      "loss": 0.3874,
+      "step": 152
+    },
+    {
+      "epoch": 0.6023622047244095,
+      "grad_norm": 1.0121475642195865,
+      "learning_rate": 1.7098342707064885e-06,
+      "loss": 0.4296,
+      "step": 153
+    },
+    {
+      "epoch": 0.6062992125984252,
+      "grad_norm": 1.137182320893546,
+      "learning_rate": 1.680559379324558e-06,
+      "loss": 0.4319,
+      "step": 154
+    },
+    {
+      "epoch": 0.610236220472441,
+      "grad_norm": 1.0725983783190618,
+      "learning_rate": 1.6514098436939834e-06,
+      "loss": 0.4253,
+      "step": 155
+    },
+    {
+      "epoch": 0.6141732283464567,
+      "grad_norm": 1.113570769604765,
+      "learning_rate": 1.6223901230298062e-06,
+      "loss": 0.41,
+      "step": 156
+    },
+    {
+      "epoch": 0.6181102362204725,
+      "grad_norm": 1.0034772104154477,
+      "learning_rate": 1.5935046566883327e-06,
+      "loss": 0.3984,
+      "step": 157
+    },
+    {
+      "epoch": 0.6220472440944882,
+      "grad_norm": 1.1403065391951734,
+      "learning_rate": 1.5647578634880174e-06,
+      "loss": 0.3675,
+      "step": 158
+    },
+    {
+      "epoch": 0.6259842519685039,
+      "grad_norm": 1.0235669179489535,
+      "learning_rate": 1.5361541410334817e-06,
+      "loss": 0.3902,
+      "step": 159
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 2.273341043469205,
+      "learning_rate": 1.5076978650427825e-06,
+      "loss": 0.3719,
+      "step": 160
+    },
+    {
+      "epoch": 0.6338582677165354,
+      "grad_norm": 0.9548901257990439,
+      "learning_rate": 1.4793933886780244e-06,
+      "loss": 0.387,
+      "step": 161
+    },
+    {
+      "epoch": 0.6377952755905512,
+      "grad_norm": 0.8790736713034711,
+      "learning_rate": 1.451245041879428e-06,
+      "loss": 0.3464,
+      "step": 162
+    },
+    {
+      "epoch": 0.6417322834645669,
+      "grad_norm": 1.023159423627926,
+      "learning_rate": 1.4232571307029458e-06,
+      "loss": 0.4082,
+      "step": 163
+    },
+    {
+      "epoch": 0.6456692913385826,
+      "grad_norm": 1.052054601215584,
+      "learning_rate": 1.3954339366615335e-06,
+      "loss": 0.4097,
+      "step": 164
+    },
+    {
+      "epoch": 0.6496062992125984,
+      "grad_norm": 0.9616429743348347,
+      "learning_rate": 1.367779716070179e-06,
+      "loss": 0.3858,
+      "step": 165
+    },
+    {
+      "epoch": 0.6535433070866141,
+      "grad_norm": 1.0589392331960652,
+      "learning_rate": 1.340298699394777e-06,
+      "loss": 0.3941,
+      "step": 166
+    },
+    {
+      "epoch": 0.65748031496063,
+      "grad_norm": 1.0143295976236535,
+      "learning_rate": 1.3129950906049716e-06,
+      "loss": 0.3887,
+      "step": 167
+    },
+    {
+      "epoch": 0.6614173228346457,
+      "grad_norm": 0.9398179357064573,
+      "learning_rate": 1.285873066531041e-06,
+      "loss": 0.3814,
+      "step": 168
+    },
+    {
+      "epoch": 0.6653543307086615,
+      "grad_norm": 1.110680829145448,
+      "learning_rate": 1.2589367762249346e-06,
+      "loss": 0.3818,
+      "step": 169
+    },
+    {
+      "epoch": 0.6692913385826772,
+      "grad_norm": 0.9925671928496989,
+      "learning_rate": 1.2321903403255672e-06,
+      "loss": 0.4148,
+      "step": 170
+    },
+    {
+      "epoch": 0.6732283464566929,
+      "grad_norm": 1.0102524289524801,
+      "learning_rate": 1.2056378504284551e-06,
+      "loss": 0.4152,
+      "step": 171
+    },
+    {
+      "epoch": 0.6771653543307087,
+      "grad_norm": 1.018095905775292,
+      "learning_rate": 1.1792833684597908e-06,
+      "loss": 0.3826,
+      "step": 172
+    },
+    {
+      "epoch": 0.6811023622047244,
+      "grad_norm": 1.1006003769832229,
+      "learning_rate": 1.153130926055066e-06,
+      "loss": 0.3981,
+      "step": 173
+    },
+    {
+      "epoch": 0.6850393700787402,
+      "grad_norm": 0.9486598239916306,
+      "learning_rate": 1.1271845239423196e-06,
+      "loss": 0.4269,
+      "step": 174
+    },
+    {
+      "epoch": 0.6889763779527559,
+      "grad_norm": 1.0981562125749977,
+      "learning_rate": 1.1014481313301173e-06,
+      "loss": 0.4193,
+      "step": 175
+    },
+    {
+      "epoch": 0.6929133858267716,
+      "grad_norm": 1.0564160134263556,
+      "learning_rate": 1.0759256853003577e-06,
+      "loss": 0.4016,
+      "step": 176
+    },
+    {
+      "epoch": 0.6968503937007874,
+      "grad_norm": 1.0087117240748105,
+      "learning_rate": 1.0506210902059815e-06,
+      "loss": 0.4018,
+      "step": 177
+    },
+    {
+      "epoch": 0.7007874015748031,
+      "grad_norm": 0.9894290911244402,
+      "learning_rate": 1.0255382170737016e-06,
+      "loss": 0.4192,
+      "step": 178
+    },
+    {
+      "epoch": 0.7047244094488189,
+      "grad_norm": 0.891330985888593,
+      "learning_rate": 1.000680903011818e-06,
+      "loss": 0.38,
+      "step": 179
+    },
+    {
+      "epoch": 0.7086614173228346,
+      "grad_norm": 1.0837492275301066,
+      "learning_rate": 9.760529506232306e-07,
+      "loss": 0.4397,
+      "step": 180
+    },
+    {
+      "epoch": 0.7125984251968503,
+      "grad_norm": 0.9465064921207751,
+      "learning_rate": 9.516581274237288e-07,
+      "loss": 0.3696,
+      "step": 181
+    },
+    {
+      "epoch": 0.7165354330708661,
+      "grad_norm": 1.0804459996566762,
+      "learning_rate": 9.275001652656445e-07,
+      "loss": 0.4376,
+      "step": 182
+    },
+    {
+      "epoch": 0.7204724409448819,
+      "grad_norm": 1.0480935931707196,
+      "learning_rate": 9.035827597669636e-07,
+      "loss": 0.3983,
+      "step": 183
+    },
+    {
+      "epoch": 0.7244094488188977,
+      "grad_norm": 1.0339084795432274,
+      "learning_rate": 8.799095697459869e-07,
+      "loss": 0.4211,
+      "step": 184
+    },
+    {
+      "epoch": 0.7283464566929134,
+      "grad_norm": 1.0065393987938336,
+      "learning_rate": 8.564842166616047e-07,
+      "loss": 0.3867,
+      "step": 185
+    },
+    {
+      "epoch": 0.7322834645669292,
+      "grad_norm": 1.0930731620579874,
+      "learning_rate": 8.333102840593016e-07,
+      "loss": 0.4111,
+      "step": 186
+    },
+    {
+      "epoch": 0.7362204724409449,
+      "grad_norm": 1.0016682048722287,
+      "learning_rate": 8.103913170229566e-07,
+      "loss": 0.4344,
+      "step": 187
+    },
+    {
+      "epoch": 0.7401574803149606,
+      "grad_norm": 0.9340818929998667,
+      "learning_rate": 7.877308216325222e-07,
+      "loss": 0.4086,
+      "step": 188
+    },
+    {
+      "epoch": 0.7440944881889764,
+      "grad_norm": 0.9377870230827421,
+      "learning_rate": 7.653322644276778e-07,
+      "loss": 0.4111,
+      "step": 189
+    },
+    {
+      "epoch": 0.7480314960629921,
+      "grad_norm": 1.0207863517031581,
+      "learning_rate": 7.43199071877525e-07,
+      "loss": 0.4075,
+      "step": 190
+    },
+    {
+      "epoch": 0.7519685039370079,
+      "grad_norm": 1.0050410984677287,
+      "learning_rate": 7.213346298564169e-07,
+      "loss": 0.407,
+      "step": 191
+    },
+    {
+      "epoch": 0.7559055118110236,
+      "grad_norm": 0.9818278406757491,
+      "learning_rate": 6.997422831259992e-07,
+      "loss": 0.3934,
+      "step": 192
+    },
+    {
+      "epoch": 0.7598425196850394,
+      "grad_norm": 0.9706053625598139,
+      "learning_rate": 6.784253348235323e-07,
+      "loss": 0.3718,
+      "step": 193
+    },
+    {
+      "epoch": 0.7637795275590551,
+      "grad_norm": 1.0149629329337544,
+      "learning_rate": 6.573870459565907e-07,
+      "loss": 0.3919,
+      "step": 194
+    },
+    {
+      "epoch": 0.7677165354330708,
+      "grad_norm": 0.9982735836617721,
+      "learning_rate": 6.366306349042034e-07,
+      "loss": 0.4167,
+      "step": 195
+    },
+    {
+      "epoch": 0.7716535433070866,
+      "grad_norm": 1.176019007258874,
+      "learning_rate": 6.161592769245115e-07,
+      "loss": 0.5578,
+      "step": 196
+    },
+    {
+      "epoch": 0.7755905511811023,
+      "grad_norm": 1.029667701376537,
+      "learning_rate": 5.959761036690307e-07,
+      "loss": 0.3596,
+      "step": 197
+    },
+    {
+      "epoch": 0.7795275590551181,
+      "grad_norm": 1.1046420368929004,
+      "learning_rate": 5.760842027035762e-07,
+      "loss": 0.4179,
+      "step": 198
+    },
+    {
+      "epoch": 0.7834645669291339,
+      "grad_norm": 0.9714600823908376,
+      "learning_rate": 5.564866170359351e-07,
+      "loss": 0.3809,
+      "step": 199
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 0.9675663875852685,
+      "learning_rate": 5.371863446503628e-07,
+      "loss": 0.3873,
+      "step": 200
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "eval_loss": 0.4238421320915222,
+      "eval_runtime": 1.2074,
+      "eval_samples_per_second": 1.656,
+      "eval_steps_per_second": 0.828,
+      "step": 200
+    },
+    {
+      "epoch": 0.7913385826771654,
+      "grad_norm": 0.9979360595293847,
+      "learning_rate": 5.181863380489485e-07,
+      "loss": 0.3982,
+      "step": 201
+    },
+    {
+      "epoch": 0.7952755905511811,
+      "grad_norm": 1.1120498557499707,
+      "learning_rate": 4.994895037999573e-07,
+      "loss": 0.4038,
+      "step": 202
+    },
+    {
+      "epoch": 0.7992125984251969,
+      "grad_norm": 0.9771579166812452,
+      "learning_rate": 4.810987020931907e-07,
+      "loss": 0.4041,
+      "step": 203
+    },
+    {
+      "epoch": 0.8031496062992126,
+      "grad_norm": 0.9053969804022379,
+      "learning_rate": 4.6301674630243934e-07,
+      "loss": 0.3767,
+      "step": 204
+    },
+    {
+      "epoch": 0.8070866141732284,
+      "grad_norm": 0.9718109762833879,
+      "learning_rate": 4.452464025551037e-07,
+      "loss": 0.4103,
+      "step": 205
+    },
+    {
+      "epoch": 0.8110236220472441,
+      "grad_norm": 0.9610495997047174,
+      "learning_rate": 4.277903893090407e-07,
+      "loss": 0.4024,
+      "step": 206
+    },
+    {
+      "epoch": 0.8149606299212598,
+      "grad_norm": 1.0267607362338869,
+      "learning_rate": 4.106513769366965e-07,
+      "loss": 0.4274,
+      "step": 207
+    },
+    {
+      "epoch": 0.8188976377952756,
+      "grad_norm": 0.9334699573182312,
+      "learning_rate": 3.938319873166066e-07,
+      "loss": 0.3904,
+      "step": 208
+    },
+    {
+      "epoch": 0.8228346456692913,
+      "grad_norm": 1.001097889827926,
+      "learning_rate": 3.773347934323035e-07,
+      "loss": 0.4096,
+      "step": 209
+    },
+    {
+      "epoch": 0.8267716535433071,
+      "grad_norm": 0.9176069341700299,
+      "learning_rate": 3.611623189787103e-07,
+      "loss": 0.3846,
+      "step": 210
+    },
+    {
+      "epoch": 0.8307086614173228,
+      "grad_norm": 1.0382528162191174,
+      "learning_rate": 3.453170379760745e-07,
+      "loss": 0.4084,
+      "step": 211
+    },
+    {
+      "epoch": 0.8346456692913385,
+      "grad_norm": 1.2177003147302798,
+      "learning_rate": 3.298013743914957e-07,
+      "loss": 0.4596,
+      "step": 212
+    },
+    {
+      "epoch": 0.8385826771653543,
+      "grad_norm": 1.0414919912791907,
+      "learning_rate": 3.1461770176811845e-07,
+      "loss": 0.388,
+      "step": 213
+    },
+    {
+      "epoch": 0.84251968503937,
+      "grad_norm": 1.031823275984156,
+      "learning_rate": 2.997683428620296e-07,
+      "loss": 0.4241,
+      "step": 214
+    },
+    {
+      "epoch": 0.8464566929133859,
+      "grad_norm": 0.979034637858283,
+      "learning_rate": 2.852555692869319e-07,
+      "loss": 0.4003,
+      "step": 215
+    },
+    {
+      "epoch": 0.8503937007874016,
+      "grad_norm": 0.8985739109603679,
+      "learning_rate": 2.7108160116663896e-07,
+      "loss": 0.3926,
+      "step": 216
+    },
+    {
+      "epoch": 0.8543307086614174,
+      "grad_norm": 0.9373638578908552,
+      "learning_rate": 2.5724860679544745e-07,
+      "loss": 0.3846,
+      "step": 217
+    },
+    {
+      "epoch": 0.8582677165354331,
+      "grad_norm": 0.9851557002995378,
+      "learning_rate": 2.437587023064342e-07,
+      "loss": 0.4081,
+      "step": 218
+    },
+    {
+      "epoch": 0.8622047244094488,
+      "grad_norm": 1.39339926688059,
+      "learning_rate": 2.306139513477404e-07,
+      "loss": 0.4031,
+      "step": 219
+    },
+    {
+      "epoch": 0.8661417322834646,
+      "grad_norm": 0.9700331734194682,
+      "learning_rate": 2.1781636476687713e-07,
+      "loss": 0.415,
+      "step": 220
+    },
+    {
+      "epoch": 0.8700787401574803,
+      "grad_norm": 1.0313369235209553,
+      "learning_rate": 2.0536790030311227e-07,
+      "loss": 0.4806,
+      "step": 221
+    },
+    {
+      "epoch": 0.8740157480314961,
+      "grad_norm": 1.019053301731295,
+      "learning_rate": 1.9327046228798357e-07,
+      "loss": 0.397,
+      "step": 222
+    },
+    {
+      "epoch": 0.8779527559055118,
+      "grad_norm": 1.0686877163099995,
+      "learning_rate": 1.8152590135397413e-07,
+      "loss": 0.4075,
+      "step": 223
+    },
+    {
+      "epoch": 0.8818897637795275,
+      "grad_norm": 0.896452812966311,
+      "learning_rate": 1.7013601415141384e-07,
+      "loss": 0.3905,
+      "step": 224
+    },
+    {
+      "epoch": 0.8858267716535433,
+      "grad_norm": 5.918509442826021,
+      "learning_rate": 1.5910254307362704e-07,
+      "loss": 0.528,
+      "step": 225
+    },
+    {
+      "epoch": 0.889763779527559,
+      "grad_norm": 0.9214815343274134,
+      "learning_rate": 1.4842717599039048e-07,
+      "loss": 0.4163,
+      "step": 226
+    },
+    {
+      "epoch": 0.8937007874015748,
+      "grad_norm": 1.0311753674936508,
+      "learning_rate": 1.381115459897253e-07,
+      "loss": 0.4116,
+      "step": 227
+    },
+    {
+      "epoch": 0.8976377952755905,
+      "grad_norm": 0.8644443813576165,
+      "learning_rate": 1.2815723112807264e-07,
+      "loss": 0.3909,
+      "step": 228
+    },
+    {
+      "epoch": 0.9015748031496063,
+      "grad_norm": 2.71325577482954,
+      "learning_rate": 1.1856575418888571e-07,
+      "loss": 0.4236,
+      "step": 229
+    },
+    {
+      "epoch": 0.905511811023622,
+      "grad_norm": 1.8431074803955776,
+      "learning_rate": 1.0933858244968148e-07,
+      "loss": 0.4055,
+      "step": 230
+    },
+    {
+      "epoch": 0.9094488188976378,
+      "grad_norm": 0.9311356866158584,
+      "learning_rate": 1.0047712745757693e-07,
+      "loss": 0.3908,
+      "step": 231
+    },
+    {
+      "epoch": 0.9133858267716536,
+      "grad_norm": 0.9482446645427801,
+      "learning_rate": 9.198274481335728e-08,
+      "loss": 0.3581,
+      "step": 232
+    },
+    {
+      "epoch": 0.9173228346456693,
+      "grad_norm": 1.0311298725102134,
+      "learning_rate": 8.385673396409915e-08,
+      "loss": 0.4035,
+      "step": 233
+    },
+    {
+      "epoch": 0.9212598425196851,
+      "grad_norm": 0.9582055065117324,
+      "learning_rate": 7.610033800438343e-08,
+      "loss": 0.3957,
+      "step": 234
+    },
+    {
+      "epoch": 0.9251968503937008,
+      "grad_norm": 0.9511083904432134,
+      "learning_rate": 6.871474348613267e-08,
+      "loss": 0.3973,
+      "step": 235
+    },
+    {
+      "epoch": 0.9291338582677166,
+      "grad_norm": 0.9325912477488292,
+      "learning_rate": 6.170108023709349e-08,
+      "loss": 0.3762,
+      "step": 236
+    },
+    {
+      "epoch": 0.9330708661417323,
+      "grad_norm": 0.9566726984111357,
+      "learning_rate": 5.506042118799904e-08,
+      "loss": 0.4001,
+      "step": 237
+    },
+    {
+      "epoch": 0.937007874015748,
+      "grad_norm": 1.1342631995021175,
+      "learning_rate": 4.8793782208436667e-08,
+      "loss": 0.4175,
+      "step": 238
+    },
+    {
+      "epoch": 0.9409448818897638,
+      "grad_norm": 0.9413428538779047,
+      "learning_rate": 4.2902121951440834e-08,
+      "loss": 0.4012,
+      "step": 239
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 1.1200674489723517,
+      "learning_rate": 3.73863417068418e-08,
+      "loss": 0.4177,
+      "step": 240
+    },
+    {
+      "epoch": 0.9488188976377953,
+      "grad_norm": 1.0108336663046313,
+      "learning_rate": 3.2247285263389824e-08,
+      "loss": 0.3921,
+      "step": 241
+    },
+    {
+      "epoch": 0.952755905511811,
+      "grad_norm": 0.9368581141499427,
+      "learning_rate": 2.7485738779673143e-08,
+      "loss": 0.3802,
+      "step": 242
+    },
+    {
+      "epoch": 0.9566929133858267,
+      "grad_norm": 0.9176796039985227,
+      "learning_rate": 2.310243066385498e-08,
+      "loss": 0.3954,
+      "step": 243
+    },
+    {
+      "epoch": 0.9606299212598425,
+      "grad_norm": 0.9204323378954434,
+      "learning_rate": 1.9098031462242704e-08,
+      "loss": 0.3732,
+      "step": 244
+    },
+    {
+      "epoch": 0.9645669291338582,
+      "grad_norm": 1.055369992146894,
+      "learning_rate": 1.5473153756709048e-08,
+      "loss": 0.3943,
+      "step": 245
+    },
+    {
+      "epoch": 0.968503937007874,
+      "grad_norm": 0.9657713252870235,
+      "learning_rate": 1.2228352070983719e-08,
+      "loss": 0.3921,
+      "step": 246
+    },
+    {
+      "epoch": 0.9724409448818898,
+      "grad_norm": 0.9676624255771817,
+      "learning_rate": 9.364122785820162e-09,
+      "loss": 0.3856,
+      "step": 247
+    },
+    {
+      "epoch": 0.9763779527559056,
+      "grad_norm": 0.9449743029414549,
+      "learning_rate": 6.880904063063243e-09,
+      "loss": 0.4032,
+      "step": 248
+    },
+    {
+      "epoch": 0.9803149606299213,
+      "grad_norm": 1.119745414402105,
+      "learning_rate": 4.779075778620079e-09,
+      "loss": 0.4013,
+      "step": 249
+    },
+    {
+      "epoch": 0.984251968503937,
+      "grad_norm": 0.9828902794084762,
+      "learning_rate": 3.0589594643468114e-09,
+      "loss": 0.3861,
+      "step": 250
+    },
+    {
+      "epoch": 0.9881889763779528,
+      "grad_norm": 0.9329397779846808,
+      "learning_rate": 1.7208182588618338e-09,
+      "loss": 0.3643,
+      "step": 251
+    },
+    {
+      "epoch": 0.9921259842519685,
+      "grad_norm": 0.9985143377008784,
+      "learning_rate": 7.648568672921631e-10,
+      "loss": 0.392,
+      "step": 252
+    },
+    {
+      "epoch": 0.9960629921259843,
+      "grad_norm": 0.9761526155780429,
+      "learning_rate": 1.9122152995765252e-10,
+      "loss": 0.3861,
+      "step": 253
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8914325770935945,
+      "learning_rate": 0.0,
+      "loss": 0.3538,
+      "step": 254
+    },
+    {
+      "epoch": 1.0,
+      "step": 254,
+      "total_flos": 24382439424000.0,
+      "train_loss": 0.4321931260307943,
+      "train_runtime": 1177.8664,
+      "train_samples_per_second": 0.86,
+      "train_steps_per_second": 0.216
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 254,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 24382439424000.0,
+  "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 sha256:5fa2f9e7dc6ae32c67195017199ef85f810a5d03ba6b8ce631ae2e44ffb2449e
+size 7160