Upload model

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the Stratos-R1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+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 +1,8 @@
+{
+    "epoch": 2.998563906175203,
+    "total_flos": 538113478688768.0,
+    "train_loss": 0.5088067185490525,
+    "train_runtime": 25669.0251,
+    "train_samples_per_second": 1.953,
+    "train_steps_per_second": 0.02
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-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
+}

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7562d655c52d8df7c6b454b0b9d658f7e775ee383d2e9e62fc36d9f346b00703
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac727eb597410b187dd138bf2ace3d7f52a9fcd65d8316d346ecfc2cbf211ca2
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e257bfae1c4838b6ca6280288fe8e30e22a7b203854a956914db03fb844de4
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36275af91d7e4d7e3c4e27b851e0891911cebdf12b38c5f486af5209167f3844
+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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.998563906175203,
+    "total_flos": 538113478688768.0,
+    "train_loss": 0.5088067185490525,
+    "train_runtime": 25669.0251,
+    "train_samples_per_second": 1.953,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,3696 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.998563906175203,
+  "eval_steps": 500,
+  "global_step": 522,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0057443752991862135,
+      "grad_norm": 5.37349271774292,
+      "learning_rate": 1.886792452830189e-07,
+      "loss": 0.8587,
+      "step": 1
+    },
+    {
+      "epoch": 0.011488750598372427,
+      "grad_norm": 5.775772571563721,
+      "learning_rate": 3.773584905660378e-07,
+      "loss": 0.8937,
+      "step": 2
+    },
+    {
+      "epoch": 0.01723312589755864,
+      "grad_norm": 5.701127529144287,
+      "learning_rate": 5.660377358490567e-07,
+      "loss": 0.9179,
+      "step": 3
+    },
+    {
+      "epoch": 0.022977501196744854,
+      "grad_norm": 5.48037576675415,
+      "learning_rate": 7.547169811320755e-07,
+      "loss": 0.8829,
+      "step": 4
+    },
+    {
+      "epoch": 0.028721876495931067,
+      "grad_norm": 5.497180938720703,
+      "learning_rate": 9.433962264150944e-07,
+      "loss": 0.8801,
+      "step": 5
+    },
+    {
+      "epoch": 0.03446625179511728,
+      "grad_norm": 5.722774028778076,
+      "learning_rate": 1.1320754716981133e-06,
+      "loss": 0.8665,
+      "step": 6
+    },
+    {
+      "epoch": 0.040210627094303494,
+      "grad_norm": 5.297784328460693,
+      "learning_rate": 1.3207547169811322e-06,
+      "loss": 0.8801,
+      "step": 7
+    },
+    {
+      "epoch": 0.04595500239348971,
+      "grad_norm": 4.2470808029174805,
+      "learning_rate": 1.509433962264151e-06,
+      "loss": 0.8368,
+      "step": 8
+    },
+    {
+      "epoch": 0.05169937769267592,
+      "grad_norm": 3.891289234161377,
+      "learning_rate": 1.6981132075471698e-06,
+      "loss": 0.8067,
+      "step": 9
+    },
+    {
+      "epoch": 0.057443752991862135,
+      "grad_norm": 3.872174024581909,
+      "learning_rate": 1.8867924528301889e-06,
+      "loss": 0.8609,
+      "step": 10
+    },
+    {
+      "epoch": 0.06318812829104835,
+      "grad_norm": 2.5940165519714355,
+      "learning_rate": 2.075471698113208e-06,
+      "loss": 0.8291,
+      "step": 11
+    },
+    {
+      "epoch": 0.06893250359023456,
+      "grad_norm": 2.293347120285034,
+      "learning_rate": 2.2641509433962266e-06,
+      "loss": 0.7539,
+      "step": 12
+    },
+    {
+      "epoch": 0.07467687888942078,
+      "grad_norm": 2.191865921020508,
+      "learning_rate": 2.4528301886792453e-06,
+      "loss": 0.8272,
+      "step": 13
+    },
+    {
+      "epoch": 0.08042125418860699,
+      "grad_norm": 2.2178380489349365,
+      "learning_rate": 2.6415094339622644e-06,
+      "loss": 0.8099,
+      "step": 14
+    },
+    {
+      "epoch": 0.0861656294877932,
+      "grad_norm": 3.483651638031006,
+      "learning_rate": 2.830188679245283e-06,
+      "loss": 0.806,
+      "step": 15
+    },
+    {
+      "epoch": 0.09191000478697942,
+      "grad_norm": 3.8942596912384033,
+      "learning_rate": 3.018867924528302e-06,
+      "loss": 0.8085,
+      "step": 16
+    },
+    {
+      "epoch": 0.09765438008616563,
+      "grad_norm": 3.8473079204559326,
+      "learning_rate": 3.207547169811321e-06,
+      "loss": 0.7816,
+      "step": 17
+    },
+    {
+      "epoch": 0.10339875538535184,
+      "grad_norm": 3.5139431953430176,
+      "learning_rate": 3.3962264150943395e-06,
+      "loss": 0.7845,
+      "step": 18
+    },
+    {
+      "epoch": 0.10914313068453806,
+      "grad_norm": 2.965437412261963,
+      "learning_rate": 3.5849056603773586e-06,
+      "loss": 0.7167,
+      "step": 19
+    },
+    {
+      "epoch": 0.11488750598372427,
+      "grad_norm": 2.0699801445007324,
+      "learning_rate": 3.7735849056603777e-06,
+      "loss": 0.7372,
+      "step": 20
+    },
+    {
+      "epoch": 0.12063188128291048,
+      "grad_norm": 1.5903819799423218,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.711,
+      "step": 21
+    },
+    {
+      "epoch": 0.1263762565820967,
+      "grad_norm": 1.460195779800415,
+      "learning_rate": 4.150943396226416e-06,
+      "loss": 0.7038,
+      "step": 22
+    },
+    {
+      "epoch": 0.13212063188128292,
+      "grad_norm": 1.229818344116211,
+      "learning_rate": 4.339622641509435e-06,
+      "loss": 0.661,
+      "step": 23
+    },
+    {
+      "epoch": 0.13786500718046912,
+      "grad_norm": 1.1705495119094849,
+      "learning_rate": 4.528301886792453e-06,
+      "loss": 0.6991,
+      "step": 24
+    },
+    {
+      "epoch": 0.14360938247965535,
+      "grad_norm": 1.2829539775848389,
+      "learning_rate": 4.716981132075472e-06,
+      "loss": 0.6844,
+      "step": 25
+    },
+    {
+      "epoch": 0.14935375777884155,
+      "grad_norm": 1.1270300149917603,
+      "learning_rate": 4.905660377358491e-06,
+      "loss": 0.6736,
+      "step": 26
+    },
+    {
+      "epoch": 0.15509813307802778,
+      "grad_norm": 1.018497109413147,
+      "learning_rate": 5.09433962264151e-06,
+      "loss": 0.7077,
+      "step": 27
+    },
+    {
+      "epoch": 0.16084250837721398,
+      "grad_norm": 0.8882578611373901,
+      "learning_rate": 5.283018867924529e-06,
+      "loss": 0.6665,
+      "step": 28
+    },
+    {
+      "epoch": 0.1665868836764002,
+      "grad_norm": 1.0214155912399292,
+      "learning_rate": 5.4716981132075475e-06,
+      "loss": 0.6512,
+      "step": 29
+    },
+    {
+      "epoch": 0.1723312589755864,
+      "grad_norm": 0.9866452813148499,
+      "learning_rate": 5.660377358490566e-06,
+      "loss": 0.6561,
+      "step": 30
+    },
+    {
+      "epoch": 0.17807563427477263,
+      "grad_norm": 0.822456955909729,
+      "learning_rate": 5.849056603773585e-06,
+      "loss": 0.6137,
+      "step": 31
+    },
+    {
+      "epoch": 0.18382000957395883,
+      "grad_norm": 0.7711695432662964,
+      "learning_rate": 6.037735849056604e-06,
+      "loss": 0.5908,
+      "step": 32
+    },
+    {
+      "epoch": 0.18956438487314506,
+      "grad_norm": 0.9906867146492004,
+      "learning_rate": 6.226415094339623e-06,
+      "loss": 0.6336,
+      "step": 33
+    },
+    {
+      "epoch": 0.19530876017233126,
+      "grad_norm": 0.9756529331207275,
+      "learning_rate": 6.415094339622642e-06,
+      "loss": 0.6528,
+      "step": 34
+    },
+    {
+      "epoch": 0.20105313547151749,
+      "grad_norm": 0.7538486123085022,
+      "learning_rate": 6.60377358490566e-06,
+      "loss": 0.6377,
+      "step": 35
+    },
+    {
+      "epoch": 0.20679751077070369,
+      "grad_norm": 0.7044028639793396,
+      "learning_rate": 6.792452830188679e-06,
+      "loss": 0.6312,
+      "step": 36
+    },
+    {
+      "epoch": 0.2125418860698899,
+      "grad_norm": 0.766700029373169,
+      "learning_rate": 6.981132075471699e-06,
+      "loss": 0.6142,
+      "step": 37
+    },
+    {
+      "epoch": 0.2182862613690761,
+      "grad_norm": 0.8737772107124329,
+      "learning_rate": 7.169811320754717e-06,
+      "loss": 0.6278,
+      "step": 38
+    },
+    {
+      "epoch": 0.22403063666826234,
+      "grad_norm": 0.7406350374221802,
+      "learning_rate": 7.358490566037736e-06,
+      "loss": 0.6274,
+      "step": 39
+    },
+    {
+      "epoch": 0.22977501196744854,
+      "grad_norm": 0.6247995495796204,
+      "learning_rate": 7.5471698113207555e-06,
+      "loss": 0.604,
+      "step": 40
+    },
+    {
+      "epoch": 0.23551938726663477,
+      "grad_norm": 0.7143349647521973,
+      "learning_rate": 7.735849056603775e-06,
+      "loss": 0.6461,
+      "step": 41
+    },
+    {
+      "epoch": 0.24126376256582097,
+      "grad_norm": 0.6662243604660034,
+      "learning_rate": 7.924528301886793e-06,
+      "loss": 0.5815,
+      "step": 42
+    },
+    {
+      "epoch": 0.2470081378650072,
+      "grad_norm": 0.7262428402900696,
+      "learning_rate": 8.113207547169812e-06,
+      "loss": 0.6194,
+      "step": 43
+    },
+    {
+      "epoch": 0.2527525131641934,
+      "grad_norm": 0.6320751905441284,
+      "learning_rate": 8.301886792452832e-06,
+      "loss": 0.6338,
+      "step": 44
+    },
+    {
+      "epoch": 0.2584968884633796,
+      "grad_norm": 0.5772255063056946,
+      "learning_rate": 8.49056603773585e-06,
+      "loss": 0.6176,
+      "step": 45
+    },
+    {
+      "epoch": 0.26424126376256585,
+      "grad_norm": 0.7007628679275513,
+      "learning_rate": 8.67924528301887e-06,
+      "loss": 0.5683,
+      "step": 46
+    },
+    {
+      "epoch": 0.26998563906175205,
+      "grad_norm": 0.7302536368370056,
+      "learning_rate": 8.867924528301887e-06,
+      "loss": 0.5975,
+      "step": 47
+    },
+    {
+      "epoch": 0.27573001436093825,
+      "grad_norm": 0.6005181670188904,
+      "learning_rate": 9.056603773584907e-06,
+      "loss": 0.5844,
+      "step": 48
+    },
+    {
+      "epoch": 0.28147438966012445,
+      "grad_norm": 0.8314005136489868,
+      "learning_rate": 9.245283018867926e-06,
+      "loss": 0.6181,
+      "step": 49
+    },
+    {
+      "epoch": 0.2872187649593107,
+      "grad_norm": 0.6696397662162781,
+      "learning_rate": 9.433962264150944e-06,
+      "loss": 0.5741,
+      "step": 50
+    },
+    {
+      "epoch": 0.2929631402584969,
+      "grad_norm": 0.6071884632110596,
+      "learning_rate": 9.622641509433963e-06,
+      "loss": 0.5599,
+      "step": 51
+    },
+    {
+      "epoch": 0.2987075155576831,
+      "grad_norm": 0.6364148259162903,
+      "learning_rate": 9.811320754716981e-06,
+      "loss": 0.6052,
+      "step": 52
+    },
+    {
+      "epoch": 0.3044518908568693,
+      "grad_norm": 0.6715644001960754,
+      "learning_rate": 1e-05,
+      "loss": 0.5774,
+      "step": 53
+    },
+    {
+      "epoch": 0.31019626615605556,
+      "grad_norm": 0.5949195623397827,
+      "learning_rate": 9.999887825938495e-06,
+      "loss": 0.5668,
+      "step": 54
+    },
+    {
+      "epoch": 0.31594064145524176,
+      "grad_norm": 0.5966293811798096,
+      "learning_rate": 9.999551308787183e-06,
+      "loss": 0.5708,
+      "step": 55
+    },
+    {
+      "epoch": 0.32168501675442795,
+      "grad_norm": 0.6295287013053894,
+      "learning_rate": 9.998990463645464e-06,
+      "loss": 0.5788,
+      "step": 56
+    },
+    {
+      "epoch": 0.32742939205361415,
+      "grad_norm": 0.623221755027771,
+      "learning_rate": 9.998205315678248e-06,
+      "loss": 0.5868,
+      "step": 57
+    },
+    {
+      "epoch": 0.3331737673528004,
+      "grad_norm": 0.6538676023483276,
+      "learning_rate": 9.997195900114833e-06,
+      "loss": 0.5802,
+      "step": 58
+    },
+    {
+      "epoch": 0.3389181426519866,
+      "grad_norm": 0.6484891772270203,
+      "learning_rate": 9.995962262247314e-06,
+      "loss": 0.5543,
+      "step": 59
+    },
+    {
+      "epoch": 0.3446625179511728,
+      "grad_norm": 0.6138676404953003,
+      "learning_rate": 9.994504457428557e-06,
+      "loss": 0.5633,
+      "step": 60
+    },
+    {
+      "epoch": 0.350406893250359,
+      "grad_norm": 0.5668913722038269,
+      "learning_rate": 9.99282255106972e-06,
+      "loss": 0.5792,
+      "step": 61
+    },
+    {
+      "epoch": 0.35615126854954526,
+      "grad_norm": 0.5608384013175964,
+      "learning_rate": 9.99091661863731e-06,
+      "loss": 0.5884,
+      "step": 62
+    },
+    {
+      "epoch": 0.36189564384873146,
+      "grad_norm": 0.5740435719490051,
+      "learning_rate": 9.988786745649798e-06,
+      "loss": 0.5722,
+      "step": 63
+    },
+    {
+      "epoch": 0.36764001914791766,
+      "grad_norm": 0.5896041393280029,
+      "learning_rate": 9.986433027673786e-06,
+      "loss": 0.5558,
+      "step": 64
+    },
+    {
+      "epoch": 0.37338439444710386,
+      "grad_norm": 0.5800390243530273,
+      "learning_rate": 9.983855570319716e-06,
+      "loss": 0.5773,
+      "step": 65
+    },
+    {
+      "epoch": 0.3791287697462901,
+      "grad_norm": 0.5293853282928467,
+      "learning_rate": 9.981054489237132e-06,
+      "loss": 0.5709,
+      "step": 66
+    },
+    {
+      "epoch": 0.3848731450454763,
+      "grad_norm": 0.5264029502868652,
+      "learning_rate": 9.978029910109491e-06,
+      "loss": 0.5314,
+      "step": 67
+    },
+    {
+      "epoch": 0.3906175203446625,
+      "grad_norm": 0.5725036859512329,
+      "learning_rate": 9.974781968648523e-06,
+      "loss": 0.5544,
+      "step": 68
+    },
+    {
+      "epoch": 0.3963618956438487,
+      "grad_norm": 0.5662187933921814,
+      "learning_rate": 9.971310810588141e-06,
+      "loss": 0.5816,
+      "step": 69
+    },
+    {
+      "epoch": 0.40210627094303497,
+      "grad_norm": 0.4821569323539734,
+      "learning_rate": 9.967616591677906e-06,
+      "loss": 0.5054,
+      "step": 70
+    },
+    {
+      "epoch": 0.40785064624222117,
+      "grad_norm": 0.6668592691421509,
+      "learning_rate": 9.963699477676031e-06,
+      "loss": 0.5594,
+      "step": 71
+    },
+    {
+      "epoch": 0.41359502154140737,
+      "grad_norm": 0.5324398279190063,
+      "learning_rate": 9.959559644341954e-06,
+      "loss": 0.5384,
+      "step": 72
+    },
+    {
+      "epoch": 0.41933939684059357,
+      "grad_norm": 0.5210046172142029,
+      "learning_rate": 9.95519727742844e-06,
+      "loss": 0.5588,
+      "step": 73
+    },
+    {
+      "epoch": 0.4250837721397798,
+      "grad_norm": 0.6099966764450073,
+      "learning_rate": 9.950612572673255e-06,
+      "loss": 0.562,
+      "step": 74
+    },
+    {
+      "epoch": 0.430828147438966,
+      "grad_norm": 0.5562371611595154,
+      "learning_rate": 9.945805735790383e-06,
+      "loss": 0.5726,
+      "step": 75
+    },
+    {
+      "epoch": 0.4365725227381522,
+      "grad_norm": 0.49663493037223816,
+      "learning_rate": 9.940776982460787e-06,
+      "loss": 0.5486,
+      "step": 76
+    },
+    {
+      "epoch": 0.4423168980373384,
+      "grad_norm": 0.5064303278923035,
+      "learning_rate": 9.935526538322744e-06,
+      "loss": 0.5751,
+      "step": 77
+    },
+    {
+      "epoch": 0.4480612733365247,
+      "grad_norm": 0.5378572344779968,
+      "learning_rate": 9.930054638961709e-06,
+      "loss": 0.552,
+      "step": 78
+    },
+    {
+      "epoch": 0.4538056486357109,
+      "grad_norm": 0.5384443402290344,
+      "learning_rate": 9.924361529899754e-06,
+      "loss": 0.5612,
+      "step": 79
+    },
+    {
+      "epoch": 0.4595500239348971,
+      "grad_norm": 0.49997466802597046,
+      "learning_rate": 9.918447466584545e-06,
+      "loss": 0.5432,
+      "step": 80
+    },
+    {
+      "epoch": 0.4652943992340833,
+      "grad_norm": 0.5184059143066406,
+      "learning_rate": 9.91231271437788e-06,
+      "loss": 0.5471,
+      "step": 81
+    },
+    {
+      "epoch": 0.47103877453326953,
+      "grad_norm": 0.5947031378746033,
+      "learning_rate": 9.905957548543794e-06,
+      "loss": 0.5658,
+      "step": 82
+    },
+    {
+      "epoch": 0.47678314983245573,
+      "grad_norm": 0.4928087592124939,
+      "learning_rate": 9.899382254236186e-06,
+      "loss": 0.5503,
+      "step": 83
+    },
+    {
+      "epoch": 0.48252752513164193,
+      "grad_norm": 0.6400409936904907,
+      "learning_rate": 9.892587126486046e-06,
+      "loss": 0.5788,
+      "step": 84
+    },
+    {
+      "epoch": 0.48827190043082813,
+      "grad_norm": 0.5572645664215088,
+      "learning_rate": 9.885572470188207e-06,
+      "loss": 0.5362,
+      "step": 85
+    },
+    {
+      "epoch": 0.4940162757300144,
+      "grad_norm": 0.49279481172561646,
+      "learning_rate": 9.878338600087658e-06,
+      "loss": 0.5539,
+      "step": 86
+    },
+    {
+      "epoch": 0.4997606510292006,
+      "grad_norm": 0.6104176640510559,
+      "learning_rate": 9.87088584076544e-06,
+      "loss": 0.5706,
+      "step": 87
+    },
+    {
+      "epoch": 0.5055050263283868,
+      "grad_norm": 0.49791330099105835,
+      "learning_rate": 9.863214526624065e-06,
+      "loss": 0.5543,
+      "step": 88
+    },
+    {
+      "epoch": 0.511249401627573,
+      "grad_norm": 0.4971017837524414,
+      "learning_rate": 9.85532500187252e-06,
+      "loss": 0.5503,
+      "step": 89
+    },
+    {
+      "epoch": 0.5169937769267592,
+      "grad_norm": 0.5559049844741821,
+      "learning_rate": 9.847217620510815e-06,
+      "loss": 0.56,
+      "step": 90
+    },
+    {
+      "epoch": 0.5227381522259454,
+      "grad_norm": 0.45909181237220764,
+      "learning_rate": 9.83889274631411e-06,
+      "loss": 0.5375,
+      "step": 91
+    },
+    {
+      "epoch": 0.5284825275251317,
+      "grad_norm": 0.6156418323516846,
+      "learning_rate": 9.830350752816386e-06,
+      "loss": 0.5436,
+      "step": 92
+    },
+    {
+      "epoch": 0.5342269028243178,
+      "grad_norm": 0.46865999698638916,
+      "learning_rate": 9.821592023293686e-06,
+      "loss": 0.5317,
+      "step": 93
+    },
+    {
+      "epoch": 0.5399712781235041,
+      "grad_norm": 0.4963522255420685,
+      "learning_rate": 9.81261695074691e-06,
+      "loss": 0.5609,
+      "step": 94
+    },
+    {
+      "epoch": 0.5457156534226902,
+      "grad_norm": 0.5644580721855164,
+      "learning_rate": 9.803425937884202e-06,
+      "loss": 0.5489,
+      "step": 95
+    },
+    {
+      "epoch": 0.5514600287218765,
+      "grad_norm": 0.5057684779167175,
+      "learning_rate": 9.794019397102852e-06,
+      "loss": 0.5628,
+      "step": 96
+    },
+    {
+      "epoch": 0.5572044040210627,
+      "grad_norm": 0.5877383947372437,
+      "learning_rate": 9.784397750470818e-06,
+      "loss": 0.5329,
+      "step": 97
+    },
+    {
+      "epoch": 0.5629487793202489,
+      "grad_norm": 0.5501551628112793,
+      "learning_rate": 9.774561429707769e-06,
+      "loss": 0.5756,
+      "step": 98
+    },
+    {
+      "epoch": 0.5686931546194351,
+      "grad_norm": 0.5017531514167786,
+      "learning_rate": 9.764510876165727e-06,
+      "loss": 0.5309,
+      "step": 99
+    },
+    {
+      "epoch": 0.5744375299186214,
+      "grad_norm": 0.5698550343513489,
+      "learning_rate": 9.754246540809257e-06,
+      "loss": 0.5344,
+      "step": 100
+    },
+    {
+      "epoch": 0.5801819052178075,
+      "grad_norm": 0.6889923810958862,
+      "learning_rate": 9.743768884195233e-06,
+      "loss": 0.566,
+      "step": 101
+    },
+    {
+      "epoch": 0.5859262805169938,
+      "grad_norm": 0.5755162835121155,
+      "learning_rate": 9.733078376452172e-06,
+      "loss": 0.5623,
+      "step": 102
+    },
+    {
+      "epoch": 0.59167065581618,
+      "grad_norm": 0.5690771341323853,
+      "learning_rate": 9.722175497259145e-06,
+      "loss": 0.5472,
+      "step": 103
+    },
+    {
+      "epoch": 0.5974150311153662,
+      "grad_norm": 0.48988884687423706,
+      "learning_rate": 9.71106073582425e-06,
+      "loss": 0.5306,
+      "step": 104
+    },
+    {
+      "epoch": 0.6031594064145525,
+      "grad_norm": 0.5045924782752991,
+      "learning_rate": 9.699734590862655e-06,
+      "loss": 0.5319,
+      "step": 105
+    },
+    {
+      "epoch": 0.6089037817137386,
+      "grad_norm": 0.6457961201667786,
+      "learning_rate": 9.688197570574238e-06,
+      "loss": 0.5546,
+      "step": 106
+    },
+    {
+      "epoch": 0.6146481570129249,
+      "grad_norm": 0.5357460379600525,
+      "learning_rate": 9.676450192620767e-06,
+      "loss": 0.5485,
+      "step": 107
+    },
+    {
+      "epoch": 0.6203925323121111,
+      "grad_norm": 0.6195516586303711,
+      "learning_rate": 9.66449298410268e-06,
+      "loss": 0.5651,
+      "step": 108
+    },
+    {
+      "epoch": 0.6261369076112973,
+      "grad_norm": 0.532525360584259,
+      "learning_rate": 9.652326481535434e-06,
+      "loss": 0.5119,
+      "step": 109
+    },
+    {
+      "epoch": 0.6318812829104835,
+      "grad_norm": 0.6295329332351685,
+      "learning_rate": 9.639951230825433e-06,
+      "loss": 0.5788,
+      "step": 110
+    },
+    {
+      "epoch": 0.6376256582096697,
+      "grad_norm": 0.6266581416130066,
+      "learning_rate": 9.62736778724553e-06,
+      "loss": 0.5582,
+      "step": 111
+    },
+    {
+      "epoch": 0.6433700335088559,
+      "grad_norm": 0.6455391645431519,
+      "learning_rate": 9.614576715410116e-06,
+      "loss": 0.5676,
+      "step": 112
+    },
+    {
+      "epoch": 0.6491144088080422,
+      "grad_norm": 0.6532648801803589,
+      "learning_rate": 9.60157858924978e-06,
+      "loss": 0.5322,
+      "step": 113
+    },
+    {
+      "epoch": 0.6548587841072283,
+      "grad_norm": 0.695582389831543,
+      "learning_rate": 9.588373991985566e-06,
+      "loss": 0.557,
+      "step": 114
+    },
+    {
+      "epoch": 0.6606031594064146,
+      "grad_norm": 0.6813830733299255,
+      "learning_rate": 9.574963516102795e-06,
+      "loss": 0.5639,
+      "step": 115
+    },
+    {
+      "epoch": 0.6663475347056008,
+      "grad_norm": 0.537449836730957,
+      "learning_rate": 9.561347763324484e-06,
+      "loss": 0.528,
+      "step": 116
+    },
+    {
+      "epoch": 0.672091910004787,
+      "grad_norm": 0.5756135582923889,
+      "learning_rate": 9.547527344584353e-06,
+      "loss": 0.5461,
+      "step": 117
+    },
+    {
+      "epoch": 0.6778362853039732,
+      "grad_norm": 0.664249837398529,
+      "learning_rate": 9.533502879999398e-06,
+      "loss": 0.5685,
+      "step": 118
+    },
+    {
+      "epoch": 0.6835806606031594,
+      "grad_norm": 0.5206965804100037,
+      "learning_rate": 9.519274998842084e-06,
+      "loss": 0.5717,
+      "step": 119
+    },
+    {
+      "epoch": 0.6893250359023456,
+      "grad_norm": 0.6174411773681641,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.5338,
+      "step": 120
+    },
+    {
+      "epoch": 0.6950694112015319,
+      "grad_norm": 0.4804738461971283,
+      "learning_rate": 9.490211549507701e-06,
+      "loss": 0.5557,
+      "step": 121
+    },
+    {
+      "epoch": 0.700813786500718,
+      "grad_norm": 0.49055036902427673,
+      "learning_rate": 9.475377285396692e-06,
+      "loss": 0.5324,
+      "step": 122
+    },
+    {
+      "epoch": 0.7065581617999043,
+      "grad_norm": 0.486482709646225,
+      "learning_rate": 9.460342212786933e-06,
+      "loss": 0.5242,
+      "step": 123
+    },
+    {
+      "epoch": 0.7123025370990905,
+      "grad_norm": 0.549220085144043,
+      "learning_rate": 9.445107006296488e-06,
+      "loss": 0.5692,
+      "step": 124
+    },
+    {
+      "epoch": 0.7180469123982767,
+      "grad_norm": 0.5209650993347168,
+      "learning_rate": 9.42967234952335e-06,
+      "loss": 0.5685,
+      "step": 125
+    },
+    {
+      "epoch": 0.7237912876974629,
+      "grad_norm": 0.5501351952552795,
+      "learning_rate": 9.414038935014777e-06,
+      "loss": 0.5288,
+      "step": 126
+    },
+    {
+      "epoch": 0.7295356629966491,
+      "grad_norm": 0.5890218615531921,
+      "learning_rate": 9.398207464236209e-06,
+      "loss": 0.5288,
+      "step": 127
+    },
+    {
+      "epoch": 0.7352800382958353,
+      "grad_norm": 0.5494324564933777,
+      "learning_rate": 9.382178647539794e-06,
+      "loss": 0.541,
+      "step": 128
+    },
+    {
+      "epoch": 0.7410244135950216,
+      "grad_norm": 0.5340805053710938,
+      "learning_rate": 9.365953204132526e-06,
+      "loss": 0.5494,
+      "step": 129
+    },
+    {
+      "epoch": 0.7467687888942077,
+      "grad_norm": 0.4657943844795227,
+      "learning_rate": 9.349531862043952e-06,
+      "loss": 0.5629,
+      "step": 130
+    },
+    {
+      "epoch": 0.752513164193394,
+      "grad_norm": 0.4700133502483368,
+      "learning_rate": 9.332915358093532e-06,
+      "loss": 0.5265,
+      "step": 131
+    },
+    {
+      "epoch": 0.7582575394925802,
+      "grad_norm": 0.5137308239936829,
+      "learning_rate": 9.316104437857561e-06,
+      "loss": 0.5315,
+      "step": 132
+    },
+    {
+      "epoch": 0.7640019147917664,
+      "grad_norm": 0.5512875914573669,
+      "learning_rate": 9.299099855635716e-06,
+      "loss": 0.5246,
+      "step": 133
+    },
+    {
+      "epoch": 0.7697462900909526,
+      "grad_norm": 0.5698496699333191,
+      "learning_rate": 9.28190237441722e-06,
+      "loss": 0.5161,
+      "step": 134
+    },
+    {
+      "epoch": 0.7754906653901388,
+      "grad_norm": 0.6161168217658997,
+      "learning_rate": 9.2645127658466e-06,
+      "loss": 0.5358,
+      "step": 135
+    },
+    {
+      "epoch": 0.781235040689325,
+      "grad_norm": 0.5661118626594543,
+      "learning_rate": 9.246931810189061e-06,
+      "loss": 0.546,
+      "step": 136
+    },
+    {
+      "epoch": 0.7869794159885113,
+      "grad_norm": 0.5279558897018433,
+      "learning_rate": 9.229160296295488e-06,
+      "loss": 0.5096,
+      "step": 137
+    },
+    {
+      "epoch": 0.7927237912876974,
+      "grad_norm": 0.5370686650276184,
+      "learning_rate": 9.211199021567034e-06,
+      "loss": 0.5523,
+      "step": 138
+    },
+    {
+      "epoch": 0.7984681665868837,
+      "grad_norm": 0.6411705613136292,
+      "learning_rate": 9.193048791919357e-06,
+      "loss": 0.5595,
+      "step": 139
+    },
+    {
+      "epoch": 0.8042125418860699,
+      "grad_norm": 0.5257410407066345,
+      "learning_rate": 9.174710421746445e-06,
+      "loss": 0.5686,
+      "step": 140
+    },
+    {
+      "epoch": 0.8099569171852561,
+      "grad_norm": 0.5763169527053833,
+      "learning_rate": 9.156184733884084e-06,
+      "loss": 0.5252,
+      "step": 141
+    },
+    {
+      "epoch": 0.8157012924844423,
+      "grad_norm": 0.5250378847122192,
+      "learning_rate": 9.137472559572935e-06,
+      "loss": 0.561,
+      "step": 142
+    },
+    {
+      "epoch": 0.8214456677836285,
+      "grad_norm": 0.6087478399276733,
+      "learning_rate": 9.118574738421236e-06,
+      "loss": 0.5177,
+      "step": 143
+    },
+    {
+      "epoch": 0.8271900430828147,
+      "grad_norm": 0.6588859558105469,
+      "learning_rate": 9.099492118367123e-06,
+      "loss": 0.5578,
+      "step": 144
+    },
+    {
+      "epoch": 0.832934418382001,
+      "grad_norm": 0.48864591121673584,
+      "learning_rate": 9.080225555640601e-06,
+      "loss": 0.5394,
+      "step": 145
+    },
+    {
+      "epoch": 0.8386787936811871,
+      "grad_norm": 0.5315064191818237,
+      "learning_rate": 9.0607759147251e-06,
+      "loss": 0.5404,
+      "step": 146
+    },
+    {
+      "epoch": 0.8444231689803734,
+      "grad_norm": 0.5749916434288025,
+      "learning_rate": 9.04114406831871e-06,
+      "loss": 0.5114,
+      "step": 147
+    },
+    {
+      "epoch": 0.8501675442795597,
+      "grad_norm": 0.47096845507621765,
+      "learning_rate": 9.021330897295011e-06,
+      "loss": 0.5383,
+      "step": 148
+    },
+    {
+      "epoch": 0.8559119195787458,
+      "grad_norm": 0.5951332449913025,
+      "learning_rate": 9.001337290663548e-06,
+      "loss": 0.5173,
+      "step": 149
+    },
+    {
+      "epoch": 0.861656294877932,
+      "grad_norm": 0.5525330305099487,
+      "learning_rate": 8.981164145529943e-06,
+      "loss": 0.5428,
+      "step": 150
+    },
+    {
+      "epoch": 0.8674006701771182,
+      "grad_norm": 0.47650671005249023,
+      "learning_rate": 8.960812367055646e-06,
+      "loss": 0.5582,
+      "step": 151
+    },
+    {
+      "epoch": 0.8731450454763044,
+      "grad_norm": 0.542094349861145,
+      "learning_rate": 8.940282868417321e-06,
+      "loss": 0.4893,
+      "step": 152
+    },
+    {
+      "epoch": 0.8788894207754907,
+      "grad_norm": 0.5436213612556458,
+      "learning_rate": 8.91957657076586e-06,
+      "loss": 0.5531,
+      "step": 153
+    },
+    {
+      "epoch": 0.8846337960746768,
+      "grad_norm": 0.529384434223175,
+      "learning_rate": 8.898694403185066e-06,
+      "loss": 0.5151,
+      "step": 154
+    },
+    {
+      "epoch": 0.8903781713738631,
+      "grad_norm": 0.5005679726600647,
+      "learning_rate": 8.877637302649962e-06,
+      "loss": 0.5259,
+      "step": 155
+    },
+    {
+      "epoch": 0.8961225466730494,
+      "grad_norm": 0.5237105488777161,
+      "learning_rate": 8.856406213984743e-06,
+      "loss": 0.5442,
+      "step": 156
+    },
+    {
+      "epoch": 0.9018669219722355,
+      "grad_norm": 0.45996320247650146,
+      "learning_rate": 8.835002089820387e-06,
+      "loss": 0.5279,
+      "step": 157
+    },
+    {
+      "epoch": 0.9076112972714218,
+      "grad_norm": 0.5661066770553589,
+      "learning_rate": 8.81342589055191e-06,
+      "loss": 0.5578,
+      "step": 158
+    },
+    {
+      "epoch": 0.9133556725706079,
+      "grad_norm": 0.46714460849761963,
+      "learning_rate": 8.791678584295276e-06,
+      "loss": 0.5223,
+      "step": 159
+    },
+    {
+      "epoch": 0.9191000478697942,
+      "grad_norm": 0.5787307024002075,
+      "learning_rate": 8.76976114684395e-06,
+      "loss": 0.5285,
+      "step": 160
+    },
+    {
+      "epoch": 0.9248444231689804,
+      "grad_norm": 0.5483257174491882,
+      "learning_rate": 8.747674561625121e-06,
+      "loss": 0.5488,
+      "step": 161
+    },
+    {
+      "epoch": 0.9305887984681666,
+      "grad_norm": 0.4516684412956238,
+      "learning_rate": 8.725419819655582e-06,
+      "loss": 0.4819,
+      "step": 162
+    },
+    {
+      "epoch": 0.9363331737673528,
+      "grad_norm": 0.5912066698074341,
+      "learning_rate": 8.702997919497247e-06,
+      "loss": 0.5398,
+      "step": 163
+    },
+    {
+      "epoch": 0.9420775490665391,
+      "grad_norm": 0.544422447681427,
+      "learning_rate": 8.680409867212359e-06,
+      "loss": 0.5563,
+      "step": 164
+    },
+    {
+      "epoch": 0.9478219243657252,
+      "grad_norm": 0.615469217300415,
+      "learning_rate": 8.657656676318346e-06,
+      "loss": 0.5527,
+      "step": 165
+    },
+    {
+      "epoch": 0.9535662996649115,
+      "grad_norm": 0.48167160153388977,
+      "learning_rate": 8.634739367742341e-06,
+      "loss": 0.5031,
+      "step": 166
+    },
+    {
+      "epoch": 0.9593106749640976,
+      "grad_norm": 0.659505307674408,
+      "learning_rate": 8.611658969775378e-06,
+      "loss": 0.5239,
+      "step": 167
+    },
+    {
+      "epoch": 0.9650550502632839,
+      "grad_norm": 0.5576907396316528,
+      "learning_rate": 8.588416518026248e-06,
+      "loss": 0.5173,
+      "step": 168
+    },
+    {
+      "epoch": 0.9707994255624701,
+      "grad_norm": 0.5543246269226074,
+      "learning_rate": 8.565013055375035e-06,
+      "loss": 0.5346,
+      "step": 169
+    },
+    {
+      "epoch": 0.9765438008616563,
+      "grad_norm": 0.6100912690162659,
+      "learning_rate": 8.541449631926325e-06,
+      "loss": 0.5268,
+      "step": 170
+    },
+    {
+      "epoch": 0.9822881761608425,
+      "grad_norm": 0.47118762135505676,
+      "learning_rate": 8.51772730496208e-06,
+      "loss": 0.5605,
+      "step": 171
+    },
+    {
+      "epoch": 0.9880325514600288,
+      "grad_norm": 0.6019647121429443,
+      "learning_rate": 8.49384713889421e-06,
+      "loss": 0.5273,
+      "step": 172
+    },
+    {
+      "epoch": 0.9937769267592149,
+      "grad_norm": 0.6136192083358765,
+      "learning_rate": 8.469810205216795e-06,
+      "loss": 0.5659,
+      "step": 173
+    },
+    {
+      "epoch": 0.9995213020584012,
+      "grad_norm": 0.5436699986457825,
+      "learning_rate": 8.445617582458033e-06,
+      "loss": 0.5469,
+      "step": 174
+    },
+    {
+      "epoch": 1.0052656773575874,
+      "grad_norm": 1.5260647535324097,
+      "learning_rate": 8.42127035613182e-06,
+      "loss": 0.9094,
+      "step": 175
+    },
+    {
+      "epoch": 1.0110100526567736,
+      "grad_norm": 0.5587025880813599,
+      "learning_rate": 8.396769618689064e-06,
+      "loss": 0.4939,
+      "step": 176
+    },
+    {
+      "epoch": 1.0167544279559597,
+      "grad_norm": 0.5418161153793335,
+      "learning_rate": 8.372116469468654e-06,
+      "loss": 0.5211,
+      "step": 177
+    },
+    {
+      "epoch": 1.022498803255146,
+      "grad_norm": 0.6211748719215393,
+      "learning_rate": 8.347312014648144e-06,
+      "loss": 0.4619,
+      "step": 178
+    },
+    {
+      "epoch": 1.0282431785543322,
+      "grad_norm": 0.5461438298225403,
+      "learning_rate": 8.32235736719411e-06,
+      "loss": 0.4424,
+      "step": 179
+    },
+    {
+      "epoch": 1.0339875538535184,
+      "grad_norm": 0.7238538861274719,
+      "learning_rate": 8.297253646812213e-06,
+      "loss": 0.5283,
+      "step": 180
+    },
+    {
+      "epoch": 1.0397319291527047,
+      "grad_norm": 0.5685709714889526,
+      "learning_rate": 8.272001979896962e-06,
+      "loss": 0.4777,
+      "step": 181
+    },
+    {
+      "epoch": 1.0454763044518909,
+      "grad_norm": 0.6029736399650574,
+      "learning_rate": 8.246603499481177e-06,
+      "loss": 0.4754,
+      "step": 182
+    },
+    {
+      "epoch": 1.051220679751077,
+      "grad_norm": 0.7201405167579651,
+      "learning_rate": 8.221059345185136e-06,
+      "loss": 0.4864,
+      "step": 183
+    },
+    {
+      "epoch": 1.0569650550502634,
+      "grad_norm": 0.5729609131813049,
+      "learning_rate": 8.195370663165455e-06,
+      "loss": 0.4793,
+      "step": 184
+    },
+    {
+      "epoch": 1.0627094303494495,
+      "grad_norm": 0.6719270944595337,
+      "learning_rate": 8.169538606063647e-06,
+      "loss": 0.4964,
+      "step": 185
+    },
+    {
+      "epoch": 1.0684538056486357,
+      "grad_norm": 0.6572569608688354,
+      "learning_rate": 8.143564332954426e-06,
+      "loss": 0.5049,
+      "step": 186
+    },
+    {
+      "epoch": 1.0741981809478218,
+      "grad_norm": 0.5375853180885315,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.5056,
+      "step": 187
+    },
+    {
+      "epoch": 1.0799425562470082,
+      "grad_norm": 0.5356974005699158,
+      "learning_rate": 8.091193806866147e-06,
+      "loss": 0.5014,
+      "step": 188
+    },
+    {
+      "epoch": 1.0856869315461943,
+      "grad_norm": 0.5870072245597839,
+      "learning_rate": 8.064799903732936e-06,
+      "loss": 0.4648,
+      "step": 189
+    },
+    {
+      "epoch": 1.0914313068453805,
+      "grad_norm": 0.4977969825267792,
+      "learning_rate": 8.038268484178566e-06,
+      "loss": 0.4912,
+      "step": 190
+    },
+    {
+      "epoch": 1.0971756821445668,
+      "grad_norm": 0.49062633514404297,
+      "learning_rate": 8.011600738657865e-06,
+      "loss": 0.493,
+      "step": 191
+    },
+    {
+      "epoch": 1.102920057443753,
+      "grad_norm": 0.5364016890525818,
+      "learning_rate": 7.98479786374257e-06,
+      "loss": 0.4551,
+      "step": 192
+    },
+    {
+      "epoch": 1.1086644327429391,
+      "grad_norm": 0.6891268491744995,
+      "learning_rate": 7.957861062067614e-06,
+      "loss": 0.4907,
+      "step": 193
+    },
+    {
+      "epoch": 1.1144088080421255,
+      "grad_norm": 0.5725308060646057,
+      "learning_rate": 7.930791542277175e-06,
+      "loss": 0.4892,
+      "step": 194
+    },
+    {
+      "epoch": 1.1201531833413116,
+      "grad_norm": 0.5667552947998047,
+      "learning_rate": 7.903590518970445e-06,
+      "loss": 0.5127,
+      "step": 195
+    },
+    {
+      "epoch": 1.1258975586404978,
+      "grad_norm": 0.462298721075058,
+      "learning_rate": 7.876259212647129e-06,
+      "loss": 0.441,
+      "step": 196
+    },
+    {
+      "epoch": 1.1316419339396842,
+      "grad_norm": 0.5504534244537354,
+      "learning_rate": 7.848798849652684e-06,
+      "loss": 0.5009,
+      "step": 197
+    },
+    {
+      "epoch": 1.1373863092388703,
+      "grad_norm": 0.48440906405448914,
+      "learning_rate": 7.821210662123284e-06,
+      "loss": 0.4731,
+      "step": 198
+    },
+    {
+      "epoch": 1.1431306845380564,
+      "grad_norm": 0.4688943922519684,
+      "learning_rate": 7.793495887930551e-06,
+      "loss": 0.4456,
+      "step": 199
+    },
+    {
+      "epoch": 1.1488750598372426,
+      "grad_norm": 0.5395812392234802,
+      "learning_rate": 7.765655770625997e-06,
+      "loss": 0.466,
+      "step": 200
+    },
+    {
+      "epoch": 1.154619435136429,
+      "grad_norm": 0.6602702140808105,
+      "learning_rate": 7.737691559385237e-06,
+      "loss": 0.4981,
+      "step": 201
+    },
+    {
+      "epoch": 1.160363810435615,
+      "grad_norm": 0.48276349902153015,
+      "learning_rate": 7.709604508951927e-06,
+      "loss": 0.5092,
+      "step": 202
+    },
+    {
+      "epoch": 1.1661081857348012,
+      "grad_norm": 0.5397800803184509,
+      "learning_rate": 7.68139587958148e-06,
+      "loss": 0.4675,
+      "step": 203
+    },
+    {
+      "epoch": 1.1718525610339876,
+      "grad_norm": 0.5717769861221313,
+      "learning_rate": 7.653066936984504e-06,
+      "loss": 0.5035,
+      "step": 204
+    },
+    {
+      "epoch": 1.1775969363331737,
+      "grad_norm": 0.5147746801376343,
+      "learning_rate": 7.6246189522700205e-06,
+      "loss": 0.5191,
+      "step": 205
+    },
+    {
+      "epoch": 1.18334131163236,
+      "grad_norm": 0.4830034077167511,
+      "learning_rate": 7.596053201888425e-06,
+      "loss": 0.4659,
+      "step": 206
+    },
+    {
+      "epoch": 1.1890856869315463,
+      "grad_norm": 0.5149533748626709,
+      "learning_rate": 7.56737096757421e-06,
+      "loss": 0.4666,
+      "step": 207
+    },
+    {
+      "epoch": 1.1948300622307324,
+      "grad_norm": 0.47677546739578247,
+      "learning_rate": 7.538573536288466e-06,
+      "loss": 0.4842,
+      "step": 208
+    },
+    {
+      "epoch": 1.2005744375299185,
+      "grad_norm": 0.42174142599105835,
+      "learning_rate": 7.509662200161122e-06,
+      "loss": 0.4519,
+      "step": 209
+    },
+    {
+      "epoch": 1.206318812829105,
+      "grad_norm": 0.5489972829818726,
+      "learning_rate": 7.480638256432977e-06,
+      "loss": 0.5119,
+      "step": 210
+    },
+    {
+      "epoch": 1.212063188128291,
+      "grad_norm": 0.4667467474937439,
+      "learning_rate": 7.4515030073974915e-06,
+      "loss": 0.4918,
+      "step": 211
+    },
+    {
+      "epoch": 1.2178075634274772,
+      "grad_norm": 0.5094060897827148,
+      "learning_rate": 7.422257760342351e-06,
+      "loss": 0.4915,
+      "step": 212
+    },
+    {
+      "epoch": 1.2235519387266636,
+      "grad_norm": 0.5071128606796265,
+      "learning_rate": 7.392903827490814e-06,
+      "loss": 0.4598,
+      "step": 213
+    },
+    {
+      "epoch": 1.2292963140258497,
+      "grad_norm": 0.49673011898994446,
+      "learning_rate": 7.363442525942827e-06,
+      "loss": 0.4467,
+      "step": 214
+    },
+    {
+      "epoch": 1.2350406893250359,
+      "grad_norm": 0.46016961336135864,
+      "learning_rate": 7.333875177615931e-06,
+      "loss": 0.4927,
+      "step": 215
+    },
+    {
+      "epoch": 1.2407850646242222,
+      "grad_norm": 0.5728297829627991,
+      "learning_rate": 7.304203109185947e-06,
+      "loss": 0.5002,
+      "step": 216
+    },
+    {
+      "epoch": 1.2465294399234084,
+      "grad_norm": 0.43362411856651306,
+      "learning_rate": 7.274427652027444e-06,
+      "loss": 0.4451,
+      "step": 217
+    },
+    {
+      "epoch": 1.2522738152225945,
+      "grad_norm": 0.496272474527359,
+      "learning_rate": 7.244550142154009e-06,
+      "loss": 0.4794,
+      "step": 218
+    },
+    {
+      "epoch": 1.2580181905217809,
+      "grad_norm": 0.5590081810951233,
+      "learning_rate": 7.214571920158293e-06,
+      "loss": 0.4845,
+      "step": 219
+    },
+    {
+      "epoch": 1.263762565820967,
+      "grad_norm": 0.5159772038459778,
+      "learning_rate": 7.1844943311518665e-06,
+      "loss": 0.5251,
+      "step": 220
+    },
+    {
+      "epoch": 1.2695069411201532,
+      "grad_norm": 0.4696570932865143,
+      "learning_rate": 7.1543187247048525e-06,
+      "loss": 0.5033,
+      "step": 221
+    },
+    {
+      "epoch": 1.2752513164193395,
+      "grad_norm": 0.5043511390686035,
+      "learning_rate": 7.124046454785387e-06,
+      "loss": 0.4739,
+      "step": 222
+    },
+    {
+      "epoch": 1.2809956917185257,
+      "grad_norm": 0.5755232572555542,
+      "learning_rate": 7.093678879698858e-06,
+      "loss": 0.5209,
+      "step": 223
+    },
+    {
+      "epoch": 1.2867400670177118,
+      "grad_norm": 0.46288853883743286,
+      "learning_rate": 7.063217362026957e-06,
+      "loss": 0.4692,
+      "step": 224
+    },
+    {
+      "epoch": 1.292484442316898,
+      "grad_norm": 0.4486297369003296,
+      "learning_rate": 7.032663268566547e-06,
+      "loss": 0.4581,
+      "step": 225
+    },
+    {
+      "epoch": 1.2982288176160843,
+      "grad_norm": 0.5111509561538696,
+      "learning_rate": 7.002017970268336e-06,
+      "loss": 0.4648,
+      "step": 226
+    },
+    {
+      "epoch": 1.3039731929152705,
+      "grad_norm": 0.5335001349449158,
+      "learning_rate": 6.97128284217535e-06,
+      "loss": 0.508,
+      "step": 227
+    },
+    {
+      "epoch": 1.3097175682144566,
+      "grad_norm": 0.5523168444633484,
+      "learning_rate": 6.9404592633612486e-06,
+      "loss": 0.546,
+      "step": 228
+    },
+    {
+      "epoch": 1.3154619435136428,
+      "grad_norm": 0.4908071458339691,
+      "learning_rate": 6.909548616868444e-06,
+      "loss": 0.4959,
+      "step": 229
+    },
+    {
+      "epoch": 1.3212063188128291,
+      "grad_norm": 0.4557272791862488,
+      "learning_rate": 6.878552289646041e-06,
+      "loss": 0.4815,
+      "step": 230
+    },
+    {
+      "epoch": 1.3269506941120153,
+      "grad_norm": 0.4479963779449463,
+      "learning_rate": 6.847471672487607e-06,
+      "loss": 0.4357,
+      "step": 231
+    },
+    {
+      "epoch": 1.3326950694112014,
+      "grad_norm": 0.4967019855976105,
+      "learning_rate": 6.816308159968761e-06,
+      "loss": 0.539,
+      "step": 232
+    },
+    {
+      "epoch": 1.3384394447103878,
+      "grad_norm": 0.4799559414386749,
+      "learning_rate": 6.7850631503846165e-06,
+      "loss": 0.4802,
+      "step": 233
+    },
+    {
+      "epoch": 1.344183820009574,
+      "grad_norm": 0.485273540019989,
+      "learning_rate": 6.753738045687021e-06,
+      "loss": 0.4945,
+      "step": 234
+    },
+    {
+      "epoch": 1.34992819530876,
+      "grad_norm": 0.4190736711025238,
+      "learning_rate": 6.722334251421665e-06,
+      "loss": 0.4703,
+      "step": 235
+    },
+    {
+      "epoch": 1.3556725706079464,
+      "grad_norm": 0.4951339364051819,
+      "learning_rate": 6.690853176665007e-06,
+      "loss": 0.5339,
+      "step": 236
+    },
+    {
+      "epoch": 1.3614169459071326,
+      "grad_norm": 0.4466400742530823,
+      "learning_rate": 6.659296233961055e-06,
+      "loss": 0.4521,
+      "step": 237
+    },
+    {
+      "epoch": 1.3671613212063187,
+      "grad_norm": 0.4460606575012207,
+      "learning_rate": 6.627664839257979e-06,
+      "loss": 0.4827,
+      "step": 238
+    },
+    {
+      "epoch": 1.372905696505505,
+      "grad_norm": 0.49249327182769775,
+      "learning_rate": 6.595960411844589e-06,
+      "loss": 0.5051,
+      "step": 239
+    },
+    {
+      "epoch": 1.3786500718046912,
+      "grad_norm": 0.491413414478302,
+      "learning_rate": 6.564184374286636e-06,
+      "loss": 0.5031,
+      "step": 240
+    },
+    {
+      "epoch": 1.3843944471038774,
+      "grad_norm": 0.42033085227012634,
+      "learning_rate": 6.532338152363001e-06,
+      "loss": 0.4646,
+      "step": 241
+    },
+    {
+      "epoch": 1.3901388224030637,
+      "grad_norm": 0.4750801920890808,
+      "learning_rate": 6.500423175001705e-06,
+      "loss": 0.4337,
+      "step": 242
+    },
+    {
+      "epoch": 1.39588319770225,
+      "grad_norm": 0.5122845768928528,
+      "learning_rate": 6.468440874215801e-06,
+      "loss": 0.5052,
+      "step": 243
+    },
+    {
+      "epoch": 1.401627573001436,
+      "grad_norm": 0.4859732985496521,
+      "learning_rate": 6.43639268503912e-06,
+      "loss": 0.499,
+      "step": 244
+    },
+    {
+      "epoch": 1.4073719483006224,
+      "grad_norm": 0.512253999710083,
+      "learning_rate": 6.40428004546188e-06,
+      "loss": 0.5064,
+      "step": 245
+    },
+    {
+      "epoch": 1.4131163235998085,
+      "grad_norm": 0.46881169080734253,
+      "learning_rate": 6.372104396366162e-06,
+      "loss": 0.4765,
+      "step": 246
+    },
+    {
+      "epoch": 1.4188606988989947,
+      "grad_norm": 0.4910268187522888,
+      "learning_rate": 6.339867181461265e-06,
+      "loss": 0.5059,
+      "step": 247
+    },
+    {
+      "epoch": 1.424605074198181,
+      "grad_norm": 0.43128618597984314,
+      "learning_rate": 6.307569847218917e-06,
+      "loss": 0.4667,
+      "step": 248
+    },
+    {
+      "epoch": 1.4303494494973672,
+      "grad_norm": 0.4424154460430145,
+      "learning_rate": 6.275213842808383e-06,
+      "loss": 0.4834,
+      "step": 249
+    },
+    {
+      "epoch": 1.4360938247965533,
+      "grad_norm": 0.49621695280075073,
+      "learning_rate": 6.242800620031434e-06,
+      "loss": 0.4701,
+      "step": 250
+    },
+    {
+      "epoch": 1.4418382000957397,
+      "grad_norm": 0.4383918344974518,
+      "learning_rate": 6.2103316332572095e-06,
+      "loss": 0.5017,
+      "step": 251
+    },
+    {
+      "epoch": 1.4475825753949259,
+      "grad_norm": 0.4955291748046875,
+      "learning_rate": 6.177808339356954e-06,
+      "loss": 0.5253,
+      "step": 252
+    },
+    {
+      "epoch": 1.453326950694112,
+      "grad_norm": 0.43212026357650757,
+      "learning_rate": 6.14523219763866e-06,
+      "loss": 0.455,
+      "step": 253
+    },
+    {
+      "epoch": 1.4590713259932984,
+      "grad_norm": 0.44476839900016785,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.4844,
+      "step": 254
+    },
+    {
+      "epoch": 1.4648157012924845,
+      "grad_norm": 0.46556708216667175,
+      "learning_rate": 6.079927219770623e-06,
+      "loss": 0.4957,
+      "step": 255
+    },
+    {
+      "epoch": 1.4705600765916707,
+      "grad_norm": 0.4209665060043335,
+      "learning_rate": 6.047201313830724e-06,
+      "loss": 0.4859,
+      "step": 256
+    },
+    {
+      "epoch": 1.4763044518908568,
+      "grad_norm": 0.4632583558559418,
+      "learning_rate": 6.014428420360987e-06,
+      "loss": 0.5136,
+      "step": 257
+    },
+    {
+      "epoch": 1.4820488271900432,
+      "grad_norm": 0.4351138472557068,
+      "learning_rate": 5.9816100098688456e-06,
+      "loss": 0.4618,
+      "step": 258
+    },
+    {
+      "epoch": 1.4877932024892293,
+      "grad_norm": 0.4440339207649231,
+      "learning_rate": 5.948747554904054e-06,
+      "loss": 0.5211,
+      "step": 259
+    },
+    {
+      "epoch": 1.4935375777884154,
+      "grad_norm": 0.49033647775650024,
+      "learning_rate": 5.915842529992632e-06,
+      "loss": 0.4836,
+      "step": 260
+    },
+    {
+      "epoch": 1.4992819530876016,
+      "grad_norm": 0.45823630690574646,
+      "learning_rate": 5.8828964115706925e-06,
+      "loss": 0.4288,
+      "step": 261
+    },
+    {
+      "epoch": 1.505026328386788,
+      "grad_norm": 0.4555763304233551,
+      "learning_rate": 5.849910677918205e-06,
+      "loss": 0.4548,
+      "step": 262
+    },
+    {
+      "epoch": 1.510770703685974,
+      "grad_norm": 0.46555453538894653,
+      "learning_rate": 5.816886809092651e-06,
+      "loss": 0.4688,
+      "step": 263
+    },
+    {
+      "epoch": 1.5165150789851602,
+      "grad_norm": 0.5020288825035095,
+      "learning_rate": 5.783826286862631e-06,
+      "loss": 0.5108,
+      "step": 264
+    },
+    {
+      "epoch": 1.5222594542843466,
+      "grad_norm": 0.410932719707489,
+      "learning_rate": 5.750730594641367e-06,
+      "loss": 0.4571,
+      "step": 265
+    },
+    {
+      "epoch": 1.5280038295835328,
+      "grad_norm": 0.46809419989585876,
+      "learning_rate": 5.717601217420143e-06,
+      "loss": 0.4691,
+      "step": 266
+    },
+    {
+      "epoch": 1.533748204882719,
+      "grad_norm": 0.44337236881256104,
+      "learning_rate": 5.68443964170168e-06,
+      "loss": 0.477,
+      "step": 267
+    },
+    {
+      "epoch": 1.5394925801819053,
+      "grad_norm": 0.4952318072319031,
+      "learning_rate": 5.6512473554334294e-06,
+      "loss": 0.49,
+      "step": 268
+    },
+    {
+      "epoch": 1.5452369554810914,
+      "grad_norm": 0.46753644943237305,
+      "learning_rate": 5.618025847940817e-06,
+      "loss": 0.4848,
+      "step": 269
+    },
+    {
+      "epoch": 1.5509813307802776,
+      "grad_norm": 0.45212316513061523,
+      "learning_rate": 5.584776609860414e-06,
+      "loss": 0.4696,
+      "step": 270
+    },
+    {
+      "epoch": 1.556725706079464,
+      "grad_norm": 0.5053378939628601,
+      "learning_rate": 5.551501133073048e-06,
+      "loss": 0.5447,
+      "step": 271
+    },
+    {
+      "epoch": 1.56247008137865,
+      "grad_norm": 0.4040236473083496,
+      "learning_rate": 5.518200910636875e-06,
+      "loss": 0.4678,
+      "step": 272
+    },
+    {
+      "epoch": 1.5682144566778362,
+      "grad_norm": 0.4419972002506256,
+      "learning_rate": 5.4848774367203715e-06,
+      "loss": 0.4994,
+      "step": 273
+    },
+    {
+      "epoch": 1.5739588319770226,
+      "grad_norm": 0.43512895703315735,
+      "learning_rate": 5.451532206535306e-06,
+      "loss": 0.5056,
+      "step": 274
+    },
+    {
+      "epoch": 1.5797032072762087,
+      "grad_norm": 0.492079496383667,
+      "learning_rate": 5.418166716269636e-06,
+      "loss": 0.4957,
+      "step": 275
+    },
+    {
+      "epoch": 1.5854475825753949,
+      "grad_norm": 0.4276512861251831,
+      "learning_rate": 5.384782463020385e-06,
+      "loss": 0.4901,
+      "step": 276
+    },
+    {
+      "epoch": 1.5911919578745812,
+      "grad_norm": 0.39996013045310974,
+      "learning_rate": 5.351380944726465e-06,
+      "loss": 0.4862,
+      "step": 277
+    },
+    {
+      "epoch": 1.5969363331737674,
+      "grad_norm": 0.3694234788417816,
+      "learning_rate": 5.317963660101464e-06,
+      "loss": 0.4218,
+      "step": 278
+    },
+    {
+      "epoch": 1.6026807084729535,
+      "grad_norm": 0.4611278772354126,
+      "learning_rate": 5.284532108566396e-06,
+      "loss": 0.4908,
+      "step": 279
+    },
+    {
+      "epoch": 1.6084250837721399,
+      "grad_norm": 0.435573548078537,
+      "learning_rate": 5.251087790182428e-06,
+      "loss": 0.4905,
+      "step": 280
+    },
+    {
+      "epoch": 1.614169459071326,
+      "grad_norm": 0.4718412458896637,
+      "learning_rate": 5.217632205583574e-06,
+      "loss": 0.5055,
+      "step": 281
+    },
+    {
+      "epoch": 1.6199138343705122,
+      "grad_norm": 0.41079840064048767,
+      "learning_rate": 5.184166855909355e-06,
+      "loss": 0.4872,
+      "step": 282
+    },
+    {
+      "epoch": 1.6256582096696985,
+      "grad_norm": 0.42057737708091736,
+      "learning_rate": 5.150693242737444e-06,
+      "loss": 0.5028,
+      "step": 283
+    },
+    {
+      "epoch": 1.6314025849688847,
+      "grad_norm": 0.43592604994773865,
+      "learning_rate": 5.117212868016303e-06,
+      "loss": 0.5228,
+      "step": 284
+    },
+    {
+      "epoch": 1.6371469602680708,
+      "grad_norm": 0.4700012803077698,
+      "learning_rate": 5.083727233997775e-06,
+      "loss": 0.4603,
+      "step": 285
+    },
+    {
+      "epoch": 1.6428913355672572,
+      "grad_norm": 0.4413910210132599,
+      "learning_rate": 5.05023784316969e-06,
+      "loss": 0.4787,
+      "step": 286
+    },
+    {
+      "epoch": 1.6486357108664431,
+      "grad_norm": 0.4498383700847626,
+      "learning_rate": 5.016746198188439e-06,
+      "loss": 0.5171,
+      "step": 287
+    },
+    {
+      "epoch": 1.6543800861656295,
+      "grad_norm": 0.3725832998752594,
+      "learning_rate": 4.983253801811562e-06,
+      "loss": 0.447,
+      "step": 288
+    },
+    {
+      "epoch": 1.6601244614648158,
+      "grad_norm": 0.41565757989883423,
+      "learning_rate": 4.949762156830312e-06,
+      "loss": 0.5029,
+      "step": 289
+    },
+    {
+      "epoch": 1.6658688367640018,
+      "grad_norm": 0.4530212879180908,
+      "learning_rate": 4.916272766002227e-06,
+      "loss": 0.487,
+      "step": 290
+    },
+    {
+      "epoch": 1.6716132120631881,
+      "grad_norm": 0.44627729058265686,
+      "learning_rate": 4.882787131983698e-06,
+      "loss": 0.4529,
+      "step": 291
+    },
+    {
+      "epoch": 1.6773575873623745,
+      "grad_norm": 0.4549354612827301,
+      "learning_rate": 4.849306757262558e-06,
+      "loss": 0.4706,
+      "step": 292
+    },
+    {
+      "epoch": 1.6831019626615604,
+      "grad_norm": 0.48366779088974,
+      "learning_rate": 4.8158331440906466e-06,
+      "loss": 0.5149,
+      "step": 293
+    },
+    {
+      "epoch": 1.6888463379607468,
+      "grad_norm": 0.46364232897758484,
+      "learning_rate": 4.7823677944164285e-06,
+      "loss": 0.5396,
+      "step": 294
+    },
+    {
+      "epoch": 1.694590713259933,
+      "grad_norm": 0.43879616260528564,
+      "learning_rate": 4.748912209817572e-06,
+      "loss": 0.4773,
+      "step": 295
+    },
+    {
+      "epoch": 1.700335088559119,
+      "grad_norm": 0.3839658200740814,
+      "learning_rate": 4.715467891433607e-06,
+      "loss": 0.4477,
+      "step": 296
+    },
+    {
+      "epoch": 1.7060794638583054,
+      "grad_norm": 0.4020622968673706,
+      "learning_rate": 4.682036339898537e-06,
+      "loss": 0.4777,
+      "step": 297
+    },
+    {
+      "epoch": 1.7118238391574916,
+      "grad_norm": 0.42523112893104553,
+      "learning_rate": 4.6486190552735375e-06,
+      "loss": 0.5096,
+      "step": 298
+    },
+    {
+      "epoch": 1.7175682144566777,
+      "grad_norm": 0.43856796622276306,
+      "learning_rate": 4.615217536979616e-06,
+      "loss": 0.4802,
+      "step": 299
+    },
+    {
+      "epoch": 1.723312589755864,
+      "grad_norm": 0.3956157863140106,
+      "learning_rate": 4.581833283730367e-06,
+      "loss": 0.4479,
+      "step": 300
+    },
+    {
+      "epoch": 1.7290569650550502,
+      "grad_norm": 0.4652330279350281,
+      "learning_rate": 4.548467793464696e-06,
+      "loss": 0.5231,
+      "step": 301
+    },
+    {
+      "epoch": 1.7348013403542364,
+      "grad_norm": 0.3997798562049866,
+      "learning_rate": 4.515122563279631e-06,
+      "loss": 0.4558,
+      "step": 302
+    },
+    {
+      "epoch": 1.7405457156534228,
+      "grad_norm": 0.4045880138874054,
+      "learning_rate": 4.481799089363127e-06,
+      "loss": 0.4589,
+      "step": 303
+    },
+    {
+      "epoch": 1.746290090952609,
+      "grad_norm": 0.4493541717529297,
+      "learning_rate": 4.448498866926952e-06,
+      "loss": 0.4963,
+      "step": 304
+    },
+    {
+      "epoch": 1.752034466251795,
+      "grad_norm": 0.3999355435371399,
+      "learning_rate": 4.415223390139588e-06,
+      "loss": 0.5129,
+      "step": 305
+    },
+    {
+      "epoch": 1.7577788415509814,
+      "grad_norm": 0.40998125076293945,
+      "learning_rate": 4.381974152059184e-06,
+      "loss": 0.49,
+      "step": 306
+    },
+    {
+      "epoch": 1.7635232168501676,
+      "grad_norm": 0.3941861391067505,
+      "learning_rate": 4.348752644566573e-06,
+      "loss": 0.4556,
+      "step": 307
+    },
+    {
+      "epoch": 1.7692675921493537,
+      "grad_norm": 0.4115658402442932,
+      "learning_rate": 4.315560358298321e-06,
+      "loss": 0.4988,
+      "step": 308
+    },
+    {
+      "epoch": 1.77501196744854,
+      "grad_norm": 0.4041730463504791,
+      "learning_rate": 4.2823987825798575e-06,
+      "loss": 0.4673,
+      "step": 309
+    },
+    {
+      "epoch": 1.7807563427477262,
+      "grad_norm": 0.3939685821533203,
+      "learning_rate": 4.249269405358634e-06,
+      "loss": 0.4542,
+      "step": 310
+    },
+    {
+      "epoch": 1.7865007180469124,
+      "grad_norm": 0.4312926232814789,
+      "learning_rate": 4.2161737131373695e-06,
+      "loss": 0.5143,
+      "step": 311
+    },
+    {
+      "epoch": 1.7922450933460987,
+      "grad_norm": 0.4078906178474426,
+      "learning_rate": 4.183113190907349e-06,
+      "loss": 0.475,
+      "step": 312
+    },
+    {
+      "epoch": 1.7979894686452849,
+      "grad_norm": 0.42950204014778137,
+      "learning_rate": 4.150089322081797e-06,
+      "loss": 0.4607,
+      "step": 313
+    },
+    {
+      "epoch": 1.803733843944471,
+      "grad_norm": 0.37166374921798706,
+      "learning_rate": 4.1171035884293075e-06,
+      "loss": 0.4488,
+      "step": 314
+    },
+    {
+      "epoch": 1.8094782192436574,
+      "grad_norm": 0.38504746556282043,
+      "learning_rate": 4.084157470007371e-06,
+      "loss": 0.4823,
+      "step": 315
+    },
+    {
+      "epoch": 1.8152225945428435,
+      "grad_norm": 0.45277538895606995,
+      "learning_rate": 4.051252445095946e-06,
+      "loss": 0.5264,
+      "step": 316
+    },
+    {
+      "epoch": 1.8209669698420297,
+      "grad_norm": 0.3826143443584442,
+      "learning_rate": 4.018389990131156e-06,
+      "loss": 0.4834,
+      "step": 317
+    },
+    {
+      "epoch": 1.826711345141216,
+      "grad_norm": 0.36567309498786926,
+      "learning_rate": 3.985571579639013e-06,
+      "loss": 0.4675,
+      "step": 318
+    },
+    {
+      "epoch": 1.832455720440402,
+      "grad_norm": 0.38398852944374084,
+      "learning_rate": 3.952798686169279e-06,
+      "loss": 0.468,
+      "step": 319
+    },
+    {
+      "epoch": 1.8382000957395883,
+      "grad_norm": 0.46181172132492065,
+      "learning_rate": 3.920072780229378e-06,
+      "loss": 0.4756,
+      "step": 320
+    },
+    {
+      "epoch": 1.8439444710387747,
+      "grad_norm": 0.4305135905742645,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.5031,
+      "step": 321
+    },
+    {
+      "epoch": 1.8496888463379606,
+      "grad_norm": 0.36271166801452637,
+      "learning_rate": 3.854767802361342e-06,
+      "loss": 0.4411,
+      "step": 322
+    },
+    {
+      "epoch": 1.855433221637147,
+      "grad_norm": 0.441859632730484,
+      "learning_rate": 3.822191660643047e-06,
+      "loss": 0.5007,
+      "step": 323
+    },
+    {
+      "epoch": 1.8611775969363333,
+      "grad_norm": 0.382299542427063,
+      "learning_rate": 3.789668366742792e-06,
+      "loss": 0.5045,
+      "step": 324
+    },
+    {
+      "epoch": 1.8669219722355193,
+      "grad_norm": 0.408326119184494,
+      "learning_rate": 3.7571993799685675e-06,
+      "loss": 0.4843,
+      "step": 325
+    },
+    {
+      "epoch": 1.8726663475347056,
+      "grad_norm": 0.42178499698638916,
+      "learning_rate": 3.7247861571916183e-06,
+      "loss": 0.4641,
+      "step": 326
+    },
+    {
+      "epoch": 1.8784107228338918,
+      "grad_norm": 0.4093269407749176,
+      "learning_rate": 3.6924301527810856e-06,
+      "loss": 0.4825,
+      "step": 327
+    },
+    {
+      "epoch": 1.884155098133078,
+      "grad_norm": 0.41595694422721863,
+      "learning_rate": 3.6601328185387364e-06,
+      "loss": 0.4981,
+      "step": 328
+    },
+    {
+      "epoch": 1.8898994734322643,
+      "grad_norm": 0.38833877444267273,
+      "learning_rate": 3.6278956036338397e-06,
+      "loss": 0.46,
+      "step": 329
+    },
+    {
+      "epoch": 1.8956438487314504,
+      "grad_norm": 0.4010329842567444,
+      "learning_rate": 3.5957199545381216e-06,
+      "loss": 0.4538,
+      "step": 330
+    },
+    {
+      "epoch": 1.9013882240306366,
+      "grad_norm": 0.42216378450393677,
+      "learning_rate": 3.5636073149608824e-06,
+      "loss": 0.477,
+      "step": 331
+    },
+    {
+      "epoch": 1.907132599329823,
+      "grad_norm": 0.39908266067504883,
+      "learning_rate": 3.5315591257842e-06,
+      "loss": 0.4271,
+      "step": 332
+    },
+    {
+      "epoch": 1.912876974629009,
+      "grad_norm": 0.41619524359703064,
+      "learning_rate": 3.4995768249982975e-06,
+      "loss": 0.4588,
+      "step": 333
+    },
+    {
+      "epoch": 1.9186213499281952,
+      "grad_norm": 0.3965836763381958,
+      "learning_rate": 3.467661847637001e-06,
+      "loss": 0.501,
+      "step": 334
+    },
+    {
+      "epoch": 1.9243657252273816,
+      "grad_norm": 0.3913739025592804,
+      "learning_rate": 3.4358156257133644e-06,
+      "loss": 0.5025,
+      "step": 335
+    },
+    {
+      "epoch": 1.9301101005265677,
+      "grad_norm": 0.42657947540283203,
+      "learning_rate": 3.404039588155413e-06,
+      "loss": 0.4434,
+      "step": 336
+    },
+    {
+      "epoch": 1.9358544758257539,
+      "grad_norm": 0.381879597902298,
+      "learning_rate": 3.372335160742022e-06,
+      "loss": 0.4315,
+      "step": 337
+    },
+    {
+      "epoch": 1.9415988511249402,
+      "grad_norm": 0.3740031123161316,
+      "learning_rate": 3.3407037660389474e-06,
+      "loss": 0.4561,
+      "step": 338
+    },
+    {
+      "epoch": 1.9473432264241264,
+      "grad_norm": 0.4027283489704132,
+      "learning_rate": 3.3091468233349934e-06,
+      "loss": 0.521,
+      "step": 339
+    },
+    {
+      "epoch": 1.9530876017233125,
+      "grad_norm": 0.4218166172504425,
+      "learning_rate": 3.2776657485783357e-06,
+      "loss": 0.4838,
+      "step": 340
+    },
+    {
+      "epoch": 1.958831977022499,
+      "grad_norm": 0.42057153582572937,
+      "learning_rate": 3.246261954312979e-06,
+      "loss": 0.4954,
+      "step": 341
+    },
+    {
+      "epoch": 1.964576352321685,
+      "grad_norm": 0.4057151675224304,
+      "learning_rate": 3.2149368496153856e-06,
+      "loss": 0.5009,
+      "step": 342
+    },
+    {
+      "epoch": 1.9703207276208712,
+      "grad_norm": 0.43289145827293396,
+      "learning_rate": 3.1836918400312387e-06,
+      "loss": 0.4539,
+      "step": 343
+    },
+    {
+      "epoch": 1.9760651029200575,
+      "grad_norm": 0.41700872778892517,
+      "learning_rate": 3.152528327512395e-06,
+      "loss": 0.4734,
+      "step": 344
+    },
+    {
+      "epoch": 1.9818094782192437,
+      "grad_norm": 0.4243963062763214,
+      "learning_rate": 3.1214477103539585e-06,
+      "loss": 0.4877,
+      "step": 345
+    },
+    {
+      "epoch": 1.9875538535184298,
+      "grad_norm": 0.4166891276836395,
+      "learning_rate": 3.0904513831315563e-06,
+      "loss": 0.5031,
+      "step": 346
+    },
+    {
+      "epoch": 1.9932982288176162,
+      "grad_norm": 0.41003891825675964,
+      "learning_rate": 3.059540736638751e-06,
+      "loss": 0.5046,
+      "step": 347
+    },
+    {
+      "epoch": 1.9990426041168023,
+      "grad_norm": 0.3934224843978882,
+      "learning_rate": 3.028717157824652e-06,
+      "loss": 0.4309,
+      "step": 348
+    },
+    {
+      "epoch": 2.0047869794159885,
+      "grad_norm": 1.5628243684768677,
+      "learning_rate": 2.9979820297316652e-06,
+      "loss": 0.7723,
+      "step": 349
+    },
+    {
+      "epoch": 2.010531354715175,
+      "grad_norm": 0.5319270491600037,
+      "learning_rate": 2.9673367314334533e-06,
+      "loss": 0.5022,
+      "step": 350
+    },
+    {
+      "epoch": 2.016275730014361,
+      "grad_norm": 0.5007623434066772,
+      "learning_rate": 2.936782637973044e-06,
+      "loss": 0.4484,
+      "step": 351
+    },
+    {
+      "epoch": 2.022020105313547,
+      "grad_norm": 0.4784458577632904,
+      "learning_rate": 2.9063211203011443e-06,
+      "loss": 0.454,
+      "step": 352
+    },
+    {
+      "epoch": 2.0277644806127335,
+      "grad_norm": 0.3986125886440277,
+      "learning_rate": 2.8759535452146128e-06,
+      "loss": 0.4522,
+      "step": 353
+    },
+    {
+      "epoch": 2.0335088559119194,
+      "grad_norm": 0.4448578953742981,
+      "learning_rate": 2.8456812752951483e-06,
+      "loss": 0.4543,
+      "step": 354
+    },
+    {
+      "epoch": 2.039253231211106,
+      "grad_norm": 0.46886104345321655,
+      "learning_rate": 2.815505668848136e-06,
+      "loss": 0.4183,
+      "step": 355
+    },
+    {
+      "epoch": 2.044997606510292,
+      "grad_norm": 0.438160240650177,
+      "learning_rate": 2.785428079841709e-06,
+      "loss": 0.4507,
+      "step": 356
+    },
+    {
+      "epoch": 2.050741981809478,
+      "grad_norm": 0.412517249584198,
+      "learning_rate": 2.755449857845992e-06,
+      "loss": 0.4479,
+      "step": 357
+    },
+    {
+      "epoch": 2.0564863571086645,
+      "grad_norm": 0.4198094308376312,
+      "learning_rate": 2.725572347972558e-06,
+      "loss": 0.4193,
+      "step": 358
+    },
+    {
+      "epoch": 2.062230732407851,
+      "grad_norm": 0.4086361825466156,
+      "learning_rate": 2.6957968908140546e-06,
+      "loss": 0.4264,
+      "step": 359
+    },
+    {
+      "epoch": 2.0679751077070367,
+      "grad_norm": 0.4513247013092041,
+      "learning_rate": 2.666124822384071e-06,
+      "loss": 0.4473,
+      "step": 360
+    },
+    {
+      "epoch": 2.073719483006223,
+      "grad_norm": 0.3780079483985901,
+      "learning_rate": 2.636557474057173e-06,
+      "loss": 0.4005,
+      "step": 361
+    },
+    {
+      "epoch": 2.0794638583054095,
+      "grad_norm": 0.3676167130470276,
+      "learning_rate": 2.607096172509187e-06,
+      "loss": 0.4392,
+      "step": 362
+    },
+    {
+      "epoch": 2.0852082336045954,
+      "grad_norm": 0.44044387340545654,
+      "learning_rate": 2.5777422396576503e-06,
+      "loss": 0.4911,
+      "step": 363
+    },
+    {
+      "epoch": 2.0909526089037818,
+      "grad_norm": 0.3587888479232788,
+      "learning_rate": 2.5484969926025114e-06,
+      "loss": 0.4374,
+      "step": 364
+    },
+    {
+      "epoch": 2.096696984202968,
+      "grad_norm": 0.41746485233306885,
+      "learning_rate": 2.5193617435670244e-06,
+      "loss": 0.4883,
+      "step": 365
+    },
+    {
+      "epoch": 2.102441359502154,
+      "grad_norm": 0.38463401794433594,
+      "learning_rate": 2.4903377998388783e-06,
+      "loss": 0.4396,
+      "step": 366
+    },
+    {
+      "epoch": 2.1081857348013404,
+      "grad_norm": 0.395751953125,
+      "learning_rate": 2.461426463711535e-06,
+      "loss": 0.4429,
+      "step": 367
+    },
+    {
+      "epoch": 2.113930110100527,
+      "grad_norm": 0.3884614109992981,
+      "learning_rate": 2.4326290324257896e-06,
+      "loss": 0.4227,
+      "step": 368
+    },
+    {
+      "epoch": 2.1196744853997127,
+      "grad_norm": 0.3690508306026459,
+      "learning_rate": 2.403946798111576e-06,
+      "loss": 0.4141,
+      "step": 369
+    },
+    {
+      "epoch": 2.125418860698899,
+      "grad_norm": 0.4512092173099518,
+      "learning_rate": 2.37538104772998e-06,
+      "loss": 0.4846,
+      "step": 370
+    },
+    {
+      "epoch": 2.131163235998085,
+      "grad_norm": 0.341816782951355,
+      "learning_rate": 2.3469330630154974e-06,
+      "loss": 0.383,
+      "step": 371
+    },
+    {
+      "epoch": 2.1369076112972714,
+      "grad_norm": 0.39507344365119934,
+      "learning_rate": 2.318604120418521e-06,
+      "loss": 0.4662,
+      "step": 372
+    },
+    {
+      "epoch": 2.1426519865964577,
+      "grad_norm": 0.36571794748306274,
+      "learning_rate": 2.2903954910480746e-06,
+      "loss": 0.4621,
+      "step": 373
+    },
+    {
+      "epoch": 2.1483963618956436,
+      "grad_norm": 0.3868046700954437,
+      "learning_rate": 2.2623084406147643e-06,
+      "loss": 0.4306,
+      "step": 374
+    },
+    {
+      "epoch": 2.15414073719483,
+      "grad_norm": 0.37293747067451477,
+      "learning_rate": 2.234344229374003e-06,
+      "loss": 0.441,
+      "step": 375
+    },
+    {
+      "epoch": 2.1598851124940164,
+      "grad_norm": 0.38192519545555115,
+      "learning_rate": 2.2065041120694487e-06,
+      "loss": 0.442,
+      "step": 376
+    },
+    {
+      "epoch": 2.1656294877932023,
+      "grad_norm": 0.373929888010025,
+      "learning_rate": 2.178789337876716e-06,
+      "loss": 0.4448,
+      "step": 377
+    },
+    {
+      "epoch": 2.1713738630923887,
+      "grad_norm": 0.40156957507133484,
+      "learning_rate": 2.151201150347318e-06,
+      "loss": 0.4359,
+      "step": 378
+    },
+    {
+      "epoch": 2.177118238391575,
+      "grad_norm": 0.3525901138782501,
+      "learning_rate": 2.123740787352872e-06,
+      "loss": 0.4045,
+      "step": 379
+    },
+    {
+      "epoch": 2.182862613690761,
+      "grad_norm": 0.3916381001472473,
+      "learning_rate": 2.096409481029556e-06,
+      "loss": 0.4423,
+      "step": 380
+    },
+    {
+      "epoch": 2.1886069889899473,
+      "grad_norm": 0.3852902948856354,
+      "learning_rate": 2.069208457722828e-06,
+      "loss": 0.421,
+      "step": 381
+    },
+    {
+      "epoch": 2.1943513642891337,
+      "grad_norm": 0.40378549695014954,
+      "learning_rate": 2.042138937932388e-06,
+      "loss": 0.4254,
+      "step": 382
+    },
+    {
+      "epoch": 2.2000957395883196,
+      "grad_norm": 0.3902316987514496,
+      "learning_rate": 2.015202136257432e-06,
+      "loss": 0.4891,
+      "step": 383
+    },
+    {
+      "epoch": 2.205840114887506,
+      "grad_norm": 0.3631356954574585,
+      "learning_rate": 1.988399261342135e-06,
+      "loss": 0.4048,
+      "step": 384
+    },
+    {
+      "epoch": 2.2115844901866923,
+      "grad_norm": 0.3928806483745575,
+      "learning_rate": 1.9617315158214363e-06,
+      "loss": 0.4654,
+      "step": 385
+    },
+    {
+      "epoch": 2.2173288654858783,
+      "grad_norm": 0.3718385100364685,
+      "learning_rate": 1.935200096267064e-06,
+      "loss": 0.4473,
+      "step": 386
+    },
+    {
+      "epoch": 2.2230732407850646,
+      "grad_norm": 0.3905206024646759,
+      "learning_rate": 1.908806193133855e-06,
+      "loss": 0.4315,
+      "step": 387
+    },
+    {
+      "epoch": 2.228817616084251,
+      "grad_norm": 0.37699949741363525,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.4605,
+      "step": 388
+    },
+    {
+      "epoch": 2.234561991383437,
+      "grad_norm": 0.4052666425704956,
+      "learning_rate": 1.856435667045577e-06,
+      "loss": 0.4561,
+      "step": 389
+    },
+    {
+      "epoch": 2.2403063666826233,
+      "grad_norm": 0.41954728960990906,
+      "learning_rate": 1.8304613939363531e-06,
+      "loss": 0.451,
+      "step": 390
+    },
+    {
+      "epoch": 2.2460507419818097,
+      "grad_norm": 0.3681614398956299,
+      "learning_rate": 1.8046293368345485e-06,
+      "loss": 0.4332,
+      "step": 391
+    },
+    {
+      "epoch": 2.2517951172809956,
+      "grad_norm": 0.3315896987915039,
+      "learning_rate": 1.7789406548148647e-06,
+      "loss": 0.4176,
+      "step": 392
+    },
+    {
+      "epoch": 2.257539492580182,
+      "grad_norm": 0.4171721935272217,
+      "learning_rate": 1.7533965005188242e-06,
+      "loss": 0.5205,
+      "step": 393
+    },
+    {
+      "epoch": 2.2632838678793683,
+      "grad_norm": 0.35167965292930603,
+      "learning_rate": 1.7279980201030382e-06,
+      "loss": 0.4135,
+      "step": 394
+    },
+    {
+      "epoch": 2.2690282431785542,
+      "grad_norm": 0.38858693838119507,
+      "learning_rate": 1.7027463531877897e-06,
+      "loss": 0.4432,
+      "step": 395
+    },
+    {
+      "epoch": 2.2747726184777406,
+      "grad_norm": 0.3728155791759491,
+      "learning_rate": 1.677642632805892e-06,
+      "loss": 0.4512,
+      "step": 396
+    },
+    {
+      "epoch": 2.280516993776927,
+      "grad_norm": 0.395333856344223,
+      "learning_rate": 1.6526879853518558e-06,
+      "loss": 0.4461,
+      "step": 397
+    },
+    {
+      "epoch": 2.286261369076113,
+      "grad_norm": 0.37841910123825073,
+      "learning_rate": 1.6278835305313462e-06,
+      "loss": 0.4539,
+      "step": 398
+    },
+    {
+      "epoch": 2.2920057443752992,
+      "grad_norm": 0.3504939675331116,
+      "learning_rate": 1.6032303813109368e-06,
+      "loss": 0.4478,
+      "step": 399
+    },
+    {
+      "epoch": 2.297750119674485,
+      "grad_norm": 0.383880615234375,
+      "learning_rate": 1.578729643868181e-06,
+      "loss": 0.4544,
+      "step": 400
+    },
+    {
+      "epoch": 2.3034944949736715,
+      "grad_norm": 0.39890047907829285,
+      "learning_rate": 1.5543824175419691e-06,
+      "loss": 0.4616,
+      "step": 401
+    },
+    {
+      "epoch": 2.309238870272858,
+      "grad_norm": 0.3388942778110504,
+      "learning_rate": 1.5301897947832063e-06,
+      "loss": 0.4472,
+      "step": 402
+    },
+    {
+      "epoch": 2.3149832455720443,
+      "grad_norm": 0.3660285770893097,
+      "learning_rate": 1.5061528611057917e-06,
+      "loss": 0.4071,
+      "step": 403
+    },
+    {
+      "epoch": 2.32072762087123,
+      "grad_norm": 0.38760945200920105,
+      "learning_rate": 1.4822726950379207e-06,
+      "loss": 0.4753,
+      "step": 404
+    },
+    {
+      "epoch": 2.3264719961704166,
+      "grad_norm": 0.36534708738327026,
+      "learning_rate": 1.4585503680736756e-06,
+      "loss": 0.4351,
+      "step": 405
+    },
+    {
+      "epoch": 2.3322163714696025,
+      "grad_norm": 0.3707476258277893,
+      "learning_rate": 1.4349869446249664e-06,
+      "loss": 0.43,
+      "step": 406
+    },
+    {
+      "epoch": 2.337960746768789,
+      "grad_norm": 0.36531203985214233,
+      "learning_rate": 1.4115834819737534e-06,
+      "loss": 0.3951,
+      "step": 407
+    },
+    {
+      "epoch": 2.343705122067975,
+      "grad_norm": 0.39617377519607544,
+      "learning_rate": 1.3883410302246237e-06,
+      "loss": 0.4387,
+      "step": 408
+    },
+    {
+      "epoch": 2.349449497367161,
+      "grad_norm": 0.36693063378334045,
+      "learning_rate": 1.3652606322576606e-06,
+      "loss": 0.4014,
+      "step": 409
+    },
+    {
+      "epoch": 2.3551938726663475,
+      "grad_norm": 0.3821011781692505,
+      "learning_rate": 1.3423433236816563e-06,
+      "loss": 0.4526,
+      "step": 410
+    },
+    {
+      "epoch": 2.360938247965534,
+      "grad_norm": 0.3760710060596466,
+      "learning_rate": 1.3195901327876426e-06,
+      "loss": 0.4402,
+      "step": 411
+    },
+    {
+      "epoch": 2.36668262326472,
+      "grad_norm": 0.3526499271392822,
+      "learning_rate": 1.2970020805027555e-06,
+      "loss": 0.4167,
+      "step": 412
+    },
+    {
+      "epoch": 2.372426998563906,
+      "grad_norm": 0.3931331932544708,
+      "learning_rate": 1.2745801803444192e-06,
+      "loss": 0.4686,
+      "step": 413
+    },
+    {
+      "epoch": 2.3781713738630925,
+      "grad_norm": 0.40180233120918274,
+      "learning_rate": 1.25232543837488e-06,
+      "loss": 0.4679,
+      "step": 414
+    },
+    {
+      "epoch": 2.3839157491622784,
+      "grad_norm": 0.35506054759025574,
+      "learning_rate": 1.2302388531560515e-06,
+      "loss": 0.4335,
+      "step": 415
+    },
+    {
+      "epoch": 2.389660124461465,
+      "grad_norm": 0.3469352126121521,
+      "learning_rate": 1.2083214157047257e-06,
+      "loss": 0.4631,
+      "step": 416
+    },
+    {
+      "epoch": 2.395404499760651,
+      "grad_norm": 0.3637499213218689,
+      "learning_rate": 1.186574109448091e-06,
+      "loss": 0.4489,
+      "step": 417
+    },
+    {
+      "epoch": 2.401148875059837,
+      "grad_norm": 0.3483814597129822,
+      "learning_rate": 1.164997910179615e-06,
+      "loss": 0.4659,
+      "step": 418
+    },
+    {
+      "epoch": 2.4068932503590235,
+      "grad_norm": 0.38259443640708923,
+      "learning_rate": 1.1435937860152579e-06,
+      "loss": 0.453,
+      "step": 419
+    },
+    {
+      "epoch": 2.41263762565821,
+      "grad_norm": 0.34772536158561707,
+      "learning_rate": 1.1223626973500395e-06,
+      "loss": 0.4076,
+      "step": 420
+    },
+    {
+      "epoch": 2.4183820009573957,
+      "grad_norm": 0.36162224411964417,
+      "learning_rate": 1.1013055968149343e-06,
+      "loss": 0.4482,
+      "step": 421
+    },
+    {
+      "epoch": 2.424126376256582,
+      "grad_norm": 0.3481464385986328,
+      "learning_rate": 1.0804234292341426e-06,
+      "loss": 0.4694,
+      "step": 422
+    },
+    {
+      "epoch": 2.4298707515557685,
+      "grad_norm": 0.3406570553779602,
+      "learning_rate": 1.0597171315826805e-06,
+      "loss": 0.4026,
+      "step": 423
+    },
+    {
+      "epoch": 2.4356151268549544,
+      "grad_norm": 0.359840452671051,
+      "learning_rate": 1.0391876329443534e-06,
+      "loss": 0.4212,
+      "step": 424
+    },
+    {
+      "epoch": 2.4413595021541408,
+      "grad_norm": 0.41036349534988403,
+      "learning_rate": 1.0188358544700583e-06,
+      "loss": 0.4463,
+      "step": 425
+    },
+    {
+      "epoch": 2.447103877453327,
+      "grad_norm": 0.3857036828994751,
+      "learning_rate": 9.986627093364542e-07,
+      "loss": 0.479,
+      "step": 426
+    },
+    {
+      "epoch": 2.452848252752513,
+      "grad_norm": 0.3274599611759186,
+      "learning_rate": 9.786691027049893e-07,
+      "loss": 0.3942,
+      "step": 427
+    },
+    {
+      "epoch": 2.4585926280516994,
+      "grad_norm": 0.41199931502342224,
+      "learning_rate": 9.588559316812906e-07,
+      "loss": 0.4954,
+      "step": 428
+    },
+    {
+      "epoch": 2.4643370033508853,
+      "grad_norm": 0.36387866735458374,
+      "learning_rate": 9.392240852749007e-07,
+      "loss": 0.4519,
+      "step": 429
+    },
+    {
+      "epoch": 2.4700813786500717,
+      "grad_norm": 0.3550173342227936,
+      "learning_rate": 9.197744443594003e-07,
+      "loss": 0.4146,
+      "step": 430
+    },
+    {
+      "epoch": 2.475825753949258,
+      "grad_norm": 0.36893606185913086,
+      "learning_rate": 9.005078816328772e-07,
+      "loss": 0.4837,
+      "step": 431
+    },
+    {
+      "epoch": 2.4815701292484444,
+      "grad_norm": 0.3411610424518585,
+      "learning_rate": 8.814252615787661e-07,
+      "loss": 0.4311,
+      "step": 432
+    },
+    {
+      "epoch": 2.4873145045476304,
+      "grad_norm": 0.3465381860733032,
+      "learning_rate": 8.625274404270662e-07,
+      "loss": 0.4731,
+      "step": 433
+    },
+    {
+      "epoch": 2.4930588798468167,
+      "grad_norm": 0.3729943633079529,
+      "learning_rate": 8.438152661159165e-07,
+      "loss": 0.4194,
+      "step": 434
+    },
+    {
+      "epoch": 2.4988032551460027,
+      "grad_norm": 0.4155563414096832,
+      "learning_rate": 8.252895782535569e-07,
+      "loss": 0.4698,
+      "step": 435
+    },
+    {
+      "epoch": 2.504547630445189,
+      "grad_norm": 0.3166390061378479,
+      "learning_rate": 8.069512080806441e-07,
+      "loss": 0.392,
+      "step": 436
+    },
+    {
+      "epoch": 2.5102920057443754,
+      "grad_norm": 0.3697630763053894,
+      "learning_rate": 7.88800978432967e-07,
+      "loss": 0.4642,
+      "step": 437
+    },
+    {
+      "epoch": 2.5160363810435618,
+      "grad_norm": 0.4319329559803009,
+      "learning_rate": 7.708397037045129e-07,
+      "loss": 0.4768,
+      "step": 438
+    },
+    {
+      "epoch": 2.5217807563427477,
+      "grad_norm": 0.32879865169525146,
+      "learning_rate": 7.530681898109393e-07,
+      "loss": 0.4141,
+      "step": 439
+    },
+    {
+      "epoch": 2.527525131641934,
+      "grad_norm": 0.3696901798248291,
+      "learning_rate": 7.35487234153402e-07,
+      "loss": 0.4802,
+      "step": 440
+    },
+    {
+      "epoch": 2.53326950694112,
+      "grad_norm": 0.3675316274166107,
+      "learning_rate": 7.180976255827809e-07,
+      "loss": 0.4756,
+      "step": 441
+    },
+    {
+      "epoch": 2.5390138822403063,
+      "grad_norm": 0.33102041482925415,
+      "learning_rate": 7.009001443642843e-07,
+      "loss": 0.3936,
+      "step": 442
+    },
+    {
+      "epoch": 2.5447582575394927,
+      "grad_norm": 0.32732781767845154,
+      "learning_rate": 6.838955621424404e-07,
+      "loss": 0.3896,
+      "step": 443
+    },
+    {
+      "epoch": 2.550502632838679,
+      "grad_norm": 0.3652030825614929,
+      "learning_rate": 6.67084641906468e-07,
+      "loss": 0.4773,
+      "step": 444
+    },
+    {
+      "epoch": 2.556247008137865,
+      "grad_norm": 0.3629269003868103,
+      "learning_rate": 6.50468137956049e-07,
+      "loss": 0.4434,
+      "step": 445
+    },
+    {
+      "epoch": 2.5619913834370514,
+      "grad_norm": 0.34360983967781067,
+      "learning_rate": 6.340467958674762e-07,
+      "loss": 0.4265,
+      "step": 446
+    },
+    {
+      "epoch": 2.5677357587362373,
+      "grad_norm": 0.3844148814678192,
+      "learning_rate": 6.178213524602061e-07,
+      "loss": 0.4666,
+      "step": 447
+    },
+    {
+      "epoch": 2.5734801340354236,
+      "grad_norm": 0.36176225543022156,
+      "learning_rate": 6.017925357637932e-07,
+      "loss": 0.4188,
+      "step": 448
+    },
+    {
+      "epoch": 2.57922450933461,
+      "grad_norm": 0.35700544714927673,
+      "learning_rate": 5.859610649852249e-07,
+      "loss": 0.426,
+      "step": 449
+    },
+    {
+      "epoch": 2.584968884633796,
+      "grad_norm": 0.3662126958370209,
+      "learning_rate": 5.703276504766514e-07,
+      "loss": 0.4135,
+      "step": 450
+    },
+    {
+      "epoch": 2.5907132599329823,
+      "grad_norm": 0.33082348108291626,
+      "learning_rate": 5.548929937035147e-07,
+      "loss": 0.3923,
+      "step": 451
+    },
+    {
+      "epoch": 2.5964576352321687,
+      "grad_norm": 0.351136714220047,
+      "learning_rate": 5.396577872130676e-07,
+      "loss": 0.4475,
+      "step": 452
+    },
+    {
+      "epoch": 2.6022020105313546,
+      "grad_norm": 0.3499198853969574,
+      "learning_rate": 5.246227146033089e-07,
+      "loss": 0.4704,
+      "step": 453
+    },
+    {
+      "epoch": 2.607946385830541,
+      "grad_norm": 0.3229888677597046,
+      "learning_rate": 5.097884504922996e-07,
+      "loss": 0.4099,
+      "step": 454
+    },
+    {
+      "epoch": 2.6136907611297273,
+      "grad_norm": 0.37059321999549866,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.5134,
+      "step": 455
+    },
+    {
+      "epoch": 2.6194351364289132,
+      "grad_norm": 0.35366615653038025,
+      "learning_rate": 4.807250011579168e-07,
+      "loss": 0.442,
+      "step": 456
+    },
+    {
+      "epoch": 2.6251795117280996,
+      "grad_norm": 0.33588507771492004,
+      "learning_rate": 4.6649712000060297e-07,
+      "loss": 0.3842,
+      "step": 457
+    },
+    {
+      "epoch": 2.6309238870272855,
+      "grad_norm": 0.33627060055732727,
+      "learning_rate": 4.5247265541564836e-07,
+      "loss": 0.4408,
+      "step": 458
+    },
+    {
+      "epoch": 2.636668262326472,
+      "grad_norm": 0.3534417450428009,
+      "learning_rate": 4.386522366755169e-07,
+      "loss": 0.4385,
+      "step": 459
+    },
+    {
+      "epoch": 2.6424126376256583,
+      "grad_norm": 0.3756772577762604,
+      "learning_rate": 4.250364838972065e-07,
+      "loss": 0.4684,
+      "step": 460
+    },
+    {
+      "epoch": 2.6481570129248446,
+      "grad_norm": 0.33255767822265625,
+      "learning_rate": 4.116260080144352e-07,
+      "loss": 0.4493,
+      "step": 461
+    },
+    {
+      "epoch": 2.6539013882240305,
+      "grad_norm": 0.3787069618701935,
+      "learning_rate": 3.98421410750221e-07,
+      "loss": 0.4556,
+      "step": 462
+    },
+    {
+      "epoch": 2.659645763523217,
+      "grad_norm": 0.35434430837631226,
+      "learning_rate": 3.854232845898859e-07,
+      "loss": 0.441,
+      "step": 463
+    },
+    {
+      "epoch": 2.665390138822403,
+      "grad_norm": 0.331163614988327,
+      "learning_rate": 3.7263221275447125e-07,
+      "loss": 0.4376,
+      "step": 464
+    },
+    {
+      "epoch": 2.671134514121589,
+      "grad_norm": 0.3512961268424988,
+      "learning_rate": 3.60048769174568e-07,
+      "loss": 0.438,
+      "step": 465
+    },
+    {
+      "epoch": 2.6768788894207756,
+      "grad_norm": 0.3708810806274414,
+      "learning_rate": 3.4767351846456744e-07,
+      "loss": 0.4711,
+      "step": 466
+    },
+    {
+      "epoch": 2.682623264719962,
+      "grad_norm": 0.35665786266326904,
+      "learning_rate": 3.355070158973212e-07,
+      "loss": 0.4434,
+      "step": 467
+    },
+    {
+      "epoch": 2.688367640019148,
+      "grad_norm": 0.3402157723903656,
+      "learning_rate": 3.235498073792342e-07,
+      "loss": 0.4436,
+      "step": 468
+    },
+    {
+      "epoch": 2.694112015318334,
+      "grad_norm": 0.3638489842414856,
+      "learning_rate": 3.118024294257621e-07,
+      "loss": 0.4612,
+      "step": 469
+    },
+    {
+      "epoch": 2.69985639061752,
+      "grad_norm": 0.3516465425491333,
+      "learning_rate": 3.002654091373453e-07,
+      "loss": 0.4177,
+      "step": 470
+    },
+    {
+      "epoch": 2.7056007659167065,
+      "grad_norm": 0.3707068860530853,
+      "learning_rate": 2.889392641757527e-07,
+      "loss": 0.4764,
+      "step": 471
+    },
+    {
+      "epoch": 2.711345141215893,
+      "grad_norm": 0.3246111571788788,
+      "learning_rate": 2.778245027408566e-07,
+      "loss": 0.4262,
+      "step": 472
+    },
+    {
+      "epoch": 2.7170895165150792,
+      "grad_norm": 0.37666356563568115,
+      "learning_rate": 2.669216235478295e-07,
+      "loss": 0.4879,
+      "step": 473
+    },
+    {
+      "epoch": 2.722833891814265,
+      "grad_norm": 0.3712378144264221,
+      "learning_rate": 2.562311158047692e-07,
+      "loss": 0.4568,
+      "step": 474
+    },
+    {
+      "epoch": 2.7285782671134515,
+      "grad_norm": 0.35843536257743835,
+      "learning_rate": 2.45753459190744e-07,
+      "loss": 0.4473,
+      "step": 475
+    },
+    {
+      "epoch": 2.7343226424126374,
+      "grad_norm": 0.36265286803245544,
+      "learning_rate": 2.354891238342738e-07,
+      "loss": 0.4247,
+      "step": 476
+    },
+    {
+      "epoch": 2.740067017711824,
+      "grad_norm": 0.35885879397392273,
+      "learning_rate": 2.254385702922318e-07,
+      "loss": 0.4544,
+      "step": 477
+    },
+    {
+      "epoch": 2.74581139301101,
+      "grad_norm": 0.3318557143211365,
+      "learning_rate": 2.1560224952918373e-07,
+      "loss": 0.3918,
+      "step": 478
+    },
+    {
+      "epoch": 2.751555768310196,
+      "grad_norm": 0.3384019732475281,
+      "learning_rate": 2.0598060289714893e-07,
+      "loss": 0.3935,
+      "step": 479
+    },
+    {
+      "epoch": 2.7573001436093825,
+      "grad_norm": 0.37354743480682373,
+      "learning_rate": 1.9657406211579966e-07,
+      "loss": 0.477,
+      "step": 480
+    },
+    {
+      "epoch": 2.763044518908569,
+      "grad_norm": 0.3306199312210083,
+      "learning_rate": 1.8738304925308926e-07,
+      "loss": 0.4606,
+      "step": 481
+    },
+    {
+      "epoch": 2.7687888942077548,
+      "grad_norm": 0.337941974401474,
+      "learning_rate": 1.7840797670631572e-07,
+      "loss": 0.4581,
+      "step": 482
+    },
+    {
+      "epoch": 2.774533269506941,
+      "grad_norm": 0.34849002957344055,
+      "learning_rate": 1.6964924718361364e-07,
+      "loss": 0.4416,
+      "step": 483
+    },
+    {
+      "epoch": 2.7802776448061275,
+      "grad_norm": 0.3213178515434265,
+      "learning_rate": 1.6110725368589041e-07,
+      "loss": 0.4177,
+      "step": 484
+    },
+    {
+      "epoch": 2.7860220201053134,
+      "grad_norm": 0.3672527074813843,
+      "learning_rate": 1.5278237948918585e-07,
+      "loss": 0.4831,
+      "step": 485
+    },
+    {
+      "epoch": 2.7917663954045,
+      "grad_norm": 0.3290295898914337,
+      "learning_rate": 1.4467499812748143e-07,
+      "loss": 0.4421,
+      "step": 486
+    },
+    {
+      "epoch": 2.7975107707036857,
+      "grad_norm": 0.32079824805259705,
+      "learning_rate": 1.3678547337593494e-07,
+      "loss": 0.4536,
+      "step": 487
+    },
+    {
+      "epoch": 2.803255146002872,
+      "grad_norm": 0.34473419189453125,
+      "learning_rate": 1.2911415923456017e-07,
+      "loss": 0.4474,
+      "step": 488
+    },
+    {
+      "epoch": 2.8089995213020584,
+      "grad_norm": 0.34892538189888,
+      "learning_rate": 1.2166139991234227e-07,
+      "loss": 0.4153,
+      "step": 489
+    },
+    {
+      "epoch": 2.814743896601245,
+      "grad_norm": 0.35367730259895325,
+      "learning_rate": 1.1442752981179527e-07,
+      "loss": 0.4633,
+      "step": 490
+    },
+    {
+      "epoch": 2.8204882719004307,
+      "grad_norm": 0.34787774085998535,
+      "learning_rate": 1.0741287351395402e-07,
+      "loss": 0.4833,
+      "step": 491
+    },
+    {
+      "epoch": 2.826232647199617,
+      "grad_norm": 0.34205448627471924,
+      "learning_rate": 1.0061774576381411e-07,
+      "loss": 0.443,
+      "step": 492
+    },
+    {
+      "epoch": 2.831977022498803,
+      "grad_norm": 0.3662581741809845,
+      "learning_rate": 9.404245145620717e-08,
+      "loss": 0.4819,
+      "step": 493
+    },
+    {
+      "epoch": 2.8377213977979894,
+      "grad_norm": 0.3398209512233734,
+      "learning_rate": 8.768728562211948e-08,
+      "loss": 0.3826,
+      "step": 494
+    },
+    {
+      "epoch": 2.8434657730971757,
+      "grad_norm": 0.3441368341445923,
+      "learning_rate": 8.155253341545655e-08,
+      "loss": 0.4825,
+      "step": 495
+    },
+    {
+      "epoch": 2.849210148396362,
+      "grad_norm": 0.36746805906295776,
+      "learning_rate": 7.563847010024716e-08,
+      "loss": 0.4402,
+      "step": 496
+    },
+    {
+      "epoch": 2.854954523695548,
+      "grad_norm": 0.3405812978744507,
+      "learning_rate": 6.994536103829164e-08,
+      "loss": 0.4468,
+      "step": 497
+    },
+    {
+      "epoch": 2.8606988989947344,
+      "grad_norm": 0.33339643478393555,
+      "learning_rate": 6.447346167725688e-08,
+      "loss": 0.4059,
+      "step": 498
+    },
+    {
+      "epoch": 2.8664432742939203,
+      "grad_norm": 0.3409021496772766,
+      "learning_rate": 5.9223017539213335e-08,
+      "loss": 0.4844,
+      "step": 499
+    },
+    {
+      "epoch": 2.8721876495931067,
+      "grad_norm": 0.30741554498672485,
+      "learning_rate": 5.4194264209617705e-08,
+      "loss": 0.4113,
+      "step": 500
+    },
+    {
+      "epoch": 2.877932024892293,
+      "grad_norm": 0.34918904304504395,
+      "learning_rate": 4.9387427326745287e-08,
+      "loss": 0.4648,
+      "step": 501
+    },
+    {
+      "epoch": 2.8836764001914794,
+      "grad_norm": 0.3559444844722748,
+      "learning_rate": 4.4802722571561374e-08,
+      "loss": 0.4712,
+      "step": 502
+    },
+    {
+      "epoch": 2.8894207754906653,
+      "grad_norm": 0.3617500960826874,
+      "learning_rate": 4.044035565804793e-08,
+      "loss": 0.4212,
+      "step": 503
+    },
+    {
+      "epoch": 2.8951651507898517,
+      "grad_norm": 0.3423933982849121,
+      "learning_rate": 3.6300522323969855e-08,
+      "loss": 0.3823,
+      "step": 504
+    },
+    {
+      "epoch": 2.9009095260890376,
+      "grad_norm": 0.32970568537712097,
+      "learning_rate": 3.2383408322095856e-08,
+      "loss": 0.483,
+      "step": 505
+    },
+    {
+      "epoch": 2.906653901388224,
+      "grad_norm": 0.32338789105415344,
+      "learning_rate": 2.8689189411859607e-08,
+      "loss": 0.4111,
+      "step": 506
+    },
+    {
+      "epoch": 2.9123982766874104,
+      "grad_norm": 0.36587268114089966,
+      "learning_rate": 2.5218031351478268e-08,
+      "loss": 0.5196,
+      "step": 507
+    },
+    {
+      "epoch": 2.9181426519865967,
+      "grad_norm": 0.372019499540329,
+      "learning_rate": 2.1970089890509527e-08,
+      "loss": 0.4153,
+      "step": 508
+    },
+    {
+      "epoch": 2.9238870272857826,
+      "grad_norm": 0.3676818907260895,
+      "learning_rate": 1.8945510762868325e-08,
+      "loss": 0.445,
+      "step": 509
+    },
+    {
+      "epoch": 2.929631402584969,
+      "grad_norm": 0.33755603432655334,
+      "learning_rate": 1.614442968028429e-08,
+      "loss": 0.4542,
+      "step": 510
+    },
+    {
+      "epoch": 2.935375777884155,
+      "grad_norm": 0.3397558629512787,
+      "learning_rate": 1.3566972326214956e-08,
+      "loss": 0.4402,
+      "step": 511
+    },
+    {
+      "epoch": 2.9411201531833413,
+      "grad_norm": 0.3535856604576111,
+      "learning_rate": 1.1213254350202486e-08,
+      "loss": 0.4235,
+      "step": 512
+    },
+    {
+      "epoch": 2.9468645284825277,
+      "grad_norm": 0.324677973985672,
+      "learning_rate": 9.083381362690603e-09,
+      "loss": 0.4315,
+      "step": 513
+    },
+    {
+      "epoch": 2.9526089037817136,
+      "grad_norm": 0.3455667495727539,
+      "learning_rate": 7.177448930279496e-09,
+      "loss": 0.4506,
+      "step": 514
+    },
+    {
+      "epoch": 2.9583532790809,
+      "grad_norm": 0.35920631885528564,
+      "learning_rate": 5.495542571443135e-09,
+      "loss": 0.4154,
+      "step": 515
+    },
+    {
+      "epoch": 2.9640976543800863,
+      "grad_norm": 0.3734237849712372,
+      "learning_rate": 4.037737752686788e-09,
+      "loss": 0.4393,
+      "step": 516
+    },
+    {
+      "epoch": 2.9698420296792722,
+      "grad_norm": 0.34162041544914246,
+      "learning_rate": 2.8040998851674996e-09,
+      "loss": 0.4448,
+      "step": 517
+    },
+    {
+      "epoch": 2.9755864049784586,
+      "grad_norm": 0.3412844240665436,
+      "learning_rate": 1.7946843217514498e-09,
+      "loss": 0.4195,
+      "step": 518
+    },
+    {
+      "epoch": 2.981330780277645,
+      "grad_norm": 0.35345590114593506,
+      "learning_rate": 1.009536354537044e-09,
+      "loss": 0.3924,
+      "step": 519
+    },
+    {
+      "epoch": 2.987075155576831,
+      "grad_norm": 0.36779072880744934,
+      "learning_rate": 4.486912128182086e-10,
+      "loss": 0.5045,
+      "step": 520
+    },
+    {
+      "epoch": 2.9928195308760173,
+      "grad_norm": 0.3303414583206177,
+      "learning_rate": 1.1217406150676457e-10,
+      "loss": 0.4413,
+      "step": 521
+    },
+    {
+      "epoch": 2.998563906175203,
+      "grad_norm": 0.33037903904914856,
+      "learning_rate": 0.0,
+      "loss": 0.4208,
+      "step": 522
+    },
+    {
+      "epoch": 2.998563906175203,
+      "step": 522,
+      "total_flos": 538113478688768.0,
+      "train_loss": 0.5088067185490525,
+      "train_runtime": 25669.0251,
+      "train_samples_per_second": 1.953,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 522,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 538113478688768.0,
+  "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 sha256:8b2c7be9d6a854256321e1dcea5671272ffb62341c43bb590e825ffc34d907ee
+size 7416