Upload folder using huggingface_hub

.gitattributes

@@ -38,3 +38,4 @@ g1_0_baseline_original_code/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -t
 g1_0_baseline_original_code/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g1_0_baseline_original_code/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g1_0_baseline_original_code__edit/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+g1_0_baseline_original_code__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text

g1_0_baseline_original_code__edit/500M/README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B-Base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 500M
+  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. -->
+
+# 500M
+
+This model is a fine-tuned version of [/lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base](https://huggingface.co//lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base) on the rv5_g1_0_baseline_original_code, the instruct_replay and the edit_instruct datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 12
+- total_train_batch_size: 12
+- total_eval_batch_size: 96
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: warmup_stable_decay
+- lr_scheduler_warmup_steps: 178
+- training_steps: 5597
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.10.0a0+git449b176
+- Datasets 4.5.0
+- Tokenizers 0.22.2

g1_0_baseline_original_code__edit/500M/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

g1_0_baseline_original_code__edit/500M/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.45305164319248825,
+    "total_flos": 2.4985159616803373e+19,
+    "train_loss": 0.059759924299742084,
+    "train_runtime": 5784.2106,
+    "train_samples_per_second": 11.612,
+    "train_steps_per_second": 0.968
+}

g1_0_baseline_original_code__edit/500M/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

g1_0_baseline_original_code__edit/500M/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

g1_0_baseline_original_code__edit/500M/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

g1_0_baseline_original_code__edit/500M/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07ac9e0a2b6a548fbed6e18d2b8fd7e805002a90e5d07443a7c6d32a8d4c1e5
+size 4902257696

g1_0_baseline_original_code__edit/500M/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c571e5f7dace04409b834275ac8b9de4dfe3ac229aeef07e6022b6d2621a05c
+size 4915960368

g1_0_baseline_original_code__edit/500M/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4676ba9309df8a07f84f83d9fe528e3d39343c43dde9c355c8497547603664e3
+size 4983068496

g1_0_baseline_original_code__edit/500M/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2020ae0a85f8301075115e9246da092c792d5f7318435deea3afb9366967ed5
+size 1580230264

g1_0_baseline_original_code__edit/500M/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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-00001-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_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

g1_0_baseline_original_code__edit/500M/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
+  }
+}

g1_0_baseline_original_code__edit/500M/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

g1_0_baseline_original_code__edit/500M/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

g1_0_baseline_original_code__edit/500M/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.45305164319248825,
+    "total_flos": 2.4985159616803373e+19,
+    "train_loss": 0.059759924299742084,
+    "train_runtime": 5784.2106,
+    "train_samples_per_second": 11.612,
+    "train_steps_per_second": 0.968
+}

g1_0_baseline_original_code__edit/500M/trainer_log.jsonl

@@ -0,0 +1,52 @@
+{"current_steps": 5090, "total_steps": 5597, "loss": 0.6214, "lr": 1.9999810479633703e-05, "epoch": 0.4120123037073013, "percentage": 90.94, "elapsed_time": "0:00:27", "remaining_time": "0:00:02"}
+{"current_steps": 5100, "total_steps": 5597, "loss": 0.7262, "lr": 1.997707677020786e-05, "epoch": 0.412821758135017, "percentage": 91.12, "elapsed_time": "0:02:20", "remaining_time": "0:00:13"}
+{"current_steps": 5110, "total_steps": 5597, "loss": 0.7154, "lr": 1.9916538196124637e-05, "epoch": 0.4136312125627327, "percentage": 91.3, "elapsed_time": "0:04:13", "remaining_time": "0:00:24"}
+{"current_steps": 5120, "total_steps": 5597, "loss": 0.671, "lr": 1.9818425303863402e-05, "epoch": 0.41444066699044846, "percentage": 91.48, "elapsed_time": "0:06:06", "remaining_time": "0:00:34"}
+{"current_steps": 5130, "total_steps": 5597, "loss": 0.6187, "lr": 1.9683111732582887e-05, "epoch": 0.41525012141816414, "percentage": 91.66, "elapsed_time": "0:07:59", "remaining_time": "0:00:43"}
+{"current_steps": 5140, "total_steps": 5597, "loss": 0.6619, "lr": 1.951111279120706e-05, "epoch": 0.4160595758458799, "percentage": 91.83, "elapsed_time": "0:09:52", "remaining_time": "0:00:52"}
+{"current_steps": 5150, "total_steps": 5597, "loss": 0.6185, "lr": 1.9303083495996028e-05, "epoch": 0.4168690302735956, "percentage": 92.01, "elapsed_time": "0:11:45", "remaining_time": "0:01:01"}
+{"current_steps": 5160, "total_steps": 5597, "loss": 0.6353, "lr": 1.9059816076075482e-05, "epoch": 0.4176784847013113, "percentage": 92.19, "elapsed_time": "0:13:38", "remaining_time": "0:01:09"}
+{"current_steps": 5170, "total_steps": 5597, "loss": 0.6471, "lr": 1.8782236956424142e-05, "epoch": 0.41848793912902704, "percentage": 92.37, "elapsed_time": "0:15:31", "remaining_time": "0:01:16"}
+{"current_steps": 5180, "total_steps": 5597, "loss": 0.6774, "lr": 1.8471403229808897e-05, "epoch": 0.4192973935567428, "percentage": 92.55, "elapsed_time": "0:17:24", "remaining_time": "0:01:24"}
+{"current_steps": 5190, "total_steps": 5597, "loss": 0.6416, "lr": 1.8128498631103333e-05, "epoch": 0.42010684798445846, "percentage": 92.73, "elapsed_time": "0:19:17", "remaining_time": "0:01:30"}
+{"current_steps": 5200, "total_steps": 5597, "loss": 0.6363, "lr": 1.7754829029320507e-05, "epoch": 0.4209163024121742, "percentage": 92.91, "elapsed_time": "0:21:10", "remaining_time": "0:01:37"}
+{"current_steps": 5210, "total_steps": 5597, "loss": 0.6613, "lr": 1.7351817454527473e-05, "epoch": 0.4217257568398899, "percentage": 93.09, "elapsed_time": "0:23:03", "remaining_time": "0:01:42"}
+{"current_steps": 5220, "total_steps": 5597, "loss": 0.6281, "lr": 1.6920998678580345e-05, "epoch": 0.4225352112676056, "percentage": 93.26, "elapsed_time": "0:24:56", "remaining_time": "0:01:48"}
+{"current_steps": 5230, "total_steps": 5597, "loss": 0.6824, "lr": 1.6464013370317854e-05, "epoch": 0.42334466569532136, "percentage": 93.44, "elapsed_time": "0:26:49", "remaining_time": "0:01:52"}
+{"current_steps": 5240, "total_steps": 5597, "loss": 0.7213, "lr": 1.5982601847471915e-05, "epoch": 0.42415412012303705, "percentage": 93.62, "elapsed_time": "0:28:42", "remaining_time": "0:01:57"}
+{"current_steps": 5250, "total_steps": 5597, "loss": 0.6992, "lr": 1.5478597449089553e-05, "epoch": 0.4249635745507528, "percentage": 93.8, "elapsed_time": "0:30:35", "remaining_time": "0:02:01"}
+{"current_steps": 5260, "total_steps": 5597, "loss": 0.6171, "lr": 1.4953919553705725e-05, "epoch": 0.4257730289784685, "percentage": 93.98, "elapsed_time": "0:32:29", "remaining_time": "0:02:04"}
+{"current_steps": 5270, "total_steps": 5597, "loss": 0.6814, "lr": 1.441056626985559e-05, "epoch": 0.4265824834061842, "percentage": 94.16, "elapsed_time": "0:34:22", "remaining_time": "0:02:07"}
+{"current_steps": 5280, "total_steps": 5597, "loss": 0.6717, "lr": 1.3850606826762668e-05, "epoch": 0.42739193783389995, "percentage": 94.34, "elapsed_time": "0:36:15", "remaining_time": "0:02:10"}
+{"current_steps": 5290, "total_steps": 5597, "loss": 0.6427, "lr": 1.3276173694181128e-05, "epoch": 0.4282013922616157, "percentage": 94.51, "elapsed_time": "0:38:08", "remaining_time": "0:02:12"}
+{"current_steps": 5300, "total_steps": 5597, "loss": 0.6681, "lr": 1.2689454461401822e-05, "epoch": 0.42901084668933137, "percentage": 94.69, "elapsed_time": "0:40:01", "remaining_time": "0:02:14"}
+{"current_steps": 5310, "total_steps": 5597, "loss": 0.7181, "lr": 1.2092683506348939e-05, "epoch": 0.4298203011170471, "percentage": 94.87, "elapsed_time": "0:41:53", "remaining_time": "0:02:15"}
+{"current_steps": 5320, "total_steps": 5597, "loss": 0.6354, "lr": 1.14881334864935e-05, "epoch": 0.43062975554476285, "percentage": 95.05, "elapsed_time": "0:43:46", "remaining_time": "0:02:16"}
+{"current_steps": 5330, "total_steps": 5597, "loss": 0.623, "lr": 1.0878106683988481e-05, "epoch": 0.43143920997247853, "percentage": 95.23, "elapsed_time": "0:45:39", "remaining_time": "0:02:17"}
+{"current_steps": 5340, "total_steps": 5597, "loss": 0.6587, "lr": 1.026492623798551e-05, "epoch": 0.43224866440019427, "percentage": 95.41, "elapsed_time": "0:47:33", "remaining_time": "0:02:17"}
+{"current_steps": 5350, "total_steps": 5597, "loss": 0.66, "lr": 9.650927297522743e-06, "epoch": 0.43305811882791, "percentage": 95.59, "elapsed_time": "0:49:26", "remaining_time": "0:02:16"}
+{"current_steps": 5360, "total_steps": 5597, "loss": 0.63, "lr": 9.038448128676012e-06, "epoch": 0.4338675732556257, "percentage": 95.77, "elapsed_time": "0:51:19", "remaining_time": "0:02:16"}
+{"current_steps": 5370, "total_steps": 5597, "loss": 0.6378, "lr": 8.42982120983949e-06, "epoch": 0.43467702768334143, "percentage": 95.94, "elapsed_time": "0:53:12", "remaining_time": "0:02:14"}
+{"current_steps": 5380, "total_steps": 5597, "loss": 0.6727, "lr": 7.827364349047303e-06, "epoch": 0.43548648211105717, "percentage": 96.12, "elapsed_time": "0:55:06", "remaining_time": "0:02:13"}
+{"current_steps": 5390, "total_steps": 5597, "loss": 0.626, "lr": 7.233371857163706e-06, "epoch": 0.43629593653877285, "percentage": 96.3, "elapsed_time": "0:56:59", "remaining_time": "0:02:11"}
+{"current_steps": 5400, "total_steps": 5597, "loss": 0.6623, "lr": 6.650105810556492e-06, "epoch": 0.4371053909664886, "percentage": 96.48, "elapsed_time": "0:58:52", "remaining_time": "0:02:08"}
+{"current_steps": 5410, "total_steps": 5597, "loss": 0.704, "lr": 6.079787436527681e-06, "epoch": 0.43791484539420433, "percentage": 96.66, "elapsed_time": "1:00:46", "remaining_time": "0:02:06"}
+{"current_steps": 5420, "total_steps": 5597, "loss": 0.6692, "lr": 5.524588654307961e-06, "epoch": 0.43872429982192, "percentage": 96.84, "elapsed_time": "1:02:39", "remaining_time": "0:02:02"}
+{"current_steps": 5430, "total_steps": 5597, "loss": 0.6931, "lr": 4.986623803828985e-06, "epoch": 0.43953375424963576, "percentage": 97.02, "elapsed_time": "1:04:33", "remaining_time": "0:01:59"}
+{"current_steps": 5440, "total_steps": 5597, "loss": 0.6983, "lr": 4.467941593772423e-06, "epoch": 0.44034320867735144, "percentage": 97.19, "elapsed_time": "1:06:26", "remaining_time": "0:01:55"}
+{"current_steps": 5450, "total_steps": 5597, "loss": 0.5934, "lr": 3.9705172995597606e-06, "epoch": 0.4411526631050672, "percentage": 97.37, "elapsed_time": "1:08:20", "remaining_time": "0:01:50"}
+{"current_steps": 5460, "total_steps": 5597, "loss": 0.661, "lr": 3.4962452409948346e-06, "epoch": 0.4419621175327829, "percentage": 97.55, "elapsed_time": "1:10:13", "remaining_time": "0:01:45"}
+{"current_steps": 5470, "total_steps": 5597, "loss": 0.6764, "lr": 3.046931568206211e-06, "epoch": 0.4427715719604986, "percentage": 97.73, "elapsed_time": "1:12:06", "remaining_time": "0:01:40"}
+{"current_steps": 5480, "total_steps": 5597, "loss": 0.6369, "lr": 2.624287383362404e-06, "epoch": 0.44358102638821434, "percentage": 97.91, "elapsed_time": "1:14:00", "remaining_time": "0:01:34"}
+{"current_steps": 5490, "total_steps": 5597, "loss": 0.6306, "lr": 2.2299222243541845e-06, "epoch": 0.4443904808159301, "percentage": 98.09, "elapsed_time": "1:15:53", "remaining_time": "0:01:28"}
+{"current_steps": 5500, "total_steps": 5597, "loss": 0.5954, "lr": 1.8653379352598246e-06, "epoch": 0.44519993524364576, "percentage": 98.27, "elapsed_time": "1:17:47", "remaining_time": "0:01:22"}
+{"current_steps": 5510, "total_steps": 5597, "loss": 0.6409, "lr": 1.5319229469361075e-06, "epoch": 0.4460093896713615, "percentage": 98.45, "elapsed_time": "1:19:40", "remaining_time": "0:01:15"}
+{"current_steps": 5520, "total_steps": 5597, "loss": 0.6343, "lr": 1.2309469895160917e-06, "epoch": 0.44681884409907724, "percentage": 98.62, "elapsed_time": "1:21:33", "remaining_time": "0:01:08"}
+{"current_steps": 5530, "total_steps": 5597, "loss": 0.6957, "lr": 9.635562569497974e-07, "epoch": 0.4476282985267929, "percentage": 98.8, "elapsed_time": "1:23:27", "remaining_time": "0:01:00"}
+{"current_steps": 5540, "total_steps": 5597, "loss": 0.6819, "lr": 7.307690420024867e-07, "epoch": 0.44843775295450866, "percentage": 98.98, "elapsed_time": "1:25:20", "remaining_time": "0:00:52"}
+{"current_steps": 5550, "total_steps": 5597, "loss": 0.6323, "lr": 5.334718583335942e-07, "epoch": 0.4492472073822244, "percentage": 99.16, "elapsed_time": "1:27:13", "remaining_time": "0:00:44"}
+{"current_steps": 5560, "total_steps": 5597, "loss": 0.6655, "lr": 3.7241606442442763e-07, "epoch": 0.4500566618099401, "percentage": 99.34, "elapsed_time": "1:29:06", "remaining_time": "0:00:35"}
+{"current_steps": 5570, "total_steps": 5597, "loss": 0.6423, "lr": 2.482150022115879e-07, "epoch": 0.4508661162376558, "percentage": 99.52, "elapsed_time": "1:30:59", "remaining_time": "0:00:26"}
+{"current_steps": 5580, "total_steps": 5597, "loss": 0.6526, "lr": 1.6134166132293174e-07, "epoch": 0.45167557066537156, "percentage": 99.7, "elapsed_time": "1:32:53", "remaining_time": "0:00:16"}
+{"current_steps": 5590, "total_steps": 5597, "loss": 0.6459, "lr": 1.1212687781127357e-07, "epoch": 0.45248502509308725, "percentage": 99.87, "elapsed_time": "1:34:46", "remaining_time": "0:00:07"}
+{"current_steps": 5597, "total_steps": 5597, "epoch": 0.45305164319248825, "percentage": 100.0, "elapsed_time": "1:36:24", "remaining_time": "0:00:00"}

g1_0_baseline_original_code__edit/500M/trainer_state.json

@@ -0,0 +1,3956 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.45305164319248825,
+  "eval_steps": 500,
+  "global_step": 5597,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008094544277157196,
+      "grad_norm": 0.774714469909668,
+      "learning_rate": 1.1061797752808989e-06,
+      "loss": 0.7945,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016189088554314393,
+      "grad_norm": 0.7580778002738953,
+      "learning_rate": 2.2241573033707866e-06,
+      "loss": 0.7737,
+      "step": 20
+    },
+    {
+      "epoch": 0.0024283632831471587,
+      "grad_norm": 0.7160061001777649,
+      "learning_rate": 3.342134831460675e-06,
+      "loss": 0.7918,
+      "step": 30
+    },
+    {
+      "epoch": 0.0032378177108628786,
+      "grad_norm": 0.7335490584373474,
+      "learning_rate": 4.4601123595505624e-06,
+      "loss": 0.8443,
+      "step": 40
+    },
+    {
+      "epoch": 0.0040472721385785984,
+      "grad_norm": 0.7954026460647583,
+      "learning_rate": 5.5780898876404495e-06,
+      "loss": 0.7975,
+      "step": 50
+    },
+    {
+      "epoch": 0.0048567265662943174,
+      "grad_norm": 0.7089179158210754,
+      "learning_rate": 6.6960674157303374e-06,
+      "loss": 0.7573,
+      "step": 60
+    },
+    {
+      "epoch": 0.005666180994010037,
+      "grad_norm": 0.8039030432701111,
+      "learning_rate": 7.814044943820226e-06,
+      "loss": 0.8359,
+      "step": 70
+    },
+    {
+      "epoch": 0.006475635421725757,
+      "grad_norm": 0.7179280519485474,
+      "learning_rate": 8.932022471910112e-06,
+      "loss": 0.7494,
+      "step": 80
+    },
+    {
+      "epoch": 0.007285089849441476,
+      "grad_norm": 0.7046342492103577,
+      "learning_rate": 1.005e-05,
+      "loss": 0.7323,
+      "step": 90
+    },
+    {
+      "epoch": 0.008094544277157197,
+      "grad_norm": 1.5505956411361694,
+      "learning_rate": 1.1167977528089888e-05,
+      "loss": 0.7762,
+      "step": 100
+    },
+    {
+      "epoch": 0.008903998704872915,
+      "grad_norm": 0.7533053159713745,
+      "learning_rate": 1.2285955056179776e-05,
+      "loss": 0.7903,
+      "step": 110
+    },
+    {
+      "epoch": 0.009713453132588635,
+      "grad_norm": 0.7143501043319702,
+      "learning_rate": 1.3403932584269664e-05,
+      "loss": 0.8177,
+      "step": 120
+    },
+    {
+      "epoch": 0.010522907560304355,
+      "grad_norm": 0.8103587031364441,
+      "learning_rate": 1.4521910112359552e-05,
+      "loss": 0.8174,
+      "step": 130
+    },
+    {
+      "epoch": 0.011332361988020075,
+      "grad_norm": 0.804781436920166,
+      "learning_rate": 1.563988764044944e-05,
+      "loss": 0.7814,
+      "step": 140
+    },
+    {
+      "epoch": 0.012141816415735794,
+      "grad_norm": 0.8317695260047913,
+      "learning_rate": 1.6757865168539328e-05,
+      "loss": 0.7917,
+      "step": 150
+    },
+    {
+      "epoch": 0.012951270843451514,
+      "grad_norm": 0.6911673545837402,
+      "learning_rate": 1.7875842696629214e-05,
+      "loss": 0.7782,
+      "step": 160
+    },
+    {
+      "epoch": 0.013760725271167232,
+      "grad_norm": 0.7639819979667664,
+      "learning_rate": 1.89938202247191e-05,
+      "loss": 0.7693,
+      "step": 170
+    },
+    {
+      "epoch": 0.014570179698882952,
+      "grad_norm": 0.7025166749954224,
+      "learning_rate": 2e-05,
+      "loss": 0.7847,
+      "step": 180
+    },
+    {
+      "epoch": 0.015379634126598672,
+      "grad_norm": 0.648499071598053,
+      "learning_rate": 2e-05,
+      "loss": 0.8672,
+      "step": 190
+    },
+    {
+      "epoch": 0.016189088554314394,
+      "grad_norm": 0.7292491793632507,
+      "learning_rate": 2e-05,
+      "loss": 0.8087,
+      "step": 200
+    },
+    {
+      "epoch": 0.016998542982030112,
+      "grad_norm": 0.657598078250885,
+      "learning_rate": 2e-05,
+      "loss": 0.7788,
+      "step": 210
+    },
+    {
+      "epoch": 0.01780799740974583,
+      "grad_norm": 0.5830397605895996,
+      "learning_rate": 2e-05,
+      "loss": 0.818,
+      "step": 220
+    },
+    {
+      "epoch": 0.01861745183746155,
+      "grad_norm": 0.749767541885376,
+      "learning_rate": 2e-05,
+      "loss": 0.804,
+      "step": 230
+    },
+    {
+      "epoch": 0.01942690626517727,
+      "grad_norm": 0.5503732562065125,
+      "learning_rate": 2e-05,
+      "loss": 0.7803,
+      "step": 240
+    },
+    {
+      "epoch": 0.02023636069289299,
+      "grad_norm": 0.6262181401252747,
+      "learning_rate": 2e-05,
+      "loss": 0.8138,
+      "step": 250
+    },
+    {
+      "epoch": 0.02104581512060871,
+      "grad_norm": 0.6462956070899963,
+      "learning_rate": 2e-05,
+      "loss": 0.8132,
+      "step": 260
+    },
+    {
+      "epoch": 0.021855269548324428,
+      "grad_norm": 0.7039015889167786,
+      "learning_rate": 2e-05,
+      "loss": 0.7831,
+      "step": 270
+    },
+    {
+      "epoch": 0.02266472397604015,
+      "grad_norm": 0.5827919840812683,
+      "learning_rate": 2e-05,
+      "loss": 0.855,
+      "step": 280
+    },
+    {
+      "epoch": 0.023474178403755867,
+      "grad_norm": 0.5572606921195984,
+      "learning_rate": 2e-05,
+      "loss": 0.7816,
+      "step": 290
+    },
+    {
+      "epoch": 0.02428363283147159,
+      "grad_norm": 0.5105332732200623,
+      "learning_rate": 2e-05,
+      "loss": 0.7946,
+      "step": 300
+    },
+    {
+      "epoch": 0.025093087259187307,
+      "grad_norm": 0.4979988932609558,
+      "learning_rate": 2e-05,
+      "loss": 0.7601,
+      "step": 310
+    },
+    {
+      "epoch": 0.02590254168690303,
+      "grad_norm": 0.5323320031166077,
+      "learning_rate": 2e-05,
+      "loss": 0.8077,
+      "step": 320
+    },
+    {
+      "epoch": 0.026711996114618747,
+      "grad_norm": 0.5434609055519104,
+      "learning_rate": 2e-05,
+      "loss": 0.7853,
+      "step": 330
+    },
+    {
+      "epoch": 0.027521450542334465,
+      "grad_norm": 0.47694942355155945,
+      "learning_rate": 2e-05,
+      "loss": 0.7603,
+      "step": 340
+    },
+    {
+      "epoch": 0.028330904970050187,
+      "grad_norm": 0.5705140829086304,
+      "learning_rate": 2e-05,
+      "loss": 0.8051,
+      "step": 350
+    },
+    {
+      "epoch": 0.029140359397765905,
+      "grad_norm": 0.49830061197280884,
+      "learning_rate": 2e-05,
+      "loss": 0.8,
+      "step": 360
+    },
+    {
+      "epoch": 0.029949813825481626,
+      "grad_norm": 0.46984052658081055,
+      "learning_rate": 2e-05,
+      "loss": 0.7715,
+      "step": 370
+    },
+    {
+      "epoch": 0.030759268253197344,
+      "grad_norm": 0.520054042339325,
+      "learning_rate": 2e-05,
+      "loss": 0.7346,
+      "step": 380
+    },
+    {
+      "epoch": 0.03156872268091306,
+      "grad_norm": 0.5275624990463257,
+      "learning_rate": 2e-05,
+      "loss": 0.8106,
+      "step": 390
+    },
+    {
+      "epoch": 0.03237817710862879,
+      "grad_norm": 0.531984806060791,
+      "learning_rate": 2e-05,
+      "loss": 0.8597,
+      "step": 400
+    },
+    {
+      "epoch": 0.033187631536344506,
+      "grad_norm": 0.5085521936416626,
+      "learning_rate": 2e-05,
+      "loss": 0.8073,
+      "step": 410
+    },
+    {
+      "epoch": 0.033997085964060224,
+      "grad_norm": 0.48784393072128296,
+      "learning_rate": 2e-05,
+      "loss": 0.7982,
+      "step": 420
+    },
+    {
+      "epoch": 0.03480654039177594,
+      "grad_norm": 0.5306409597396851,
+      "learning_rate": 2e-05,
+      "loss": 0.7869,
+      "step": 430
+    },
+    {
+      "epoch": 0.03561599481949166,
+      "grad_norm": 0.5166577696800232,
+      "learning_rate": 2e-05,
+      "loss": 0.7919,
+      "step": 440
+    },
+    {
+      "epoch": 0.036425449247207385,
+      "grad_norm": 0.4593251347541809,
+      "learning_rate": 2e-05,
+      "loss": 0.7962,
+      "step": 450
+    },
+    {
+      "epoch": 0.0372349036749231,
+      "grad_norm": 0.47085559368133545,
+      "learning_rate": 2e-05,
+      "loss": 0.8032,
+      "step": 460
+    },
+    {
+      "epoch": 0.03804435810263882,
+      "grad_norm": 0.4564686715602875,
+      "learning_rate": 2e-05,
+      "loss": 0.7661,
+      "step": 470
+    },
+    {
+      "epoch": 0.03885381253035454,
+      "grad_norm": 0.483305960893631,
+      "learning_rate": 2e-05,
+      "loss": 0.7869,
+      "step": 480
+    },
+    {
+      "epoch": 0.03966326695807026,
+      "grad_norm": 1.5653489828109741,
+      "learning_rate": 2e-05,
+      "loss": 0.79,
+      "step": 490
+    },
+    {
+      "epoch": 0.04047272138578598,
+      "grad_norm": 0.49064645171165466,
+      "learning_rate": 2e-05,
+      "loss": 0.7629,
+      "step": 500
+    },
+    {
+      "epoch": 0.0412821758135017,
+      "grad_norm": 0.5050569176673889,
+      "learning_rate": 2e-05,
+      "loss": 0.8016,
+      "step": 510
+    },
+    {
+      "epoch": 0.04209163024121742,
+      "grad_norm": 0.681684672832489,
+      "learning_rate": 2e-05,
+      "loss": 0.7562,
+      "step": 520
+    },
+    {
+      "epoch": 0.04290108466893314,
+      "grad_norm": 0.5061203241348267,
+      "learning_rate": 2e-05,
+      "loss": 0.782,
+      "step": 530
+    },
+    {
+      "epoch": 0.043710539096648855,
+      "grad_norm": 0.47255396842956543,
+      "learning_rate": 2e-05,
+      "loss": 0.7775,
+      "step": 540
+    },
+    {
+      "epoch": 0.04451999352436458,
+      "grad_norm": 0.4580098092556,
+      "learning_rate": 2e-05,
+      "loss": 0.7922,
+      "step": 550
+    },
+    {
+      "epoch": 0.0453294479520803,
+      "grad_norm": 0.5001001954078674,
+      "learning_rate": 2e-05,
+      "loss": 0.7784,
+      "step": 560
+    },
+    {
+      "epoch": 0.04613890237979602,
+      "grad_norm": 0.47442105412483215,
+      "learning_rate": 2e-05,
+      "loss": 0.7666,
+      "step": 570
+    },
+    {
+      "epoch": 0.046948356807511735,
+      "grad_norm": 0.49136412143707275,
+      "learning_rate": 2e-05,
+      "loss": 0.7511,
+      "step": 580
+    },
+    {
+      "epoch": 0.04775781123522746,
+      "grad_norm": 1.8537838459014893,
+      "learning_rate": 2e-05,
+      "loss": 0.7732,
+      "step": 590
+    },
+    {
+      "epoch": 0.04856726566294318,
+      "grad_norm": 0.45473712682724,
+      "learning_rate": 2e-05,
+      "loss": 0.784,
+      "step": 600
+    },
+    {
+      "epoch": 0.049376720090658896,
+      "grad_norm": 0.5283686518669128,
+      "learning_rate": 2e-05,
+      "loss": 0.7529,
+      "step": 610
+    },
+    {
+      "epoch": 0.050186174518374614,
+      "grad_norm": 0.42911580204963684,
+      "learning_rate": 2e-05,
+      "loss": 0.804,
+      "step": 620
+    },
+    {
+      "epoch": 0.05099562894609033,
+      "grad_norm": 0.46790334582328796,
+      "learning_rate": 2e-05,
+      "loss": 0.7762,
+      "step": 630
+    },
+    {
+      "epoch": 0.05180508337380606,
+      "grad_norm": 0.5284407138824463,
+      "learning_rate": 2e-05,
+      "loss": 0.7677,
+      "step": 640
+    },
+    {
+      "epoch": 0.052614537801521775,
+      "grad_norm": 0.46369025111198425,
+      "learning_rate": 2e-05,
+      "loss": 0.772,
+      "step": 650
+    },
+    {
+      "epoch": 0.053423992229237494,
+      "grad_norm": 0.46754327416419983,
+      "learning_rate": 2e-05,
+      "loss": 0.7556,
+      "step": 660
+    },
+    {
+      "epoch": 0.05423344665695321,
+      "grad_norm": 0.41686615347862244,
+      "learning_rate": 2e-05,
+      "loss": 0.7712,
+      "step": 670
+    },
+    {
+      "epoch": 0.05504290108466893,
+      "grad_norm": 0.44895514845848083,
+      "learning_rate": 2e-05,
+      "loss": 0.7524,
+      "step": 680
+    },
+    {
+      "epoch": 0.055852355512384655,
+      "grad_norm": 2.016817569732666,
+      "learning_rate": 2e-05,
+      "loss": 0.794,
+      "step": 690
+    },
+    {
+      "epoch": 0.05666180994010037,
+      "grad_norm": 0.48561564087867737,
+      "learning_rate": 2e-05,
+      "loss": 0.7787,
+      "step": 700
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.4898475408554077,
+      "learning_rate": 2e-05,
+      "loss": 0.7653,
+      "step": 710
+    },
+    {
+      "epoch": 0.05828071879553181,
+      "grad_norm": 0.46037253737449646,
+      "learning_rate": 2e-05,
+      "loss": 0.7313,
+      "step": 720
+    },
+    {
+      "epoch": 0.059090173223247534,
+      "grad_norm": 0.5363634824752808,
+      "learning_rate": 2e-05,
+      "loss": 0.7856,
+      "step": 730
+    },
+    {
+      "epoch": 0.05989962765096325,
+      "grad_norm": 0.5166125297546387,
+      "learning_rate": 2e-05,
+      "loss": 0.7452,
+      "step": 740
+    },
+    {
+      "epoch": 0.06070908207867897,
+      "grad_norm": 0.49302196502685547,
+      "learning_rate": 2e-05,
+      "loss": 0.7794,
+      "step": 750
+    },
+    {
+      "epoch": 0.06151853650639469,
+      "grad_norm": 0.46284180879592896,
+      "learning_rate": 2e-05,
+      "loss": 0.7756,
+      "step": 760
+    },
+    {
+      "epoch": 0.06232799093411041,
+      "grad_norm": 0.7627009749412537,
+      "learning_rate": 2e-05,
+      "loss": 0.8394,
+      "step": 770
+    },
+    {
+      "epoch": 0.06313744536182612,
+      "grad_norm": 0.4596160352230072,
+      "learning_rate": 2e-05,
+      "loss": 0.7943,
+      "step": 780
+    },
+    {
+      "epoch": 0.06394689978954185,
+      "grad_norm": 0.5382130742073059,
+      "learning_rate": 2e-05,
+      "loss": 0.8123,
+      "step": 790
+    },
+    {
+      "epoch": 0.06475635421725758,
+      "grad_norm": 0.508547842502594,
+      "learning_rate": 2e-05,
+      "loss": 0.8342,
+      "step": 800
+    },
+    {
+      "epoch": 0.06556580864497329,
+      "grad_norm": 0.45580655336380005,
+      "learning_rate": 2e-05,
+      "loss": 0.7421,
+      "step": 810
+    },
+    {
+      "epoch": 0.06637526307268901,
+      "grad_norm": 0.5044952034950256,
+      "learning_rate": 2e-05,
+      "loss": 0.7962,
+      "step": 820
+    },
+    {
+      "epoch": 0.06718471750040472,
+      "grad_norm": 0.5014200806617737,
+      "learning_rate": 2e-05,
+      "loss": 0.7479,
+      "step": 830
+    },
+    {
+      "epoch": 0.06799417192812045,
+      "grad_norm": 0.4626830220222473,
+      "learning_rate": 2e-05,
+      "loss": 0.7486,
+      "step": 840
+    },
+    {
+      "epoch": 0.06880362635583617,
+      "grad_norm": 0.43822088837623596,
+      "learning_rate": 2e-05,
+      "loss": 0.76,
+      "step": 850
+    },
+    {
+      "epoch": 0.06961308078355188,
+      "grad_norm": 0.46575048565864563,
+      "learning_rate": 2e-05,
+      "loss": 0.7635,
+      "step": 860
+    },
+    {
+      "epoch": 0.07042253521126761,
+      "grad_norm": 0.5015127062797546,
+      "learning_rate": 2e-05,
+      "loss": 0.7438,
+      "step": 870
+    },
+    {
+      "epoch": 0.07123198963898332,
+      "grad_norm": 0.44600915908813477,
+      "learning_rate": 2e-05,
+      "loss": 0.7707,
+      "step": 880
+    },
+    {
+      "epoch": 0.07204144406669905,
+      "grad_norm": 0.46959471702575684,
+      "learning_rate": 2e-05,
+      "loss": 0.7495,
+      "step": 890
+    },
+    {
+      "epoch": 0.07285089849441477,
+      "grad_norm": 0.48399248719215393,
+      "learning_rate": 2e-05,
+      "loss": 0.7553,
+      "step": 900
+    },
+    {
+      "epoch": 0.07366035292213048,
+      "grad_norm": 0.4153420925140381,
+      "learning_rate": 2e-05,
+      "loss": 0.7662,
+      "step": 910
+    },
+    {
+      "epoch": 0.0744698073498462,
+      "grad_norm": 0.5788819789886475,
+      "learning_rate": 2e-05,
+      "loss": 0.7823,
+      "step": 920
+    },
+    {
+      "epoch": 0.07527926177756192,
+      "grad_norm": 0.4399629831314087,
+      "learning_rate": 2e-05,
+      "loss": 0.7719,
+      "step": 930
+    },
+    {
+      "epoch": 0.07608871620527764,
+      "grad_norm": 0.5023682713508606,
+      "learning_rate": 2e-05,
+      "loss": 0.7904,
+      "step": 940
+    },
+    {
+      "epoch": 0.07689817063299337,
+      "grad_norm": 0.47167086601257324,
+      "learning_rate": 2e-05,
+      "loss": 0.75,
+      "step": 950
+    },
+    {
+      "epoch": 0.07770762506070908,
+      "grad_norm": 0.5453641414642334,
+      "learning_rate": 2e-05,
+      "loss": 0.815,
+      "step": 960
+    },
+    {
+      "epoch": 0.0785170794884248,
+      "grad_norm": 0.48484450578689575,
+      "learning_rate": 2e-05,
+      "loss": 0.7443,
+      "step": 970
+    },
+    {
+      "epoch": 0.07932653391614052,
+      "grad_norm": 0.47146138548851013,
+      "learning_rate": 2e-05,
+      "loss": 0.7976,
+      "step": 980
+    },
+    {
+      "epoch": 0.08013598834385624,
+      "grad_norm": 0.4631673991680145,
+      "learning_rate": 2e-05,
+      "loss": 0.7802,
+      "step": 990
+    },
+    {
+      "epoch": 0.08094544277157197,
+      "grad_norm": 0.6332235336303711,
+      "learning_rate": 2e-05,
+      "loss": 0.7254,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08175489719928768,
+      "grad_norm": 0.5243743062019348,
+      "learning_rate": 2e-05,
+      "loss": 0.7638,
+      "step": 1010
+    },
+    {
+      "epoch": 0.0825643516270034,
+      "grad_norm": 0.4702272117137909,
+      "learning_rate": 2e-05,
+      "loss": 0.7951,
+      "step": 1020
+    },
+    {
+      "epoch": 0.08337380605471911,
+      "grad_norm": 0.7140534520149231,
+      "learning_rate": 2e-05,
+      "loss": 0.7971,
+      "step": 1030
+    },
+    {
+      "epoch": 0.08418326048243484,
+      "grad_norm": 0.6146261096000671,
+      "learning_rate": 2e-05,
+      "loss": 0.801,
+      "step": 1040
+    },
+    {
+      "epoch": 0.08499271491015056,
+      "grad_norm": 0.5314843058586121,
+      "learning_rate": 2e-05,
+      "loss": 0.7556,
+      "step": 1050
+    },
+    {
+      "epoch": 0.08580216933786627,
+      "grad_norm": 0.538650631904602,
+      "learning_rate": 2e-05,
+      "loss": 0.7422,
+      "step": 1060
+    },
+    {
+      "epoch": 0.086611623765582,
+      "grad_norm": 0.4428916275501251,
+      "learning_rate": 2e-05,
+      "loss": 0.7636,
+      "step": 1070
+    },
+    {
+      "epoch": 0.08742107819329771,
+      "grad_norm": 0.42931386828422546,
+      "learning_rate": 2e-05,
+      "loss": 0.7472,
+      "step": 1080
+    },
+    {
+      "epoch": 0.08823053262101344,
+      "grad_norm": 0.43152469396591187,
+      "learning_rate": 2e-05,
+      "loss": 0.7589,
+      "step": 1090
+    },
+    {
+      "epoch": 0.08903998704872916,
+      "grad_norm": 0.44176748394966125,
+      "learning_rate": 2e-05,
+      "loss": 0.7469,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08984944147644487,
+      "grad_norm": 0.47536471486091614,
+      "learning_rate": 2e-05,
+      "loss": 0.7772,
+      "step": 1110
+    },
+    {
+      "epoch": 0.0906588959041606,
+      "grad_norm": 1.264855146408081,
+      "learning_rate": 2e-05,
+      "loss": 0.8112,
+      "step": 1120
+    },
+    {
+      "epoch": 0.09146835033187632,
+      "grad_norm": 0.45444777607917786,
+      "learning_rate": 2e-05,
+      "loss": 0.7205,
+      "step": 1130
+    },
+    {
+      "epoch": 0.09227780475959203,
+      "grad_norm": 1.26339590549469,
+      "learning_rate": 2e-05,
+      "loss": 0.7768,
+      "step": 1140
+    },
+    {
+      "epoch": 0.09308725918730776,
+      "grad_norm": 0.4771409332752228,
+      "learning_rate": 2e-05,
+      "loss": 0.7225,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09389671361502347,
+      "grad_norm": 0.4884716868400574,
+      "learning_rate": 2e-05,
+      "loss": 0.8224,
+      "step": 1160
+    },
+    {
+      "epoch": 0.0947061680427392,
+      "grad_norm": 0.4324626922607422,
+      "learning_rate": 2e-05,
+      "loss": 0.7114,
+      "step": 1170
+    },
+    {
+      "epoch": 0.09551562247045492,
+      "grad_norm": 0.43965938687324524,
+      "learning_rate": 2e-05,
+      "loss": 0.7421,
+      "step": 1180
+    },
+    {
+      "epoch": 0.09632507689817063,
+      "grad_norm": 0.4681050181388855,
+      "learning_rate": 2e-05,
+      "loss": 0.7498,
+      "step": 1190
+    },
+    {
+      "epoch": 0.09713453132588636,
+      "grad_norm": 0.467864990234375,
+      "learning_rate": 2e-05,
+      "loss": 0.7312,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09794398575360207,
+      "grad_norm": 0.5152101516723633,
+      "learning_rate": 2e-05,
+      "loss": 0.7203,
+      "step": 1210
+    },
+    {
+      "epoch": 0.09875344018131779,
+      "grad_norm": 0.4910126030445099,
+      "learning_rate": 2e-05,
+      "loss": 0.7758,
+      "step": 1220
+    },
+    {
+      "epoch": 0.09956289460903352,
+      "grad_norm": 0.4851621091365814,
+      "learning_rate": 2e-05,
+      "loss": 0.7441,
+      "step": 1230
+    },
+    {
+      "epoch": 0.10037234903674923,
+      "grad_norm": 0.5710118412971497,
+      "learning_rate": 2e-05,
+      "loss": 0.7633,
+      "step": 1240
+    },
+    {
+      "epoch": 0.10118180346446495,
+      "grad_norm": 0.46566280722618103,
+      "learning_rate": 2e-05,
+      "loss": 0.7502,
+      "step": 1250
+    },
+    {
+      "epoch": 0.10199125789218066,
+      "grad_norm": 0.4801681339740753,
+      "learning_rate": 2e-05,
+      "loss": 0.7888,
+      "step": 1260
+    },
+    {
+      "epoch": 0.10280071231989639,
+      "grad_norm": 0.4482283592224121,
+      "learning_rate": 2e-05,
+      "loss": 0.804,
+      "step": 1270
+    },
+    {
+      "epoch": 0.10361016674761211,
+      "grad_norm": 0.469234824180603,
+      "learning_rate": 2e-05,
+      "loss": 0.8012,
+      "step": 1280
+    },
+    {
+      "epoch": 0.10441962117532783,
+      "grad_norm": 0.4327784776687622,
+      "learning_rate": 2e-05,
+      "loss": 0.7738,
+      "step": 1290
+    },
+    {
+      "epoch": 0.10522907560304355,
+      "grad_norm": 0.43423494696617126,
+      "learning_rate": 2e-05,
+      "loss": 0.8743,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10603853003075926,
+      "grad_norm": 0.5133379101753235,
+      "learning_rate": 2e-05,
+      "loss": 0.7578,
+      "step": 1310
+    },
+    {
+      "epoch": 0.10684798445847499,
+      "grad_norm": 0.4603078067302704,
+      "learning_rate": 2e-05,
+      "loss": 0.824,
+      "step": 1320
+    },
+    {
+      "epoch": 0.10765743888619071,
+      "grad_norm": 0.4119458496570587,
+      "learning_rate": 2e-05,
+      "loss": 0.7907,
+      "step": 1330
+    },
+    {
+      "epoch": 0.10846689331390642,
+      "grad_norm": 0.5244287848472595,
+      "learning_rate": 2e-05,
+      "loss": 0.7364,
+      "step": 1340
+    },
+    {
+      "epoch": 0.10927634774162215,
+      "grad_norm": 0.6392405033111572,
+      "learning_rate": 2e-05,
+      "loss": 0.7386,
+      "step": 1350
+    },
+    {
+      "epoch": 0.11008580216933786,
+      "grad_norm": 0.47154614329338074,
+      "learning_rate": 2e-05,
+      "loss": 0.7523,
+      "step": 1360
+    },
+    {
+      "epoch": 0.11089525659705358,
+      "grad_norm": 1.028759479522705,
+      "learning_rate": 2e-05,
+      "loss": 0.7638,
+      "step": 1370
+    },
+    {
+      "epoch": 0.11170471102476931,
+      "grad_norm": 0.49940794706344604,
+      "learning_rate": 2e-05,
+      "loss": 0.7399,
+      "step": 1380
+    },
+    {
+      "epoch": 0.11251416545248502,
+      "grad_norm": 0.46295166015625,
+      "learning_rate": 2e-05,
+      "loss": 0.7601,
+      "step": 1390
+    },
+    {
+      "epoch": 0.11332361988020075,
+      "grad_norm": 0.4681835472583771,
+      "learning_rate": 2e-05,
+      "loss": 0.7557,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11413307430791647,
+      "grad_norm": 0.445651650428772,
+      "learning_rate": 2e-05,
+      "loss": 0.7029,
+      "step": 1410
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.49928438663482666,
+      "learning_rate": 2e-05,
+      "loss": 0.7366,
+      "step": 1420
+    },
+    {
+      "epoch": 0.11575198316334791,
+      "grad_norm": 0.4365691542625427,
+      "learning_rate": 2e-05,
+      "loss": 0.7487,
+      "step": 1430
+    },
+    {
+      "epoch": 0.11656143759106362,
+      "grad_norm": 0.42280900478363037,
+      "learning_rate": 2e-05,
+      "loss": 0.7403,
+      "step": 1440
+    },
+    {
+      "epoch": 0.11737089201877934,
+      "grad_norm": 0.42231833934783936,
+      "learning_rate": 2e-05,
+      "loss": 0.7484,
+      "step": 1450
+    },
+    {
+      "epoch": 0.11818034644649507,
+      "grad_norm": 0.47429877519607544,
+      "learning_rate": 2e-05,
+      "loss": 0.769,
+      "step": 1460
+    },
+    {
+      "epoch": 0.11898980087421078,
+      "grad_norm": 0.4231085777282715,
+      "learning_rate": 2e-05,
+      "loss": 0.8055,
+      "step": 1470
+    },
+    {
+      "epoch": 0.1197992553019265,
+      "grad_norm": 0.4662066400051117,
+      "learning_rate": 2e-05,
+      "loss": 0.757,
+      "step": 1480
+    },
+    {
+      "epoch": 0.12060870972964222,
+      "grad_norm": 0.42176687717437744,
+      "learning_rate": 2e-05,
+      "loss": 0.7639,
+      "step": 1490
+    },
+    {
+      "epoch": 0.12141816415735794,
+      "grad_norm": 0.42362654209136963,
+      "learning_rate": 2e-05,
+      "loss": 0.7801,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12222761858507367,
+      "grad_norm": 0.45252448320388794,
+      "learning_rate": 2e-05,
+      "loss": 0.8053,
+      "step": 1510
+    },
+    {
+      "epoch": 0.12303707301278938,
+      "grad_norm": 0.41214272379875183,
+      "learning_rate": 2e-05,
+      "loss": 0.7781,
+      "step": 1520
+    },
+    {
+      "epoch": 0.1238465274405051,
+      "grad_norm": 0.5552160739898682,
+      "learning_rate": 2e-05,
+      "loss": 0.7838,
+      "step": 1530
+    },
+    {
+      "epoch": 0.12465598186822081,
+      "grad_norm": 0.48546385765075684,
+      "learning_rate": 2e-05,
+      "loss": 0.746,
+      "step": 1540
+    },
+    {
+      "epoch": 0.12546543629593654,
+      "grad_norm": 0.5322508215904236,
+      "learning_rate": 2e-05,
+      "loss": 0.7759,
+      "step": 1550
+    },
+    {
+      "epoch": 0.12627489072365225,
+      "grad_norm": 0.4386695325374603,
+      "learning_rate": 2e-05,
+      "loss": 0.7285,
+      "step": 1560
+    },
+    {
+      "epoch": 0.127084345151368,
+      "grad_norm": 0.46420738101005554,
+      "learning_rate": 2e-05,
+      "loss": 0.7126,
+      "step": 1570
+    },
+    {
+      "epoch": 0.1278937995790837,
+      "grad_norm": 0.41287338733673096,
+      "learning_rate": 2e-05,
+      "loss": 0.7325,
+      "step": 1580
+    },
+    {
+      "epoch": 0.1287032540067994,
+      "grad_norm": 0.45373618602752686,
+      "learning_rate": 2e-05,
+      "loss": 0.7364,
+      "step": 1590
+    },
+    {
+      "epoch": 0.12951270843451515,
+      "grad_norm": 0.4711339771747589,
+      "learning_rate": 2e-05,
+      "loss": 0.7457,
+      "step": 1600
+    },
+    {
+      "epoch": 0.13032216286223086,
+      "grad_norm": 0.4376307725906372,
+      "learning_rate": 2e-05,
+      "loss": 0.8464,
+      "step": 1610
+    },
+    {
+      "epoch": 0.13113161728994657,
+      "grad_norm": 0.4227166175842285,
+      "learning_rate": 2e-05,
+      "loss": 0.7383,
+      "step": 1620
+    },
+    {
+      "epoch": 0.13194107171766228,
+      "grad_norm": 0.5024327039718628,
+      "learning_rate": 2e-05,
+      "loss": 0.7722,
+      "step": 1630
+    },
+    {
+      "epoch": 0.13275052614537802,
+      "grad_norm": 0.511847198009491,
+      "learning_rate": 2e-05,
+      "loss": 0.7613,
+      "step": 1640
+    },
+    {
+      "epoch": 0.13355998057309373,
+      "grad_norm": 0.4578017592430115,
+      "learning_rate": 2e-05,
+      "loss": 0.7595,
+      "step": 1650
+    },
+    {
+      "epoch": 0.13436943500080945,
+      "grad_norm": 0.5495266318321228,
+      "learning_rate": 2e-05,
+      "loss": 0.7524,
+      "step": 1660
+    },
+    {
+      "epoch": 0.13517888942852518,
+      "grad_norm": 0.4338504374027252,
+      "learning_rate": 2e-05,
+      "loss": 0.7777,
+      "step": 1670
+    },
+    {
+      "epoch": 0.1359883438562409,
+      "grad_norm": 0.4964742660522461,
+      "learning_rate": 2e-05,
+      "loss": 0.7457,
+      "step": 1680
+    },
+    {
+      "epoch": 0.1367977982839566,
+      "grad_norm": 0.45121821761131287,
+      "learning_rate": 2e-05,
+      "loss": 0.6842,
+      "step": 1690
+    },
+    {
+      "epoch": 0.13760725271167235,
+      "grad_norm": 0.4793744683265686,
+      "learning_rate": 2e-05,
+      "loss": 0.7367,
+      "step": 1700
+    },
+    {
+      "epoch": 0.13841670713938806,
+      "grad_norm": 0.4436648190021515,
+      "learning_rate": 2e-05,
+      "loss": 0.7575,
+      "step": 1710
+    },
+    {
+      "epoch": 0.13922616156710377,
+      "grad_norm": 0.4348134696483612,
+      "learning_rate": 2e-05,
+      "loss": 0.7508,
+      "step": 1720
+    },
+    {
+      "epoch": 0.14003561599481948,
+      "grad_norm": 0.4088887870311737,
+      "learning_rate": 2e-05,
+      "loss": 0.7659,
+      "step": 1730
+    },
+    {
+      "epoch": 0.14084507042253522,
+      "grad_norm": 0.44128718972206116,
+      "learning_rate": 2e-05,
+      "loss": 0.6901,
+      "step": 1740
+    },
+    {
+      "epoch": 0.14165452485025093,
+      "grad_norm": 0.43519139289855957,
+      "learning_rate": 2e-05,
+      "loss": 0.7033,
+      "step": 1750
+    },
+    {
+      "epoch": 0.14246397927796664,
+      "grad_norm": 0.44742947816848755,
+      "learning_rate": 2e-05,
+      "loss": 0.7604,
+      "step": 1760
+    },
+    {
+      "epoch": 0.14327343370568238,
+      "grad_norm": 0.4164932370185852,
+      "learning_rate": 2e-05,
+      "loss": 0.728,
+      "step": 1770
+    },
+    {
+      "epoch": 0.1440828881333981,
+      "grad_norm": 0.4277600049972534,
+      "learning_rate": 2e-05,
+      "loss": 0.7303,
+      "step": 1780
+    },
+    {
+      "epoch": 0.1448923425611138,
+      "grad_norm": 0.4718596935272217,
+      "learning_rate": 2e-05,
+      "loss": 0.7068,
+      "step": 1790
+    },
+    {
+      "epoch": 0.14570179698882954,
+      "grad_norm": 0.5774624943733215,
+      "learning_rate": 2e-05,
+      "loss": 0.7345,
+      "step": 1800
+    },
+    {
+      "epoch": 0.14651125141654525,
+      "grad_norm": 0.49676021933555603,
+      "learning_rate": 2e-05,
+      "loss": 0.7422,
+      "step": 1810
+    },
+    {
+      "epoch": 0.14732070584426096,
+      "grad_norm": 0.5230264067649841,
+      "learning_rate": 2e-05,
+      "loss": 0.7131,
+      "step": 1820
+    },
+    {
+      "epoch": 0.14813016027197667,
+      "grad_norm": 0.48116421699523926,
+      "learning_rate": 2e-05,
+      "loss": 0.7346,
+      "step": 1830
+    },
+    {
+      "epoch": 0.1489396146996924,
+      "grad_norm": 0.49445751309394836,
+      "learning_rate": 2e-05,
+      "loss": 0.749,
+      "step": 1840
+    },
+    {
+      "epoch": 0.14974906912740812,
+      "grad_norm": 0.4187740385532379,
+      "learning_rate": 2e-05,
+      "loss": 0.7537,
+      "step": 1850
+    },
+    {
+      "epoch": 0.15055852355512384,
+      "grad_norm": 0.43644264340400696,
+      "learning_rate": 2e-05,
+      "loss": 0.7574,
+      "step": 1860
+    },
+    {
+      "epoch": 0.15136797798283957,
+      "grad_norm": 0.45833197236061096,
+      "learning_rate": 2e-05,
+      "loss": 0.7706,
+      "step": 1870
+    },
+    {
+      "epoch": 0.15217743241055529,
+      "grad_norm": 0.46808063983917236,
+      "learning_rate": 2e-05,
+      "loss": 0.7368,
+      "step": 1880
+    },
+    {
+      "epoch": 0.152986886838271,
+      "grad_norm": 0.4546162188053131,
+      "learning_rate": 2e-05,
+      "loss": 0.7805,
+      "step": 1890
+    },
+    {
+      "epoch": 0.15379634126598674,
+      "grad_norm": 0.46581682562828064,
+      "learning_rate": 2e-05,
+      "loss": 0.7036,
+      "step": 1900
+    },
+    {
+      "epoch": 0.15460579569370245,
+      "grad_norm": 0.5166182518005371,
+      "learning_rate": 2e-05,
+      "loss": 0.7134,
+      "step": 1910
+    },
+    {
+      "epoch": 0.15541525012141816,
+      "grad_norm": 0.4229692220687866,
+      "learning_rate": 2e-05,
+      "loss": 0.7186,
+      "step": 1920
+    },
+    {
+      "epoch": 0.1562247045491339,
+      "grad_norm": 0.43001192808151245,
+      "learning_rate": 2e-05,
+      "loss": 0.7249,
+      "step": 1930
+    },
+    {
+      "epoch": 0.1570341589768496,
+      "grad_norm": 0.632479190826416,
+      "learning_rate": 2e-05,
+      "loss": 0.7181,
+      "step": 1940
+    },
+    {
+      "epoch": 0.15784361340456532,
+      "grad_norm": 0.38017889857292175,
+      "learning_rate": 2e-05,
+      "loss": 0.7245,
+      "step": 1950
+    },
+    {
+      "epoch": 0.15865306783228103,
+      "grad_norm": 0.995253324508667,
+      "learning_rate": 2e-05,
+      "loss": 0.7226,
+      "step": 1960
+    },
+    {
+      "epoch": 0.15946252225999677,
+      "grad_norm": 0.4979926645755768,
+      "learning_rate": 2e-05,
+      "loss": 0.7349,
+      "step": 1970
+    },
+    {
+      "epoch": 0.16027197668771248,
+      "grad_norm": 0.41947174072265625,
+      "learning_rate": 2e-05,
+      "loss": 0.7376,
+      "step": 1980
+    },
+    {
+      "epoch": 0.1610814311154282,
+      "grad_norm": 0.4291357398033142,
+      "learning_rate": 2e-05,
+      "loss": 0.7206,
+      "step": 1990
+    },
+    {
+      "epoch": 0.16189088554314393,
+      "grad_norm": 0.49654513597488403,
+      "learning_rate": 2e-05,
+      "loss": 0.7434,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16270033997085964,
+      "grad_norm": 0.43926090002059937,
+      "learning_rate": 2e-05,
+      "loss": 0.723,
+      "step": 2010
+    },
+    {
+      "epoch": 0.16350979439857535,
+      "grad_norm": 0.42181116342544556,
+      "learning_rate": 2e-05,
+      "loss": 0.7511,
+      "step": 2020
+    },
+    {
+      "epoch": 0.1643192488262911,
+      "grad_norm": 0.38657787442207336,
+      "learning_rate": 2e-05,
+      "loss": 0.8156,
+      "step": 2030
+    },
+    {
+      "epoch": 0.1651287032540068,
+      "grad_norm": 0.5168091058731079,
+      "learning_rate": 2e-05,
+      "loss": 0.7882,
+      "step": 2040
+    },
+    {
+      "epoch": 0.16593815768172251,
+      "grad_norm": 0.46282458305358887,
+      "learning_rate": 2e-05,
+      "loss": 0.7269,
+      "step": 2050
+    },
+    {
+      "epoch": 0.16674761210943823,
+      "grad_norm": 0.4763840436935425,
+      "learning_rate": 2e-05,
+      "loss": 0.7288,
+      "step": 2060
+    },
+    {
+      "epoch": 0.16755706653715396,
+      "grad_norm": 0.5941051840782166,
+      "learning_rate": 2e-05,
+      "loss": 0.7375,
+      "step": 2070
+    },
+    {
+      "epoch": 0.16836652096486968,
+      "grad_norm": 0.447085976600647,
+      "learning_rate": 2e-05,
+      "loss": 0.7436,
+      "step": 2080
+    },
+    {
+      "epoch": 0.1691759753925854,
+      "grad_norm": 0.4851274788379669,
+      "learning_rate": 2e-05,
+      "loss": 0.7253,
+      "step": 2090
+    },
+    {
+      "epoch": 0.16998542982030113,
+      "grad_norm": 0.46441686153411865,
+      "learning_rate": 2e-05,
+      "loss": 0.7251,
+      "step": 2100
+    },
+    {
+      "epoch": 0.17079488424801684,
+      "grad_norm": 0.464144229888916,
+      "learning_rate": 2e-05,
+      "loss": 0.7528,
+      "step": 2110
+    },
+    {
+      "epoch": 0.17160433867573255,
+      "grad_norm": 0.5921929478645325,
+      "learning_rate": 2e-05,
+      "loss": 0.7548,
+      "step": 2120
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.4341529607772827,
+      "learning_rate": 2e-05,
+      "loss": 0.7464,
+      "step": 2130
+    },
+    {
+      "epoch": 0.173223247531164,
+      "grad_norm": 0.42261070013046265,
+      "learning_rate": 2e-05,
+      "loss": 0.7216,
+      "step": 2140
+    },
+    {
+      "epoch": 0.1740327019588797,
+      "grad_norm": 0.6212247610092163,
+      "learning_rate": 2e-05,
+      "loss": 0.7282,
+      "step": 2150
+    },
+    {
+      "epoch": 0.17484215638659542,
+      "grad_norm": 0.4890407919883728,
+      "learning_rate": 2e-05,
+      "loss": 0.7025,
+      "step": 2160
+    },
+    {
+      "epoch": 0.17565161081431116,
+      "grad_norm": 0.4194985032081604,
+      "learning_rate": 2e-05,
+      "loss": 0.7085,
+      "step": 2170
+    },
+    {
+      "epoch": 0.17646106524202687,
+      "grad_norm": 0.5223554372787476,
+      "learning_rate": 2e-05,
+      "loss": 0.7265,
+      "step": 2180
+    },
+    {
+      "epoch": 0.17727051966974258,
+      "grad_norm": 0.4059622287750244,
+      "learning_rate": 2e-05,
+      "loss": 0.7225,
+      "step": 2190
+    },
+    {
+      "epoch": 0.17807997409745832,
+      "grad_norm": 0.4829890727996826,
+      "learning_rate": 2e-05,
+      "loss": 0.7205,
+      "step": 2200
+    },
+    {
+      "epoch": 0.17888942852517403,
+      "grad_norm": 0.5763494968414307,
+      "learning_rate": 2e-05,
+      "loss": 0.7415,
+      "step": 2210
+    },
+    {
+      "epoch": 0.17969888295288974,
+      "grad_norm": 0.45062094926834106,
+      "learning_rate": 2e-05,
+      "loss": 0.7562,
+      "step": 2220
+    },
+    {
+      "epoch": 0.18050833738060548,
+      "grad_norm": 0.48508694767951965,
+      "learning_rate": 2e-05,
+      "loss": 0.732,
+      "step": 2230
+    },
+    {
+      "epoch": 0.1813177918083212,
+      "grad_norm": 0.4222659170627594,
+      "learning_rate": 2e-05,
+      "loss": 0.6896,
+      "step": 2240
+    },
+    {
+      "epoch": 0.1821272462360369,
+      "grad_norm": 0.4189082682132721,
+      "learning_rate": 2e-05,
+      "loss": 0.7105,
+      "step": 2250
+    },
+    {
+      "epoch": 0.18293670066375264,
+      "grad_norm": 0.44298243522644043,
+      "learning_rate": 2e-05,
+      "loss": 0.6771,
+      "step": 2260
+    },
+    {
+      "epoch": 0.18374615509146836,
+      "grad_norm": 0.47490832209587097,
+      "learning_rate": 2e-05,
+      "loss": 0.7941,
+      "step": 2270
+    },
+    {
+      "epoch": 0.18455560951918407,
+      "grad_norm": 0.48890191316604614,
+      "learning_rate": 2e-05,
+      "loss": 0.7463,
+      "step": 2280
+    },
+    {
+      "epoch": 0.18536506394689978,
+      "grad_norm": 0.5026359558105469,
+      "learning_rate": 2e-05,
+      "loss": 0.7041,
+      "step": 2290
+    },
+    {
+      "epoch": 0.18617451837461552,
+      "grad_norm": 0.47705215215682983,
+      "learning_rate": 2e-05,
+      "loss": 0.7326,
+      "step": 2300
+    },
+    {
+      "epoch": 0.18698397280233123,
+      "grad_norm": 0.47245997190475464,
+      "learning_rate": 2e-05,
+      "loss": 0.7243,
+      "step": 2310
+    },
+    {
+      "epoch": 0.18779342723004694,
+      "grad_norm": 0.44321408867836,
+      "learning_rate": 2e-05,
+      "loss": 0.7706,
+      "step": 2320
+    },
+    {
+      "epoch": 0.18860288165776268,
+      "grad_norm": 0.7248201966285706,
+      "learning_rate": 2e-05,
+      "loss": 0.7138,
+      "step": 2330
+    },
+    {
+      "epoch": 0.1894123360854784,
+      "grad_norm": 0.5578175187110901,
+      "learning_rate": 2e-05,
+      "loss": 0.7876,
+      "step": 2340
+    },
+    {
+      "epoch": 0.1902217905131941,
+      "grad_norm": 0.4405210614204407,
+      "learning_rate": 2e-05,
+      "loss": 0.7364,
+      "step": 2350
+    },
+    {
+      "epoch": 0.19103124494090984,
+      "grad_norm": 0.43062642216682434,
+      "learning_rate": 2e-05,
+      "loss": 0.7445,
+      "step": 2360
+    },
+    {
+      "epoch": 0.19184069936862555,
+      "grad_norm": 0.4260861575603485,
+      "learning_rate": 2e-05,
+      "loss": 0.6936,
+      "step": 2370
+    },
+    {
+      "epoch": 0.19265015379634126,
+      "grad_norm": 0.5034523606300354,
+      "learning_rate": 2e-05,
+      "loss": 0.7381,
+      "step": 2380
+    },
+    {
+      "epoch": 0.19345960822405697,
+      "grad_norm": 0.4679977595806122,
+      "learning_rate": 2e-05,
+      "loss": 0.8005,
+      "step": 2390
+    },
+    {
+      "epoch": 0.1942690626517727,
+      "grad_norm": 0.41857269406318665,
+      "learning_rate": 2e-05,
+      "loss": 0.8099,
+      "step": 2400
+    },
+    {
+      "epoch": 0.19507851707948842,
+      "grad_norm": 0.4574667811393738,
+      "learning_rate": 2e-05,
+      "loss": 0.7028,
+      "step": 2410
+    },
+    {
+      "epoch": 0.19588797150720413,
+      "grad_norm": 0.48357775807380676,
+      "learning_rate": 2e-05,
+      "loss": 0.6844,
+      "step": 2420
+    },
+    {
+      "epoch": 0.19669742593491987,
+      "grad_norm": 0.5094761848449707,
+      "learning_rate": 2e-05,
+      "loss": 0.7703,
+      "step": 2430
+    },
+    {
+      "epoch": 0.19750688036263558,
+      "grad_norm": 0.46051591634750366,
+      "learning_rate": 2e-05,
+      "loss": 0.7042,
+      "step": 2440
+    },
+    {
+      "epoch": 0.1983163347903513,
+      "grad_norm": 0.4417215883731842,
+      "learning_rate": 2e-05,
+      "loss": 0.7691,
+      "step": 2450
+    },
+    {
+      "epoch": 0.19912578921806703,
+      "grad_norm": 0.8022627830505371,
+      "learning_rate": 2e-05,
+      "loss": 0.7005,
+      "step": 2460
+    },
+    {
+      "epoch": 0.19993524364578275,
+      "grad_norm": 0.4908968210220337,
+      "learning_rate": 2e-05,
+      "loss": 0.7046,
+      "step": 2470
+    },
+    {
+      "epoch": 0.20074469807349846,
+      "grad_norm": 0.46133020520210266,
+      "learning_rate": 2e-05,
+      "loss": 0.6992,
+      "step": 2480
+    },
+    {
+      "epoch": 0.2015541525012142,
+      "grad_norm": 0.46527135372161865,
+      "learning_rate": 2e-05,
+      "loss": 0.772,
+      "step": 2490
+    },
+    {
+      "epoch": 0.2023636069289299,
+      "grad_norm": 0.5197440981864929,
+      "learning_rate": 2e-05,
+      "loss": 0.7482,
+      "step": 2500
+    },
+    {
+      "epoch": 0.20317306135664562,
+      "grad_norm": 0.45445793867111206,
+      "learning_rate": 2e-05,
+      "loss": 0.692,
+      "step": 2510
+    },
+    {
+      "epoch": 0.20398251578436133,
+      "grad_norm": 0.41100093722343445,
+      "learning_rate": 2e-05,
+      "loss": 0.747,
+      "step": 2520
+    },
+    {
+      "epoch": 0.20479197021207707,
+      "grad_norm": 0.45717301964759827,
+      "learning_rate": 2e-05,
+      "loss": 0.7046,
+      "step": 2530
+    },
+    {
+      "epoch": 0.20560142463979278,
+      "grad_norm": 0.47410184144973755,
+      "learning_rate": 2e-05,
+      "loss": 0.7498,
+      "step": 2540
+    },
+    {
+      "epoch": 0.2064108790675085,
+      "grad_norm": 0.4788081645965576,
+      "learning_rate": 2e-05,
+      "loss": 0.6538,
+      "step": 2550
+    },
+    {
+      "epoch": 0.20722033349522423,
+      "grad_norm": 0.46788862347602844,
+      "learning_rate": 2e-05,
+      "loss": 0.7533,
+      "step": 2560
+    },
+    {
+      "epoch": 0.20802978792293994,
+      "grad_norm": 0.5249082446098328,
+      "learning_rate": 2e-05,
+      "loss": 0.741,
+      "step": 2570
+    },
+    {
+      "epoch": 0.20883924235065565,
+      "grad_norm": 0.4899987578392029,
+      "learning_rate": 2e-05,
+      "loss": 0.7144,
+      "step": 2580
+    },
+    {
+      "epoch": 0.2096486967783714,
+      "grad_norm": 0.4946480095386505,
+      "learning_rate": 2e-05,
+      "loss": 0.7537,
+      "step": 2590
+    },
+    {
+      "epoch": 0.2104581512060871,
+      "grad_norm": 0.465324342250824,
+      "learning_rate": 2e-05,
+      "loss": 0.8197,
+      "step": 2600
+    },
+    {
+      "epoch": 0.2112676056338028,
+      "grad_norm": 0.5274069309234619,
+      "learning_rate": 2e-05,
+      "loss": 0.7237,
+      "step": 2610
+    },
+    {
+      "epoch": 0.21207706006151852,
+      "grad_norm": 0.8420001864433289,
+      "learning_rate": 2e-05,
+      "loss": 0.7391,
+      "step": 2620
+    },
+    {
+      "epoch": 0.21288651448923426,
+      "grad_norm": 0.387223482131958,
+      "learning_rate": 2e-05,
+      "loss": 0.6853,
+      "step": 2630
+    },
+    {
+      "epoch": 0.21369596891694997,
+      "grad_norm": 0.4945930540561676,
+      "learning_rate": 2e-05,
+      "loss": 0.668,
+      "step": 2640
+    },
+    {
+      "epoch": 0.21450542334466569,
+      "grad_norm": 0.5009126663208008,
+      "learning_rate": 2e-05,
+      "loss": 0.7398,
+      "step": 2650
+    },
+    {
+      "epoch": 0.21531487777238142,
+      "grad_norm": 0.4894900918006897,
+      "learning_rate": 2e-05,
+      "loss": 0.7638,
+      "step": 2660
+    },
+    {
+      "epoch": 0.21612433220009714,
+      "grad_norm": 0.428073912858963,
+      "learning_rate": 2e-05,
+      "loss": 0.7039,
+      "step": 2670
+    },
+    {
+      "epoch": 0.21693378662781285,
+      "grad_norm": 0.5131125450134277,
+      "learning_rate": 2e-05,
+      "loss": 0.7382,
+      "step": 2680
+    },
+    {
+      "epoch": 0.21774324105552859,
+      "grad_norm": 0.43352752923965454,
+      "learning_rate": 2e-05,
+      "loss": 0.7205,
+      "step": 2690
+    },
+    {
+      "epoch": 0.2185526954832443,
+      "grad_norm": 0.4441218078136444,
+      "learning_rate": 2e-05,
+      "loss": 0.7268,
+      "step": 2700
+    },
+    {
+      "epoch": 0.21936214991096,
+      "grad_norm": 0.4631691873073578,
+      "learning_rate": 2e-05,
+      "loss": 0.7342,
+      "step": 2710
+    },
+    {
+      "epoch": 0.22017160433867572,
+      "grad_norm": 0.4848051369190216,
+      "learning_rate": 2e-05,
+      "loss": 0.679,
+      "step": 2720
+    },
+    {
+      "epoch": 0.22098105876639146,
+      "grad_norm": 0.6282009482383728,
+      "learning_rate": 2e-05,
+      "loss": 0.7073,
+      "step": 2730
+    },
+    {
+      "epoch": 0.22179051319410717,
+      "grad_norm": 0.5711313486099243,
+      "learning_rate": 2e-05,
+      "loss": 0.72,
+      "step": 2740
+    },
+    {
+      "epoch": 0.22259996762182288,
+      "grad_norm": 0.4070909917354584,
+      "learning_rate": 2e-05,
+      "loss": 0.6875,
+      "step": 2750
+    },
+    {
+      "epoch": 0.22340942204953862,
+      "grad_norm": 0.4884268045425415,
+      "learning_rate": 2e-05,
+      "loss": 0.702,
+      "step": 2760
+    },
+    {
+      "epoch": 0.22421887647725433,
+      "grad_norm": 0.4249865710735321,
+      "learning_rate": 2e-05,
+      "loss": 0.7006,
+      "step": 2770
+    },
+    {
+      "epoch": 0.22502833090497004,
+      "grad_norm": 0.545239269733429,
+      "learning_rate": 2e-05,
+      "loss": 0.7256,
+      "step": 2780
+    },
+    {
+      "epoch": 0.22583778533268578,
+      "grad_norm": 0.48316675424575806,
+      "learning_rate": 2e-05,
+      "loss": 0.7262,
+      "step": 2790
+    },
+    {
+      "epoch": 0.2266472397604015,
+      "grad_norm": 0.3983636796474457,
+      "learning_rate": 2e-05,
+      "loss": 0.713,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2274566941881172,
+      "grad_norm": 0.44548025727272034,
+      "learning_rate": 2e-05,
+      "loss": 0.6556,
+      "step": 2810
+    },
+    {
+      "epoch": 0.22826614861583294,
+      "grad_norm": 0.45560216903686523,
+      "learning_rate": 2e-05,
+      "loss": 0.7183,
+      "step": 2820
+    },
+    {
+      "epoch": 0.22907560304354865,
+      "grad_norm": 0.46689340472221375,
+      "learning_rate": 2e-05,
+      "loss": 0.6921,
+      "step": 2830
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.4595479965209961,
+      "learning_rate": 2e-05,
+      "loss": 0.8193,
+      "step": 2840
+    },
+    {
+      "epoch": 0.23069451189898008,
+      "grad_norm": 0.455394983291626,
+      "learning_rate": 2e-05,
+      "loss": 0.7014,
+      "step": 2850
+    },
+    {
+      "epoch": 0.23150396632669581,
+      "grad_norm": 0.46580660343170166,
+      "learning_rate": 2e-05,
+      "loss": 0.7042,
+      "step": 2860
+    },
+    {
+      "epoch": 0.23231342075441153,
+      "grad_norm": 0.5154122114181519,
+      "learning_rate": 2e-05,
+      "loss": 0.7738,
+      "step": 2870
+    },
+    {
+      "epoch": 0.23312287518212724,
+      "grad_norm": 0.5446767807006836,
+      "learning_rate": 2e-05,
+      "loss": 0.8146,
+      "step": 2880
+    },
+    {
+      "epoch": 0.23393232960984298,
+      "grad_norm": 0.6093187928199768,
+      "learning_rate": 2e-05,
+      "loss": 0.7173,
+      "step": 2890
+    },
+    {
+      "epoch": 0.2347417840375587,
+      "grad_norm": 0.5807092785835266,
+      "learning_rate": 2e-05,
+      "loss": 0.6792,
+      "step": 2900
+    },
+    {
+      "epoch": 0.2355512384652744,
+      "grad_norm": 0.3840983510017395,
+      "learning_rate": 2e-05,
+      "loss": 0.7421,
+      "step": 2910
+    },
+    {
+      "epoch": 0.23636069289299014,
+      "grad_norm": 0.41512519121170044,
+      "learning_rate": 2e-05,
+      "loss": 0.8324,
+      "step": 2920
+    },
+    {
+      "epoch": 0.23717014732070585,
+      "grad_norm": 0.4607084095478058,
+      "learning_rate": 2e-05,
+      "loss": 0.7114,
+      "step": 2930
+    },
+    {
+      "epoch": 0.23797960174842156,
+      "grad_norm": 0.4260174036026001,
+      "learning_rate": 2e-05,
+      "loss": 0.705,
+      "step": 2940
+    },
+    {
+      "epoch": 0.23878905617613727,
+      "grad_norm": 0.45369887351989746,
+      "learning_rate": 2e-05,
+      "loss": 0.7353,
+      "step": 2950
+    },
+    {
+      "epoch": 0.239598510603853,
+      "grad_norm": 0.5064823627471924,
+      "learning_rate": 2e-05,
+      "loss": 0.6783,
+      "step": 2960
+    },
+    {
+      "epoch": 0.24040796503156872,
+      "grad_norm": 0.49162572622299194,
+      "learning_rate": 2e-05,
+      "loss": 0.714,
+      "step": 2970
+    },
+    {
+      "epoch": 0.24121741945928443,
+      "grad_norm": 0.49628496170043945,
+      "learning_rate": 2e-05,
+      "loss": 0.6903,
+      "step": 2980
+    },
+    {
+      "epoch": 0.24202687388700017,
+      "grad_norm": 0.4112568795681,
+      "learning_rate": 2e-05,
+      "loss": 0.6773,
+      "step": 2990
+    },
+    {
+      "epoch": 0.24283632831471588,
+      "grad_norm": 0.4564688503742218,
+      "learning_rate": 2e-05,
+      "loss": 0.7291,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2436457827424316,
+      "grad_norm": 0.47345349192619324,
+      "learning_rate": 2e-05,
+      "loss": 0.7009,
+      "step": 3010
+    },
+    {
+      "epoch": 0.24445523717014733,
+      "grad_norm": 0.43283340334892273,
+      "learning_rate": 2e-05,
+      "loss": 0.7812,
+      "step": 3020
+    },
+    {
+      "epoch": 0.24526469159786304,
+      "grad_norm": 0.4109693467617035,
+      "learning_rate": 2e-05,
+      "loss": 0.7006,
+      "step": 3030
+    },
+    {
+      "epoch": 0.24607414602557875,
+      "grad_norm": 0.4560668468475342,
+      "learning_rate": 2e-05,
+      "loss": 0.6869,
+      "step": 3040
+    },
+    {
+      "epoch": 0.24688360045329447,
+      "grad_norm": 0.4617603123188019,
+      "learning_rate": 2e-05,
+      "loss": 0.7343,
+      "step": 3050
+    },
+    {
+      "epoch": 0.2476930548810102,
+      "grad_norm": 0.4108160734176636,
+      "learning_rate": 2e-05,
+      "loss": 0.7218,
+      "step": 3060
+    },
+    {
+      "epoch": 0.24850250930872592,
+      "grad_norm": 0.45599716901779175,
+      "learning_rate": 2e-05,
+      "loss": 0.7609,
+      "step": 3070
+    },
+    {
+      "epoch": 0.24931196373644163,
+      "grad_norm": 0.46107056736946106,
+      "learning_rate": 2e-05,
+      "loss": 0.7566,
+      "step": 3080
+    },
+    {
+      "epoch": 0.25012141816415734,
+      "grad_norm": 0.4458453357219696,
+      "learning_rate": 2e-05,
+      "loss": 0.7072,
+      "step": 3090
+    },
+    {
+      "epoch": 0.2509308725918731,
+      "grad_norm": 0.46771135926246643,
+      "learning_rate": 2e-05,
+      "loss": 0.755,
+      "step": 3100
+    },
+    {
+      "epoch": 0.2517403270195888,
+      "grad_norm": 0.4939885139465332,
+      "learning_rate": 2e-05,
+      "loss": 0.7066,
+      "step": 3110
+    },
+    {
+      "epoch": 0.2525497814473045,
+      "grad_norm": 0.6678000688552856,
+      "learning_rate": 2e-05,
+      "loss": 0.6807,
+      "step": 3120
+    },
+    {
+      "epoch": 0.25335923587502024,
+      "grad_norm": 0.4881975054740906,
+      "learning_rate": 2e-05,
+      "loss": 0.7145,
+      "step": 3130
+    },
+    {
+      "epoch": 0.254168690302736,
+      "grad_norm": 0.5237253904342651,
+      "learning_rate": 2e-05,
+      "loss": 0.7363,
+      "step": 3140
+    },
+    {
+      "epoch": 0.25497814473045166,
+      "grad_norm": 0.48959338665008545,
+      "learning_rate": 2e-05,
+      "loss": 0.6873,
+      "step": 3150
+    },
+    {
+      "epoch": 0.2557875991581674,
+      "grad_norm": 0.5326708555221558,
+      "learning_rate": 2e-05,
+      "loss": 0.784,
+      "step": 3160
+    },
+    {
+      "epoch": 0.25659705358588314,
+      "grad_norm": 0.5291874408721924,
+      "learning_rate": 2e-05,
+      "loss": 0.7462,
+      "step": 3170
+    },
+    {
+      "epoch": 0.2574065080135988,
+      "grad_norm": 0.3957138657569885,
+      "learning_rate": 2e-05,
+      "loss": 0.7149,
+      "step": 3180
+    },
+    {
+      "epoch": 0.25821596244131456,
+      "grad_norm": 0.44915515184402466,
+      "learning_rate": 2e-05,
+      "loss": 0.6854,
+      "step": 3190
+    },
+    {
+      "epoch": 0.2590254168690303,
+      "grad_norm": 0.5247088670730591,
+      "learning_rate": 2e-05,
+      "loss": 0.6816,
+      "step": 3200
+    },
+    {
+      "epoch": 0.259834871296746,
+      "grad_norm": 0.4631572961807251,
+      "learning_rate": 2e-05,
+      "loss": 0.7783,
+      "step": 3210
+    },
+    {
+      "epoch": 0.2606443257244617,
+      "grad_norm": 0.4066582918167114,
+      "learning_rate": 2e-05,
+      "loss": 0.6402,
+      "step": 3220
+    },
+    {
+      "epoch": 0.2614537801521774,
+      "grad_norm": 0.49353843927383423,
+      "learning_rate": 2e-05,
+      "loss": 0.6712,
+      "step": 3230
+    },
+    {
+      "epoch": 0.26226323457989315,
+      "grad_norm": 0.48097503185272217,
+      "learning_rate": 2e-05,
+      "loss": 0.7242,
+      "step": 3240
+    },
+    {
+      "epoch": 0.2630726890076089,
+      "grad_norm": 0.4604363739490509,
+      "learning_rate": 2e-05,
+      "loss": 0.7386,
+      "step": 3250
+    },
+    {
+      "epoch": 0.26388214343532457,
+      "grad_norm": 0.5349531173706055,
+      "learning_rate": 2e-05,
+      "loss": 0.7752,
+      "step": 3260
+    },
+    {
+      "epoch": 0.2646915978630403,
+      "grad_norm": 0.45135924220085144,
+      "learning_rate": 2e-05,
+      "loss": 0.7965,
+      "step": 3270
+    },
+    {
+      "epoch": 0.26550105229075605,
+      "grad_norm": 0.515646755695343,
+      "learning_rate": 2e-05,
+      "loss": 0.744,
+      "step": 3280
+    },
+    {
+      "epoch": 0.26631050671847173,
+      "grad_norm": 0.5010042786598206,
+      "learning_rate": 2e-05,
+      "loss": 0.647,
+      "step": 3290
+    },
+    {
+      "epoch": 0.26711996114618747,
+      "grad_norm": 0.46902549266815186,
+      "learning_rate": 2e-05,
+      "loss": 0.7099,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2679294155739032,
+      "grad_norm": 0.46021324396133423,
+      "learning_rate": 2e-05,
+      "loss": 0.7004,
+      "step": 3310
+    },
+    {
+      "epoch": 0.2687388700016189,
+      "grad_norm": 0.44553154706954956,
+      "learning_rate": 2e-05,
+      "loss": 0.7162,
+      "step": 3320
+    },
+    {
+      "epoch": 0.26954832442933463,
+      "grad_norm": 0.43146756291389465,
+      "learning_rate": 2e-05,
+      "loss": 0.7416,
+      "step": 3330
+    },
+    {
+      "epoch": 0.27035777885705037,
+      "grad_norm": 0.4589480459690094,
+      "learning_rate": 2e-05,
+      "loss": 0.7093,
+      "step": 3340
+    },
+    {
+      "epoch": 0.27116723328476605,
+      "grad_norm": 0.43556371331214905,
+      "learning_rate": 2e-05,
+      "loss": 0.7463,
+      "step": 3350
+    },
+    {
+      "epoch": 0.2719766877124818,
+      "grad_norm": 0.4406108856201172,
+      "learning_rate": 2e-05,
+      "loss": 0.7009,
+      "step": 3360
+    },
+    {
+      "epoch": 0.27278614214019753,
+      "grad_norm": 0.4366849660873413,
+      "learning_rate": 2e-05,
+      "loss": 0.7427,
+      "step": 3370
+    },
+    {
+      "epoch": 0.2735955965679132,
+      "grad_norm": 0.46490341424942017,
+      "learning_rate": 2e-05,
+      "loss": 0.6833,
+      "step": 3380
+    },
+    {
+      "epoch": 0.27440505099562895,
+      "grad_norm": 0.42424312233924866,
+      "learning_rate": 2e-05,
+      "loss": 0.6811,
+      "step": 3390
+    },
+    {
+      "epoch": 0.2752145054233447,
+      "grad_norm": 0.48185995221138,
+      "learning_rate": 2e-05,
+      "loss": 0.6924,
+      "step": 3400
+    },
+    {
+      "epoch": 0.2760239598510604,
+      "grad_norm": 0.5333611965179443,
+      "learning_rate": 2e-05,
+      "loss": 0.7021,
+      "step": 3410
+    },
+    {
+      "epoch": 0.2768334142787761,
+      "grad_norm": 0.4085567891597748,
+      "learning_rate": 2e-05,
+      "loss": 0.644,
+      "step": 3420
+    },
+    {
+      "epoch": 0.27764286870649185,
+      "grad_norm": 0.48974353075027466,
+      "learning_rate": 2e-05,
+      "loss": 0.7131,
+      "step": 3430
+    },
+    {
+      "epoch": 0.27845232313420754,
+      "grad_norm": 0.48298534750938416,
+      "learning_rate": 2e-05,
+      "loss": 0.7078,
+      "step": 3440
+    },
+    {
+      "epoch": 0.2792617775619233,
+      "grad_norm": 0.4364076554775238,
+      "learning_rate": 2e-05,
+      "loss": 0.6997,
+      "step": 3450
+    },
+    {
+      "epoch": 0.28007123198963896,
+      "grad_norm": 0.4964418411254883,
+      "learning_rate": 2e-05,
+      "loss": 0.7281,
+      "step": 3460
+    },
+    {
+      "epoch": 0.2808806864173547,
+      "grad_norm": 0.4781351685523987,
+      "learning_rate": 2e-05,
+      "loss": 0.7491,
+      "step": 3470
+    },
+    {
+      "epoch": 0.28169014084507044,
+      "grad_norm": 0.44572120904922485,
+      "learning_rate": 2e-05,
+      "loss": 0.6948,
+      "step": 3480
+    },
+    {
+      "epoch": 0.2824995952727861,
+      "grad_norm": 0.446929931640625,
+      "learning_rate": 2e-05,
+      "loss": 0.7326,
+      "step": 3490
+    },
+    {
+      "epoch": 0.28330904970050186,
+      "grad_norm": 0.4871025085449219,
+      "learning_rate": 2e-05,
+      "loss": 0.7749,
+      "step": 3500
+    },
+    {
+      "epoch": 0.2841185041282176,
+      "grad_norm": 0.40288984775543213,
+      "learning_rate": 2e-05,
+      "loss": 0.6889,
+      "step": 3510
+    },
+    {
+      "epoch": 0.2849279585559333,
+      "grad_norm": 0.4722198247909546,
+      "learning_rate": 2e-05,
+      "loss": 0.7291,
+      "step": 3520
+    },
+    {
+      "epoch": 0.285737412983649,
+      "grad_norm": 0.44551727175712585,
+      "learning_rate": 2e-05,
+      "loss": 0.7462,
+      "step": 3530
+    },
+    {
+      "epoch": 0.28654686741136476,
+      "grad_norm": 0.4199100136756897,
+      "learning_rate": 2e-05,
+      "loss": 0.7499,
+      "step": 3540
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.4146755039691925,
+      "learning_rate": 2e-05,
+      "loss": 0.6747,
+      "step": 3550
+    },
+    {
+      "epoch": 0.2881657762667962,
+      "grad_norm": 0.5446410775184631,
+      "learning_rate": 2e-05,
+      "loss": 0.6709,
+      "step": 3560
+    },
+    {
+      "epoch": 0.2889752306945119,
+      "grad_norm": 0.4841379225254059,
+      "learning_rate": 2e-05,
+      "loss": 0.6236,
+      "step": 3570
+    },
+    {
+      "epoch": 0.2897846851222276,
+      "grad_norm": 0.42586493492126465,
+      "learning_rate": 2e-05,
+      "loss": 0.7772,
+      "step": 3580
+    },
+    {
+      "epoch": 0.29059413954994334,
+      "grad_norm": 0.469958633184433,
+      "learning_rate": 2e-05,
+      "loss": 0.7508,
+      "step": 3590
+    },
+    {
+      "epoch": 0.2914035939776591,
+      "grad_norm": 0.4327908158302307,
+      "learning_rate": 2e-05,
+      "loss": 0.748,
+      "step": 3600
+    },
+    {
+      "epoch": 0.29221304840537476,
+      "grad_norm": 0.4472779333591461,
+      "learning_rate": 2e-05,
+      "loss": 0.7131,
+      "step": 3610
+    },
+    {
+      "epoch": 0.2930225028330905,
+      "grad_norm": 0.6391100287437439,
+      "learning_rate": 2e-05,
+      "loss": 0.7075,
+      "step": 3620
+    },
+    {
+      "epoch": 0.29383195726080624,
+      "grad_norm": 0.47938913106918335,
+      "learning_rate": 2e-05,
+      "loss": 0.7446,
+      "step": 3630
+    },
+    {
+      "epoch": 0.2946414116885219,
+      "grad_norm": 0.4306207001209259,
+      "learning_rate": 2e-05,
+      "loss": 0.6811,
+      "step": 3640
+    },
+    {
+      "epoch": 0.29545086611623766,
+      "grad_norm": 0.5047845244407654,
+      "learning_rate": 2e-05,
+      "loss": 0.7344,
+      "step": 3650
+    },
+    {
+      "epoch": 0.29626032054395335,
+      "grad_norm": 0.3869243562221527,
+      "learning_rate": 2e-05,
+      "loss": 0.6937,
+      "step": 3660
+    },
+    {
+      "epoch": 0.2970697749716691,
+      "grad_norm": 0.4521953761577606,
+      "learning_rate": 2e-05,
+      "loss": 0.6846,
+      "step": 3670
+    },
+    {
+      "epoch": 0.2978792293993848,
+      "grad_norm": 0.44332656264305115,
+      "learning_rate": 2e-05,
+      "loss": 0.709,
+      "step": 3680
+    },
+    {
+      "epoch": 0.2986886838271005,
+      "grad_norm": 0.46174564957618713,
+      "learning_rate": 2e-05,
+      "loss": 0.683,
+      "step": 3690
+    },
+    {
+      "epoch": 0.29949813825481625,
+      "grad_norm": 0.5133185982704163,
+      "learning_rate": 2e-05,
+      "loss": 0.7001,
+      "step": 3700
+    },
+    {
+      "epoch": 0.300307592682532,
+      "grad_norm": 0.4167000353336334,
+      "learning_rate": 2e-05,
+      "loss": 0.6851,
+      "step": 3710
+    },
+    {
+      "epoch": 0.30111704711024767,
+      "grad_norm": 0.47097164392471313,
+      "learning_rate": 2e-05,
+      "loss": 0.6941,
+      "step": 3720
+    },
+    {
+      "epoch": 0.3019265015379634,
+      "grad_norm": 0.5172642469406128,
+      "learning_rate": 2e-05,
+      "loss": 0.7146,
+      "step": 3730
+    },
+    {
+      "epoch": 0.30273595596567915,
+      "grad_norm": 0.4969281256198883,
+      "learning_rate": 2e-05,
+      "loss": 0.717,
+      "step": 3740
+    },
+    {
+      "epoch": 0.30354541039339483,
+      "grad_norm": 0.43054044246673584,
+      "learning_rate": 2e-05,
+      "loss": 0.7446,
+      "step": 3750
+    },
+    {
+      "epoch": 0.30435486482111057,
+      "grad_norm": 0.44192495942115784,
+      "learning_rate": 2e-05,
+      "loss": 0.7149,
+      "step": 3760
+    },
+    {
+      "epoch": 0.3051643192488263,
+      "grad_norm": 0.4416216015815735,
+      "learning_rate": 2e-05,
+      "loss": 0.6796,
+      "step": 3770
+    },
+    {
+      "epoch": 0.305973773676542,
+      "grad_norm": 0.4835241436958313,
+      "learning_rate": 2e-05,
+      "loss": 0.6595,
+      "step": 3780
+    },
+    {
+      "epoch": 0.30678322810425773,
+      "grad_norm": 0.41878876090049744,
+      "learning_rate": 2e-05,
+      "loss": 0.7645,
+      "step": 3790
+    },
+    {
+      "epoch": 0.30759268253197347,
+      "grad_norm": 0.4477061331272125,
+      "learning_rate": 2e-05,
+      "loss": 0.6913,
+      "step": 3800
+    },
+    {
+      "epoch": 0.30840213695968915,
+      "grad_norm": 0.46791255474090576,
+      "learning_rate": 2e-05,
+      "loss": 0.6735,
+      "step": 3810
+    },
+    {
+      "epoch": 0.3092115913874049,
+      "grad_norm": 0.45904427766799927,
+      "learning_rate": 2e-05,
+      "loss": 0.7248,
+      "step": 3820
+    },
+    {
+      "epoch": 0.31002104581512063,
+      "grad_norm": 0.7113839983940125,
+      "learning_rate": 2e-05,
+      "loss": 0.6982,
+      "step": 3830
+    },
+    {
+      "epoch": 0.3108305002428363,
+      "grad_norm": 0.5111123919487,
+      "learning_rate": 2e-05,
+      "loss": 0.6475,
+      "step": 3840
+    },
+    {
+      "epoch": 0.31163995467055206,
+      "grad_norm": 0.3900131285190582,
+      "learning_rate": 2e-05,
+      "loss": 0.762,
+      "step": 3850
+    },
+    {
+      "epoch": 0.3124494090982678,
+      "grad_norm": 0.4657941460609436,
+      "learning_rate": 2e-05,
+      "loss": 0.7174,
+      "step": 3860
+    },
+    {
+      "epoch": 0.3132588635259835,
+      "grad_norm": 0.454732745885849,
+      "learning_rate": 2e-05,
+      "loss": 0.6853,
+      "step": 3870
+    },
+    {
+      "epoch": 0.3140683179536992,
+      "grad_norm": 0.4248451590538025,
+      "learning_rate": 2e-05,
+      "loss": 0.683,
+      "step": 3880
+    },
+    {
+      "epoch": 0.3148777723814149,
+      "grad_norm": 0.42916038632392883,
+      "learning_rate": 2e-05,
+      "loss": 0.6786,
+      "step": 3890
+    },
+    {
+      "epoch": 0.31568722680913064,
+      "grad_norm": 0.6808509826660156,
+      "learning_rate": 2e-05,
+      "loss": 0.7378,
+      "step": 3900
+    },
+    {
+      "epoch": 0.3164966812368464,
+      "grad_norm": 0.47840702533721924,
+      "learning_rate": 2e-05,
+      "loss": 0.7332,
+      "step": 3910
+    },
+    {
+      "epoch": 0.31730613566456206,
+      "grad_norm": 0.42135486006736755,
+      "learning_rate": 2e-05,
+      "loss": 0.6621,
+      "step": 3920
+    },
+    {
+      "epoch": 0.3181155900922778,
+      "grad_norm": 0.4288185238838196,
+      "learning_rate": 2e-05,
+      "loss": 0.6842,
+      "step": 3930
+    },
+    {
+      "epoch": 0.31892504451999354,
+      "grad_norm": 0.5326945185661316,
+      "learning_rate": 2e-05,
+      "loss": 0.696,
+      "step": 3940
+    },
+    {
+      "epoch": 0.3197344989477092,
+      "grad_norm": 0.45170846581459045,
+      "learning_rate": 2e-05,
+      "loss": 0.6671,
+      "step": 3950
+    },
+    {
+      "epoch": 0.32054395337542496,
+      "grad_norm": 0.4467420279979706,
+      "learning_rate": 2e-05,
+      "loss": 0.7035,
+      "step": 3960
+    },
+    {
+      "epoch": 0.3213534078031407,
+      "grad_norm": 0.43998798727989197,
+      "learning_rate": 2e-05,
+      "loss": 0.7307,
+      "step": 3970
+    },
+    {
+      "epoch": 0.3221628622308564,
+      "grad_norm": 0.486310750246048,
+      "learning_rate": 2e-05,
+      "loss": 0.7143,
+      "step": 3980
+    },
+    {
+      "epoch": 0.3229723166585721,
+      "grad_norm": 0.4439856708049774,
+      "learning_rate": 2e-05,
+      "loss": 0.7008,
+      "step": 3990
+    },
+    {
+      "epoch": 0.32378177108628786,
+      "grad_norm": 0.43430188298225403,
+      "learning_rate": 2e-05,
+      "loss": 0.6917,
+      "step": 4000
+    },
+    {
+      "epoch": 0.32459122551400355,
+      "grad_norm": 0.4712444543838501,
+      "learning_rate": 2e-05,
+      "loss": 0.7276,
+      "step": 4010
+    },
+    {
+      "epoch": 0.3254006799417193,
+      "grad_norm": 0.5521031022071838,
+      "learning_rate": 2e-05,
+      "loss": 0.6872,
+      "step": 4020
+    },
+    {
+      "epoch": 0.326210134369435,
+      "grad_norm": 0.5101237893104553,
+      "learning_rate": 2e-05,
+      "loss": 0.6997,
+      "step": 4030
+    },
+    {
+      "epoch": 0.3270195887971507,
+      "grad_norm": 0.4471038281917572,
+      "learning_rate": 2e-05,
+      "loss": 0.6869,
+      "step": 4040
+    },
+    {
+      "epoch": 0.32782904322486645,
+      "grad_norm": 0.4599039554595947,
+      "learning_rate": 2e-05,
+      "loss": 0.6676,
+      "step": 4050
+    },
+    {
+      "epoch": 0.3286384976525822,
+      "grad_norm": 1.877204418182373,
+      "learning_rate": 2e-05,
+      "loss": 0.7269,
+      "step": 4060
+    },
+    {
+      "epoch": 0.32944795208029787,
+      "grad_norm": 0.6414173245429993,
+      "learning_rate": 2e-05,
+      "loss": 0.6645,
+      "step": 4070
+    },
+    {
+      "epoch": 0.3302574065080136,
+      "grad_norm": 0.4076804220676422,
+      "learning_rate": 2e-05,
+      "loss": 0.6357,
+      "step": 4080
+    },
+    {
+      "epoch": 0.33106686093572935,
+      "grad_norm": 0.49065500497817993,
+      "learning_rate": 2e-05,
+      "loss": 0.6931,
+      "step": 4090
+    },
+    {
+      "epoch": 0.33187631536344503,
+      "grad_norm": 0.40050044655799866,
+      "learning_rate": 2e-05,
+      "loss": 0.6924,
+      "step": 4100
+    },
+    {
+      "epoch": 0.33268576979116077,
+      "grad_norm": 0.4543343484401703,
+      "learning_rate": 2e-05,
+      "loss": 0.6659,
+      "step": 4110
+    },
+    {
+      "epoch": 0.33349522421887645,
+      "grad_norm": 0.4257263243198395,
+      "learning_rate": 2e-05,
+      "loss": 0.7196,
+      "step": 4120
+    },
+    {
+      "epoch": 0.3343046786465922,
+      "grad_norm": 0.6431072354316711,
+      "learning_rate": 2e-05,
+      "loss": 0.6801,
+      "step": 4130
+    },
+    {
+      "epoch": 0.33511413307430793,
+      "grad_norm": 0.4574109613895416,
+      "learning_rate": 2e-05,
+      "loss": 0.753,
+      "step": 4140
+    },
+    {
+      "epoch": 0.3359235875020236,
+      "grad_norm": 0.5690491199493408,
+      "learning_rate": 2e-05,
+      "loss": 0.7835,
+      "step": 4150
+    },
+    {
+      "epoch": 0.33673304192973935,
+      "grad_norm": 0.42611411213874817,
+      "learning_rate": 2e-05,
+      "loss": 0.6784,
+      "step": 4160
+    },
+    {
+      "epoch": 0.3375424963574551,
+      "grad_norm": 0.4732431173324585,
+      "learning_rate": 2e-05,
+      "loss": 0.7357,
+      "step": 4170
+    },
+    {
+      "epoch": 0.3383519507851708,
+      "grad_norm": 0.4582887887954712,
+      "learning_rate": 2e-05,
+      "loss": 0.6636,
+      "step": 4180
+    },
+    {
+      "epoch": 0.3391614052128865,
+      "grad_norm": 0.45281198620796204,
+      "learning_rate": 2e-05,
+      "loss": 0.6699,
+      "step": 4190
+    },
+    {
+      "epoch": 0.33997085964060225,
+      "grad_norm": 0.40201619267463684,
+      "learning_rate": 2e-05,
+      "loss": 0.7054,
+      "step": 4200
+    },
+    {
+      "epoch": 0.34078031406831794,
+      "grad_norm": 0.46499624848365784,
+      "learning_rate": 2e-05,
+      "loss": 0.6389,
+      "step": 4210
+    },
+    {
+      "epoch": 0.3415897684960337,
+      "grad_norm": 0.4530957043170929,
+      "learning_rate": 2e-05,
+      "loss": 0.7431,
+      "step": 4220
+    },
+    {
+      "epoch": 0.3423992229237494,
+      "grad_norm": 0.48627784848213196,
+      "learning_rate": 2e-05,
+      "loss": 0.6899,
+      "step": 4230
+    },
+    {
+      "epoch": 0.3432086773514651,
+      "grad_norm": 0.4580783545970917,
+      "learning_rate": 2e-05,
+      "loss": 0.7442,
+      "step": 4240
+    },
+    {
+      "epoch": 0.34401813177918084,
+      "grad_norm": 0.48237690329551697,
+      "learning_rate": 2e-05,
+      "loss": 0.7153,
+      "step": 4250
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.4806967079639435,
+      "learning_rate": 2e-05,
+      "loss": 0.6801,
+      "step": 4260
+    },
+    {
+      "epoch": 0.34563704063461226,
+      "grad_norm": 0.44575124979019165,
+      "learning_rate": 2e-05,
+      "loss": 0.6022,
+      "step": 4270
+    },
+    {
+      "epoch": 0.346446495062328,
+      "grad_norm": 0.4467647075653076,
+      "learning_rate": 2e-05,
+      "loss": 0.6595,
+      "step": 4280
+    },
+    {
+      "epoch": 0.34725594949004374,
+      "grad_norm": 0.46690958738327026,
+      "learning_rate": 2e-05,
+      "loss": 0.6864,
+      "step": 4290
+    },
+    {
+      "epoch": 0.3480654039177594,
+      "grad_norm": 0.603374719619751,
+      "learning_rate": 2e-05,
+      "loss": 0.7237,
+      "step": 4300
+    },
+    {
+      "epoch": 0.34887485834547516,
+      "grad_norm": 0.4918270409107208,
+      "learning_rate": 2e-05,
+      "loss": 0.6757,
+      "step": 4310
+    },
+    {
+      "epoch": 0.34968431277319084,
+      "grad_norm": 0.4592750668525696,
+      "learning_rate": 2e-05,
+      "loss": 0.7001,
+      "step": 4320
+    },
+    {
+      "epoch": 0.3504937672009066,
+      "grad_norm": 0.45143067836761475,
+      "learning_rate": 2e-05,
+      "loss": 0.6912,
+      "step": 4330
+    },
+    {
+      "epoch": 0.3513032216286223,
+      "grad_norm": 0.39186620712280273,
+      "learning_rate": 2e-05,
+      "loss": 0.6749,
+      "step": 4340
+    },
+    {
+      "epoch": 0.352112676056338,
+      "grad_norm": 0.5056009292602539,
+      "learning_rate": 2e-05,
+      "loss": 0.6643,
+      "step": 4350
+    },
+    {
+      "epoch": 0.35292213048405374,
+      "grad_norm": 0.421114444732666,
+      "learning_rate": 2e-05,
+      "loss": 0.6838,
+      "step": 4360
+    },
+    {
+      "epoch": 0.3537315849117695,
+      "grad_norm": 0.49863582849502563,
+      "learning_rate": 2e-05,
+      "loss": 0.7103,
+      "step": 4370
+    },
+    {
+      "epoch": 0.35454103933948516,
+      "grad_norm": 0.4858655333518982,
+      "learning_rate": 2e-05,
+      "loss": 0.6457,
+      "step": 4380
+    },
+    {
+      "epoch": 0.3553504937672009,
+      "grad_norm": 0.3983035981655121,
+      "learning_rate": 2e-05,
+      "loss": 0.6282,
+      "step": 4390
+    },
+    {
+      "epoch": 0.35615994819491664,
+      "grad_norm": 0.4564099907875061,
+      "learning_rate": 2e-05,
+      "loss": 0.6764,
+      "step": 4400
+    },
+    {
+      "epoch": 0.3569694026226323,
+      "grad_norm": 0.44877055287361145,
+      "learning_rate": 2e-05,
+      "loss": 0.6403,
+      "step": 4410
+    },
+    {
+      "epoch": 0.35777885705034806,
+      "grad_norm": 0.4411391615867615,
+      "learning_rate": 2e-05,
+      "loss": 0.7268,
+      "step": 4420
+    },
+    {
+      "epoch": 0.3585883114780638,
+      "grad_norm": 0.5089889764785767,
+      "learning_rate": 2e-05,
+      "loss": 0.6938,
+      "step": 4430
+    },
+    {
+      "epoch": 0.3593977659057795,
+      "grad_norm": 0.4940913915634155,
+      "learning_rate": 2e-05,
+      "loss": 0.7064,
+      "step": 4440
+    },
+    {
+      "epoch": 0.3602072203334952,
+      "grad_norm": 0.45706281065940857,
+      "learning_rate": 2e-05,
+      "loss": 0.6661,
+      "step": 4450
+    },
+    {
+      "epoch": 0.36101667476121097,
+      "grad_norm": 0.5058935284614563,
+      "learning_rate": 2e-05,
+      "loss": 0.6737,
+      "step": 4460
+    },
+    {
+      "epoch": 0.36182612918892665,
+      "grad_norm": 0.5108110904693604,
+      "learning_rate": 2e-05,
+      "loss": 0.669,
+      "step": 4470
+    },
+    {
+      "epoch": 0.3626355836166424,
+      "grad_norm": 0.4330281913280487,
+      "learning_rate": 2e-05,
+      "loss": 0.6669,
+      "step": 4480
+    },
+    {
+      "epoch": 0.3634450380443581,
+      "grad_norm": 0.49222707748413086,
+      "learning_rate": 2e-05,
+      "loss": 0.7241,
+      "step": 4490
+    },
+    {
+      "epoch": 0.3642544924720738,
+      "grad_norm": 0.4001592695713043,
+      "learning_rate": 2e-05,
+      "loss": 0.6835,
+      "step": 4500
+    },
+    {
+      "epoch": 0.36506394689978955,
+      "grad_norm": 0.4468865990638733,
+      "learning_rate": 2e-05,
+      "loss": 0.6794,
+      "step": 4510
+    },
+    {
+      "epoch": 0.3658734013275053,
+      "grad_norm": 0.4768028259277344,
+      "learning_rate": 2e-05,
+      "loss": 0.6694,
+      "step": 4520
+    },
+    {
+      "epoch": 0.36668285575522097,
+      "grad_norm": 0.47764843702316284,
+      "learning_rate": 2e-05,
+      "loss": 0.7209,
+      "step": 4530
+    },
+    {
+      "epoch": 0.3674923101829367,
+      "grad_norm": 0.5243435502052307,
+      "learning_rate": 2e-05,
+      "loss": 0.6979,
+      "step": 4540
+    },
+    {
+      "epoch": 0.3683017646106524,
+      "grad_norm": 0.43978050351142883,
+      "learning_rate": 2e-05,
+      "loss": 0.7294,
+      "step": 4550
+    },
+    {
+      "epoch": 0.36911121903836813,
+      "grad_norm": 0.4600770175457001,
+      "learning_rate": 2e-05,
+      "loss": 0.6767,
+      "step": 4560
+    },
+    {
+      "epoch": 0.36992067346608387,
+      "grad_norm": 0.5084247589111328,
+      "learning_rate": 2e-05,
+      "loss": 0.6484,
+      "step": 4570
+    },
+    {
+      "epoch": 0.37073012789379955,
+      "grad_norm": 0.4830254912376404,
+      "learning_rate": 2e-05,
+      "loss": 0.6589,
+      "step": 4580
+    },
+    {
+      "epoch": 0.3715395823215153,
+      "grad_norm": 0.38199731707572937,
+      "learning_rate": 2e-05,
+      "loss": 0.7055,
+      "step": 4590
+    },
+    {
+      "epoch": 0.37234903674923103,
+      "grad_norm": 0.4064747393131256,
+      "learning_rate": 2e-05,
+      "loss": 0.6683,
+      "step": 4600
+    },
+    {
+      "epoch": 0.3731584911769467,
+      "grad_norm": 0.4430438280105591,
+      "learning_rate": 2e-05,
+      "loss": 0.6931,
+      "step": 4610
+    },
+    {
+      "epoch": 0.37396794560466246,
+      "grad_norm": 0.4438480734825134,
+      "learning_rate": 2e-05,
+      "loss": 0.6854,
+      "step": 4620
+    },
+    {
+      "epoch": 0.3747774000323782,
+      "grad_norm": 1.211795687675476,
+      "learning_rate": 2e-05,
+      "loss": 0.7097,
+      "step": 4630
+    },
+    {
+      "epoch": 0.3755868544600939,
+      "grad_norm": 0.44138050079345703,
+      "learning_rate": 2e-05,
+      "loss": 0.6623,
+      "step": 4640
+    },
+    {
+      "epoch": 0.3763963088878096,
+      "grad_norm": 0.43387487530708313,
+      "learning_rate": 2e-05,
+      "loss": 0.7059,
+      "step": 4650
+    },
+    {
+      "epoch": 0.37720576331552536,
+      "grad_norm": 0.5490158200263977,
+      "learning_rate": 2e-05,
+      "loss": 0.7156,
+      "step": 4660
+    },
+    {
+      "epoch": 0.37801521774324104,
+      "grad_norm": 0.46521300077438354,
+      "learning_rate": 2e-05,
+      "loss": 0.7427,
+      "step": 4670
+    },
+    {
+      "epoch": 0.3788246721709568,
+      "grad_norm": 0.4105255901813507,
+      "learning_rate": 2e-05,
+      "loss": 0.6652,
+      "step": 4680
+    },
+    {
+      "epoch": 0.3796341265986725,
+      "grad_norm": 0.41078534722328186,
+      "learning_rate": 2e-05,
+      "loss": 0.6902,
+      "step": 4690
+    },
+    {
+      "epoch": 0.3804435810263882,
+      "grad_norm": 0.47453001141548157,
+      "learning_rate": 2e-05,
+      "loss": 0.6753,
+      "step": 4700
+    },
+    {
+      "epoch": 0.38125303545410394,
+      "grad_norm": 0.4386219084262848,
+      "learning_rate": 2e-05,
+      "loss": 0.7124,
+      "step": 4710
+    },
+    {
+      "epoch": 0.3820624898818197,
+      "grad_norm": 0.5246437191963196,
+      "learning_rate": 2e-05,
+      "loss": 0.7303,
+      "step": 4720
+    },
+    {
+      "epoch": 0.38287194430953536,
+      "grad_norm": 0.41538214683532715,
+      "learning_rate": 2e-05,
+      "loss": 0.6989,
+      "step": 4730
+    },
+    {
+      "epoch": 0.3836813987372511,
+      "grad_norm": 0.5306440591812134,
+      "learning_rate": 2e-05,
+      "loss": 0.6723,
+      "step": 4740
+    },
+    {
+      "epoch": 0.38449085316496684,
+      "grad_norm": 0.48846235871315,
+      "learning_rate": 2e-05,
+      "loss": 0.7196,
+      "step": 4750
+    },
+    {
+      "epoch": 0.3853003075926825,
+      "grad_norm": 0.5100388526916504,
+      "learning_rate": 2e-05,
+      "loss": 0.6979,
+      "step": 4760
+    },
+    {
+      "epoch": 0.38610976202039826,
+      "grad_norm": 0.4623964726924896,
+      "learning_rate": 2e-05,
+      "loss": 0.6801,
+      "step": 4770
+    },
+    {
+      "epoch": 0.38691921644811395,
+      "grad_norm": 0.4462847113609314,
+      "learning_rate": 2e-05,
+      "loss": 0.6815,
+      "step": 4780
+    },
+    {
+      "epoch": 0.3877286708758297,
+      "grad_norm": 0.523942768573761,
+      "learning_rate": 2e-05,
+      "loss": 0.694,
+      "step": 4790
+    },
+    {
+      "epoch": 0.3885381253035454,
+      "grad_norm": 0.49190187454223633,
+      "learning_rate": 2e-05,
+      "loss": 0.6622,
+      "step": 4800
+    },
+    {
+      "epoch": 0.3893475797312611,
+      "grad_norm": 0.5738032460212708,
+      "learning_rate": 2e-05,
+      "loss": 0.6636,
+      "step": 4810
+    },
+    {
+      "epoch": 0.39015703415897685,
+      "grad_norm": 0.4949702322483063,
+      "learning_rate": 2e-05,
+      "loss": 0.6698,
+      "step": 4820
+    },
+    {
+      "epoch": 0.3909664885866926,
+      "grad_norm": 0.46383774280548096,
+      "learning_rate": 2e-05,
+      "loss": 0.7011,
+      "step": 4830
+    },
+    {
+      "epoch": 0.39177594301440827,
+      "grad_norm": 0.48111361265182495,
+      "learning_rate": 2e-05,
+      "loss": 0.7222,
+      "step": 4840
+    },
+    {
+      "epoch": 0.392585397442124,
+      "grad_norm": 0.4159325957298279,
+      "learning_rate": 2e-05,
+      "loss": 0.6941,
+      "step": 4850
+    },
+    {
+      "epoch": 0.39339485186983975,
+      "grad_norm": 0.5137020945549011,
+      "learning_rate": 2e-05,
+      "loss": 0.6788,
+      "step": 4860
+    },
+    {
+      "epoch": 0.39420430629755543,
+      "grad_norm": 0.4810377359390259,
+      "learning_rate": 2e-05,
+      "loss": 0.6306,
+      "step": 4870
+    },
+    {
+      "epoch": 0.39501376072527117,
+      "grad_norm": 0.4386044442653656,
+      "learning_rate": 2e-05,
+      "loss": 0.6517,
+      "step": 4880
+    },
+    {
+      "epoch": 0.3958232151529869,
+      "grad_norm": 0.5054970979690552,
+      "learning_rate": 2e-05,
+      "loss": 0.6264,
+      "step": 4890
+    },
+    {
+      "epoch": 0.3966326695807026,
+      "grad_norm": 0.46128809452056885,
+      "learning_rate": 2e-05,
+      "loss": 0.6896,
+      "step": 4900
+    },
+    {
+      "epoch": 0.39744212400841833,
+      "grad_norm": 0.4951207637786865,
+      "learning_rate": 2e-05,
+      "loss": 0.6846,
+      "step": 4910
+    },
+    {
+      "epoch": 0.39825157843613407,
+      "grad_norm": 0.4434981942176819,
+      "learning_rate": 2e-05,
+      "loss": 0.6829,
+      "step": 4920
+    },
+    {
+      "epoch": 0.39906103286384975,
+      "grad_norm": 0.44960111379623413,
+      "learning_rate": 2e-05,
+      "loss": 0.6696,
+      "step": 4930
+    },
+    {
+      "epoch": 0.3998704872915655,
+      "grad_norm": 0.49066969752311707,
+      "learning_rate": 2e-05,
+      "loss": 0.7007,
+      "step": 4940
+    },
+    {
+      "epoch": 0.40067994171928123,
+      "grad_norm": 0.5422534942626953,
+      "learning_rate": 2e-05,
+      "loss": 0.702,
+      "step": 4950
+    },
+    {
+      "epoch": 0.4014893961469969,
+      "grad_norm": 0.46425700187683105,
+      "learning_rate": 2e-05,
+      "loss": 0.6803,
+      "step": 4960
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.41511040925979614,
+      "learning_rate": 2e-05,
+      "loss": 0.6833,
+      "step": 4970
+    },
+    {
+      "epoch": 0.4031083050024284,
+      "grad_norm": 0.4407956898212433,
+      "learning_rate": 2e-05,
+      "loss": 0.68,
+      "step": 4980
+    },
+    {
+      "epoch": 0.4039177594301441,
+      "grad_norm": 0.4285918176174164,
+      "learning_rate": 2e-05,
+      "loss": 0.6471,
+      "step": 4990
+    },
+    {
+      "epoch": 0.4047272138578598,
+      "grad_norm": 0.49652159214019775,
+      "learning_rate": 2e-05,
+      "loss": 0.6911,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4055366682855755,
+      "grad_norm": 0.4497791528701782,
+      "learning_rate": 2e-05,
+      "loss": 0.673,
+      "step": 5010
+    },
+    {
+      "epoch": 0.40634612271329124,
+      "grad_norm": 0.5438094735145569,
+      "learning_rate": 2e-05,
+      "loss": 0.6861,
+      "step": 5020
+    },
+    {
+      "epoch": 0.407155577141007,
+      "grad_norm": 0.42526596784591675,
+      "learning_rate": 2e-05,
+      "loss": 0.671,
+      "step": 5030
+    },
+    {
+      "epoch": 0.40796503156872266,
+      "grad_norm": 0.48864299058914185,
+      "learning_rate": 2e-05,
+      "loss": 0.6752,
+      "step": 5040
+    },
+    {
+      "epoch": 0.4087744859964384,
+      "grad_norm": 0.4516984224319458,
+      "learning_rate": 2e-05,
+      "loss": 0.7171,
+      "step": 5050
+    },
+    {
+      "epoch": 0.40958394042415414,
+      "grad_norm": 0.43522337079048157,
+      "learning_rate": 2e-05,
+      "loss": 0.6371,
+      "step": 5060
+    },
+    {
+      "epoch": 0.4103933948518698,
+      "grad_norm": 0.5544494390487671,
+      "learning_rate": 2e-05,
+      "loss": 0.6905,
+      "step": 5070
+    },
+    {
+      "epoch": 0.41120284927958556,
+      "grad_norm": 0.4180936813354492,
+      "learning_rate": 2e-05,
+      "loss": 0.6968,
+      "step": 5080
+    },
+    {
+      "epoch": 0.4120123037073013,
+      "grad_norm": 0.41191527247428894,
+      "learning_rate": 1.9999810479633703e-05,
+      "loss": 0.6214,
+      "step": 5090
+    },
+    {
+      "epoch": 0.412821758135017,
+      "grad_norm": 0.4334999918937683,
+      "learning_rate": 1.997707677020786e-05,
+      "loss": 0.7262,
+      "step": 5100
+    },
+    {
+      "epoch": 0.4136312125627327,
+      "grad_norm": 0.4753339886665344,
+      "learning_rate": 1.9916538196124637e-05,
+      "loss": 0.7154,
+      "step": 5110
+    },
+    {
+      "epoch": 0.41444066699044846,
+      "grad_norm": 0.44304409623146057,
+      "learning_rate": 1.9818425303863402e-05,
+      "loss": 0.671,
+      "step": 5120
+    },
+    {
+      "epoch": 0.41525012141816414,
+      "grad_norm": 0.42817243933677673,
+      "learning_rate": 1.9683111732582887e-05,
+      "loss": 0.6187,
+      "step": 5130
+    },
+    {
+      "epoch": 0.4160595758458799,
+      "grad_norm": 0.44804060459136963,
+      "learning_rate": 1.951111279120706e-05,
+      "loss": 0.6619,
+      "step": 5140
+    },
+    {
+      "epoch": 0.4168690302735956,
+      "grad_norm": 0.4851824939250946,
+      "learning_rate": 1.9303083495996028e-05,
+      "loss": 0.6185,
+      "step": 5150
+    },
+    {
+      "epoch": 0.4176784847013113,
+      "grad_norm": 0.4449150264263153,
+      "learning_rate": 1.9059816076075482e-05,
+      "loss": 0.6353,
+      "step": 5160
+    },
+    {
+      "epoch": 0.41848793912902704,
+      "grad_norm": 0.49478092789649963,
+      "learning_rate": 1.8782236956424142e-05,
+      "loss": 0.6471,
+      "step": 5170
+    },
+    {
+      "epoch": 0.4192973935567428,
+      "grad_norm": 0.5233897566795349,
+      "learning_rate": 1.8471403229808897e-05,
+      "loss": 0.6774,
+      "step": 5180
+    },
+    {
+      "epoch": 0.42010684798445846,
+      "grad_norm": 0.5123249888420105,
+      "learning_rate": 1.8128498631103333e-05,
+      "loss": 0.6416,
+      "step": 5190
+    },
+    {
+      "epoch": 0.4209163024121742,
+      "grad_norm": 0.5680985450744629,
+      "learning_rate": 1.7754829029320507e-05,
+      "loss": 0.6363,
+      "step": 5200
+    },
+    {
+      "epoch": 0.4217257568398899,
+      "grad_norm": 0.4455265998840332,
+      "learning_rate": 1.7351817454527473e-05,
+      "loss": 0.6613,
+      "step": 5210
+    },
+    {
+      "epoch": 0.4225352112676056,
+      "grad_norm": 0.4371964931488037,
+      "learning_rate": 1.6920998678580345e-05,
+      "loss": 0.6281,
+      "step": 5220
+    },
+    {
+      "epoch": 0.42334466569532136,
+      "grad_norm": 0.46882548928260803,
+      "learning_rate": 1.6464013370317854e-05,
+      "loss": 0.6824,
+      "step": 5230
+    },
+    {
+      "epoch": 0.42415412012303705,
+      "grad_norm": 0.44246041774749756,
+      "learning_rate": 1.5982601847471915e-05,
+      "loss": 0.7213,
+      "step": 5240
+    },
+    {
+      "epoch": 0.4249635745507528,
+      "grad_norm": 0.5136589407920837,
+      "learning_rate": 1.5478597449089553e-05,
+      "loss": 0.6992,
+      "step": 5250
+    },
+    {
+      "epoch": 0.4257730289784685,
+      "grad_norm": 0.4447018802165985,
+      "learning_rate": 1.4953919553705725e-05,
+      "loss": 0.6171,
+      "step": 5260
+    },
+    {
+      "epoch": 0.4265824834061842,
+      "grad_norm": 0.46415215730667114,
+      "learning_rate": 1.441056626985559e-05,
+      "loss": 0.6814,
+      "step": 5270
+    },
+    {
+      "epoch": 0.42739193783389995,
+      "grad_norm": 0.4595086872577667,
+      "learning_rate": 1.3850606826762668e-05,
+      "loss": 0.6717,
+      "step": 5280
+    },
+    {
+      "epoch": 0.4282013922616157,
+      "grad_norm": 0.4416121542453766,
+      "learning_rate": 1.3276173694181128e-05,
+      "loss": 0.6427,
+      "step": 5290
+    },
+    {
+      "epoch": 0.42901084668933137,
+      "grad_norm": 0.44978103041648865,
+      "learning_rate": 1.2689454461401822e-05,
+      "loss": 0.6681,
+      "step": 5300
+    },
+    {
+      "epoch": 0.4298203011170471,
+      "grad_norm": 0.4354971647262573,
+      "learning_rate": 1.2092683506348939e-05,
+      "loss": 0.7181,
+      "step": 5310
+    },
+    {
+      "epoch": 0.43062975554476285,
+      "grad_norm": 0.4659983813762665,
+      "learning_rate": 1.14881334864935e-05,
+      "loss": 0.6354,
+      "step": 5320
+    },
+    {
+      "epoch": 0.43143920997247853,
+      "grad_norm": 0.48951101303100586,
+      "learning_rate": 1.0878106683988481e-05,
+      "loss": 0.623,
+      "step": 5330
+    },
+    {
+      "epoch": 0.43224866440019427,
+      "grad_norm": 0.41098055243492126,
+      "learning_rate": 1.026492623798551e-05,
+      "loss": 0.6587,
+      "step": 5340
+    },
+    {
+      "epoch": 0.43305811882791,
+      "grad_norm": 0.3987131416797638,
+      "learning_rate": 9.650927297522743e-06,
+      "loss": 0.66,
+      "step": 5350
+    },
+    {
+      "epoch": 0.4338675732556257,
+      "grad_norm": 0.42033424973487854,
+      "learning_rate": 9.038448128676012e-06,
+      "loss": 0.63,
+      "step": 5360
+    },
+    {
+      "epoch": 0.43467702768334143,
+      "grad_norm": 0.4581470489501953,
+      "learning_rate": 8.42982120983949e-06,
+      "loss": 0.6378,
+      "step": 5370
+    },
+    {
+      "epoch": 0.43548648211105717,
+      "grad_norm": 0.48343685269355774,
+      "learning_rate": 7.827364349047303e-06,
+      "loss": 0.6727,
+      "step": 5380
+    },
+    {
+      "epoch": 0.43629593653877285,
+      "grad_norm": 0.45132192969322205,
+      "learning_rate": 7.233371857163706e-06,
+      "loss": 0.626,
+      "step": 5390
+    },
+    {
+      "epoch": 0.4371053909664886,
+      "grad_norm": 0.4376398026943207,
+      "learning_rate": 6.650105810556492e-06,
+      "loss": 0.6623,
+      "step": 5400
+    },
+    {
+      "epoch": 0.43791484539420433,
+      "grad_norm": 0.47387632727622986,
+      "learning_rate": 6.079787436527681e-06,
+      "loss": 0.704,
+      "step": 5410
+    },
+    {
+      "epoch": 0.43872429982192,
+      "grad_norm": 0.49392449855804443,
+      "learning_rate": 5.524588654307961e-06,
+      "loss": 0.6692,
+      "step": 5420
+    },
+    {
+      "epoch": 0.43953375424963576,
+      "grad_norm": 0.4364570081233978,
+      "learning_rate": 4.986623803828985e-06,
+      "loss": 0.6931,
+      "step": 5430
+    },
+    {
+      "epoch": 0.44034320867735144,
+      "grad_norm": 0.4273184537887573,
+      "learning_rate": 4.467941593772423e-06,
+      "loss": 0.6983,
+      "step": 5440
+    },
+    {
+      "epoch": 0.4411526631050672,
+      "grad_norm": 0.502163290977478,
+      "learning_rate": 3.9705172995597606e-06,
+      "loss": 0.5934,
+      "step": 5450
+    },
+    {
+      "epoch": 0.4419621175327829,
+      "grad_norm": 0.4272233843803406,
+      "learning_rate": 3.4962452409948346e-06,
+      "loss": 0.661,
+      "step": 5460
+    },
+    {
+      "epoch": 0.4427715719604986,
+      "grad_norm": 0.4013231694698334,
+      "learning_rate": 3.046931568206211e-06,
+      "loss": 0.6764,
+      "step": 5470
+    },
+    {
+      "epoch": 0.44358102638821434,
+      "grad_norm": 0.4973040521144867,
+      "learning_rate": 2.624287383362404e-06,
+      "loss": 0.6369,
+      "step": 5480
+    },
+    {
+      "epoch": 0.4443904808159301,
+      "grad_norm": 0.4623737633228302,
+      "learning_rate": 2.2299222243541845e-06,
+      "loss": 0.6306,
+      "step": 5490
+    },
+    {
+      "epoch": 0.44519993524364576,
+      "grad_norm": 0.45081615447998047,
+      "learning_rate": 1.8653379352598246e-06,
+      "loss": 0.5954,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4460093896713615,
+      "grad_norm": 0.518165111541748,
+      "learning_rate": 1.5319229469361075e-06,
+      "loss": 0.6409,
+      "step": 5510
+    },
+    {
+      "epoch": 0.44681884409907724,
+      "grad_norm": 0.46359625458717346,
+      "learning_rate": 1.2309469895160917e-06,
+      "loss": 0.6343,
+      "step": 5520
+    },
+    {
+      "epoch": 0.4476282985267929,
+      "grad_norm": 0.4623735249042511,
+      "learning_rate": 9.635562569497974e-07,
+      "loss": 0.6957,
+      "step": 5530
+    },
+    {
+      "epoch": 0.44843775295450866,
+      "grad_norm": 0.4246928095817566,
+      "learning_rate": 7.307690420024867e-07,
+      "loss": 0.6819,
+      "step": 5540
+    },
+    {
+      "epoch": 0.4492472073822244,
+      "grad_norm": 0.5064653754234314,
+      "learning_rate": 5.334718583335942e-07,
+      "loss": 0.6323,
+      "step": 5550
+    },
+    {
+      "epoch": 0.4500566618099401,
+      "grad_norm": 0.4438730776309967,
+      "learning_rate": 3.7241606442442763e-07,
+      "loss": 0.6655,
+      "step": 5560
+    },
+    {
+      "epoch": 0.4508661162376558,
+      "grad_norm": 0.4611038863658905,
+      "learning_rate": 2.482150022115879e-07,
+      "loss": 0.6423,
+      "step": 5570
+    },
+    {
+      "epoch": 0.45167557066537156,
+      "grad_norm": 0.4258471131324768,
+      "learning_rate": 1.6134166132293174e-07,
+      "loss": 0.6526,
+      "step": 5580
+    },
+    {
+      "epoch": 0.45248502509308725,
+      "grad_norm": 0.4484739899635315,
+      "learning_rate": 1.1212687781127357e-07,
+      "loss": 0.6459,
+      "step": 5590
+    },
+    {
+      "epoch": 0.45305164319248825,
+      "step": 5597,
+      "total_flos": 2.4985159616803373e+19,
+      "train_loss": 0.059759924299742084,
+      "train_runtime": 5784.2106,
+      "train_samples_per_second": 11.612,
+      "train_steps_per_second": 0.968
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5597,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 636,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4985159616803373e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

g1_0_baseline_original_code__edit/500M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0287b98f75c2d25aca3dfc68e2989399089dd672b7126d94405c9e2859a0212f
+size 9105