Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 200M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+400M/tokenizer.json filter=lfs diff=lfs merge=lfs -text

400M/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
+}

400M/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 %}

400M/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
+}

400M/generation_config.json

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

400M/latest

@@ -0,0 +1 @@
+global_step4070

400M/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bc7ae88c851222ba2a5f5d4e26767026e718dcf48be9e21f6b6139dea9f874
+size 4902257696

400M/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7246e248f960028ec3671a2828d735892e48132358709394bbd6aa4ba8139d15
+size 4915960368

400M/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4825866a167f86f23462eb3e3e72faee3e735fabe46b4b6878d632bdb38cd0c9
+size 4983068496

400M/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fbc43049f16151fbf9cde3132456997013b8fb1dcc495a64c9eb0eb78eeccc
+size 1580230264

400M/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"
+  }
+}

400M/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7dcf54a8dbd1fff243640ddc034149fbe7c90ed70b8a95a6bb093e989a7577
+size 14469

400M/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a2b0b9d330140afd742a57df45106276d425d38a78e53b0fd43dba9559f8d4
+size 14469

400M/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce222f8f11fd62fd6cb82264500aefbc9e7ef16907ed3e4aa3a8a99c21d95d3
+size 14476

400M/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07144bfc4ed675dda70ab66923d17d6f9233560b2db09689cbe1f262c590c88
+size 14476

400M/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5db634f6ed5151d3c898fbe3c365f950516c404bed926de16b253b26e63c7cf
+size 14469

400M/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad774eade44525098fff2d5910e3d16565fca4c2af29ed0bc4d9315a8ac9607a
+size 14469

400M/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdee1b37be2238764bcfeed9dad268e938248152b0fba60eaf89adda99eac0f
+size 14469

400M/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6046157bd3d69a7cf6ee508b7359b30cb71488a11b11b07a614041b06813c553
+size 14469

400M/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc9300f101a324d0361f01aec1d57e26b57a703b4e536f4fe982c8ba57a9144
+size 14469

400M/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357df7b609d6ffd7f22b998281f7856a711ee83505e5ed2835959554b0185df7
+size 14469

400M/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb33667d752a94ade6841f62b8b8fcc22256b4712bd568b141bc690d4a42e11
+size 14469

400M/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354a7a38e97ba11b8ad29bf4d00d74f92295b32124cff0ef46baa862aa9b0f2f
+size 14469

400M/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c373bca4c9a6ef963a59ee82f3b16a9a90b89b812375170f487261fe4db9e20a
+size 1465

400M/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
+  }
+}

400M/tokenizer.json

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

400M/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
+}

400M/trainer_state.json

@@ -0,0 +1,2883 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3442442696439144,
+  "eval_steps": 500,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000845809016324114,
+      "grad_norm": 0.8241106867790222,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.8023,
+      "step": 10
+    },
+    {
+      "epoch": 0.001691618032648228,
+      "grad_norm": 0.7677053809165955,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.8319,
+      "step": 20
+    },
+    {
+      "epoch": 0.002537427048972342,
+      "grad_norm": 0.9122608304023743,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.8048,
+      "step": 30
+    },
+    {
+      "epoch": 0.003383236065296456,
+      "grad_norm": 1.000952959060669,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.8035,
+      "step": 40
+    },
+    {
+      "epoch": 0.00422904508162057,
+      "grad_norm": 0.7540556192398071,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.8453,
+      "step": 50
+    },
+    {
+      "epoch": 0.005074854097944684,
+      "grad_norm": 0.7352889180183411,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.7924,
+      "step": 60
+    },
+    {
+      "epoch": 0.005920663114268798,
+      "grad_norm": 0.8109757304191589,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.8292,
+      "step": 70
+    },
+    {
+      "epoch": 0.006766472130592912,
+      "grad_norm": 0.7200285196304321,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.799,
+      "step": 80
+    },
+    {
+      "epoch": 0.0076122811469170265,
+      "grad_norm": 0.9241945743560791,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.8368,
+      "step": 90
+    },
+    {
+      "epoch": 0.00845809016324114,
+      "grad_norm": 0.7442223429679871,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.8183,
+      "step": 100
+    },
+    {
+      "epoch": 0.009303899179565254,
+      "grad_norm": 0.772197425365448,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.8196,
+      "step": 110
+    },
+    {
+      "epoch": 0.010149708195889368,
+      "grad_norm": 0.8228936195373535,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.8509,
+      "step": 120
+    },
+    {
+      "epoch": 0.010995517212213483,
+      "grad_norm": 0.7811132669448853,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.8013,
+      "step": 130
+    },
+    {
+      "epoch": 0.011841326228537596,
+      "grad_norm": 0.8089613318443298,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.8164,
+      "step": 140
+    },
+    {
+      "epoch": 0.01268713524486171,
+      "grad_norm": 0.749538779258728,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.8228,
+      "step": 150
+    },
+    {
+      "epoch": 0.013532944261185825,
+      "grad_norm": 0.6700263023376465,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.8083,
+      "step": 160
+    },
+    {
+      "epoch": 0.014378753277509938,
+      "grad_norm": 0.7520489692687988,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.8247,
+      "step": 170
+    },
+    {
+      "epoch": 0.015224562293834053,
+      "grad_norm": 0.7081424593925476,
+      "learning_rate": 2e-05,
+      "loss": 0.8391,
+      "step": 180
+    },
+    {
+      "epoch": 0.016070371310158166,
+      "grad_norm": 0.8052947521209717,
+      "learning_rate": 2e-05,
+      "loss": 0.8132,
+      "step": 190
+    },
+    {
+      "epoch": 0.01691618032648228,
+      "grad_norm": 0.6062344312667847,
+      "learning_rate": 2e-05,
+      "loss": 0.8288,
+      "step": 200
+    },
+    {
+      "epoch": 0.017761989342806393,
+      "grad_norm": 0.6124718189239502,
+      "learning_rate": 2e-05,
+      "loss": 0.8459,
+      "step": 210
+    },
+    {
+      "epoch": 0.01860779835913051,
+      "grad_norm": 1.3280489444732666,
+      "learning_rate": 2e-05,
+      "loss": 0.8093,
+      "step": 220
+    },
+    {
+      "epoch": 0.019453607375454623,
+      "grad_norm": 0.5424445271492004,
+      "learning_rate": 2e-05,
+      "loss": 0.8144,
+      "step": 230
+    },
+    {
+      "epoch": 0.020299416391778735,
+      "grad_norm": 0.5595471262931824,
+      "learning_rate": 2e-05,
+      "loss": 0.8374,
+      "step": 240
+    },
+    {
+      "epoch": 0.02114522540810285,
+      "grad_norm": 0.5471348166465759,
+      "learning_rate": 2e-05,
+      "loss": 0.8427,
+      "step": 250
+    },
+    {
+      "epoch": 0.021991034424426965,
+      "grad_norm": 0.5580955743789673,
+      "learning_rate": 2e-05,
+      "loss": 0.8227,
+      "step": 260
+    },
+    {
+      "epoch": 0.022836843440751077,
+      "grad_norm": 0.5975316166877747,
+      "learning_rate": 2e-05,
+      "loss": 0.8145,
+      "step": 270
+    },
+    {
+      "epoch": 0.023682652457075192,
+      "grad_norm": 0.6378592848777771,
+      "learning_rate": 2e-05,
+      "loss": 0.8272,
+      "step": 280
+    },
+    {
+      "epoch": 0.024528461473399307,
+      "grad_norm": 0.681553065776825,
+      "learning_rate": 2e-05,
+      "loss": 0.8213,
+      "step": 290
+    },
+    {
+      "epoch": 0.02537427048972342,
+      "grad_norm": 0.5406049489974976,
+      "learning_rate": 2e-05,
+      "loss": 0.8121,
+      "step": 300
+    },
+    {
+      "epoch": 0.026220079506047534,
+      "grad_norm": 1.5000685453414917,
+      "learning_rate": 2e-05,
+      "loss": 0.7811,
+      "step": 310
+    },
+    {
+      "epoch": 0.02706588852237165,
+      "grad_norm": 0.4823637306690216,
+      "learning_rate": 2e-05,
+      "loss": 0.7895,
+      "step": 320
+    },
+    {
+      "epoch": 0.02791169753869576,
+      "grad_norm": 0.5392424464225769,
+      "learning_rate": 2e-05,
+      "loss": 0.7803,
+      "step": 330
+    },
+    {
+      "epoch": 0.028757506555019876,
+      "grad_norm": 0.5222411155700684,
+      "learning_rate": 2e-05,
+      "loss": 0.833,
+      "step": 340
+    },
+    {
+      "epoch": 0.02960331557134399,
+      "grad_norm": 0.4875090718269348,
+      "learning_rate": 2e-05,
+      "loss": 0.8237,
+      "step": 350
+    },
+    {
+      "epoch": 0.030449124587668106,
+      "grad_norm": 0.5114459991455078,
+      "learning_rate": 2e-05,
+      "loss": 0.8246,
+      "step": 360
+    },
+    {
+      "epoch": 0.03129493360399222,
+      "grad_norm": 0.49320992827415466,
+      "learning_rate": 2e-05,
+      "loss": 0.8044,
+      "step": 370
+    },
+    {
+      "epoch": 0.03214074262031633,
+      "grad_norm": 0.5030165910720825,
+      "learning_rate": 2e-05,
+      "loss": 0.8429,
+      "step": 380
+    },
+    {
+      "epoch": 0.032986551636640445,
+      "grad_norm": 0.47301071882247925,
+      "learning_rate": 2e-05,
+      "loss": 0.8538,
+      "step": 390
+    },
+    {
+      "epoch": 0.03383236065296456,
+      "grad_norm": 0.531063437461853,
+      "learning_rate": 2e-05,
+      "loss": 0.7949,
+      "step": 400
+    },
+    {
+      "epoch": 0.034678169669288675,
+      "grad_norm": 0.4545452892780304,
+      "learning_rate": 2e-05,
+      "loss": 0.8215,
+      "step": 410
+    },
+    {
+      "epoch": 0.035523978685612786,
+      "grad_norm": 0.5426740050315857,
+      "learning_rate": 2e-05,
+      "loss": 0.8088,
+      "step": 420
+    },
+    {
+      "epoch": 0.036369787701936905,
+      "grad_norm": 0.4993586838245392,
+      "learning_rate": 2e-05,
+      "loss": 0.8134,
+      "step": 430
+    },
+    {
+      "epoch": 0.03721559671826102,
+      "grad_norm": 0.49263498187065125,
+      "learning_rate": 2e-05,
+      "loss": 0.8278,
+      "step": 440
+    },
+    {
+      "epoch": 0.03806140573458513,
+      "grad_norm": 0.6844013333320618,
+      "learning_rate": 2e-05,
+      "loss": 0.8297,
+      "step": 450
+    },
+    {
+      "epoch": 0.03890721475090925,
+      "grad_norm": 0.43999695777893066,
+      "learning_rate": 2e-05,
+      "loss": 0.835,
+      "step": 460
+    },
+    {
+      "epoch": 0.03975302376723336,
+      "grad_norm": 0.46915218234062195,
+      "learning_rate": 2e-05,
+      "loss": 0.8554,
+      "step": 470
+    },
+    {
+      "epoch": 0.04059883278355747,
+      "grad_norm": 0.5281141400337219,
+      "learning_rate": 2e-05,
+      "loss": 0.8107,
+      "step": 480
+    },
+    {
+      "epoch": 0.04144464179988159,
+      "grad_norm": 0.4556983411312103,
+      "learning_rate": 2e-05,
+      "loss": 0.8179,
+      "step": 490
+    },
+    {
+      "epoch": 0.0422904508162057,
+      "grad_norm": 0.45689892768859863,
+      "learning_rate": 2e-05,
+      "loss": 0.8185,
+      "step": 500
+    },
+    {
+      "epoch": 0.04313625983252981,
+      "grad_norm": 0.45884785056114197,
+      "learning_rate": 2e-05,
+      "loss": 0.8329,
+      "step": 510
+    },
+    {
+      "epoch": 0.04398206884885393,
+      "grad_norm": 0.5012974739074707,
+      "learning_rate": 2e-05,
+      "loss": 0.8521,
+      "step": 520
+    },
+    {
+      "epoch": 0.04482787786517804,
+      "grad_norm": 0.4988952875137329,
+      "learning_rate": 2e-05,
+      "loss": 0.8304,
+      "step": 530
+    },
+    {
+      "epoch": 0.045673686881502154,
+      "grad_norm": 0.6683245897293091,
+      "learning_rate": 2e-05,
+      "loss": 0.8214,
+      "step": 540
+    },
+    {
+      "epoch": 0.04651949589782627,
+      "grad_norm": 0.4693884253501892,
+      "learning_rate": 2e-05,
+      "loss": 0.8125,
+      "step": 550
+    },
+    {
+      "epoch": 0.047365304914150384,
+      "grad_norm": 1.1734286546707153,
+      "learning_rate": 2e-05,
+      "loss": 0.844,
+      "step": 560
+    },
+    {
+      "epoch": 0.048211113930474496,
+      "grad_norm": 0.5317685604095459,
+      "learning_rate": 2e-05,
+      "loss": 0.8246,
+      "step": 570
+    },
+    {
+      "epoch": 0.049056922946798615,
+      "grad_norm": 0.46421676874160767,
+      "learning_rate": 2e-05,
+      "loss": 0.8427,
+      "step": 580
+    },
+    {
+      "epoch": 0.049902731963122726,
+      "grad_norm": 0.4967503547668457,
+      "learning_rate": 2e-05,
+      "loss": 0.8077,
+      "step": 590
+    },
+    {
+      "epoch": 0.05074854097944684,
+      "grad_norm": 0.5842324495315552,
+      "learning_rate": 2e-05,
+      "loss": 0.8186,
+      "step": 600
+    },
+    {
+      "epoch": 0.051594349995770956,
+      "grad_norm": 0.41733992099761963,
+      "learning_rate": 2e-05,
+      "loss": 0.8117,
+      "step": 610
+    },
+    {
+      "epoch": 0.05244015901209507,
+      "grad_norm": 0.44647812843322754,
+      "learning_rate": 2e-05,
+      "loss": 0.8126,
+      "step": 620
+    },
+    {
+      "epoch": 0.05328596802841918,
+      "grad_norm": 0.4602642059326172,
+      "learning_rate": 2e-05,
+      "loss": 0.8319,
+      "step": 630
+    },
+    {
+      "epoch": 0.0541317770447433,
+      "grad_norm": 0.5208284258842468,
+      "learning_rate": 2e-05,
+      "loss": 0.8123,
+      "step": 640
+    },
+    {
+      "epoch": 0.05497758606106741,
+      "grad_norm": 0.4798184633255005,
+      "learning_rate": 2e-05,
+      "loss": 0.8163,
+      "step": 650
+    },
+    {
+      "epoch": 0.05582339507739152,
+      "grad_norm": 0.40655434131622314,
+      "learning_rate": 2e-05,
+      "loss": 0.8123,
+      "step": 660
+    },
+    {
+      "epoch": 0.05666920409371564,
+      "grad_norm": 0.49001210927963257,
+      "learning_rate": 2e-05,
+      "loss": 0.8545,
+      "step": 670
+    },
+    {
+      "epoch": 0.05751501311003975,
+      "grad_norm": 0.4423077702522278,
+      "learning_rate": 2e-05,
+      "loss": 0.8283,
+      "step": 680
+    },
+    {
+      "epoch": 0.05836082212636387,
+      "grad_norm": 0.45661529898643494,
+      "learning_rate": 2e-05,
+      "loss": 0.8008,
+      "step": 690
+    },
+    {
+      "epoch": 0.05920663114268798,
+      "grad_norm": 0.47006598114967346,
+      "learning_rate": 2e-05,
+      "loss": 0.816,
+      "step": 700
+    },
+    {
+      "epoch": 0.060052440159012094,
+      "grad_norm": 0.46463993191719055,
+      "learning_rate": 2e-05,
+      "loss": 0.8355,
+      "step": 710
+    },
+    {
+      "epoch": 0.06089824917533621,
+      "grad_norm": 0.4940764009952545,
+      "learning_rate": 2e-05,
+      "loss": 0.8346,
+      "step": 720
+    },
+    {
+      "epoch": 0.061744058191660324,
+      "grad_norm": 0.423129141330719,
+      "learning_rate": 2e-05,
+      "loss": 0.8413,
+      "step": 730
+    },
+    {
+      "epoch": 0.06258986720798444,
+      "grad_norm": 0.4457870423793793,
+      "learning_rate": 2e-05,
+      "loss": 0.7961,
+      "step": 740
+    },
+    {
+      "epoch": 0.06343567622430855,
+      "grad_norm": 0.45665088295936584,
+      "learning_rate": 2e-05,
+      "loss": 0.8297,
+      "step": 750
+    },
+    {
+      "epoch": 0.06428148524063267,
+      "grad_norm": 0.4797661006450653,
+      "learning_rate": 2e-05,
+      "loss": 0.8008,
+      "step": 760
+    },
+    {
+      "epoch": 0.06512729425695678,
+      "grad_norm": 0.5712248086929321,
+      "learning_rate": 2e-05,
+      "loss": 0.8283,
+      "step": 770
+    },
+    {
+      "epoch": 0.06597310327328089,
+      "grad_norm": 0.43924763798713684,
+      "learning_rate": 2e-05,
+      "loss": 0.8281,
+      "step": 780
+    },
+    {
+      "epoch": 0.066818912289605,
+      "grad_norm": 0.48926714062690735,
+      "learning_rate": 2e-05,
+      "loss": 0.8312,
+      "step": 790
+    },
+    {
+      "epoch": 0.06766472130592913,
+      "grad_norm": 0.4769990146160126,
+      "learning_rate": 2e-05,
+      "loss": 0.8069,
+      "step": 800
+    },
+    {
+      "epoch": 0.06851053032225324,
+      "grad_norm": 0.42610347270965576,
+      "learning_rate": 2e-05,
+      "loss": 0.768,
+      "step": 810
+    },
+    {
+      "epoch": 0.06935633933857735,
+      "grad_norm": 0.43810147047042847,
+      "learning_rate": 2e-05,
+      "loss": 0.7922,
+      "step": 820
+    },
+    {
+      "epoch": 0.07020214835490146,
+      "grad_norm": 0.47039204835891724,
+      "learning_rate": 2e-05,
+      "loss": 0.7849,
+      "step": 830
+    },
+    {
+      "epoch": 0.07104795737122557,
+      "grad_norm": 0.44504624605178833,
+      "learning_rate": 2e-05,
+      "loss": 0.8239,
+      "step": 840
+    },
+    {
+      "epoch": 0.07189376638754968,
+      "grad_norm": 0.448843389749527,
+      "learning_rate": 2e-05,
+      "loss": 0.7781,
+      "step": 850
+    },
+    {
+      "epoch": 0.07273957540387381,
+      "grad_norm": 0.4455089867115021,
+      "learning_rate": 2e-05,
+      "loss": 0.8298,
+      "step": 860
+    },
+    {
+      "epoch": 0.07358538442019792,
+      "grad_norm": 0.42929205298423767,
+      "learning_rate": 2e-05,
+      "loss": 0.8202,
+      "step": 870
+    },
+    {
+      "epoch": 0.07443119343652203,
+      "grad_norm": 0.4794764220714569,
+      "learning_rate": 2e-05,
+      "loss": 0.8175,
+      "step": 880
+    },
+    {
+      "epoch": 0.07527700245284615,
+      "grad_norm": 0.4734118580818176,
+      "learning_rate": 2e-05,
+      "loss": 0.7947,
+      "step": 890
+    },
+    {
+      "epoch": 0.07612281146917026,
+      "grad_norm": 0.4543229937553406,
+      "learning_rate": 2e-05,
+      "loss": 0.8245,
+      "step": 900
+    },
+    {
+      "epoch": 0.07696862048549438,
+      "grad_norm": 0.44303321838378906,
+      "learning_rate": 2e-05,
+      "loss": 0.7987,
+      "step": 910
+    },
+    {
+      "epoch": 0.0778144295018185,
+      "grad_norm": 0.4595701992511749,
+      "learning_rate": 2e-05,
+      "loss": 0.781,
+      "step": 920
+    },
+    {
+      "epoch": 0.0786602385181426,
+      "grad_norm": 0.42940250039100647,
+      "learning_rate": 2e-05,
+      "loss": 0.8154,
+      "step": 930
+    },
+    {
+      "epoch": 0.07950604753446672,
+      "grad_norm": 0.4868500232696533,
+      "learning_rate": 2e-05,
+      "loss": 0.8292,
+      "step": 940
+    },
+    {
+      "epoch": 0.08035185655079083,
+      "grad_norm": 0.4093605577945709,
+      "learning_rate": 2e-05,
+      "loss": 0.7935,
+      "step": 950
+    },
+    {
+      "epoch": 0.08119766556711494,
+      "grad_norm": 0.4410911500453949,
+      "learning_rate": 2e-05,
+      "loss": 0.8365,
+      "step": 960
+    },
+    {
+      "epoch": 0.08204347458343907,
+      "grad_norm": 0.5222998261451721,
+      "learning_rate": 2e-05,
+      "loss": 0.7956,
+      "step": 970
+    },
+    {
+      "epoch": 0.08288928359976318,
+      "grad_norm": 0.46435871720314026,
+      "learning_rate": 2e-05,
+      "loss": 0.8217,
+      "step": 980
+    },
+    {
+      "epoch": 0.08373509261608729,
+      "grad_norm": 0.4304494559764862,
+      "learning_rate": 2e-05,
+      "loss": 0.8021,
+      "step": 990
+    },
+    {
+      "epoch": 0.0845809016324114,
+      "grad_norm": 0.4986684322357178,
+      "learning_rate": 2e-05,
+      "loss": 0.7744,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08542671064873551,
+      "grad_norm": 0.4378027617931366,
+      "learning_rate": 2e-05,
+      "loss": 0.7945,
+      "step": 1010
+    },
+    {
+      "epoch": 0.08627251966505962,
+      "grad_norm": 0.47464582324028015,
+      "learning_rate": 2e-05,
+      "loss": 0.8366,
+      "step": 1020
+    },
+    {
+      "epoch": 0.08711832868138375,
+      "grad_norm": 0.49523982405662537,
+      "learning_rate": 2e-05,
+      "loss": 0.8105,
+      "step": 1030
+    },
+    {
+      "epoch": 0.08796413769770786,
+      "grad_norm": 0.44961807131767273,
+      "learning_rate": 2e-05,
+      "loss": 0.82,
+      "step": 1040
+    },
+    {
+      "epoch": 0.08880994671403197,
+      "grad_norm": 0.4544869065284729,
+      "learning_rate": 2e-05,
+      "loss": 0.8164,
+      "step": 1050
+    },
+    {
+      "epoch": 0.08965575573035608,
+      "grad_norm": 0.4726337790489197,
+      "learning_rate": 2e-05,
+      "loss": 0.8033,
+      "step": 1060
+    },
+    {
+      "epoch": 0.0905015647466802,
+      "grad_norm": 0.43836507201194763,
+      "learning_rate": 2e-05,
+      "loss": 0.8219,
+      "step": 1070
+    },
+    {
+      "epoch": 0.09134737376300431,
+      "grad_norm": 0.453037291765213,
+      "learning_rate": 2e-05,
+      "loss": 0.8018,
+      "step": 1080
+    },
+    {
+      "epoch": 0.09219318277932843,
+      "grad_norm": 0.4820594787597656,
+      "learning_rate": 2e-05,
+      "loss": 0.8153,
+      "step": 1090
+    },
+    {
+      "epoch": 0.09303899179565255,
+      "grad_norm": 0.5157103538513184,
+      "learning_rate": 2e-05,
+      "loss": 0.8018,
+      "step": 1100
+    },
+    {
+      "epoch": 0.09388480081197666,
+      "grad_norm": 0.8149513006210327,
+      "learning_rate": 2e-05,
+      "loss": 0.7979,
+      "step": 1110
+    },
+    {
+      "epoch": 0.09473060982830077,
+      "grad_norm": 0.4654536843299866,
+      "learning_rate": 2e-05,
+      "loss": 0.7757,
+      "step": 1120
+    },
+    {
+      "epoch": 0.09557641884462488,
+      "grad_norm": 0.45552128553390503,
+      "learning_rate": 2e-05,
+      "loss": 0.8238,
+      "step": 1130
+    },
+    {
+      "epoch": 0.09642222786094899,
+      "grad_norm": 0.46994927525520325,
+      "learning_rate": 2e-05,
+      "loss": 0.8146,
+      "step": 1140
+    },
+    {
+      "epoch": 0.09726803687727312,
+      "grad_norm": 0.4299950897693634,
+      "learning_rate": 2e-05,
+      "loss": 0.7954,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09811384589359723,
+      "grad_norm": 0.4697369933128357,
+      "learning_rate": 2e-05,
+      "loss": 0.7886,
+      "step": 1160
+    },
+    {
+      "epoch": 0.09895965490992134,
+      "grad_norm": 0.4231007993221283,
+      "learning_rate": 2e-05,
+      "loss": 0.8165,
+      "step": 1170
+    },
+    {
+      "epoch": 0.09980546392624545,
+      "grad_norm": 0.42168501019477844,
+      "learning_rate": 2e-05,
+      "loss": 0.7961,
+      "step": 1180
+    },
+    {
+      "epoch": 0.10065127294256956,
+      "grad_norm": 0.4500163197517395,
+      "learning_rate": 2e-05,
+      "loss": 0.8286,
+      "step": 1190
+    },
+    {
+      "epoch": 0.10149708195889368,
+      "grad_norm": 0.6341075301170349,
+      "learning_rate": 2e-05,
+      "loss": 0.8061,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1023428909752178,
+      "grad_norm": 0.502292811870575,
+      "learning_rate": 2e-05,
+      "loss": 0.8238,
+      "step": 1210
+    },
+    {
+      "epoch": 0.10318869999154191,
+      "grad_norm": 0.3936860263347626,
+      "learning_rate": 2e-05,
+      "loss": 0.8029,
+      "step": 1220
+    },
+    {
+      "epoch": 0.10403450900786602,
+      "grad_norm": 0.44225117564201355,
+      "learning_rate": 2e-05,
+      "loss": 0.8159,
+      "step": 1230
+    },
+    {
+      "epoch": 0.10488031802419014,
+      "grad_norm": 0.6825657486915588,
+      "learning_rate": 2e-05,
+      "loss": 0.8033,
+      "step": 1240
+    },
+    {
+      "epoch": 0.10572612704051425,
+      "grad_norm": 0.5130757689476013,
+      "learning_rate": 2e-05,
+      "loss": 0.7956,
+      "step": 1250
+    },
+    {
+      "epoch": 0.10657193605683836,
+      "grad_norm": 0.44218507409095764,
+      "learning_rate": 2e-05,
+      "loss": 0.7881,
+      "step": 1260
+    },
+    {
+      "epoch": 0.10741774507316248,
+      "grad_norm": 0.4423086941242218,
+      "learning_rate": 2e-05,
+      "loss": 0.8178,
+      "step": 1270
+    },
+    {
+      "epoch": 0.1082635540894866,
+      "grad_norm": 0.5452187061309814,
+      "learning_rate": 2e-05,
+      "loss": 0.8007,
+      "step": 1280
+    },
+    {
+      "epoch": 0.10910936310581071,
+      "grad_norm": 0.5330957174301147,
+      "learning_rate": 2e-05,
+      "loss": 0.7857,
+      "step": 1290
+    },
+    {
+      "epoch": 0.10995517212213482,
+      "grad_norm": 0.5264826416969299,
+      "learning_rate": 2e-05,
+      "loss": 0.7988,
+      "step": 1300
+    },
+    {
+      "epoch": 0.11080098113845893,
+      "grad_norm": 0.4270782172679901,
+      "learning_rate": 2e-05,
+      "loss": 0.7994,
+      "step": 1310
+    },
+    {
+      "epoch": 0.11164679015478304,
+      "grad_norm": 0.4306176006793976,
+      "learning_rate": 2e-05,
+      "loss": 0.7881,
+      "step": 1320
+    },
+    {
+      "epoch": 0.11249259917110717,
+      "grad_norm": 0.421113520860672,
+      "learning_rate": 2e-05,
+      "loss": 0.7992,
+      "step": 1330
+    },
+    {
+      "epoch": 0.11333840818743128,
+      "grad_norm": 0.43613556027412415,
+      "learning_rate": 2e-05,
+      "loss": 0.8156,
+      "step": 1340
+    },
+    {
+      "epoch": 0.11418421720375539,
+      "grad_norm": 0.9733187556266785,
+      "learning_rate": 2e-05,
+      "loss": 0.8002,
+      "step": 1350
+    },
+    {
+      "epoch": 0.1150300262200795,
+      "grad_norm": 0.4190857410430908,
+      "learning_rate": 2e-05,
+      "loss": 0.7965,
+      "step": 1360
+    },
+    {
+      "epoch": 0.11587583523640362,
+      "grad_norm": 0.5424562692642212,
+      "learning_rate": 2e-05,
+      "loss": 0.7873,
+      "step": 1370
+    },
+    {
+      "epoch": 0.11672164425272774,
+      "grad_norm": 0.47067514061927795,
+      "learning_rate": 2e-05,
+      "loss": 0.808,
+      "step": 1380
+    },
+    {
+      "epoch": 0.11756745326905185,
+      "grad_norm": 0.4544713497161865,
+      "learning_rate": 2e-05,
+      "loss": 0.8203,
+      "step": 1390
+    },
+    {
+      "epoch": 0.11841326228537596,
+      "grad_norm": 0.4768624007701874,
+      "learning_rate": 2e-05,
+      "loss": 0.8102,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11925907130170008,
+      "grad_norm": 0.4631892442703247,
+      "learning_rate": 2e-05,
+      "loss": 0.8102,
+      "step": 1410
+    },
+    {
+      "epoch": 0.12010488031802419,
+      "grad_norm": 0.5050587058067322,
+      "learning_rate": 2e-05,
+      "loss": 0.829,
+      "step": 1420
+    },
+    {
+      "epoch": 0.1209506893343483,
+      "grad_norm": 0.4511262774467468,
+      "learning_rate": 2e-05,
+      "loss": 0.8035,
+      "step": 1430
+    },
+    {
+      "epoch": 0.12179649835067242,
+      "grad_norm": 0.43339452147483826,
+      "learning_rate": 2e-05,
+      "loss": 0.8051,
+      "step": 1440
+    },
+    {
+      "epoch": 0.12264230736699654,
+      "grad_norm": 0.5338362455368042,
+      "learning_rate": 2e-05,
+      "loss": 0.8059,
+      "step": 1450
+    },
+    {
+      "epoch": 0.12348811638332065,
+      "grad_norm": 0.47970321774482727,
+      "learning_rate": 2e-05,
+      "loss": 0.815,
+      "step": 1460
+    },
+    {
+      "epoch": 0.12433392539964476,
+      "grad_norm": 0.4572729766368866,
+      "learning_rate": 2e-05,
+      "loss": 0.8127,
+      "step": 1470
+    },
+    {
+      "epoch": 0.12517973441596889,
+      "grad_norm": 0.38782718777656555,
+      "learning_rate": 2e-05,
+      "loss": 0.7933,
+      "step": 1480
+    },
+    {
+      "epoch": 0.126025543432293,
+      "grad_norm": 0.43446066975593567,
+      "learning_rate": 2e-05,
+      "loss": 0.8175,
+      "step": 1490
+    },
+    {
+      "epoch": 0.1268713524486171,
+      "grad_norm": 0.4613476097583771,
+      "learning_rate": 2e-05,
+      "loss": 0.7775,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12771716146494122,
+      "grad_norm": 0.48205533623695374,
+      "learning_rate": 2e-05,
+      "loss": 0.7967,
+      "step": 1510
+    },
+    {
+      "epoch": 0.12856297048126533,
+      "grad_norm": 0.5545839071273804,
+      "learning_rate": 2e-05,
+      "loss": 0.8012,
+      "step": 1520
+    },
+    {
+      "epoch": 0.12940877949758944,
+      "grad_norm": 0.4609675109386444,
+      "learning_rate": 2e-05,
+      "loss": 0.8135,
+      "step": 1530
+    },
+    {
+      "epoch": 0.13025458851391356,
+      "grad_norm": 0.4784204363822937,
+      "learning_rate": 2e-05,
+      "loss": 0.7922,
+      "step": 1540
+    },
+    {
+      "epoch": 0.13110039753023767,
+      "grad_norm": 0.4227185547351837,
+      "learning_rate": 2e-05,
+      "loss": 0.7951,
+      "step": 1550
+    },
+    {
+      "epoch": 0.13194620654656178,
+      "grad_norm": 0.4403364956378937,
+      "learning_rate": 2e-05,
+      "loss": 0.7984,
+      "step": 1560
+    },
+    {
+      "epoch": 0.1327920155628859,
+      "grad_norm": 0.4523667097091675,
+      "learning_rate": 2e-05,
+      "loss": 0.7925,
+      "step": 1570
+    },
+    {
+      "epoch": 0.13363782457921,
+      "grad_norm": 0.43016231060028076,
+      "learning_rate": 2e-05,
+      "loss": 0.8288,
+      "step": 1580
+    },
+    {
+      "epoch": 0.13448363359553414,
+      "grad_norm": 0.42455920577049255,
+      "learning_rate": 2e-05,
+      "loss": 0.7893,
+      "step": 1590
+    },
+    {
+      "epoch": 0.13532944261185825,
+      "grad_norm": 0.46288159489631653,
+      "learning_rate": 2e-05,
+      "loss": 0.8009,
+      "step": 1600
+    },
+    {
+      "epoch": 0.13617525162818236,
+      "grad_norm": 0.4296059012413025,
+      "learning_rate": 2e-05,
+      "loss": 0.8127,
+      "step": 1610
+    },
+    {
+      "epoch": 0.13702106064450648,
+      "grad_norm": 0.48048466444015503,
+      "learning_rate": 2e-05,
+      "loss": 0.7905,
+      "step": 1620
+    },
+    {
+      "epoch": 0.1378668696608306,
+      "grad_norm": 0.44896018505096436,
+      "learning_rate": 2e-05,
+      "loss": 0.8014,
+      "step": 1630
+    },
+    {
+      "epoch": 0.1387126786771547,
+      "grad_norm": 0.4625764787197113,
+      "learning_rate": 2e-05,
+      "loss": 0.8012,
+      "step": 1640
+    },
+    {
+      "epoch": 0.1395584876934788,
+      "grad_norm": 0.4218761622905731,
+      "learning_rate": 2e-05,
+      "loss": 0.7818,
+      "step": 1650
+    },
+    {
+      "epoch": 0.14040429670980292,
+      "grad_norm": 0.585142195224762,
+      "learning_rate": 2e-05,
+      "loss": 0.8171,
+      "step": 1660
+    },
+    {
+      "epoch": 0.14125010572612703,
+      "grad_norm": 0.5669842958450317,
+      "learning_rate": 2e-05,
+      "loss": 0.8024,
+      "step": 1670
+    },
+    {
+      "epoch": 0.14209591474245115,
+      "grad_norm": 0.45047566294670105,
+      "learning_rate": 2e-05,
+      "loss": 0.7835,
+      "step": 1680
+    },
+    {
+      "epoch": 0.14294172375877526,
+      "grad_norm": 0.4753831624984741,
+      "learning_rate": 2e-05,
+      "loss": 0.7544,
+      "step": 1690
+    },
+    {
+      "epoch": 0.14378753277509937,
+      "grad_norm": 0.4583908021450043,
+      "learning_rate": 2e-05,
+      "loss": 0.795,
+      "step": 1700
+    },
+    {
+      "epoch": 0.1446333417914235,
+      "grad_norm": 0.44783419370651245,
+      "learning_rate": 2e-05,
+      "loss": 0.8283,
+      "step": 1710
+    },
+    {
+      "epoch": 0.14547915080774762,
+      "grad_norm": 0.46793651580810547,
+      "learning_rate": 2e-05,
+      "loss": 0.7912,
+      "step": 1720
+    },
+    {
+      "epoch": 0.14632495982407173,
+      "grad_norm": 0.47512468695640564,
+      "learning_rate": 2e-05,
+      "loss": 0.7783,
+      "step": 1730
+    },
+    {
+      "epoch": 0.14717076884039584,
+      "grad_norm": 0.448434442281723,
+      "learning_rate": 2e-05,
+      "loss": 0.802,
+      "step": 1740
+    },
+    {
+      "epoch": 0.14801657785671996,
+      "grad_norm": 0.4518120288848877,
+      "learning_rate": 2e-05,
+      "loss": 0.786,
+      "step": 1750
+    },
+    {
+      "epoch": 0.14886238687304407,
+      "grad_norm": 0.4621693193912506,
+      "learning_rate": 2e-05,
+      "loss": 0.7936,
+      "step": 1760
+    },
+    {
+      "epoch": 0.14970819588936818,
+      "grad_norm": 0.4969255030155182,
+      "learning_rate": 2e-05,
+      "loss": 0.8095,
+      "step": 1770
+    },
+    {
+      "epoch": 0.1505540049056923,
+      "grad_norm": 0.43839049339294434,
+      "learning_rate": 2e-05,
+      "loss": 0.7985,
+      "step": 1780
+    },
+    {
+      "epoch": 0.1513998139220164,
+      "grad_norm": 0.37961190938949585,
+      "learning_rate": 2e-05,
+      "loss": 0.789,
+      "step": 1790
+    },
+    {
+      "epoch": 0.1522456229383405,
+      "grad_norm": 0.45644503831863403,
+      "learning_rate": 2e-05,
+      "loss": 0.7976,
+      "step": 1800
+    },
+    {
+      "epoch": 0.15309143195466463,
+      "grad_norm": 0.4018310606479645,
+      "learning_rate": 2e-05,
+      "loss": 0.7814,
+      "step": 1810
+    },
+    {
+      "epoch": 0.15393724097098876,
+      "grad_norm": 0.45710137486457825,
+      "learning_rate": 2e-05,
+      "loss": 0.7776,
+      "step": 1820
+    },
+    {
+      "epoch": 0.15478304998731288,
+      "grad_norm": 0.41975775361061096,
+      "learning_rate": 2e-05,
+      "loss": 0.7871,
+      "step": 1830
+    },
+    {
+      "epoch": 0.155628859003637,
+      "grad_norm": 0.4338706135749817,
+      "learning_rate": 2e-05,
+      "loss": 0.8084,
+      "step": 1840
+    },
+    {
+      "epoch": 0.1564746680199611,
+      "grad_norm": 0.4133562445640564,
+      "learning_rate": 2e-05,
+      "loss": 0.7729,
+      "step": 1850
+    },
+    {
+      "epoch": 0.1573204770362852,
+      "grad_norm": 0.42560043931007385,
+      "learning_rate": 2e-05,
+      "loss": 0.7944,
+      "step": 1860
+    },
+    {
+      "epoch": 0.15816628605260932,
+      "grad_norm": 0.41439342498779297,
+      "learning_rate": 2e-05,
+      "loss": 0.8019,
+      "step": 1870
+    },
+    {
+      "epoch": 0.15901209506893343,
+      "grad_norm": 0.395673006772995,
+      "learning_rate": 2e-05,
+      "loss": 0.7791,
+      "step": 1880
+    },
+    {
+      "epoch": 0.15985790408525755,
+      "grad_norm": 0.4551609456539154,
+      "learning_rate": 2e-05,
+      "loss": 0.792,
+      "step": 1890
+    },
+    {
+      "epoch": 0.16070371310158166,
+      "grad_norm": 0.4200981557369232,
+      "learning_rate": 2e-05,
+      "loss": 0.8108,
+      "step": 1900
+    },
+    {
+      "epoch": 0.16154952211790577,
+      "grad_norm": 0.4462941586971283,
+      "learning_rate": 2e-05,
+      "loss": 0.7994,
+      "step": 1910
+    },
+    {
+      "epoch": 0.16239533113422988,
+      "grad_norm": 0.4103948771953583,
+      "learning_rate": 2e-05,
+      "loss": 0.7816,
+      "step": 1920
+    },
+    {
+      "epoch": 0.163241140150554,
+      "grad_norm": 0.42093852162361145,
+      "learning_rate": 2e-05,
+      "loss": 0.8016,
+      "step": 1930
+    },
+    {
+      "epoch": 0.16408694916687813,
+      "grad_norm": 0.4158271551132202,
+      "learning_rate": 2e-05,
+      "loss": 0.8263,
+      "step": 1940
+    },
+    {
+      "epoch": 0.16493275818320224,
+      "grad_norm": 0.44030293822288513,
+      "learning_rate": 2e-05,
+      "loss": 0.8116,
+      "step": 1950
+    },
+    {
+      "epoch": 0.16577856719952636,
+      "grad_norm": 0.5266362428665161,
+      "learning_rate": 2e-05,
+      "loss": 0.8033,
+      "step": 1960
+    },
+    {
+      "epoch": 0.16662437621585047,
+      "grad_norm": 0.4341905415058136,
+      "learning_rate": 2e-05,
+      "loss": 0.7776,
+      "step": 1970
+    },
+    {
+      "epoch": 0.16747018523217458,
+      "grad_norm": 0.46349701285362244,
+      "learning_rate": 2e-05,
+      "loss": 0.7933,
+      "step": 1980
+    },
+    {
+      "epoch": 0.1683159942484987,
+      "grad_norm": 0.43137380480766296,
+      "learning_rate": 2e-05,
+      "loss": 0.776,
+      "step": 1990
+    },
+    {
+      "epoch": 0.1691618032648228,
+      "grad_norm": 0.5078220367431641,
+      "learning_rate": 2e-05,
+      "loss": 0.789,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1700076122811469,
+      "grad_norm": 0.47885942459106445,
+      "learning_rate": 2e-05,
+      "loss": 0.8118,
+      "step": 2010
+    },
+    {
+      "epoch": 0.17085342129747103,
+      "grad_norm": 0.44221749901771545,
+      "learning_rate": 2e-05,
+      "loss": 0.8316,
+      "step": 2020
+    },
+    {
+      "epoch": 0.17169923031379514,
+      "grad_norm": 0.5326676368713379,
+      "learning_rate": 2e-05,
+      "loss": 0.8023,
+      "step": 2030
+    },
+    {
+      "epoch": 0.17254503933011925,
+      "grad_norm": 0.40410059690475464,
+      "learning_rate": 2e-05,
+      "loss": 0.8023,
+      "step": 2040
+    },
+    {
+      "epoch": 0.17339084834644336,
+      "grad_norm": 0.4702794849872589,
+      "learning_rate": 2e-05,
+      "loss": 0.801,
+      "step": 2050
+    },
+    {
+      "epoch": 0.1742366573627675,
+      "grad_norm": 0.42183738946914673,
+      "learning_rate": 2e-05,
+      "loss": 0.792,
+      "step": 2060
+    },
+    {
+      "epoch": 0.1750824663790916,
+      "grad_norm": 0.4325072765350342,
+      "learning_rate": 2e-05,
+      "loss": 0.7822,
+      "step": 2070
+    },
+    {
+      "epoch": 0.17592827539541572,
+      "grad_norm": 0.42313942313194275,
+      "learning_rate": 2e-05,
+      "loss": 0.7592,
+      "step": 2080
+    },
+    {
+      "epoch": 0.17677408441173983,
+      "grad_norm": 0.435320645570755,
+      "learning_rate": 2e-05,
+      "loss": 0.7525,
+      "step": 2090
+    },
+    {
+      "epoch": 0.17761989342806395,
+      "grad_norm": 0.42551541328430176,
+      "learning_rate": 2e-05,
+      "loss": 0.7801,
+      "step": 2100
+    },
+    {
+      "epoch": 0.17846570244438806,
+      "grad_norm": 0.5708727240562439,
+      "learning_rate": 2e-05,
+      "loss": 0.7879,
+      "step": 2110
+    },
+    {
+      "epoch": 0.17931151146071217,
+      "grad_norm": 0.4572547674179077,
+      "learning_rate": 2e-05,
+      "loss": 0.7471,
+      "step": 2120
+    },
+    {
+      "epoch": 0.18015732047703628,
+      "grad_norm": 0.42310115694999695,
+      "learning_rate": 2e-05,
+      "loss": 0.7761,
+      "step": 2130
+    },
+    {
+      "epoch": 0.1810031294933604,
+      "grad_norm": 0.4499841332435608,
+      "learning_rate": 2e-05,
+      "loss": 0.8208,
+      "step": 2140
+    },
+    {
+      "epoch": 0.1818489385096845,
+      "grad_norm": 0.4960625469684601,
+      "learning_rate": 2e-05,
+      "loss": 0.7854,
+      "step": 2150
+    },
+    {
+      "epoch": 0.18269474752600862,
+      "grad_norm": 0.417538583278656,
+      "learning_rate": 2e-05,
+      "loss": 0.7757,
+      "step": 2160
+    },
+    {
+      "epoch": 0.18354055654233273,
+      "grad_norm": 0.4538043737411499,
+      "learning_rate": 2e-05,
+      "loss": 0.7689,
+      "step": 2170
+    },
+    {
+      "epoch": 0.18438636555865687,
+      "grad_norm": 0.5369532704353333,
+      "learning_rate": 2e-05,
+      "loss": 0.8262,
+      "step": 2180
+    },
+    {
+      "epoch": 0.18523217457498098,
+      "grad_norm": 0.46377670764923096,
+      "learning_rate": 2e-05,
+      "loss": 0.7843,
+      "step": 2190
+    },
+    {
+      "epoch": 0.1860779835913051,
+      "grad_norm": 0.6210406422615051,
+      "learning_rate": 2e-05,
+      "loss": 0.8207,
+      "step": 2200
+    },
+    {
+      "epoch": 0.1869237926076292,
+      "grad_norm": 0.42272546887397766,
+      "learning_rate": 2e-05,
+      "loss": 0.7806,
+      "step": 2210
+    },
+    {
+      "epoch": 0.18776960162395331,
+      "grad_norm": 0.4674997329711914,
+      "learning_rate": 2e-05,
+      "loss": 0.757,
+      "step": 2220
+    },
+    {
+      "epoch": 0.18861541064027743,
+      "grad_norm": 0.4644511044025421,
+      "learning_rate": 2e-05,
+      "loss": 0.7846,
+      "step": 2230
+    },
+    {
+      "epoch": 0.18946121965660154,
+      "grad_norm": 0.46675005555152893,
+      "learning_rate": 2e-05,
+      "loss": 0.7699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.19030702867292565,
+      "grad_norm": 0.4362230598926544,
+      "learning_rate": 2e-05,
+      "loss": 0.7872,
+      "step": 2250
+    },
+    {
+      "epoch": 0.19115283768924976,
+      "grad_norm": 0.4449322819709778,
+      "learning_rate": 2e-05,
+      "loss": 0.7759,
+      "step": 2260
+    },
+    {
+      "epoch": 0.19199864670557387,
+      "grad_norm": 0.4517369270324707,
+      "learning_rate": 2e-05,
+      "loss": 0.755,
+      "step": 2270
+    },
+    {
+      "epoch": 0.19284445572189798,
+      "grad_norm": 0.42636391520500183,
+      "learning_rate": 2e-05,
+      "loss": 0.7666,
+      "step": 2280
+    },
+    {
+      "epoch": 0.19369026473822212,
+      "grad_norm": 0.44382089376449585,
+      "learning_rate": 2e-05,
+      "loss": 0.7936,
+      "step": 2290
+    },
+    {
+      "epoch": 0.19453607375454623,
+      "grad_norm": 0.42471468448638916,
+      "learning_rate": 2e-05,
+      "loss": 0.7524,
+      "step": 2300
+    },
+    {
+      "epoch": 0.19538188277087035,
+      "grad_norm": 0.42539870738983154,
+      "learning_rate": 2e-05,
+      "loss": 0.7638,
+      "step": 2310
+    },
+    {
+      "epoch": 0.19622769178719446,
+      "grad_norm": 0.4424472451210022,
+      "learning_rate": 2e-05,
+      "loss": 0.8212,
+      "step": 2320
+    },
+    {
+      "epoch": 0.19707350080351857,
+      "grad_norm": 0.44723621010780334,
+      "learning_rate": 2e-05,
+      "loss": 0.8267,
+      "step": 2330
+    },
+    {
+      "epoch": 0.19791930981984268,
+      "grad_norm": 0.4656752049922943,
+      "learning_rate": 2e-05,
+      "loss": 0.7989,
+      "step": 2340
+    },
+    {
+      "epoch": 0.1987651188361668,
+      "grad_norm": 0.4924338757991791,
+      "learning_rate": 2e-05,
+      "loss": 0.7805,
+      "step": 2350
+    },
+    {
+      "epoch": 0.1996109278524909,
+      "grad_norm": 0.46828511357307434,
+      "learning_rate": 2e-05,
+      "loss": 0.7802,
+      "step": 2360
+    },
+    {
+      "epoch": 0.20045673686881502,
+      "grad_norm": 0.3915436863899231,
+      "learning_rate": 2e-05,
+      "loss": 0.7956,
+      "step": 2370
+    },
+    {
+      "epoch": 0.20130254588513913,
+      "grad_norm": 0.4222668707370758,
+      "learning_rate": 2e-05,
+      "loss": 0.7604,
+      "step": 2380
+    },
+    {
+      "epoch": 0.20214835490146324,
+      "grad_norm": 0.4440152049064636,
+      "learning_rate": 2e-05,
+      "loss": 0.7649,
+      "step": 2390
+    },
+    {
+      "epoch": 0.20299416391778735,
+      "grad_norm": 0.4797949492931366,
+      "learning_rate": 2e-05,
+      "loss": 0.7803,
+      "step": 2400
+    },
+    {
+      "epoch": 0.2038399729341115,
+      "grad_norm": 0.48502403497695923,
+      "learning_rate": 2e-05,
+      "loss": 0.8036,
+      "step": 2410
+    },
+    {
+      "epoch": 0.2046857819504356,
+      "grad_norm": 0.4094001352787018,
+      "learning_rate": 2e-05,
+      "loss": 0.7795,
+      "step": 2420
+    },
+    {
+      "epoch": 0.20553159096675971,
+      "grad_norm": 0.40637558698654175,
+      "learning_rate": 2e-05,
+      "loss": 0.7579,
+      "step": 2430
+    },
+    {
+      "epoch": 0.20637739998308383,
+      "grad_norm": 0.4431319236755371,
+      "learning_rate": 2e-05,
+      "loss": 0.8001,
+      "step": 2440
+    },
+    {
+      "epoch": 0.20722320899940794,
+      "grad_norm": 0.49175867438316345,
+      "learning_rate": 2e-05,
+      "loss": 0.7851,
+      "step": 2450
+    },
+    {
+      "epoch": 0.20806901801573205,
+      "grad_norm": 0.4432580769062042,
+      "learning_rate": 2e-05,
+      "loss": 0.7793,
+      "step": 2460
+    },
+    {
+      "epoch": 0.20891482703205616,
+      "grad_norm": 0.44891810417175293,
+      "learning_rate": 2e-05,
+      "loss": 0.752,
+      "step": 2470
+    },
+    {
+      "epoch": 0.20976063604838027,
+      "grad_norm": 0.4552386403083801,
+      "learning_rate": 2e-05,
+      "loss": 0.7647,
+      "step": 2480
+    },
+    {
+      "epoch": 0.21060644506470438,
+      "grad_norm": 0.49954554438591003,
+      "learning_rate": 2e-05,
+      "loss": 0.7447,
+      "step": 2490
+    },
+    {
+      "epoch": 0.2114522540810285,
+      "grad_norm": 0.500321090221405,
+      "learning_rate": 2e-05,
+      "loss": 0.7877,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2122980630973526,
+      "grad_norm": 0.4038744866847992,
+      "learning_rate": 2e-05,
+      "loss": 0.8237,
+      "step": 2510
+    },
+    {
+      "epoch": 0.21314387211367672,
+      "grad_norm": 0.46424946188926697,
+      "learning_rate": 2e-05,
+      "loss": 0.7423,
+      "step": 2520
+    },
+    {
+      "epoch": 0.21398968113000086,
+      "grad_norm": 0.41768935322761536,
+      "learning_rate": 2e-05,
+      "loss": 0.7934,
+      "step": 2530
+    },
+    {
+      "epoch": 0.21483549014632497,
+      "grad_norm": 0.4619862735271454,
+      "learning_rate": 2e-05,
+      "loss": 0.7702,
+      "step": 2540
+    },
+    {
+      "epoch": 0.21568129916264908,
+      "grad_norm": 0.640251100063324,
+      "learning_rate": 2e-05,
+      "loss": 0.7725,
+      "step": 2550
+    },
+    {
+      "epoch": 0.2165271081789732,
+      "grad_norm": 0.4279073178768158,
+      "learning_rate": 2e-05,
+      "loss": 0.7684,
+      "step": 2560
+    },
+    {
+      "epoch": 0.2173729171952973,
+      "grad_norm": 0.414326936006546,
+      "learning_rate": 2e-05,
+      "loss": 0.7838,
+      "step": 2570
+    },
+    {
+      "epoch": 0.21821872621162142,
+      "grad_norm": 0.7426477670669556,
+      "learning_rate": 2e-05,
+      "loss": 0.7989,
+      "step": 2580
+    },
+    {
+      "epoch": 0.21906453522794553,
+      "grad_norm": 0.4603583812713623,
+      "learning_rate": 2e-05,
+      "loss": 0.7971,
+      "step": 2590
+    },
+    {
+      "epoch": 0.21991034424426964,
+      "grad_norm": 0.4465532898902893,
+      "learning_rate": 2e-05,
+      "loss": 0.7807,
+      "step": 2600
+    },
+    {
+      "epoch": 0.22075615326059375,
+      "grad_norm": 0.42773884534835815,
+      "learning_rate": 2e-05,
+      "loss": 0.778,
+      "step": 2610
+    },
+    {
+      "epoch": 0.22160196227691786,
+      "grad_norm": 0.49307650327682495,
+      "learning_rate": 2e-05,
+      "loss": 0.7894,
+      "step": 2620
+    },
+    {
+      "epoch": 0.22244777129324197,
+      "grad_norm": 0.46584203839302063,
+      "learning_rate": 2e-05,
+      "loss": 0.7858,
+      "step": 2630
+    },
+    {
+      "epoch": 0.2232935803095661,
+      "grad_norm": 0.41671979427337646,
+      "learning_rate": 2e-05,
+      "loss": 0.7614,
+      "step": 2640
+    },
+    {
+      "epoch": 0.22413938932589023,
+      "grad_norm": 0.42979925870895386,
+      "learning_rate": 2e-05,
+      "loss": 0.7956,
+      "step": 2650
+    },
+    {
+      "epoch": 0.22498519834221434,
+      "grad_norm": 0.44125261902809143,
+      "learning_rate": 2e-05,
+      "loss": 0.8024,
+      "step": 2660
+    },
+    {
+      "epoch": 0.22583100735853845,
+      "grad_norm": 0.4487869441509247,
+      "learning_rate": 2e-05,
+      "loss": 0.8061,
+      "step": 2670
+    },
+    {
+      "epoch": 0.22667681637486256,
+      "grad_norm": 0.41210177540779114,
+      "learning_rate": 2e-05,
+      "loss": 0.7495,
+      "step": 2680
+    },
+    {
+      "epoch": 0.22752262539118667,
+      "grad_norm": 0.47433891892433167,
+      "learning_rate": 2e-05,
+      "loss": 0.7768,
+      "step": 2690
+    },
+    {
+      "epoch": 0.22836843440751078,
+      "grad_norm": 0.41296109557151794,
+      "learning_rate": 2e-05,
+      "loss": 0.8046,
+      "step": 2700
+    },
+    {
+      "epoch": 0.2292142434238349,
+      "grad_norm": 0.4591984152793884,
+      "learning_rate": 2e-05,
+      "loss": 0.7765,
+      "step": 2710
+    },
+    {
+      "epoch": 0.230060052440159,
+      "grad_norm": 0.44367364048957825,
+      "learning_rate": 2e-05,
+      "loss": 0.7893,
+      "step": 2720
+    },
+    {
+      "epoch": 0.23090586145648312,
+      "grad_norm": 0.4004356861114502,
+      "learning_rate": 2e-05,
+      "loss": 0.7795,
+      "step": 2730
+    },
+    {
+      "epoch": 0.23175167047280723,
+      "grad_norm": 0.4360814690589905,
+      "learning_rate": 2e-05,
+      "loss": 0.7923,
+      "step": 2740
+    },
+    {
+      "epoch": 0.23259747948913134,
+      "grad_norm": 0.41821685433387756,
+      "learning_rate": 2e-05,
+      "loss": 0.8028,
+      "step": 2750
+    },
+    {
+      "epoch": 0.23344328850545548,
+      "grad_norm": 0.42375466227531433,
+      "learning_rate": 2e-05,
+      "loss": 0.7726,
+      "step": 2760
+    },
+    {
+      "epoch": 0.2342890975217796,
+      "grad_norm": 0.4679203927516937,
+      "learning_rate": 2e-05,
+      "loss": 0.7495,
+      "step": 2770
+    },
+    {
+      "epoch": 0.2351349065381037,
+      "grad_norm": 0.46849754452705383,
+      "learning_rate": 2e-05,
+      "loss": 0.7789,
+      "step": 2780
+    },
+    {
+      "epoch": 0.23598071555442782,
+      "grad_norm": 0.45304617285728455,
+      "learning_rate": 2e-05,
+      "loss": 0.77,
+      "step": 2790
+    },
+    {
+      "epoch": 0.23682652457075193,
+      "grad_norm": 0.4693162441253662,
+      "learning_rate": 2e-05,
+      "loss": 0.8115,
+      "step": 2800
+    },
+    {
+      "epoch": 0.23767233358707604,
+      "grad_norm": 0.4511564373970032,
+      "learning_rate": 2e-05,
+      "loss": 0.7584,
+      "step": 2810
+    },
+    {
+      "epoch": 0.23851814260340015,
+      "grad_norm": 0.45412859320640564,
+      "learning_rate": 2e-05,
+      "loss": 0.8035,
+      "step": 2820
+    },
+    {
+      "epoch": 0.23936395161972426,
+      "grad_norm": 0.4556509554386139,
+      "learning_rate": 2e-05,
+      "loss": 0.7786,
+      "step": 2830
+    },
+    {
+      "epoch": 0.24020976063604838,
+      "grad_norm": 0.5524949431419373,
+      "learning_rate": 2e-05,
+      "loss": 0.7859,
+      "step": 2840
+    },
+    {
+      "epoch": 0.2410555696523725,
+      "grad_norm": 0.4725969731807709,
+      "learning_rate": 2e-05,
+      "loss": 0.7959,
+      "step": 2850
+    },
+    {
+      "epoch": 0.2419013786686966,
+      "grad_norm": 0.4201352000236511,
+      "learning_rate": 2e-05,
+      "loss": 0.7899,
+      "step": 2860
+    },
+    {
+      "epoch": 0.2427471876850207,
+      "grad_norm": 0.46002620458602905,
+      "learning_rate": 2e-05,
+      "loss": 0.8203,
+      "step": 2870
+    },
+    {
+      "epoch": 0.24359299670134485,
+      "grad_norm": 0.4765322804450989,
+      "learning_rate": 2e-05,
+      "loss": 0.7743,
+      "step": 2880
+    },
+    {
+      "epoch": 0.24443880571766896,
+      "grad_norm": 0.43338263034820557,
+      "learning_rate": 2e-05,
+      "loss": 0.7963,
+      "step": 2890
+    },
+    {
+      "epoch": 0.24528461473399307,
+      "grad_norm": 0.4687747359275818,
+      "learning_rate": 2e-05,
+      "loss": 0.7907,
+      "step": 2900
+    },
+    {
+      "epoch": 0.24613042375031718,
+      "grad_norm": 0.4330938458442688,
+      "learning_rate": 2e-05,
+      "loss": 0.7575,
+      "step": 2910
+    },
+    {
+      "epoch": 0.2469762327666413,
+      "grad_norm": 0.44089579582214355,
+      "learning_rate": 2e-05,
+      "loss": 0.7579,
+      "step": 2920
+    },
+    {
+      "epoch": 0.2478220417829654,
+      "grad_norm": 0.44153931736946106,
+      "learning_rate": 2e-05,
+      "loss": 0.7685,
+      "step": 2930
+    },
+    {
+      "epoch": 0.24866785079928952,
+      "grad_norm": 0.4301970899105072,
+      "learning_rate": 2e-05,
+      "loss": 0.7613,
+      "step": 2940
+    },
+    {
+      "epoch": 0.24951365981561363,
+      "grad_norm": 0.5281918048858643,
+      "learning_rate": 2e-05,
+      "loss": 0.7704,
+      "step": 2950
+    },
+    {
+      "epoch": 0.25035946883193777,
+      "grad_norm": 0.47316303849220276,
+      "learning_rate": 2e-05,
+      "loss": 0.7891,
+      "step": 2960
+    },
+    {
+      "epoch": 0.25120527784826185,
+      "grad_norm": 0.4362885057926178,
+      "learning_rate": 2e-05,
+      "loss": 0.7782,
+      "step": 2970
+    },
+    {
+      "epoch": 0.252051086864586,
+      "grad_norm": 0.4286717474460602,
+      "learning_rate": 2e-05,
+      "loss": 0.7369,
+      "step": 2980
+    },
+    {
+      "epoch": 0.2528968958809101,
+      "grad_norm": 0.43915069103240967,
+      "learning_rate": 2e-05,
+      "loss": 0.7578,
+      "step": 2990
+    },
+    {
+      "epoch": 0.2537427048972342,
+      "grad_norm": 0.4347997307777405,
+      "learning_rate": 2e-05,
+      "loss": 0.7576,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2545885139135583,
+      "grad_norm": 0.509215235710144,
+      "learning_rate": 2e-05,
+      "loss": 0.8031,
+      "step": 3010
+    },
+    {
+      "epoch": 0.25543432292988244,
+      "grad_norm": 0.42407557368278503,
+      "learning_rate": 2e-05,
+      "loss": 0.7702,
+      "step": 3020
+    },
+    {
+      "epoch": 0.2562801319462065,
+      "grad_norm": 0.5860919952392578,
+      "learning_rate": 2e-05,
+      "loss": 0.7734,
+      "step": 3030
+    },
+    {
+      "epoch": 0.25712594096253066,
+      "grad_norm": 0.44230198860168457,
+      "learning_rate": 2e-05,
+      "loss": 0.7895,
+      "step": 3040
+    },
+    {
+      "epoch": 0.25797174997885475,
+      "grad_norm": 0.4194599390029907,
+      "learning_rate": 2e-05,
+      "loss": 0.7929,
+      "step": 3050
+    },
+    {
+      "epoch": 0.2588175589951789,
+      "grad_norm": 0.49500542879104614,
+      "learning_rate": 2e-05,
+      "loss": 0.7776,
+      "step": 3060
+    },
+    {
+      "epoch": 0.259663368011503,
+      "grad_norm": 0.428522527217865,
+      "learning_rate": 2e-05,
+      "loss": 0.7537,
+      "step": 3070
+    },
+    {
+      "epoch": 0.2605091770278271,
+      "grad_norm": 0.4581354558467865,
+      "learning_rate": 2e-05,
+      "loss": 0.7927,
+      "step": 3080
+    },
+    {
+      "epoch": 0.26135498604415125,
+      "grad_norm": 0.44287940859794617,
+      "learning_rate": 2e-05,
+      "loss": 0.7758,
+      "step": 3090
+    },
+    {
+      "epoch": 0.26220079506047533,
+      "grad_norm": 0.5998321175575256,
+      "learning_rate": 2e-05,
+      "loss": 0.7898,
+      "step": 3100
+    },
+    {
+      "epoch": 0.2630466040767995,
+      "grad_norm": 0.44311368465423584,
+      "learning_rate": 2e-05,
+      "loss": 0.7706,
+      "step": 3110
+    },
+    {
+      "epoch": 0.26389241309312356,
+      "grad_norm": 0.43940284848213196,
+      "learning_rate": 2e-05,
+      "loss": 0.7876,
+      "step": 3120
+    },
+    {
+      "epoch": 0.2647382221094477,
+      "grad_norm": 0.46256837248802185,
+      "learning_rate": 2e-05,
+      "loss": 0.7873,
+      "step": 3130
+    },
+    {
+      "epoch": 0.2655840311257718,
+      "grad_norm": 0.3986041247844696,
+      "learning_rate": 2e-05,
+      "loss": 0.7576,
+      "step": 3140
+    },
+    {
+      "epoch": 0.2664298401420959,
+      "grad_norm": 0.4460200369358063,
+      "learning_rate": 2e-05,
+      "loss": 0.767,
+      "step": 3150
+    },
+    {
+      "epoch": 0.26727564915842,
+      "grad_norm": 0.4661593437194824,
+      "learning_rate": 2e-05,
+      "loss": 0.7704,
+      "step": 3160
+    },
+    {
+      "epoch": 0.26812145817474414,
+      "grad_norm": 0.4676179587841034,
+      "learning_rate": 2e-05,
+      "loss": 0.8029,
+      "step": 3170
+    },
+    {
+      "epoch": 0.2689672671910683,
+      "grad_norm": 0.4331599175930023,
+      "learning_rate": 2e-05,
+      "loss": 0.783,
+      "step": 3180
+    },
+    {
+      "epoch": 0.26981307620739237,
+      "grad_norm": 0.416753351688385,
+      "learning_rate": 2e-05,
+      "loss": 0.7835,
+      "step": 3190
+    },
+    {
+      "epoch": 0.2706588852237165,
+      "grad_norm": 0.41046181321144104,
+      "learning_rate": 2e-05,
+      "loss": 0.7824,
+      "step": 3200
+    },
+    {
+      "epoch": 0.2715046942400406,
+      "grad_norm": 0.4057115614414215,
+      "learning_rate": 2e-05,
+      "loss": 0.7857,
+      "step": 3210
+    },
+    {
+      "epoch": 0.27235050325636473,
+      "grad_norm": 0.4670395255088806,
+      "learning_rate": 2e-05,
+      "loss": 0.7562,
+      "step": 3220
+    },
+    {
+      "epoch": 0.2731963122726888,
+      "grad_norm": 0.4727485775947571,
+      "learning_rate": 2e-05,
+      "loss": 0.7634,
+      "step": 3230
+    },
+    {
+      "epoch": 0.27404212128901295,
+      "grad_norm": 0.5169165730476379,
+      "learning_rate": 2e-05,
+      "loss": 0.7606,
+      "step": 3240
+    },
+    {
+      "epoch": 0.27488793030533704,
+      "grad_norm": 0.4498447775840759,
+      "learning_rate": 2e-05,
+      "loss": 0.7713,
+      "step": 3250
+    },
+    {
+      "epoch": 0.2757337393216612,
+      "grad_norm": 0.41400662064552307,
+      "learning_rate": 2e-05,
+      "loss": 0.7604,
+      "step": 3260
+    },
+    {
+      "epoch": 0.27657954833798526,
+      "grad_norm": 0.4343860149383545,
+      "learning_rate": 2e-05,
+      "loss": 0.7695,
+      "step": 3270
+    },
+    {
+      "epoch": 0.2774253573543094,
+      "grad_norm": 0.4273575246334076,
+      "learning_rate": 2e-05,
+      "loss": 0.7315,
+      "step": 3280
+    },
+    {
+      "epoch": 0.27827116637063354,
+      "grad_norm": 0.405123233795166,
+      "learning_rate": 2e-05,
+      "loss": 0.808,
+      "step": 3290
+    },
+    {
+      "epoch": 0.2791169753869576,
+      "grad_norm": 0.41338470578193665,
+      "learning_rate": 2e-05,
+      "loss": 0.7888,
+      "step": 3300
+    },
+    {
+      "epoch": 0.27996278440328176,
+      "grad_norm": 0.42915669083595276,
+      "learning_rate": 2e-05,
+      "loss": 0.7562,
+      "step": 3310
+    },
+    {
+      "epoch": 0.28080859341960585,
+      "grad_norm": 0.4712754487991333,
+      "learning_rate": 2e-05,
+      "loss": 0.7486,
+      "step": 3320
+    },
+    {
+      "epoch": 0.28165440243593,
+      "grad_norm": 0.44827619194984436,
+      "learning_rate": 2e-05,
+      "loss": 0.7727,
+      "step": 3330
+    },
+    {
+      "epoch": 0.28250021145225407,
+      "grad_norm": 0.5953311920166016,
+      "learning_rate": 2e-05,
+      "loss": 0.7857,
+      "step": 3340
+    },
+    {
+      "epoch": 0.2833460204685782,
+      "grad_norm": 0.4361172616481781,
+      "learning_rate": 2e-05,
+      "loss": 0.7753,
+      "step": 3350
+    },
+    {
+      "epoch": 0.2841918294849023,
+      "grad_norm": 0.4695591330528259,
+      "learning_rate": 2e-05,
+      "loss": 0.7553,
+      "step": 3360
+    },
+    {
+      "epoch": 0.28503763850122643,
+      "grad_norm": 1.3656271696090698,
+      "learning_rate": 2e-05,
+      "loss": 0.7926,
+      "step": 3370
+    },
+    {
+      "epoch": 0.2858834475175505,
+      "grad_norm": 0.44531548023223877,
+      "learning_rate": 2e-05,
+      "loss": 0.7591,
+      "step": 3380
+    },
+    {
+      "epoch": 0.28672925653387465,
+      "grad_norm": 0.48033207654953003,
+      "learning_rate": 2e-05,
+      "loss": 0.7636,
+      "step": 3390
+    },
+    {
+      "epoch": 0.28757506555019874,
+      "grad_norm": 0.4642755389213562,
+      "learning_rate": 2e-05,
+      "loss": 0.7654,
+      "step": 3400
+    },
+    {
+      "epoch": 0.2884208745665229,
+      "grad_norm": 0.5093075633049011,
+      "learning_rate": 2e-05,
+      "loss": 0.7504,
+      "step": 3410
+    },
+    {
+      "epoch": 0.289266683582847,
+      "grad_norm": 0.4360235631465912,
+      "learning_rate": 2e-05,
+      "loss": 0.7579,
+      "step": 3420
+    },
+    {
+      "epoch": 0.2901124925991711,
+      "grad_norm": 0.4275346100330353,
+      "learning_rate": 2e-05,
+      "loss": 0.7834,
+      "step": 3430
+    },
+    {
+      "epoch": 0.29095830161549524,
+      "grad_norm": 0.4238315522670746,
+      "learning_rate": 2e-05,
+      "loss": 0.7716,
+      "step": 3440
+    },
+    {
+      "epoch": 0.2918041106318193,
+      "grad_norm": 0.43771207332611084,
+      "learning_rate": 2e-05,
+      "loss": 0.7708,
+      "step": 3450
+    },
+    {
+      "epoch": 0.29264991964814346,
+      "grad_norm": 0.4327355623245239,
+      "learning_rate": 2e-05,
+      "loss": 0.7358,
+      "step": 3460
+    },
+    {
+      "epoch": 0.29349572866446755,
+      "grad_norm": 0.4890783429145813,
+      "learning_rate": 2e-05,
+      "loss": 0.7458,
+      "step": 3470
+    },
+    {
+      "epoch": 0.2943415376807917,
+      "grad_norm": 0.45127320289611816,
+      "learning_rate": 2e-05,
+      "loss": 0.7599,
+      "step": 3480
+    },
+    {
+      "epoch": 0.29518734669711577,
+      "grad_norm": 0.46975794434547424,
+      "learning_rate": 2e-05,
+      "loss": 0.751,
+      "step": 3490
+    },
+    {
+      "epoch": 0.2960331557134399,
+      "grad_norm": 0.5134473443031311,
+      "learning_rate": 2e-05,
+      "loss": 0.7814,
+      "step": 3500
+    },
+    {
+      "epoch": 0.296878964729764,
+      "grad_norm": 0.5506858229637146,
+      "learning_rate": 2e-05,
+      "loss": 0.7604,
+      "step": 3510
+    },
+    {
+      "epoch": 0.29772477374608813,
+      "grad_norm": 0.4502047896385193,
+      "learning_rate": 2e-05,
+      "loss": 0.7653,
+      "step": 3520
+    },
+    {
+      "epoch": 0.2985705827624123,
+      "grad_norm": 0.47807902097702026,
+      "learning_rate": 2e-05,
+      "loss": 0.8238,
+      "step": 3530
+    },
+    {
+      "epoch": 0.29941639177873636,
+      "grad_norm": 0.44825828075408936,
+      "learning_rate": 2e-05,
+      "loss": 0.7975,
+      "step": 3540
+    },
+    {
+      "epoch": 0.3002622007950605,
+      "grad_norm": 0.6734495162963867,
+      "learning_rate": 2e-05,
+      "loss": 0.7969,
+      "step": 3550
+    },
+    {
+      "epoch": 0.3011080098113846,
+      "grad_norm": 0.4248940348625183,
+      "learning_rate": 2e-05,
+      "loss": 0.7626,
+      "step": 3560
+    },
+    {
+      "epoch": 0.3019538188277087,
+      "grad_norm": 0.4616678059101105,
+      "learning_rate": 2e-05,
+      "loss": 0.7549,
+      "step": 3570
+    },
+    {
+      "epoch": 0.3027996278440328,
+      "grad_norm": 0.44951459765434265,
+      "learning_rate": 2e-05,
+      "loss": 0.783,
+      "step": 3580
+    },
+    {
+      "epoch": 0.30364543686035694,
+      "grad_norm": 0.6219090819358826,
+      "learning_rate": 2e-05,
+      "loss": 0.7734,
+      "step": 3590
+    },
+    {
+      "epoch": 0.304491245876681,
+      "grad_norm": 0.5511556267738342,
+      "learning_rate": 2e-05,
+      "loss": 0.7389,
+      "step": 3600
+    },
+    {
+      "epoch": 0.30533705489300517,
+      "grad_norm": 0.40981152653694153,
+      "learning_rate": 2e-05,
+      "loss": 0.7792,
+      "step": 3610
+    },
+    {
+      "epoch": 0.30618286390932925,
+      "grad_norm": 0.5050520896911621,
+      "learning_rate": 2e-05,
+      "loss": 0.7695,
+      "step": 3620
+    },
+    {
+      "epoch": 0.3070286729256534,
+      "grad_norm": 0.467257559299469,
+      "learning_rate": 2e-05,
+      "loss": 0.7594,
+      "step": 3630
+    },
+    {
+      "epoch": 0.30787448194197753,
+      "grad_norm": 0.47798600792884827,
+      "learning_rate": 2e-05,
+      "loss": 0.7679,
+      "step": 3640
+    },
+    {
+      "epoch": 0.3087202909583016,
+      "grad_norm": 0.49520930647850037,
+      "learning_rate": 2e-05,
+      "loss": 0.7509,
+      "step": 3650
+    },
+    {
+      "epoch": 0.30956609997462575,
+      "grad_norm": 0.454575777053833,
+      "learning_rate": 2e-05,
+      "loss": 0.753,
+      "step": 3660
+    },
+    {
+      "epoch": 0.31041190899094984,
+      "grad_norm": 0.9249985814094543,
+      "learning_rate": 2e-05,
+      "loss": 0.7713,
+      "step": 3670
+    },
+    {
+      "epoch": 0.311257718007274,
+      "grad_norm": 0.42839786410331726,
+      "learning_rate": 2e-05,
+      "loss": 0.7641,
+      "step": 3680
+    },
+    {
+      "epoch": 0.31210352702359806,
+      "grad_norm": 0.4245745539665222,
+      "learning_rate": 2e-05,
+      "loss": 0.7514,
+      "step": 3690
+    },
+    {
+      "epoch": 0.3129493360399222,
+      "grad_norm": 0.4420894980430603,
+      "learning_rate": 2e-05,
+      "loss": 0.7854,
+      "step": 3700
+    },
+    {
+      "epoch": 0.3137951450562463,
+      "grad_norm": 0.48038947582244873,
+      "learning_rate": 2e-05,
+      "loss": 0.7716,
+      "step": 3710
+    },
+    {
+      "epoch": 0.3146409540725704,
+      "grad_norm": 0.46390315890312195,
+      "learning_rate": 2e-05,
+      "loss": 0.781,
+      "step": 3720
+    },
+    {
+      "epoch": 0.3154867630888945,
+      "grad_norm": 0.44603219628334045,
+      "learning_rate": 2e-05,
+      "loss": 0.763,
+      "step": 3730
+    },
+    {
+      "epoch": 0.31633257210521865,
+      "grad_norm": 0.44132134318351746,
+      "learning_rate": 2e-05,
+      "loss": 0.7326,
+      "step": 3740
+    },
+    {
+      "epoch": 0.31717838112154273,
+      "grad_norm": 0.5154607892036438,
+      "learning_rate": 2e-05,
+      "loss": 0.761,
+      "step": 3750
+    },
+    {
+      "epoch": 0.31802419013786687,
+      "grad_norm": 0.4380301833152771,
+      "learning_rate": 2e-05,
+      "loss": 0.7544,
+      "step": 3760
+    },
+    {
+      "epoch": 0.318869999154191,
+      "grad_norm": 0.4140898585319519,
+      "learning_rate": 2e-05,
+      "loss": 0.7633,
+      "step": 3770
+    },
+    {
+      "epoch": 0.3197158081705151,
+      "grad_norm": 0.4655788838863373,
+      "learning_rate": 2e-05,
+      "loss": 0.7958,
+      "step": 3780
+    },
+    {
+      "epoch": 0.32056161718683923,
+      "grad_norm": 0.508803129196167,
+      "learning_rate": 2e-05,
+      "loss": 0.7646,
+      "step": 3790
+    },
+    {
+      "epoch": 0.3214074262031633,
+      "grad_norm": 0.45458531379699707,
+      "learning_rate": 2e-05,
+      "loss": 0.7674,
+      "step": 3800
+    },
+    {
+      "epoch": 0.32225323521948745,
+      "grad_norm": 0.44534432888031006,
+      "learning_rate": 2e-05,
+      "loss": 0.7549,
+      "step": 3810
+    },
+    {
+      "epoch": 0.32309904423581154,
+      "grad_norm": 0.49804991483688354,
+      "learning_rate": 2e-05,
+      "loss": 0.7805,
+      "step": 3820
+    },
+    {
+      "epoch": 0.3239448532521357,
+      "grad_norm": 0.45358508825302124,
+      "learning_rate": 2e-05,
+      "loss": 0.7761,
+      "step": 3830
+    },
+    {
+      "epoch": 0.32479066226845976,
+      "grad_norm": 0.4265481233596802,
+      "learning_rate": 2e-05,
+      "loss": 0.7407,
+      "step": 3840
+    },
+    {
+      "epoch": 0.3256364712847839,
+      "grad_norm": 0.4509756863117218,
+      "learning_rate": 2e-05,
+      "loss": 0.7771,
+      "step": 3850
+    },
+    {
+      "epoch": 0.326482280301108,
+      "grad_norm": 0.41183415055274963,
+      "learning_rate": 2e-05,
+      "loss": 0.7688,
+      "step": 3860
+    },
+    {
+      "epoch": 0.3273280893174321,
+      "grad_norm": 0.47716838121414185,
+      "learning_rate": 2e-05,
+      "loss": 0.8115,
+      "step": 3870
+    },
+    {
+      "epoch": 0.32817389833375626,
+      "grad_norm": 0.41577062010765076,
+      "learning_rate": 2e-05,
+      "loss": 0.7548,
+      "step": 3880
+    },
+    {
+      "epoch": 0.32901970735008035,
+      "grad_norm": 0.4355597496032715,
+      "learning_rate": 2e-05,
+      "loss": 0.7384,
+      "step": 3890
+    },
+    {
+      "epoch": 0.3298655163664045,
+      "grad_norm": 0.4310600757598877,
+      "learning_rate": 2e-05,
+      "loss": 0.7748,
+      "step": 3900
+    },
+    {
+      "epoch": 0.33071132538272857,
+      "grad_norm": 0.43311387300491333,
+      "learning_rate": 2e-05,
+      "loss": 0.7521,
+      "step": 3910
+    },
+    {
+      "epoch": 0.3315571343990527,
+      "grad_norm": 0.44744375348091125,
+      "learning_rate": 2e-05,
+      "loss": 0.7415,
+      "step": 3920
+    },
+    {
+      "epoch": 0.3324029434153768,
+      "grad_norm": 0.4440036118030548,
+      "learning_rate": 2e-05,
+      "loss": 0.7518,
+      "step": 3930
+    },
+    {
+      "epoch": 0.33324875243170093,
+      "grad_norm": 0.45403510332107544,
+      "learning_rate": 2e-05,
+      "loss": 0.7653,
+      "step": 3940
+    },
+    {
+      "epoch": 0.334094561448025,
+      "grad_norm": 0.4582141041755676,
+      "learning_rate": 2e-05,
+      "loss": 0.7469,
+      "step": 3950
+    },
+    {
+      "epoch": 0.33494037046434916,
+      "grad_norm": 0.5419275164604187,
+      "learning_rate": 2e-05,
+      "loss": 0.7552,
+      "step": 3960
+    },
+    {
+      "epoch": 0.33578617948067324,
+      "grad_norm": 0.4752144515514374,
+      "learning_rate": 2e-05,
+      "loss": 0.7278,
+      "step": 3970
+    },
+    {
+      "epoch": 0.3366319884969974,
+      "grad_norm": 0.4493894577026367,
+      "learning_rate": 2e-05,
+      "loss": 0.7547,
+      "step": 3980
+    },
+    {
+      "epoch": 0.33747779751332146,
+      "grad_norm": 0.48888641595840454,
+      "learning_rate": 2e-05,
+      "loss": 0.7732,
+      "step": 3990
+    },
+    {
+      "epoch": 0.3383236065296456,
+      "grad_norm": 0.4883195757865906,
+      "learning_rate": 2e-05,
+      "loss": 0.7737,
+      "step": 4000
+    },
+    {
+      "epoch": 0.33916941554596974,
+      "grad_norm": 0.4471829831600189,
+      "learning_rate": 2e-05,
+      "loss": 0.8009,
+      "step": 4010
+    },
+    {
+      "epoch": 0.3400152245622938,
+      "grad_norm": 0.46654587984085083,
+      "learning_rate": 2e-05,
+      "loss": 0.7836,
+      "step": 4020
+    },
+    {
+      "epoch": 0.34086103357861797,
+      "grad_norm": 0.8931681513786316,
+      "learning_rate": 2e-05,
+      "loss": 0.7583,
+      "step": 4030
+    },
+    {
+      "epoch": 0.34170684259494205,
+      "grad_norm": 0.4310699701309204,
+      "learning_rate": 2e-05,
+      "loss": 0.7264,
+      "step": 4040
+    },
+    {
+      "epoch": 0.3425526516112662,
+      "grad_norm": 0.6010509133338928,
+      "learning_rate": 2e-05,
+      "loss": 0.7509,
+      "step": 4050
+    },
+    {
+      "epoch": 0.3433984606275903,
+      "grad_norm": 0.43623340129852295,
+      "learning_rate": 2e-05,
+      "loss": 0.7544,
+      "step": 4060
+    },
+    {
+      "epoch": 0.3442442696439144,
+      "grad_norm": 0.45183423161506653,
+      "learning_rate": 2e-05,
+      "loss": 0.7857,
+      "step": 4070
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5935,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2035,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8168590244885037e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

400M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce978f4bc6aba2e48cf1e9fa0eec29b57c02e8a135c8dc511c4521d4fc9155a1
+size 7953