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:a822e422f03513ed3f2bed07056cef2a8489f20b6f66ebcb7404aeae814db44f
+size 4902257696

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2155ecc2175c68c847d250fe1647176c7dbc1c8da2c712781d44e44c2833b563
+size 4915960368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0e045e5b91a3dd692420a1b8fb7fc0ae99638af55c187f192e61090493a3ba
+size 4983068496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d8d4dd9e488c29a7999daa5e7767baf584b2cfb99e60c378a9106462d37d0a
+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": 0.16313279089342259,
+  "eval_steps": 500,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004008176680428073,
+      "grad_norm": 0.8771801590919495,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.5885,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008016353360856146,
+      "grad_norm": 0.7135661840438843,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.5855,
+      "step": 20
+    },
+    {
+      "epoch": 0.001202453004128422,
+      "grad_norm": 0.684427797794342,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.6184,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016032706721712292,
+      "grad_norm": 0.6721655130386353,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.6311,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020040883402140364,
+      "grad_norm": 0.6820604801177979,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.6092,
+      "step": 50
+    },
+    {
+      "epoch": 0.002404906008256844,
+      "grad_norm": 0.6614678502082825,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.6381,
+      "step": 60
+    },
+    {
+      "epoch": 0.0028057236762996512,
+      "grad_norm": 0.7028018236160278,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.5996,
+      "step": 70
+    },
+    {
+      "epoch": 0.0032065413443424584,
+      "grad_norm": 0.618502140045166,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.5959,
+      "step": 80
+    },
+    {
+      "epoch": 0.003607359012385266,
+      "grad_norm": 1.102985143661499,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.5787,
+      "step": 90
+    },
+    {
+      "epoch": 0.004008176680428073,
+      "grad_norm": 0.9070648550987244,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.6572,
+      "step": 100
+    },
+    {
+      "epoch": 0.004408994348470881,
+      "grad_norm": 0.8499509692192078,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.5635,
+      "step": 110
+    },
+    {
+      "epoch": 0.004809812016513688,
+      "grad_norm": 0.8052905797958374,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.637,
+      "step": 120
+    },
+    {
+      "epoch": 0.005210629684556495,
+      "grad_norm": 0.5784770250320435,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.621,
+      "step": 130
+    },
+    {
+      "epoch": 0.0056114473525993025,
+      "grad_norm": 0.7975672483444214,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.6094,
+      "step": 140
+    },
+    {
+      "epoch": 0.00601226502064211,
+      "grad_norm": 0.7009092569351196,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.5613,
+      "step": 150
+    },
+    {
+      "epoch": 0.006413082688684917,
+      "grad_norm": 0.6548627018928528,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.6051,
+      "step": 160
+    },
+    {
+      "epoch": 0.006813900356727725,
+      "grad_norm": 0.6045688390731812,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.563,
+      "step": 170
+    },
+    {
+      "epoch": 0.007214718024770532,
+      "grad_norm": 0.6471413373947144,
+      "learning_rate": 2e-05,
+      "loss": 0.6005,
+      "step": 180
+    },
+    {
+      "epoch": 0.007615535692813339,
+      "grad_norm": 0.629910945892334,
+      "learning_rate": 2e-05,
+      "loss": 0.6198,
+      "step": 190
+    },
+    {
+      "epoch": 0.008016353360856146,
+      "grad_norm": 0.927505373954773,
+      "learning_rate": 2e-05,
+      "loss": 0.582,
+      "step": 200
+    },
+    {
+      "epoch": 0.008417171028898954,
+      "grad_norm": 0.5309529304504395,
+      "learning_rate": 2e-05,
+      "loss": 0.5922,
+      "step": 210
+    },
+    {
+      "epoch": 0.008817988696941762,
+      "grad_norm": 0.5308235287666321,
+      "learning_rate": 2e-05,
+      "loss": 0.62,
+      "step": 220
+    },
+    {
+      "epoch": 0.009218806364984568,
+      "grad_norm": 0.8441914319992065,
+      "learning_rate": 2e-05,
+      "loss": 0.5574,
+      "step": 230
+    },
+    {
+      "epoch": 0.009619624033027376,
+      "grad_norm": 0.6029269099235535,
+      "learning_rate": 2e-05,
+      "loss": 0.5807,
+      "step": 240
+    },
+    {
+      "epoch": 0.010020441701070183,
+      "grad_norm": 0.5120773911476135,
+      "learning_rate": 2e-05,
+      "loss": 0.6125,
+      "step": 250
+    },
+    {
+      "epoch": 0.01042125936911299,
+      "grad_norm": 0.5556898713111877,
+      "learning_rate": 2e-05,
+      "loss": 0.608,
+      "step": 260
+    },
+    {
+      "epoch": 0.010822077037155799,
+      "grad_norm": 0.550104558467865,
+      "learning_rate": 2e-05,
+      "loss": 0.603,
+      "step": 270
+    },
+    {
+      "epoch": 0.011222894705198605,
+      "grad_norm": 0.46029090881347656,
+      "learning_rate": 2e-05,
+      "loss": 0.6234,
+      "step": 280
+    },
+    {
+      "epoch": 0.011623712373241413,
+      "grad_norm": 0.4434625208377838,
+      "learning_rate": 2e-05,
+      "loss": 0.5865,
+      "step": 290
+    },
+    {
+      "epoch": 0.01202453004128422,
+      "grad_norm": 0.49364206194877625,
+      "learning_rate": 2e-05,
+      "loss": 0.5991,
+      "step": 300
+    },
+    {
+      "epoch": 0.012425347709327027,
+      "grad_norm": 0.41587820649147034,
+      "learning_rate": 2e-05,
+      "loss": 0.5954,
+      "step": 310
+    },
+    {
+      "epoch": 0.012826165377369834,
+      "grad_norm": 0.4016185700893402,
+      "learning_rate": 2e-05,
+      "loss": 0.5823,
+      "step": 320
+    },
+    {
+      "epoch": 0.013226983045412642,
+      "grad_norm": 0.42542213201522827,
+      "learning_rate": 2e-05,
+      "loss": 0.629,
+      "step": 330
+    },
+    {
+      "epoch": 0.01362780071345545,
+      "grad_norm": 0.5087456703186035,
+      "learning_rate": 2e-05,
+      "loss": 0.6184,
+      "step": 340
+    },
+    {
+      "epoch": 0.014028618381498256,
+      "grad_norm": 0.46378353238105774,
+      "learning_rate": 2e-05,
+      "loss": 0.5894,
+      "step": 350
+    },
+    {
+      "epoch": 0.014429436049541064,
+      "grad_norm": 0.4463004171848297,
+      "learning_rate": 2e-05,
+      "loss": 0.6111,
+      "step": 360
+    },
+    {
+      "epoch": 0.01483025371758387,
+      "grad_norm": 0.5027539730072021,
+      "learning_rate": 2e-05,
+      "loss": 0.5779,
+      "step": 370
+    },
+    {
+      "epoch": 0.015231071385626679,
+      "grad_norm": 0.4367392361164093,
+      "learning_rate": 2e-05,
+      "loss": 0.6042,
+      "step": 380
+    },
+    {
+      "epoch": 0.015631889053669485,
+      "grad_norm": 0.4877663254737854,
+      "learning_rate": 2e-05,
+      "loss": 0.5847,
+      "step": 390
+    },
+    {
+      "epoch": 0.01603270672171229,
+      "grad_norm": 0.615467369556427,
+      "learning_rate": 2e-05,
+      "loss": 0.6312,
+      "step": 400
+    },
+    {
+      "epoch": 0.0164335243897551,
+      "grad_norm": 0.44901445508003235,
+      "learning_rate": 2e-05,
+      "loss": 0.5789,
+      "step": 410
+    },
+    {
+      "epoch": 0.016834342057797907,
+      "grad_norm": 0.5024731755256653,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 420
+    },
+    {
+      "epoch": 0.017235159725840714,
+      "grad_norm": 0.47739124298095703,
+      "learning_rate": 2e-05,
+      "loss": 0.6386,
+      "step": 430
+    },
+    {
+      "epoch": 0.017635977393883524,
+      "grad_norm": 0.3923758864402771,
+      "learning_rate": 2e-05,
+      "loss": 0.6097,
+      "step": 440
+    },
+    {
+      "epoch": 0.01803679506192633,
+      "grad_norm": 0.38089510798454285,
+      "learning_rate": 2e-05,
+      "loss": 0.5916,
+      "step": 450
+    },
+    {
+      "epoch": 0.018437612729969136,
+      "grad_norm": 0.37581101059913635,
+      "learning_rate": 2e-05,
+      "loss": 0.6205,
+      "step": 460
+    },
+    {
+      "epoch": 0.018838430398011946,
+      "grad_norm": 0.4052000343799591,
+      "learning_rate": 2e-05,
+      "loss": 0.6101,
+      "step": 470
+    },
+    {
+      "epoch": 0.019239248066054752,
+      "grad_norm": 0.4212661385536194,
+      "learning_rate": 2e-05,
+      "loss": 0.6051,
+      "step": 480
+    },
+    {
+      "epoch": 0.01964006573409756,
+      "grad_norm": 0.3834267556667328,
+      "learning_rate": 2e-05,
+      "loss": 0.5524,
+      "step": 490
+    },
+    {
+      "epoch": 0.020040883402140365,
+      "grad_norm": 0.38489559292793274,
+      "learning_rate": 2e-05,
+      "loss": 0.595,
+      "step": 500
+    },
+    {
+      "epoch": 0.020441701070183175,
+      "grad_norm": 0.42016276717185974,
+      "learning_rate": 2e-05,
+      "loss": 0.5996,
+      "step": 510
+    },
+    {
+      "epoch": 0.02084251873822598,
+      "grad_norm": 0.38279569149017334,
+      "learning_rate": 2e-05,
+      "loss": 0.586,
+      "step": 520
+    },
+    {
+      "epoch": 0.021243336406268788,
+      "grad_norm": 1.364205241203308,
+      "learning_rate": 2e-05,
+      "loss": 0.5536,
+      "step": 530
+    },
+    {
+      "epoch": 0.021644154074311597,
+      "grad_norm": 0.4498082995414734,
+      "learning_rate": 2e-05,
+      "loss": 0.5895,
+      "step": 540
+    },
+    {
+      "epoch": 0.022044971742354404,
+      "grad_norm": 0.38928699493408203,
+      "learning_rate": 2e-05,
+      "loss": 0.573,
+      "step": 550
+    },
+    {
+      "epoch": 0.02244578941039721,
+      "grad_norm": 0.39118388295173645,
+      "learning_rate": 2e-05,
+      "loss": 0.6096,
+      "step": 560
+    },
+    {
+      "epoch": 0.022846607078440016,
+      "grad_norm": 0.32673704624176025,
+      "learning_rate": 2e-05,
+      "loss": 0.5765,
+      "step": 570
+    },
+    {
+      "epoch": 0.023247424746482826,
+      "grad_norm": 0.36165913939476013,
+      "learning_rate": 2e-05,
+      "loss": 0.6114,
+      "step": 580
+    },
+    {
+      "epoch": 0.023648242414525632,
+      "grad_norm": 0.3407866954803467,
+      "learning_rate": 2e-05,
+      "loss": 0.5656,
+      "step": 590
+    },
+    {
+      "epoch": 0.02404906008256844,
+      "grad_norm": 0.3884231150150299,
+      "learning_rate": 2e-05,
+      "loss": 0.6137,
+      "step": 600
+    },
+    {
+      "epoch": 0.02444987775061125,
+      "grad_norm": 0.359744668006897,
+      "learning_rate": 2e-05,
+      "loss": 0.5952,
+      "step": 610
+    },
+    {
+      "epoch": 0.024850695418654055,
+      "grad_norm": 0.44357308745384216,
+      "learning_rate": 2e-05,
+      "loss": 0.5999,
+      "step": 620
+    },
+    {
+      "epoch": 0.02525151308669686,
+      "grad_norm": 0.3912670910358429,
+      "learning_rate": 2e-05,
+      "loss": 0.6191,
+      "step": 630
+    },
+    {
+      "epoch": 0.025652330754739668,
+      "grad_norm": 0.34180188179016113,
+      "learning_rate": 2e-05,
+      "loss": 0.597,
+      "step": 640
+    },
+    {
+      "epoch": 0.026053148422782477,
+      "grad_norm": 0.4104002118110657,
+      "learning_rate": 2e-05,
+      "loss": 0.5491,
+      "step": 650
+    },
+    {
+      "epoch": 0.026453966090825284,
+      "grad_norm": 0.3853461742401123,
+      "learning_rate": 2e-05,
+      "loss": 0.5516,
+      "step": 660
+    },
+    {
+      "epoch": 0.02685478375886809,
+      "grad_norm": 0.43015527725219727,
+      "learning_rate": 2e-05,
+      "loss": 0.6129,
+      "step": 670
+    },
+    {
+      "epoch": 0.0272556014269109,
+      "grad_norm": 0.3709610402584076,
+      "learning_rate": 2e-05,
+      "loss": 0.6228,
+      "step": 680
+    },
+    {
+      "epoch": 0.027656419094953706,
+      "grad_norm": 0.42639583349227905,
+      "learning_rate": 2e-05,
+      "loss": 0.6351,
+      "step": 690
+    },
+    {
+      "epoch": 0.028057236762996512,
+      "grad_norm": 0.402164489030838,
+      "learning_rate": 2e-05,
+      "loss": 0.6049,
+      "step": 700
+    },
+    {
+      "epoch": 0.02845805443103932,
+      "grad_norm": 0.6255981922149658,
+      "learning_rate": 2e-05,
+      "loss": 0.6139,
+      "step": 710
+    },
+    {
+      "epoch": 0.02885887209908213,
+      "grad_norm": 0.3667871952056885,
+      "learning_rate": 2e-05,
+      "loss": 0.5691,
+      "step": 720
+    },
+    {
+      "epoch": 0.029259689767124935,
+      "grad_norm": 0.36819183826446533,
+      "learning_rate": 2e-05,
+      "loss": 0.6111,
+      "step": 730
+    },
+    {
+      "epoch": 0.02966050743516774,
+      "grad_norm": 0.40006792545318604,
+      "learning_rate": 2e-05,
+      "loss": 0.613,
+      "step": 740
+    },
+    {
+      "epoch": 0.03006132510321055,
+      "grad_norm": 0.397798091173172,
+      "learning_rate": 2e-05,
+      "loss": 0.5872,
+      "step": 750
+    },
+    {
+      "epoch": 0.030462142771253357,
+      "grad_norm": 0.3581616282463074,
+      "learning_rate": 2e-05,
+      "loss": 0.5831,
+      "step": 760
+    },
+    {
+      "epoch": 0.030862960439296164,
+      "grad_norm": 0.3883630931377411,
+      "learning_rate": 2e-05,
+      "loss": 0.6182,
+      "step": 770
+    },
+    {
+      "epoch": 0.03126377810733897,
+      "grad_norm": 0.4035130739212036,
+      "learning_rate": 2e-05,
+      "loss": 0.58,
+      "step": 780
+    },
+    {
+      "epoch": 0.031664595775381776,
+      "grad_norm": 0.4688993990421295,
+      "learning_rate": 2e-05,
+      "loss": 0.5971,
+      "step": 790
+    },
+    {
+      "epoch": 0.03206541344342458,
+      "grad_norm": 0.37623828649520874,
+      "learning_rate": 2e-05,
+      "loss": 0.5682,
+      "step": 800
+    },
+    {
+      "epoch": 0.032466231111467396,
+      "grad_norm": 0.38642242550849915,
+      "learning_rate": 2e-05,
+      "loss": 0.6227,
+      "step": 810
+    },
+    {
+      "epoch": 0.0328670487795102,
+      "grad_norm": 0.3684792220592499,
+      "learning_rate": 2e-05,
+      "loss": 0.5819,
+      "step": 820
+    },
+    {
+      "epoch": 0.03326786644755301,
+      "grad_norm": 0.4786039888858795,
+      "learning_rate": 2e-05,
+      "loss": 0.5936,
+      "step": 830
+    },
+    {
+      "epoch": 0.033668684115595815,
+      "grad_norm": 0.3609310984611511,
+      "learning_rate": 2e-05,
+      "loss": 0.5941,
+      "step": 840
+    },
+    {
+      "epoch": 0.03406950178363862,
+      "grad_norm": 0.3404565751552582,
+      "learning_rate": 2e-05,
+      "loss": 0.6299,
+      "step": 850
+    },
+    {
+      "epoch": 0.03447031945168143,
+      "grad_norm": 0.3853689134120941,
+      "learning_rate": 2e-05,
+      "loss": 0.604,
+      "step": 860
+    },
+    {
+      "epoch": 0.03487113711972424,
+      "grad_norm": 0.3917834162712097,
+      "learning_rate": 2e-05,
+      "loss": 0.6053,
+      "step": 870
+    },
+    {
+      "epoch": 0.03527195478776705,
+      "grad_norm": 0.36823081970214844,
+      "learning_rate": 2e-05,
+      "loss": 0.6171,
+      "step": 880
+    },
+    {
+      "epoch": 0.035672772455809854,
+      "grad_norm": 0.3762242794036865,
+      "learning_rate": 2e-05,
+      "loss": 0.64,
+      "step": 890
+    },
+    {
+      "epoch": 0.03607359012385266,
+      "grad_norm": 0.8369109034538269,
+      "learning_rate": 2e-05,
+      "loss": 0.6405,
+      "step": 900
+    },
+    {
+      "epoch": 0.036474407791895466,
+      "grad_norm": 0.4162234365940094,
+      "learning_rate": 2e-05,
+      "loss": 0.6021,
+      "step": 910
+    },
+    {
+      "epoch": 0.03687522545993827,
+      "grad_norm": 0.4115590453147888,
+      "learning_rate": 2e-05,
+      "loss": 0.6031,
+      "step": 920
+    },
+    {
+      "epoch": 0.03727604312798108,
+      "grad_norm": 0.3745420277118683,
+      "learning_rate": 2e-05,
+      "loss": 0.5785,
+      "step": 930
+    },
+    {
+      "epoch": 0.03767686079602389,
+      "grad_norm": 0.38241758942604065,
+      "learning_rate": 2e-05,
+      "loss": 0.6068,
+      "step": 940
+    },
+    {
+      "epoch": 0.0380776784640667,
+      "grad_norm": 0.37572914361953735,
+      "learning_rate": 2e-05,
+      "loss": 0.6126,
+      "step": 950
+    },
+    {
+      "epoch": 0.038478496132109505,
+      "grad_norm": 0.3598463535308838,
+      "learning_rate": 2e-05,
+      "loss": 0.5647,
+      "step": 960
+    },
+    {
+      "epoch": 0.03887931380015231,
+      "grad_norm": 0.3645531237125397,
+      "learning_rate": 2e-05,
+      "loss": 0.5874,
+      "step": 970
+    },
+    {
+      "epoch": 0.03928013146819512,
+      "grad_norm": 0.37088748812675476,
+      "learning_rate": 2e-05,
+      "loss": 0.5966,
+      "step": 980
+    },
+    {
+      "epoch": 0.039680949136237924,
+      "grad_norm": 0.3901059031486511,
+      "learning_rate": 2e-05,
+      "loss": 0.6214,
+      "step": 990
+    },
+    {
+      "epoch": 0.04008176680428073,
+      "grad_norm": 0.3765749931335449,
+      "learning_rate": 2e-05,
+      "loss": 0.5771,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04048258447232354,
+      "grad_norm": 0.3934212028980255,
+      "learning_rate": 2e-05,
+      "loss": 0.5661,
+      "step": 1010
+    },
+    {
+      "epoch": 0.04088340214036635,
+      "grad_norm": 0.3081901967525482,
+      "learning_rate": 2e-05,
+      "loss": 0.5772,
+      "step": 1020
+    },
+    {
+      "epoch": 0.041284219808409156,
+      "grad_norm": 0.5176882743835449,
+      "learning_rate": 2e-05,
+      "loss": 0.5925,
+      "step": 1030
+    },
+    {
+      "epoch": 0.04168503747645196,
+      "grad_norm": 0.3315117657184601,
+      "learning_rate": 2e-05,
+      "loss": 0.588,
+      "step": 1040
+    },
+    {
+      "epoch": 0.04208585514449477,
+      "grad_norm": 0.36918768286705017,
+      "learning_rate": 2e-05,
+      "loss": 0.6049,
+      "step": 1050
+    },
+    {
+      "epoch": 0.042486672812537575,
+      "grad_norm": 0.42960917949676514,
+      "learning_rate": 2e-05,
+      "loss": 0.6315,
+      "step": 1060
+    },
+    {
+      "epoch": 0.04288749048058038,
+      "grad_norm": 0.38764506578445435,
+      "learning_rate": 2e-05,
+      "loss": 0.5556,
+      "step": 1070
+    },
+    {
+      "epoch": 0.043288308148623195,
+      "grad_norm": 0.38045603036880493,
+      "learning_rate": 2e-05,
+      "loss": 0.578,
+      "step": 1080
+    },
+    {
+      "epoch": 0.043689125816666,
+      "grad_norm": 0.40927988290786743,
+      "learning_rate": 2e-05,
+      "loss": 0.5735,
+      "step": 1090
+    },
+    {
+      "epoch": 0.04408994348470881,
+      "grad_norm": 0.37116703391075134,
+      "learning_rate": 2e-05,
+      "loss": 0.5898,
+      "step": 1100
+    },
+    {
+      "epoch": 0.044490761152751614,
+      "grad_norm": 0.4863120913505554,
+      "learning_rate": 2e-05,
+      "loss": 0.6207,
+      "step": 1110
+    },
+    {
+      "epoch": 0.04489157882079442,
+      "grad_norm": 0.4080751836299896,
+      "learning_rate": 2e-05,
+      "loss": 0.6031,
+      "step": 1120
+    },
+    {
+      "epoch": 0.045292396488837226,
+      "grad_norm": 0.38050946593284607,
+      "learning_rate": 2e-05,
+      "loss": 0.5693,
+      "step": 1130
+    },
+    {
+      "epoch": 0.04569321415688003,
+      "grad_norm": 0.4002411365509033,
+      "learning_rate": 2e-05,
+      "loss": 0.5546,
+      "step": 1140
+    },
+    {
+      "epoch": 0.046094031824922846,
+      "grad_norm": 0.337520569562912,
+      "learning_rate": 2e-05,
+      "loss": 0.5649,
+      "step": 1150
+    },
+    {
+      "epoch": 0.04649484949296565,
+      "grad_norm": 0.4152458608150482,
+      "learning_rate": 2e-05,
+      "loss": 0.5985,
+      "step": 1160
+    },
+    {
+      "epoch": 0.04689566716100846,
+      "grad_norm": 0.3427383601665497,
+      "learning_rate": 2e-05,
+      "loss": 0.5974,
+      "step": 1170
+    },
+    {
+      "epoch": 0.047296484829051265,
+      "grad_norm": 0.48308777809143066,
+      "learning_rate": 2e-05,
+      "loss": 0.5676,
+      "step": 1180
+    },
+    {
+      "epoch": 0.04769730249709407,
+      "grad_norm": 0.3868969976902008,
+      "learning_rate": 2e-05,
+      "loss": 0.5791,
+      "step": 1190
+    },
+    {
+      "epoch": 0.04809812016513688,
+      "grad_norm": 0.4252076745033264,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 1200
+    },
+    {
+      "epoch": 0.048498937833179684,
+      "grad_norm": 0.3403521478176117,
+      "learning_rate": 2e-05,
+      "loss": 0.5721,
+      "step": 1210
+    },
+    {
+      "epoch": 0.0488997555012225,
+      "grad_norm": 0.3935258090496063,
+      "learning_rate": 2e-05,
+      "loss": 0.6194,
+      "step": 1220
+    },
+    {
+      "epoch": 0.049300573169265303,
+      "grad_norm": 0.39958739280700684,
+      "learning_rate": 2e-05,
+      "loss": 0.5838,
+      "step": 1230
+    },
+    {
+      "epoch": 0.04970139083730811,
+      "grad_norm": 0.3761332035064697,
+      "learning_rate": 2e-05,
+      "loss": 0.5746,
+      "step": 1240
+    },
+    {
+      "epoch": 0.050102208505350916,
+      "grad_norm": 0.3709917962551117,
+      "learning_rate": 2e-05,
+      "loss": 0.5925,
+      "step": 1250
+    },
+    {
+      "epoch": 0.05050302617339372,
+      "grad_norm": 0.4449377954006195,
+      "learning_rate": 2e-05,
+      "loss": 0.5975,
+      "step": 1260
+    },
+    {
+      "epoch": 0.05090384384143653,
+      "grad_norm": 0.4874597489833832,
+      "learning_rate": 2e-05,
+      "loss": 0.6075,
+      "step": 1270
+    },
+    {
+      "epoch": 0.051304661509479335,
+      "grad_norm": 0.5181390047073364,
+      "learning_rate": 2e-05,
+      "loss": 0.5873,
+      "step": 1280
+    },
+    {
+      "epoch": 0.05170547917752215,
+      "grad_norm": 0.38032063841819763,
+      "learning_rate": 2e-05,
+      "loss": 0.5734,
+      "step": 1290
+    },
+    {
+      "epoch": 0.052106296845564955,
+      "grad_norm": 0.3566950857639313,
+      "learning_rate": 2e-05,
+      "loss": 0.5876,
+      "step": 1300
+    },
+    {
+      "epoch": 0.05250711451360776,
+      "grad_norm": 0.3316211998462677,
+      "learning_rate": 2e-05,
+      "loss": 0.5729,
+      "step": 1310
+    },
+    {
+      "epoch": 0.05290793218165057,
+      "grad_norm": 0.3991880416870117,
+      "learning_rate": 2e-05,
+      "loss": 0.5903,
+      "step": 1320
+    },
+    {
+      "epoch": 0.053308749849693374,
+      "grad_norm": 0.4019741714000702,
+      "learning_rate": 2e-05,
+      "loss": 0.5768,
+      "step": 1330
+    },
+    {
+      "epoch": 0.05370956751773618,
+      "grad_norm": 0.417432963848114,
+      "learning_rate": 2e-05,
+      "loss": 0.6152,
+      "step": 1340
+    },
+    {
+      "epoch": 0.054110385185778986,
+      "grad_norm": 0.3510989248752594,
+      "learning_rate": 2e-05,
+      "loss": 0.5694,
+      "step": 1350
+    },
+    {
+      "epoch": 0.0545112028538218,
+      "grad_norm": 0.4420473575592041,
+      "learning_rate": 2e-05,
+      "loss": 0.5697,
+      "step": 1360
+    },
+    {
+      "epoch": 0.054912020521864606,
+      "grad_norm": 0.4099363684654236,
+      "learning_rate": 2e-05,
+      "loss": 0.5891,
+      "step": 1370
+    },
+    {
+      "epoch": 0.05531283818990741,
+      "grad_norm": 0.44445106387138367,
+      "learning_rate": 2e-05,
+      "loss": 0.5602,
+      "step": 1380
+    },
+    {
+      "epoch": 0.05571365585795022,
+      "grad_norm": 0.35209330916404724,
+      "learning_rate": 2e-05,
+      "loss": 0.6442,
+      "step": 1390
+    },
+    {
+      "epoch": 0.056114473525993025,
+      "grad_norm": 0.3788399398326874,
+      "learning_rate": 2e-05,
+      "loss": 0.6103,
+      "step": 1400
+    },
+    {
+      "epoch": 0.05651529119403583,
+      "grad_norm": 0.3592466711997986,
+      "learning_rate": 2e-05,
+      "loss": 0.5739,
+      "step": 1410
+    },
+    {
+      "epoch": 0.05691610886207864,
+      "grad_norm": 0.3659421503543854,
+      "learning_rate": 2e-05,
+      "loss": 0.5754,
+      "step": 1420
+    },
+    {
+      "epoch": 0.05731692653012145,
+      "grad_norm": 0.33240798115730286,
+      "learning_rate": 2e-05,
+      "loss": 0.5657,
+      "step": 1430
+    },
+    {
+      "epoch": 0.05771774419816426,
+      "grad_norm": 0.3574551045894623,
+      "learning_rate": 2e-05,
+      "loss": 0.599,
+      "step": 1440
+    },
+    {
+      "epoch": 0.058118561866207064,
+      "grad_norm": 0.3870832920074463,
+      "learning_rate": 2e-05,
+      "loss": 0.586,
+      "step": 1450
+    },
+    {
+      "epoch": 0.05851937953424987,
+      "grad_norm": 0.3373236656188965,
+      "learning_rate": 2e-05,
+      "loss": 0.6046,
+      "step": 1460
+    },
+    {
+      "epoch": 0.058920197202292676,
+      "grad_norm": 0.3652302026748657,
+      "learning_rate": 2e-05,
+      "loss": 0.5895,
+      "step": 1470
+    },
+    {
+      "epoch": 0.05932101487033548,
+      "grad_norm": 0.3693019449710846,
+      "learning_rate": 2e-05,
+      "loss": 0.6038,
+      "step": 1480
+    },
+    {
+      "epoch": 0.05972183253837829,
+      "grad_norm": 0.4179181158542633,
+      "learning_rate": 2e-05,
+      "loss": 0.5379,
+      "step": 1490
+    },
+    {
+      "epoch": 0.0601226502064211,
+      "grad_norm": 0.3929535746574402,
+      "learning_rate": 2e-05,
+      "loss": 0.5814,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06052346787446391,
+      "grad_norm": 0.34511131048202515,
+      "learning_rate": 2e-05,
+      "loss": 0.5608,
+      "step": 1510
+    },
+    {
+      "epoch": 0.060924285542506715,
+      "grad_norm": 0.3240802586078644,
+      "learning_rate": 2e-05,
+      "loss": 0.6026,
+      "step": 1520
+    },
+    {
+      "epoch": 0.06132510321054952,
+      "grad_norm": 0.3732409179210663,
+      "learning_rate": 2e-05,
+      "loss": 0.5922,
+      "step": 1530
+    },
+    {
+      "epoch": 0.06172592087859233,
+      "grad_norm": 0.3403308391571045,
+      "learning_rate": 2e-05,
+      "loss": 0.5784,
+      "step": 1540
+    },
+    {
+      "epoch": 0.062126738546635134,
+      "grad_norm": 0.43892017006874084,
+      "learning_rate": 2e-05,
+      "loss": 0.5733,
+      "step": 1550
+    },
+    {
+      "epoch": 0.06252755621467794,
+      "grad_norm": 0.32453539967536926,
+      "learning_rate": 2e-05,
+      "loss": 0.6164,
+      "step": 1560
+    },
+    {
+      "epoch": 0.06292837388272075,
+      "grad_norm": 0.4057670533657074,
+      "learning_rate": 2e-05,
+      "loss": 0.5654,
+      "step": 1570
+    },
+    {
+      "epoch": 0.06332919155076355,
+      "grad_norm": 0.401593953371048,
+      "learning_rate": 2e-05,
+      "loss": 0.5708,
+      "step": 1580
+    },
+    {
+      "epoch": 0.06373000921880637,
+      "grad_norm": 0.9239656329154968,
+      "learning_rate": 2e-05,
+      "loss": 0.6037,
+      "step": 1590
+    },
+    {
+      "epoch": 0.06413082688684917,
+      "grad_norm": 0.43078750371932983,
+      "learning_rate": 2e-05,
+      "loss": 0.5834,
+      "step": 1600
+    },
+    {
+      "epoch": 0.06453164455489198,
+      "grad_norm": 0.3466830253601074,
+      "learning_rate": 2e-05,
+      "loss": 0.5737,
+      "step": 1610
+    },
+    {
+      "epoch": 0.06493246222293479,
+      "grad_norm": 0.3531036078929901,
+      "learning_rate": 2e-05,
+      "loss": 0.5849,
+      "step": 1620
+    },
+    {
+      "epoch": 0.06533327989097759,
+      "grad_norm": 0.5453006029129028,
+      "learning_rate": 2e-05,
+      "loss": 0.5575,
+      "step": 1630
+    },
+    {
+      "epoch": 0.0657340975590204,
+      "grad_norm": 0.3632678687572479,
+      "learning_rate": 2e-05,
+      "loss": 0.61,
+      "step": 1640
+    },
+    {
+      "epoch": 0.0661349152270632,
+      "grad_norm": 0.410371869802475,
+      "learning_rate": 2e-05,
+      "loss": 0.5943,
+      "step": 1650
+    },
+    {
+      "epoch": 0.06653573289510602,
+      "grad_norm": 0.3581090569496155,
+      "learning_rate": 2e-05,
+      "loss": 0.583,
+      "step": 1660
+    },
+    {
+      "epoch": 0.06693655056314882,
+      "grad_norm": 0.3194616436958313,
+      "learning_rate": 2e-05,
+      "loss": 0.5872,
+      "step": 1670
+    },
+    {
+      "epoch": 0.06733736823119163,
+      "grad_norm": 0.3554430603981018,
+      "learning_rate": 2e-05,
+      "loss": 0.6039,
+      "step": 1680
+    },
+    {
+      "epoch": 0.06773818589923444,
+      "grad_norm": 0.3838396966457367,
+      "learning_rate": 2e-05,
+      "loss": 0.6044,
+      "step": 1690
+    },
+    {
+      "epoch": 0.06813900356727724,
+      "grad_norm": 0.3924729824066162,
+      "learning_rate": 2e-05,
+      "loss": 0.6208,
+      "step": 1700
+    },
+    {
+      "epoch": 0.06853982123532006,
+      "grad_norm": 0.3942250907421112,
+      "learning_rate": 2e-05,
+      "loss": 0.5827,
+      "step": 1710
+    },
+    {
+      "epoch": 0.06894063890336286,
+      "grad_norm": 0.3890213072299957,
+      "learning_rate": 2e-05,
+      "loss": 0.5413,
+      "step": 1720
+    },
+    {
+      "epoch": 0.06934145657140567,
+      "grad_norm": 0.3526347577571869,
+      "learning_rate": 2e-05,
+      "loss": 0.5835,
+      "step": 1730
+    },
+    {
+      "epoch": 0.06974227423944848,
+      "grad_norm": 0.3879394829273224,
+      "learning_rate": 2e-05,
+      "loss": 0.5952,
+      "step": 1740
+    },
+    {
+      "epoch": 0.07014309190749128,
+      "grad_norm": 0.33095234632492065,
+      "learning_rate": 2e-05,
+      "loss": 0.5891,
+      "step": 1750
+    },
+    {
+      "epoch": 0.0705439095755341,
+      "grad_norm": 0.38446444272994995,
+      "learning_rate": 2e-05,
+      "loss": 0.5971,
+      "step": 1760
+    },
+    {
+      "epoch": 0.0709447272435769,
+      "grad_norm": 0.4128134250640869,
+      "learning_rate": 2e-05,
+      "loss": 0.5613,
+      "step": 1770
+    },
+    {
+      "epoch": 0.07134554491161971,
+      "grad_norm": 0.33474040031433105,
+      "learning_rate": 2e-05,
+      "loss": 0.5702,
+      "step": 1780
+    },
+    {
+      "epoch": 0.0717463625796625,
+      "grad_norm": 0.36933767795562744,
+      "learning_rate": 2e-05,
+      "loss": 0.5887,
+      "step": 1790
+    },
+    {
+      "epoch": 0.07214718024770532,
+      "grad_norm": 0.40623337030410767,
+      "learning_rate": 2e-05,
+      "loss": 0.5752,
+      "step": 1800
+    },
+    {
+      "epoch": 0.07254799791574813,
+      "grad_norm": 0.34252020716667175,
+      "learning_rate": 2e-05,
+      "loss": 0.5703,
+      "step": 1810
+    },
+    {
+      "epoch": 0.07294881558379093,
+      "grad_norm": 0.3257846236228943,
+      "learning_rate": 2e-05,
+      "loss": 0.5845,
+      "step": 1820
+    },
+    {
+      "epoch": 0.07334963325183375,
+      "grad_norm": 0.3836072087287903,
+      "learning_rate": 2e-05,
+      "loss": 0.5863,
+      "step": 1830
+    },
+    {
+      "epoch": 0.07375045091987655,
+      "grad_norm": 0.4434497058391571,
+      "learning_rate": 2e-05,
+      "loss": 0.5607,
+      "step": 1840
+    },
+    {
+      "epoch": 0.07415126858791936,
+      "grad_norm": 0.369035929441452,
+      "learning_rate": 2e-05,
+      "loss": 0.5759,
+      "step": 1850
+    },
+    {
+      "epoch": 0.07455208625596216,
+      "grad_norm": 0.4021732807159424,
+      "learning_rate": 2e-05,
+      "loss": 0.5941,
+      "step": 1860
+    },
+    {
+      "epoch": 0.07495290392400497,
+      "grad_norm": 0.343211829662323,
+      "learning_rate": 2e-05,
+      "loss": 0.6035,
+      "step": 1870
+    },
+    {
+      "epoch": 0.07535372159204778,
+      "grad_norm": 0.3816221356391907,
+      "learning_rate": 2e-05,
+      "loss": 0.5661,
+      "step": 1880
+    },
+    {
+      "epoch": 0.07575453926009058,
+      "grad_norm": 0.35929223895072937,
+      "learning_rate": 2e-05,
+      "loss": 0.5867,
+      "step": 1890
+    },
+    {
+      "epoch": 0.0761553569281334,
+      "grad_norm": 0.36963996291160583,
+      "learning_rate": 2e-05,
+      "loss": 0.5842,
+      "step": 1900
+    },
+    {
+      "epoch": 0.0765561745961762,
+      "grad_norm": 0.4415839612483978,
+      "learning_rate": 2e-05,
+      "loss": 0.6102,
+      "step": 1910
+    },
+    {
+      "epoch": 0.07695699226421901,
+      "grad_norm": 0.3494766354560852,
+      "learning_rate": 2e-05,
+      "loss": 0.5586,
+      "step": 1920
+    },
+    {
+      "epoch": 0.07735780993226181,
+      "grad_norm": 0.434241384267807,
+      "learning_rate": 2e-05,
+      "loss": 0.609,
+      "step": 1930
+    },
+    {
+      "epoch": 0.07775862760030462,
+      "grad_norm": 0.39981046319007874,
+      "learning_rate": 2e-05,
+      "loss": 0.5942,
+      "step": 1940
+    },
+    {
+      "epoch": 0.07815944526834744,
+      "grad_norm": 0.3525627553462982,
+      "learning_rate": 2e-05,
+      "loss": 0.5905,
+      "step": 1950
+    },
+    {
+      "epoch": 0.07856026293639023,
+      "grad_norm": 0.48807239532470703,
+      "learning_rate": 2e-05,
+      "loss": 0.5696,
+      "step": 1960
+    },
+    {
+      "epoch": 0.07896108060443305,
+      "grad_norm": 0.35398364067077637,
+      "learning_rate": 2e-05,
+      "loss": 0.5505,
+      "step": 1970
+    },
+    {
+      "epoch": 0.07936189827247585,
+      "grad_norm": 0.4212177097797394,
+      "learning_rate": 2e-05,
+      "loss": 0.582,
+      "step": 1980
+    },
+    {
+      "epoch": 0.07976271594051866,
+      "grad_norm": 0.33485740423202515,
+      "learning_rate": 2e-05,
+      "loss": 0.5564,
+      "step": 1990
+    },
+    {
+      "epoch": 0.08016353360856146,
+      "grad_norm": 0.39947226643562317,
+      "learning_rate": 2e-05,
+      "loss": 0.562,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08056435127660427,
+      "grad_norm": 0.3385741412639618,
+      "learning_rate": 2e-05,
+      "loss": 0.6098,
+      "step": 2010
+    },
+    {
+      "epoch": 0.08096516894464709,
+      "grad_norm": 0.3568948209285736,
+      "learning_rate": 2e-05,
+      "loss": 0.5853,
+      "step": 2020
+    },
+    {
+      "epoch": 0.08136598661268989,
+      "grad_norm": 0.36856064200401306,
+      "learning_rate": 2e-05,
+      "loss": 0.5616,
+      "step": 2030
+    },
+    {
+      "epoch": 0.0817668042807327,
+      "grad_norm": 0.36307284235954285,
+      "learning_rate": 2e-05,
+      "loss": 0.581,
+      "step": 2040
+    },
+    {
+      "epoch": 0.0821676219487755,
+      "grad_norm": 0.3536205589771271,
+      "learning_rate": 2e-05,
+      "loss": 0.5635,
+      "step": 2050
+    },
+    {
+      "epoch": 0.08256843961681831,
+      "grad_norm": 0.43149474263191223,
+      "learning_rate": 2e-05,
+      "loss": 0.6025,
+      "step": 2060
+    },
+    {
+      "epoch": 0.08296925728486111,
+      "grad_norm": 0.3605656325817108,
+      "learning_rate": 2e-05,
+      "loss": 0.5634,
+      "step": 2070
+    },
+    {
+      "epoch": 0.08337007495290392,
+      "grad_norm": 0.393462598323822,
+      "learning_rate": 2e-05,
+      "loss": 0.596,
+      "step": 2080
+    },
+    {
+      "epoch": 0.08377089262094674,
+      "grad_norm": 0.318276047706604,
+      "learning_rate": 2e-05,
+      "loss": 0.5504,
+      "step": 2090
+    },
+    {
+      "epoch": 0.08417171028898954,
+      "grad_norm": 0.46484410762786865,
+      "learning_rate": 2e-05,
+      "loss": 0.5638,
+      "step": 2100
+    },
+    {
+      "epoch": 0.08457252795703235,
+      "grad_norm": 0.4350844919681549,
+      "learning_rate": 2e-05,
+      "loss": 0.5854,
+      "step": 2110
+    },
+    {
+      "epoch": 0.08497334562507515,
+      "grad_norm": 0.3690831661224365,
+      "learning_rate": 2e-05,
+      "loss": 0.5923,
+      "step": 2120
+    },
+    {
+      "epoch": 0.08537416329311796,
+      "grad_norm": 0.32239291071891785,
+      "learning_rate": 2e-05,
+      "loss": 0.557,
+      "step": 2130
+    },
+    {
+      "epoch": 0.08577498096116076,
+      "grad_norm": 0.37218692898750305,
+      "learning_rate": 2e-05,
+      "loss": 0.5719,
+      "step": 2140
+    },
+    {
+      "epoch": 0.08617579862920358,
+      "grad_norm": 0.3764131963253021,
+      "learning_rate": 2e-05,
+      "loss": 0.5597,
+      "step": 2150
+    },
+    {
+      "epoch": 0.08657661629724639,
+      "grad_norm": 0.3383973240852356,
+      "learning_rate": 2e-05,
+      "loss": 0.5722,
+      "step": 2160
+    },
+    {
+      "epoch": 0.08697743396528919,
+      "grad_norm": 0.4094143211841583,
+      "learning_rate": 2e-05,
+      "loss": 0.57,
+      "step": 2170
+    },
+    {
+      "epoch": 0.087378251633332,
+      "grad_norm": 0.406859427690506,
+      "learning_rate": 2e-05,
+      "loss": 0.5704,
+      "step": 2180
+    },
+    {
+      "epoch": 0.0877790693013748,
+      "grad_norm": 0.3579443395137787,
+      "learning_rate": 2e-05,
+      "loss": 0.5896,
+      "step": 2190
+    },
+    {
+      "epoch": 0.08817988696941761,
+      "grad_norm": 0.3546210527420044,
+      "learning_rate": 2e-05,
+      "loss": 0.559,
+      "step": 2200
+    },
+    {
+      "epoch": 0.08858070463746041,
+      "grad_norm": 0.3182368278503418,
+      "learning_rate": 2e-05,
+      "loss": 0.5713,
+      "step": 2210
+    },
+    {
+      "epoch": 0.08898152230550323,
+      "grad_norm": 0.3846684396266937,
+      "learning_rate": 2e-05,
+      "loss": 0.5724,
+      "step": 2220
+    },
+    {
+      "epoch": 0.08938233997354604,
+      "grad_norm": 0.37794479727745056,
+      "learning_rate": 2e-05,
+      "loss": 0.6047,
+      "step": 2230
+    },
+    {
+      "epoch": 0.08978315764158884,
+      "grad_norm": 0.31841838359832764,
+      "learning_rate": 2e-05,
+      "loss": 0.5544,
+      "step": 2240
+    },
+    {
+      "epoch": 0.09018397530963165,
+      "grad_norm": 0.37598782777786255,
+      "learning_rate": 2e-05,
+      "loss": 0.5687,
+      "step": 2250
+    },
+    {
+      "epoch": 0.09058479297767445,
+      "grad_norm": 1.1034108400344849,
+      "learning_rate": 2e-05,
+      "loss": 0.5758,
+      "step": 2260
+    },
+    {
+      "epoch": 0.09098561064571727,
+      "grad_norm": 0.34686070680618286,
+      "learning_rate": 2e-05,
+      "loss": 0.5782,
+      "step": 2270
+    },
+    {
+      "epoch": 0.09138642831376007,
+      "grad_norm": 0.34697771072387695,
+      "learning_rate": 2e-05,
+      "loss": 0.5602,
+      "step": 2280
+    },
+    {
+      "epoch": 0.09178724598180288,
+      "grad_norm": 0.370018869638443,
+      "learning_rate": 2e-05,
+      "loss": 0.5912,
+      "step": 2290
+    },
+    {
+      "epoch": 0.09218806364984569,
+      "grad_norm": 0.390052855014801,
+      "learning_rate": 2e-05,
+      "loss": 0.5788,
+      "step": 2300
+    },
+    {
+      "epoch": 0.09258888131788849,
+      "grad_norm": 0.3554167151451111,
+      "learning_rate": 2e-05,
+      "loss": 0.56,
+      "step": 2310
+    },
+    {
+      "epoch": 0.0929896989859313,
+      "grad_norm": 0.343339204788208,
+      "learning_rate": 2e-05,
+      "loss": 0.6,
+      "step": 2320
+    },
+    {
+      "epoch": 0.0933905166539741,
+      "grad_norm": 0.3061367869377136,
+      "learning_rate": 2e-05,
+      "loss": 0.604,
+      "step": 2330
+    },
+    {
+      "epoch": 0.09379133432201692,
+      "grad_norm": 0.3962571322917938,
+      "learning_rate": 2e-05,
+      "loss": 0.5975,
+      "step": 2340
+    },
+    {
+      "epoch": 0.09419215199005972,
+      "grad_norm": 0.3495456576347351,
+      "learning_rate": 2e-05,
+      "loss": 0.5676,
+      "step": 2350
+    },
+    {
+      "epoch": 0.09459296965810253,
+      "grad_norm": 0.964829683303833,
+      "learning_rate": 2e-05,
+      "loss": 0.5851,
+      "step": 2360
+    },
+    {
+      "epoch": 0.09499378732614534,
+      "grad_norm": 0.4385446012020111,
+      "learning_rate": 2e-05,
+      "loss": 0.5538,
+      "step": 2370
+    },
+    {
+      "epoch": 0.09539460499418814,
+      "grad_norm": 0.37227344512939453,
+      "learning_rate": 2e-05,
+      "loss": 0.5631,
+      "step": 2380
+    },
+    {
+      "epoch": 0.09579542266223096,
+      "grad_norm": 0.3347318470478058,
+      "learning_rate": 2e-05,
+      "loss": 0.5681,
+      "step": 2390
+    },
+    {
+      "epoch": 0.09619624033027376,
+      "grad_norm": 0.3704676032066345,
+      "learning_rate": 2e-05,
+      "loss": 0.5869,
+      "step": 2400
+    },
+    {
+      "epoch": 0.09659705799831657,
+      "grad_norm": 0.35813140869140625,
+      "learning_rate": 2e-05,
+      "loss": 0.5553,
+      "step": 2410
+    },
+    {
+      "epoch": 0.09699787566635937,
+      "grad_norm": 0.3712270259857178,
+      "learning_rate": 2e-05,
+      "loss": 0.5476,
+      "step": 2420
+    },
+    {
+      "epoch": 0.09739869333440218,
+      "grad_norm": 0.4175005257129669,
+      "learning_rate": 2e-05,
+      "loss": 0.6143,
+      "step": 2430
+    },
+    {
+      "epoch": 0.097799511002445,
+      "grad_norm": 0.36217042803764343,
+      "learning_rate": 2e-05,
+      "loss": 0.5752,
+      "step": 2440
+    },
+    {
+      "epoch": 0.0982003286704878,
+      "grad_norm": 0.3934085965156555,
+      "learning_rate": 2e-05,
+      "loss": 0.5822,
+      "step": 2450
+    },
+    {
+      "epoch": 0.09860114633853061,
+      "grad_norm": 0.3451460599899292,
+      "learning_rate": 2e-05,
+      "loss": 0.5783,
+      "step": 2460
+    },
+    {
+      "epoch": 0.0990019640065734,
+      "grad_norm": 0.35573357343673706,
+      "learning_rate": 2e-05,
+      "loss": 0.5586,
+      "step": 2470
+    },
+    {
+      "epoch": 0.09940278167461622,
+      "grad_norm": 0.34175917506217957,
+      "learning_rate": 2e-05,
+      "loss": 0.5564,
+      "step": 2480
+    },
+    {
+      "epoch": 0.09980359934265902,
+      "grad_norm": 0.3565382659435272,
+      "learning_rate": 2e-05,
+      "loss": 0.5524,
+      "step": 2490
+    },
+    {
+      "epoch": 0.10020441701070183,
+      "grad_norm": 0.4152110517024994,
+      "learning_rate": 2e-05,
+      "loss": 0.5831,
+      "step": 2500
+    },
+    {
+      "epoch": 0.10060523467874465,
+      "grad_norm": 0.3308890163898468,
+      "learning_rate": 2e-05,
+      "loss": 0.5485,
+      "step": 2510
+    },
+    {
+      "epoch": 0.10100605234678744,
+      "grad_norm": 0.45242831110954285,
+      "learning_rate": 2e-05,
+      "loss": 0.5838,
+      "step": 2520
+    },
+    {
+      "epoch": 0.10140687001483026,
+      "grad_norm": 0.37882164120674133,
+      "learning_rate": 2e-05,
+      "loss": 0.5674,
+      "step": 2530
+    },
+    {
+      "epoch": 0.10180768768287306,
+      "grad_norm": 0.37527206540107727,
+      "learning_rate": 2e-05,
+      "loss": 0.56,
+      "step": 2540
+    },
+    {
+      "epoch": 0.10220850535091587,
+      "grad_norm": 0.45134904980659485,
+      "learning_rate": 2e-05,
+      "loss": 0.5398,
+      "step": 2550
+    },
+    {
+      "epoch": 0.10260932301895867,
+      "grad_norm": 0.44729816913604736,
+      "learning_rate": 2e-05,
+      "loss": 0.5569,
+      "step": 2560
+    },
+    {
+      "epoch": 0.10301014068700148,
+      "grad_norm": 0.29179856181144714,
+      "learning_rate": 2e-05,
+      "loss": 0.5806,
+      "step": 2570
+    },
+    {
+      "epoch": 0.1034109583550443,
+      "grad_norm": 0.3566204905509949,
+      "learning_rate": 2e-05,
+      "loss": 0.5792,
+      "step": 2580
+    },
+    {
+      "epoch": 0.1038117760230871,
+      "grad_norm": 0.34388139843940735,
+      "learning_rate": 2e-05,
+      "loss": 0.5607,
+      "step": 2590
+    },
+    {
+      "epoch": 0.10421259369112991,
+      "grad_norm": 0.4333122670650482,
+      "learning_rate": 2e-05,
+      "loss": 0.5567,
+      "step": 2600
+    },
+    {
+      "epoch": 0.10461341135917271,
+      "grad_norm": 0.3270779252052307,
+      "learning_rate": 2e-05,
+      "loss": 0.572,
+      "step": 2610
+    },
+    {
+      "epoch": 0.10501422902721552,
+      "grad_norm": 0.3311755657196045,
+      "learning_rate": 2e-05,
+      "loss": 0.5705,
+      "step": 2620
+    },
+    {
+      "epoch": 0.10541504669525832,
+      "grad_norm": 0.355700820684433,
+      "learning_rate": 2e-05,
+      "loss": 0.5679,
+      "step": 2630
+    },
+    {
+      "epoch": 0.10581586436330113,
+      "grad_norm": 0.3758179247379303,
+      "learning_rate": 2e-05,
+      "loss": 0.5837,
+      "step": 2640
+    },
+    {
+      "epoch": 0.10621668203134395,
+      "grad_norm": 0.4235946536064148,
+      "learning_rate": 2e-05,
+      "loss": 0.5706,
+      "step": 2650
+    },
+    {
+      "epoch": 0.10661749969938675,
+      "grad_norm": 0.4534910023212433,
+      "learning_rate": 2e-05,
+      "loss": 0.545,
+      "step": 2660
+    },
+    {
+      "epoch": 0.10701831736742956,
+      "grad_norm": 0.3604424297809601,
+      "learning_rate": 2e-05,
+      "loss": 0.5662,
+      "step": 2670
+    },
+    {
+      "epoch": 0.10741913503547236,
+      "grad_norm": 0.32635748386383057,
+      "learning_rate": 2e-05,
+      "loss": 0.5581,
+      "step": 2680
+    },
+    {
+      "epoch": 0.10781995270351517,
+      "grad_norm": 0.3974153697490692,
+      "learning_rate": 2e-05,
+      "loss": 0.5658,
+      "step": 2690
+    },
+    {
+      "epoch": 0.10822077037155797,
+      "grad_norm": 0.37879955768585205,
+      "learning_rate": 2e-05,
+      "loss": 0.5591,
+      "step": 2700
+    },
+    {
+      "epoch": 0.10862158803960079,
+      "grad_norm": 0.39657601714134216,
+      "learning_rate": 2e-05,
+      "loss": 0.5888,
+      "step": 2710
+    },
+    {
+      "epoch": 0.1090224057076436,
+      "grad_norm": 0.38731491565704346,
+      "learning_rate": 2e-05,
+      "loss": 0.5804,
+      "step": 2720
+    },
+    {
+      "epoch": 0.1094232233756864,
+      "grad_norm": 0.5076712965965271,
+      "learning_rate": 2e-05,
+      "loss": 0.5961,
+      "step": 2730
+    },
+    {
+      "epoch": 0.10982404104372921,
+      "grad_norm": 0.3596253991127014,
+      "learning_rate": 2e-05,
+      "loss": 0.5465,
+      "step": 2740
+    },
+    {
+      "epoch": 0.11022485871177201,
+      "grad_norm": 0.6818852424621582,
+      "learning_rate": 2e-05,
+      "loss": 0.5708,
+      "step": 2750
+    },
+    {
+      "epoch": 0.11062567637981482,
+      "grad_norm": 0.3373611569404602,
+      "learning_rate": 2e-05,
+      "loss": 0.5681,
+      "step": 2760
+    },
+    {
+      "epoch": 0.11102649404785762,
+      "grad_norm": 0.41528621315956116,
+      "learning_rate": 2e-05,
+      "loss": 0.5874,
+      "step": 2770
+    },
+    {
+      "epoch": 0.11142731171590044,
+      "grad_norm": 0.3721466064453125,
+      "learning_rate": 2e-05,
+      "loss": 0.5433,
+      "step": 2780
+    },
+    {
+      "epoch": 0.11182812938394325,
+      "grad_norm": 0.3605429232120514,
+      "learning_rate": 2e-05,
+      "loss": 0.5582,
+      "step": 2790
+    },
+    {
+      "epoch": 0.11222894705198605,
+      "grad_norm": 0.4084005653858185,
+      "learning_rate": 2e-05,
+      "loss": 0.6014,
+      "step": 2800
+    },
+    {
+      "epoch": 0.11262976472002886,
+      "grad_norm": 0.35510143637657166,
+      "learning_rate": 2e-05,
+      "loss": 0.5312,
+      "step": 2810
+    },
+    {
+      "epoch": 0.11303058238807166,
+      "grad_norm": 0.4171420633792877,
+      "learning_rate": 2e-05,
+      "loss": 0.5833,
+      "step": 2820
+    },
+    {
+      "epoch": 0.11343140005611448,
+      "grad_norm": 0.38897544145584106,
+      "learning_rate": 2e-05,
+      "loss": 0.543,
+      "step": 2830
+    },
+    {
+      "epoch": 0.11383221772415728,
+      "grad_norm": 0.3851448595523834,
+      "learning_rate": 2e-05,
+      "loss": 0.5484,
+      "step": 2840
+    },
+    {
+      "epoch": 0.11423303539220009,
+      "grad_norm": 0.41326257586479187,
+      "learning_rate": 2e-05,
+      "loss": 0.5719,
+      "step": 2850
+    },
+    {
+      "epoch": 0.1146338530602429,
+      "grad_norm": 0.37410998344421387,
+      "learning_rate": 2e-05,
+      "loss": 0.5597,
+      "step": 2860
+    },
+    {
+      "epoch": 0.1150346707282857,
+      "grad_norm": 0.4749361574649811,
+      "learning_rate": 2e-05,
+      "loss": 0.583,
+      "step": 2870
+    },
+    {
+      "epoch": 0.11543548839632851,
+      "grad_norm": 0.4170619547367096,
+      "learning_rate": 2e-05,
+      "loss": 0.5713,
+      "step": 2880
+    },
+    {
+      "epoch": 0.11583630606437131,
+      "grad_norm": 0.41376549005508423,
+      "learning_rate": 2e-05,
+      "loss": 0.5582,
+      "step": 2890
+    },
+    {
+      "epoch": 0.11623712373241413,
+      "grad_norm": 0.37296295166015625,
+      "learning_rate": 2e-05,
+      "loss": 0.5574,
+      "step": 2900
+    },
+    {
+      "epoch": 0.11663794140045693,
+      "grad_norm": 0.3766053020954132,
+      "learning_rate": 2e-05,
+      "loss": 0.5911,
+      "step": 2910
+    },
+    {
+      "epoch": 0.11703875906849974,
+      "grad_norm": 0.40055564045906067,
+      "learning_rate": 2e-05,
+      "loss": 0.6162,
+      "step": 2920
+    },
+    {
+      "epoch": 0.11743957673654255,
+      "grad_norm": 0.34108811616897583,
+      "learning_rate": 2e-05,
+      "loss": 0.5413,
+      "step": 2930
+    },
+    {
+      "epoch": 0.11784039440458535,
+      "grad_norm": 0.3507615327835083,
+      "learning_rate": 2e-05,
+      "loss": 0.5779,
+      "step": 2940
+    },
+    {
+      "epoch": 0.11824121207262817,
+      "grad_norm": 0.39660125970840454,
+      "learning_rate": 2e-05,
+      "loss": 0.613,
+      "step": 2950
+    },
+    {
+      "epoch": 0.11864202974067097,
+      "grad_norm": 0.35685157775878906,
+      "learning_rate": 2e-05,
+      "loss": 0.5553,
+      "step": 2960
+    },
+    {
+      "epoch": 0.11904284740871378,
+      "grad_norm": 0.3450596332550049,
+      "learning_rate": 2e-05,
+      "loss": 0.5538,
+      "step": 2970
+    },
+    {
+      "epoch": 0.11944366507675658,
+      "grad_norm": 0.36301591992378235,
+      "learning_rate": 2e-05,
+      "loss": 0.5696,
+      "step": 2980
+    },
+    {
+      "epoch": 0.11984448274479939,
+      "grad_norm": 0.38117361068725586,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 2990
+    },
+    {
+      "epoch": 0.1202453004128422,
+      "grad_norm": 0.39063242077827454,
+      "learning_rate": 2e-05,
+      "loss": 0.571,
+      "step": 3000
+    },
+    {
+      "epoch": 0.120646118080885,
+      "grad_norm": 0.37124958634376526,
+      "learning_rate": 2e-05,
+      "loss": 0.5638,
+      "step": 3010
+    },
+    {
+      "epoch": 0.12104693574892782,
+      "grad_norm": 0.36760056018829346,
+      "learning_rate": 2e-05,
+      "loss": 0.5463,
+      "step": 3020
+    },
+    {
+      "epoch": 0.12144775341697062,
+      "grad_norm": 0.38047149777412415,
+      "learning_rate": 2e-05,
+      "loss": 0.5883,
+      "step": 3030
+    },
+    {
+      "epoch": 0.12184857108501343,
+      "grad_norm": 0.366414874792099,
+      "learning_rate": 2e-05,
+      "loss": 0.5626,
+      "step": 3040
+    },
+    {
+      "epoch": 0.12224938875305623,
+      "grad_norm": 0.6604557633399963,
+      "learning_rate": 2e-05,
+      "loss": 0.5845,
+      "step": 3050
+    },
+    {
+      "epoch": 0.12265020642109904,
+      "grad_norm": 0.36171624064445496,
+      "learning_rate": 2e-05,
+      "loss": 0.5455,
+      "step": 3060
+    },
+    {
+      "epoch": 0.12305102408914186,
+      "grad_norm": 0.36407172679901123,
+      "learning_rate": 2e-05,
+      "loss": 0.5672,
+      "step": 3070
+    },
+    {
+      "epoch": 0.12345184175718465,
+      "grad_norm": 0.3666282296180725,
+      "learning_rate": 2e-05,
+      "loss": 0.5636,
+      "step": 3080
+    },
+    {
+      "epoch": 0.12385265942522747,
+      "grad_norm": 0.3591126501560211,
+      "learning_rate": 2e-05,
+      "loss": 0.5561,
+      "step": 3090
+    },
+    {
+      "epoch": 0.12425347709327027,
+      "grad_norm": 0.5449425578117371,
+      "learning_rate": 2e-05,
+      "loss": 0.5575,
+      "step": 3100
+    },
+    {
+      "epoch": 0.12465429476131308,
+      "grad_norm": 0.35526731610298157,
+      "learning_rate": 2e-05,
+      "loss": 0.5565,
+      "step": 3110
+    },
+    {
+      "epoch": 0.12505511242935588,
+      "grad_norm": 0.401933878660202,
+      "learning_rate": 2e-05,
+      "loss": 0.6013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.1254559300973987,
+      "grad_norm": 0.35224899649620056,
+      "learning_rate": 2e-05,
+      "loss": 0.5502,
+      "step": 3130
+    },
+    {
+      "epoch": 0.1258567477654415,
+      "grad_norm": 0.38501036167144775,
+      "learning_rate": 2e-05,
+      "loss": 0.5908,
+      "step": 3140
+    },
+    {
+      "epoch": 0.12625756543348432,
+      "grad_norm": 0.37840890884399414,
+      "learning_rate": 2e-05,
+      "loss": 0.5408,
+      "step": 3150
+    },
+    {
+      "epoch": 0.1266583831015271,
+      "grad_norm": 0.8629856705665588,
+      "learning_rate": 2e-05,
+      "loss": 0.5785,
+      "step": 3160
+    },
+    {
+      "epoch": 0.12705920076956992,
+      "grad_norm": 0.3897327482700348,
+      "learning_rate": 2e-05,
+      "loss": 0.5699,
+      "step": 3170
+    },
+    {
+      "epoch": 0.12746001843761273,
+      "grad_norm": 0.32331597805023193,
+      "learning_rate": 2e-05,
+      "loss": 0.5867,
+      "step": 3180
+    },
+    {
+      "epoch": 0.12786083610565555,
+      "grad_norm": 0.3642168939113617,
+      "learning_rate": 2e-05,
+      "loss": 0.521,
+      "step": 3190
+    },
+    {
+      "epoch": 0.12826165377369833,
+      "grad_norm": 0.49447524547576904,
+      "learning_rate": 2e-05,
+      "loss": 0.5716,
+      "step": 3200
+    },
+    {
+      "epoch": 0.12866247144174114,
+      "grad_norm": 0.3670274317264557,
+      "learning_rate": 2e-05,
+      "loss": 0.587,
+      "step": 3210
+    },
+    {
+      "epoch": 0.12906328910978396,
+      "grad_norm": 0.36232125759124756,
+      "learning_rate": 2e-05,
+      "loss": 0.5616,
+      "step": 3220
+    },
+    {
+      "epoch": 0.12946410677782677,
+      "grad_norm": 0.3495625853538513,
+      "learning_rate": 2e-05,
+      "loss": 0.5484,
+      "step": 3230
+    },
+    {
+      "epoch": 0.12986492444586958,
+      "grad_norm": 0.3833344578742981,
+      "learning_rate": 2e-05,
+      "loss": 0.5517,
+      "step": 3240
+    },
+    {
+      "epoch": 0.13026574211391237,
+      "grad_norm": 0.3367772102355957,
+      "learning_rate": 2e-05,
+      "loss": 0.5767,
+      "step": 3250
+    },
+    {
+      "epoch": 0.13066655978195518,
+      "grad_norm": 0.4046475291252136,
+      "learning_rate": 2e-05,
+      "loss": 0.5342,
+      "step": 3260
+    },
+    {
+      "epoch": 0.131067377449998,
+      "grad_norm": 0.4214325249195099,
+      "learning_rate": 2e-05,
+      "loss": 0.5268,
+      "step": 3270
+    },
+    {
+      "epoch": 0.1314681951180408,
+      "grad_norm": 0.4093036651611328,
+      "learning_rate": 2e-05,
+      "loss": 0.5912,
+      "step": 3280
+    },
+    {
+      "epoch": 0.13186901278608362,
+      "grad_norm": 0.45690345764160156,
+      "learning_rate": 2e-05,
+      "loss": 0.5754,
+      "step": 3290
+    },
+    {
+      "epoch": 0.1322698304541264,
+      "grad_norm": 0.3545232117176056,
+      "learning_rate": 2e-05,
+      "loss": 0.5598,
+      "step": 3300
+    },
+    {
+      "epoch": 0.13267064812216922,
+      "grad_norm": 0.3392185568809509,
+      "learning_rate": 2e-05,
+      "loss": 0.5602,
+      "step": 3310
+    },
+    {
+      "epoch": 0.13307146579021203,
+      "grad_norm": 0.4475401043891907,
+      "learning_rate": 2e-05,
+      "loss": 0.5655,
+      "step": 3320
+    },
+    {
+      "epoch": 0.13347228345825485,
+      "grad_norm": 0.4275551736354828,
+      "learning_rate": 2e-05,
+      "loss": 0.56,
+      "step": 3330
+    },
+    {
+      "epoch": 0.13387310112629763,
+      "grad_norm": 0.4727897346019745,
+      "learning_rate": 2e-05,
+      "loss": 0.5706,
+      "step": 3340
+    },
+    {
+      "epoch": 0.13427391879434045,
+      "grad_norm": 0.43208369612693787,
+      "learning_rate": 2e-05,
+      "loss": 0.5734,
+      "step": 3350
+    },
+    {
+      "epoch": 0.13467473646238326,
+      "grad_norm": 0.33621519804000854,
+      "learning_rate": 2e-05,
+      "loss": 0.5431,
+      "step": 3360
+    },
+    {
+      "epoch": 0.13507555413042607,
+      "grad_norm": 0.42468395829200745,
+      "learning_rate": 2e-05,
+      "loss": 0.6185,
+      "step": 3370
+    },
+    {
+      "epoch": 0.1354763717984689,
+      "grad_norm": 0.4151937663555145,
+      "learning_rate": 2e-05,
+      "loss": 0.5393,
+      "step": 3380
+    },
+    {
+      "epoch": 0.13587718946651167,
+      "grad_norm": 0.38833171129226685,
+      "learning_rate": 2e-05,
+      "loss": 0.5525,
+      "step": 3390
+    },
+    {
+      "epoch": 0.13627800713455449,
+      "grad_norm": 0.5158320665359497,
+      "learning_rate": 2e-05,
+      "loss": 0.5895,
+      "step": 3400
+    },
+    {
+      "epoch": 0.1366788248025973,
+      "grad_norm": 0.41796988248825073,
+      "learning_rate": 2e-05,
+      "loss": 0.554,
+      "step": 3410
+    },
+    {
+      "epoch": 0.1370796424706401,
+      "grad_norm": 0.42714154720306396,
+      "learning_rate": 2e-05,
+      "loss": 0.5294,
+      "step": 3420
+    },
+    {
+      "epoch": 0.13748046013868293,
+      "grad_norm": 0.38487645983695984,
+      "learning_rate": 2e-05,
+      "loss": 0.5707,
+      "step": 3430
+    },
+    {
+      "epoch": 0.1378812778067257,
+      "grad_norm": 0.33553385734558105,
+      "learning_rate": 2e-05,
+      "loss": 0.5772,
+      "step": 3440
+    },
+    {
+      "epoch": 0.13828209547476852,
+      "grad_norm": 0.3741719424724579,
+      "learning_rate": 2e-05,
+      "loss": 0.5593,
+      "step": 3450
+    },
+    {
+      "epoch": 0.13868291314281134,
+      "grad_norm": 0.4149104952812195,
+      "learning_rate": 2e-05,
+      "loss": 0.5677,
+      "step": 3460
+    },
+    {
+      "epoch": 0.13908373081085415,
+      "grad_norm": 0.33128297328948975,
+      "learning_rate": 2e-05,
+      "loss": 0.5684,
+      "step": 3470
+    },
+    {
+      "epoch": 0.13948454847889696,
+      "grad_norm": 0.35428762435913086,
+      "learning_rate": 2e-05,
+      "loss": 0.5665,
+      "step": 3480
+    },
+    {
+      "epoch": 0.13988536614693975,
+      "grad_norm": 0.39158743619918823,
+      "learning_rate": 2e-05,
+      "loss": 0.5705,
+      "step": 3490
+    },
+    {
+      "epoch": 0.14028618381498256,
+      "grad_norm": 0.3916440010070801,
+      "learning_rate": 2e-05,
+      "loss": 0.547,
+      "step": 3500
+    },
+    {
+      "epoch": 0.14068700148302538,
+      "grad_norm": 0.4144287407398224,
+      "learning_rate": 2e-05,
+      "loss": 0.5539,
+      "step": 3510
+    },
+    {
+      "epoch": 0.1410878191510682,
+      "grad_norm": 0.41197875142097473,
+      "learning_rate": 2e-05,
+      "loss": 0.5764,
+      "step": 3520
+    },
+    {
+      "epoch": 0.14148863681911097,
+      "grad_norm": 0.4137912392616272,
+      "learning_rate": 2e-05,
+      "loss": 0.5362,
+      "step": 3530
+    },
+    {
+      "epoch": 0.1418894544871538,
+      "grad_norm": 0.413318008184433,
+      "learning_rate": 2e-05,
+      "loss": 0.5404,
+      "step": 3540
+    },
+    {
+      "epoch": 0.1422902721551966,
+      "grad_norm": 0.3670721650123596,
+      "learning_rate": 2e-05,
+      "loss": 0.5541,
+      "step": 3550
+    },
+    {
+      "epoch": 0.14269108982323941,
+      "grad_norm": 0.3639812171459198,
+      "learning_rate": 2e-05,
+      "loss": 0.5438,
+      "step": 3560
+    },
+    {
+      "epoch": 0.14309190749128223,
+      "grad_norm": 0.39278337359428406,
+      "learning_rate": 2e-05,
+      "loss": 0.5451,
+      "step": 3570
+    },
+    {
+      "epoch": 0.143492725159325,
+      "grad_norm": 0.3662254512310028,
+      "learning_rate": 2e-05,
+      "loss": 0.5813,
+      "step": 3580
+    },
+    {
+      "epoch": 0.14389354282736783,
+      "grad_norm": 0.393451452255249,
+      "learning_rate": 2e-05,
+      "loss": 0.5461,
+      "step": 3590
+    },
+    {
+      "epoch": 0.14429436049541064,
+      "grad_norm": 0.40145015716552734,
+      "learning_rate": 2e-05,
+      "loss": 0.5427,
+      "step": 3600
+    },
+    {
+      "epoch": 0.14469517816345345,
+      "grad_norm": 0.39159318804740906,
+      "learning_rate": 2e-05,
+      "loss": 0.5701,
+      "step": 3610
+    },
+    {
+      "epoch": 0.14509599583149627,
+      "grad_norm": 0.32462480664253235,
+      "learning_rate": 2e-05,
+      "loss": 0.547,
+      "step": 3620
+    },
+    {
+      "epoch": 0.14549681349953905,
+      "grad_norm": 0.3443101644515991,
+      "learning_rate": 2e-05,
+      "loss": 0.5462,
+      "step": 3630
+    },
+    {
+      "epoch": 0.14589763116758186,
+      "grad_norm": 0.3691333830356598,
+      "learning_rate": 2e-05,
+      "loss": 0.5755,
+      "step": 3640
+    },
+    {
+      "epoch": 0.14629844883562468,
+      "grad_norm": 0.3583635687828064,
+      "learning_rate": 2e-05,
+      "loss": 0.5476,
+      "step": 3650
+    },
+    {
+      "epoch": 0.1466992665036675,
+      "grad_norm": 0.41858625411987305,
+      "learning_rate": 2e-05,
+      "loss": 0.5432,
+      "step": 3660
+    },
+    {
+      "epoch": 0.14710008417171028,
+      "grad_norm": 0.37000134587287903,
+      "learning_rate": 2e-05,
+      "loss": 0.5893,
+      "step": 3670
+    },
+    {
+      "epoch": 0.1475009018397531,
+      "grad_norm": 0.3400837481021881,
+      "learning_rate": 2e-05,
+      "loss": 0.5558,
+      "step": 3680
+    },
+    {
+      "epoch": 0.1479017195077959,
+      "grad_norm": 0.3961534798145294,
+      "learning_rate": 2e-05,
+      "loss": 0.5749,
+      "step": 3690
+    },
+    {
+      "epoch": 0.14830253717583872,
+      "grad_norm": 0.5130637884140015,
+      "learning_rate": 2e-05,
+      "loss": 0.5261,
+      "step": 3700
+    },
+    {
+      "epoch": 0.14870335484388153,
+      "grad_norm": 0.41944175958633423,
+      "learning_rate": 2e-05,
+      "loss": 0.6251,
+      "step": 3710
+    },
+    {
+      "epoch": 0.14910417251192432,
+      "grad_norm": 0.37696608901023865,
+      "learning_rate": 2e-05,
+      "loss": 0.578,
+      "step": 3720
+    },
+    {
+      "epoch": 0.14950499017996713,
+      "grad_norm": 0.35710376501083374,
+      "learning_rate": 2e-05,
+      "loss": 0.5317,
+      "step": 3730
+    },
+    {
+      "epoch": 0.14990580784800994,
+      "grad_norm": 0.39019304513931274,
+      "learning_rate": 2e-05,
+      "loss": 0.568,
+      "step": 3740
+    },
+    {
+      "epoch": 0.15030662551605276,
+      "grad_norm": 0.36526137590408325,
+      "learning_rate": 2e-05,
+      "loss": 0.539,
+      "step": 3750
+    },
+    {
+      "epoch": 0.15070744318409557,
+      "grad_norm": 0.39668208360671997,
+      "learning_rate": 2e-05,
+      "loss": 0.5691,
+      "step": 3760
+    },
+    {
+      "epoch": 0.15110826085213835,
+      "grad_norm": 0.3485737144947052,
+      "learning_rate": 2e-05,
+      "loss": 0.5579,
+      "step": 3770
+    },
+    {
+      "epoch": 0.15150907852018117,
+      "grad_norm": 0.4233294725418091,
+      "learning_rate": 2e-05,
+      "loss": 0.5503,
+      "step": 3780
+    },
+    {
+      "epoch": 0.15190989618822398,
+      "grad_norm": 0.3929007947444916,
+      "learning_rate": 2e-05,
+      "loss": 0.5794,
+      "step": 3790
+    },
+    {
+      "epoch": 0.1523107138562668,
+      "grad_norm": 0.7184209227561951,
+      "learning_rate": 2e-05,
+      "loss": 0.5272,
+      "step": 3800
+    },
+    {
+      "epoch": 0.15271153152430958,
+      "grad_norm": 0.3964136838912964,
+      "learning_rate": 2e-05,
+      "loss": 0.5294,
+      "step": 3810
+    },
+    {
+      "epoch": 0.1531123491923524,
+      "grad_norm": 0.48776546120643616,
+      "learning_rate": 2e-05,
+      "loss": 0.562,
+      "step": 3820
+    },
+    {
+      "epoch": 0.1535131668603952,
+      "grad_norm": 0.41285786032676697,
+      "learning_rate": 2e-05,
+      "loss": 0.5546,
+      "step": 3830
+    },
+    {
+      "epoch": 0.15391398452843802,
+      "grad_norm": 0.33892032504081726,
+      "learning_rate": 2e-05,
+      "loss": 0.5638,
+      "step": 3840
+    },
+    {
+      "epoch": 0.15431480219648083,
+      "grad_norm": 0.365267813205719,
+      "learning_rate": 2e-05,
+      "loss": 0.557,
+      "step": 3850
+    },
+    {
+      "epoch": 0.15471561986452362,
+      "grad_norm": 0.36361292004585266,
+      "learning_rate": 2e-05,
+      "loss": 0.5403,
+      "step": 3860
+    },
+    {
+      "epoch": 0.15511643753256643,
+      "grad_norm": 0.35188499093055725,
+      "learning_rate": 2e-05,
+      "loss": 0.5161,
+      "step": 3870
+    },
+    {
+      "epoch": 0.15551725520060924,
+      "grad_norm": 0.3540356755256653,
+      "learning_rate": 2e-05,
+      "loss": 0.5593,
+      "step": 3880
+    },
+    {
+      "epoch": 0.15591807286865206,
+      "grad_norm": 0.3354050815105438,
+      "learning_rate": 2e-05,
+      "loss": 0.5553,
+      "step": 3890
+    },
+    {
+      "epoch": 0.15631889053669487,
+      "grad_norm": 0.36081844568252563,
+      "learning_rate": 2e-05,
+      "loss": 0.5633,
+      "step": 3900
+    },
+    {
+      "epoch": 0.15671970820473766,
+      "grad_norm": 0.3673272430896759,
+      "learning_rate": 2e-05,
+      "loss": 0.565,
+      "step": 3910
+    },
+    {
+      "epoch": 0.15712052587278047,
+      "grad_norm": 0.3504160940647125,
+      "learning_rate": 2e-05,
+      "loss": 0.5637,
+      "step": 3920
+    },
+    {
+      "epoch": 0.15752134354082328,
+      "grad_norm": 0.3604793846607208,
+      "learning_rate": 2e-05,
+      "loss": 0.5542,
+      "step": 3930
+    },
+    {
+      "epoch": 0.1579221612088661,
+      "grad_norm": 0.389984667301178,
+      "learning_rate": 2e-05,
+      "loss": 0.5333,
+      "step": 3940
+    },
+    {
+      "epoch": 0.15832297887690888,
+      "grad_norm": 0.4087458848953247,
+      "learning_rate": 2e-05,
+      "loss": 0.5887,
+      "step": 3950
+    },
+    {
+      "epoch": 0.1587237965449517,
+      "grad_norm": 0.4695092439651489,
+      "learning_rate": 2e-05,
+      "loss": 0.5821,
+      "step": 3960
+    },
+    {
+      "epoch": 0.1591246142129945,
+      "grad_norm": 0.4853971004486084,
+      "learning_rate": 2e-05,
+      "loss": 0.5412,
+      "step": 3970
+    },
+    {
+      "epoch": 0.15952543188103732,
+      "grad_norm": 0.3997495472431183,
+      "learning_rate": 2e-05,
+      "loss": 0.5536,
+      "step": 3980
+    },
+    {
+      "epoch": 0.15992624954908014,
+      "grad_norm": 0.40451139211654663,
+      "learning_rate": 2e-05,
+      "loss": 0.534,
+      "step": 3990
+    },
+    {
+      "epoch": 0.16032706721712292,
+      "grad_norm": 0.39277586340904236,
+      "learning_rate": 2e-05,
+      "loss": 0.538,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16072788488516573,
+      "grad_norm": 0.3622714877128601,
+      "learning_rate": 2e-05,
+      "loss": 0.5459,
+      "step": 4010
+    },
+    {
+      "epoch": 0.16112870255320855,
+      "grad_norm": 0.3667004108428955,
+      "learning_rate": 2e-05,
+      "loss": 0.5495,
+      "step": 4020
+    },
+    {
+      "epoch": 0.16152952022125136,
+      "grad_norm": 0.3324030041694641,
+      "learning_rate": 2e-05,
+      "loss": 0.548,
+      "step": 4030
+    },
+    {
+      "epoch": 0.16193033788929417,
+      "grad_norm": 0.3541210889816284,
+      "learning_rate": 2e-05,
+      "loss": 0.5511,
+      "step": 4040
+    },
+    {
+      "epoch": 0.16233115555733696,
+      "grad_norm": 0.3800106942653656,
+      "learning_rate": 2e-05,
+      "loss": 0.5828,
+      "step": 4050
+    },
+    {
+      "epoch": 0.16273197322537977,
+      "grad_norm": 0.4944571256637573,
+      "learning_rate": 2e-05,
+      "loss": 0.5362,
+      "step": 4060
+    },
+    {
+      "epoch": 0.16313279089342259,
+      "grad_norm": 0.4176241159439087,
+      "learning_rate": 2e-05,
+      "loss": 0.535,
+      "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:d73d0679abedb6a93cff636b6ca56826e618f662f66f1590691c3ded99e72793
+size 7889