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 sha256:55d91794db56c900d514b7373dae5491502a6114bf7fb0d08225fd0d908e5d44
+size 4902257696

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bbe85cbcfb191c234ff791b7a2bebe384f35c8c290db1110bb9c3d7fcea88c
+size 4915960368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e962e91f1bc9f48c9d69b30dd72f6c8d15c1a2bebe21616b2b9efb38f73cdb9a
+size 4983068496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27965eba8c852aa9c52616fa4f647c13713baa1650b5fa7081753f78f2e3ea80
+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": 0.19057876006742835,
+  "eval_steps": 500,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004682524817381532,
+      "grad_norm": 0.7815176248550415,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.8415,
+      "step": 10
+    },
+    {
+      "epoch": 0.0009365049634763064,
+      "grad_norm": 0.8108879327774048,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.8485,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014047574452144597,
+      "grad_norm": 0.8000619411468506,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.83,
+      "step": 30
+    },
+    {
+      "epoch": 0.0018730099269526129,
+      "grad_norm": 0.7511084675788879,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.8517,
+      "step": 40
+    },
+    {
+      "epoch": 0.002341262408690766,
+      "grad_norm": 0.7430337071418762,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.847,
+      "step": 50
+    },
+    {
+      "epoch": 0.0028095148904289193,
+      "grad_norm": 0.8726410269737244,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.8172,
+      "step": 60
+    },
+    {
+      "epoch": 0.0032777673721670723,
+      "grad_norm": 0.8567508459091187,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.8377,
+      "step": 70
+    },
+    {
+      "epoch": 0.0037460198539052258,
+      "grad_norm": 0.7639268040657043,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.8184,
+      "step": 80
+    },
+    {
+      "epoch": 0.004214272335643379,
+      "grad_norm": 0.9645025134086609,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.8178,
+      "step": 90
+    },
+    {
+      "epoch": 0.004682524817381532,
+      "grad_norm": 0.801426887512207,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.8351,
+      "step": 100
+    },
+    {
+      "epoch": 0.005150777299119685,
+      "grad_norm": 0.8018251061439514,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.8493,
+      "step": 110
+    },
+    {
+      "epoch": 0.005619029780857839,
+      "grad_norm": 1.6218419075012207,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.8367,
+      "step": 120
+    },
+    {
+      "epoch": 0.006087282262595992,
+      "grad_norm": 0.738893449306488,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.8622,
+      "step": 130
+    },
+    {
+      "epoch": 0.006555534744334145,
+      "grad_norm": 0.9413527846336365,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.8024,
+      "step": 140
+    },
+    {
+      "epoch": 0.007023787226072298,
+      "grad_norm": 0.8190211653709412,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.8216,
+      "step": 150
+    },
+    {
+      "epoch": 0.0074920397078104516,
+      "grad_norm": 0.6878272294998169,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.8609,
+      "step": 160
+    },
+    {
+      "epoch": 0.007960292189548605,
+      "grad_norm": 0.7031309008598328,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.8954,
+      "step": 170
+    },
+    {
+      "epoch": 0.008428544671286758,
+      "grad_norm": 0.7149655818939209,
+      "learning_rate": 2e-05,
+      "loss": 0.8378,
+      "step": 180
+    },
+    {
+      "epoch": 0.008896797153024912,
+      "grad_norm": 0.6629250645637512,
+      "learning_rate": 2e-05,
+      "loss": 0.8002,
+      "step": 190
+    },
+    {
+      "epoch": 0.009365049634763064,
+      "grad_norm": 0.6915798783302307,
+      "learning_rate": 2e-05,
+      "loss": 0.8358,
+      "step": 200
+    },
+    {
+      "epoch": 0.009833302116501217,
+      "grad_norm": 0.6538642644882202,
+      "learning_rate": 2e-05,
+      "loss": 0.8535,
+      "step": 210
+    },
+    {
+      "epoch": 0.01030155459823937,
+      "grad_norm": 0.584514856338501,
+      "learning_rate": 2e-05,
+      "loss": 0.8362,
+      "step": 220
+    },
+    {
+      "epoch": 0.010769807079977524,
+      "grad_norm": 1.3603894710540771,
+      "learning_rate": 2e-05,
+      "loss": 0.8086,
+      "step": 230
+    },
+    {
+      "epoch": 0.011238059561715677,
+      "grad_norm": 0.5758199691772461,
+      "learning_rate": 2e-05,
+      "loss": 0.8336,
+      "step": 240
+    },
+    {
+      "epoch": 0.01170631204345383,
+      "grad_norm": 0.6881021857261658,
+      "learning_rate": 2e-05,
+      "loss": 0.8444,
+      "step": 250
+    },
+    {
+      "epoch": 0.012174564525191984,
+      "grad_norm": 1.9581451416015625,
+      "learning_rate": 2e-05,
+      "loss": 0.8433,
+      "step": 260
+    },
+    {
+      "epoch": 0.012642817006930136,
+      "grad_norm": 0.5425940752029419,
+      "learning_rate": 2e-05,
+      "loss": 0.8213,
+      "step": 270
+    },
+    {
+      "epoch": 0.01311106948866829,
+      "grad_norm": 0.5425044298171997,
+      "learning_rate": 2e-05,
+      "loss": 0.8179,
+      "step": 280
+    },
+    {
+      "epoch": 0.013579321970406443,
+      "grad_norm": 0.657163143157959,
+      "learning_rate": 2e-05,
+      "loss": 0.8649,
+      "step": 290
+    },
+    {
+      "epoch": 0.014047574452144596,
+      "grad_norm": 0.569369375705719,
+      "learning_rate": 2e-05,
+      "loss": 0.8438,
+      "step": 300
+    },
+    {
+      "epoch": 0.01451582693388275,
+      "grad_norm": 0.554995059967041,
+      "learning_rate": 2e-05,
+      "loss": 0.8085,
+      "step": 310
+    },
+    {
+      "epoch": 0.014984079415620903,
+      "grad_norm": 0.5484607219696045,
+      "learning_rate": 2e-05,
+      "loss": 0.8089,
+      "step": 320
+    },
+    {
+      "epoch": 0.015452331897359057,
+      "grad_norm": 0.5753210186958313,
+      "learning_rate": 2e-05,
+      "loss": 0.8142,
+      "step": 330
+    },
+    {
+      "epoch": 0.01592058437909721,
+      "grad_norm": 0.7434160113334656,
+      "learning_rate": 2e-05,
+      "loss": 0.8188,
+      "step": 340
+    },
+    {
+      "epoch": 0.01638883686083536,
+      "grad_norm": 0.574074923992157,
+      "learning_rate": 2e-05,
+      "loss": 0.8563,
+      "step": 350
+    },
+    {
+      "epoch": 0.016857089342573517,
+      "grad_norm": 0.5934783816337585,
+      "learning_rate": 2e-05,
+      "loss": 0.839,
+      "step": 360
+    },
+    {
+      "epoch": 0.01732534182431167,
+      "grad_norm": 2.1430094242095947,
+      "learning_rate": 2e-05,
+      "loss": 0.8244,
+      "step": 370
+    },
+    {
+      "epoch": 0.017793594306049824,
+      "grad_norm": 0.5127322673797607,
+      "learning_rate": 2e-05,
+      "loss": 0.7979,
+      "step": 380
+    },
+    {
+      "epoch": 0.018261846787787975,
+      "grad_norm": 0.5187241435050964,
+      "learning_rate": 2e-05,
+      "loss": 0.8122,
+      "step": 390
+    },
+    {
+      "epoch": 0.018730099269526127,
+      "grad_norm": 0.5075030326843262,
+      "learning_rate": 2e-05,
+      "loss": 0.8645,
+      "step": 400
+    },
+    {
+      "epoch": 0.019198351751264282,
+      "grad_norm": 0.4950161576271057,
+      "learning_rate": 2e-05,
+      "loss": 0.8418,
+      "step": 410
+    },
+    {
+      "epoch": 0.019666604233002434,
+      "grad_norm": 0.5396143794059753,
+      "learning_rate": 2e-05,
+      "loss": 0.8152,
+      "step": 420
+    },
+    {
+      "epoch": 0.02013485671474059,
+      "grad_norm": 0.5515366196632385,
+      "learning_rate": 2e-05,
+      "loss": 0.7911,
+      "step": 430
+    },
+    {
+      "epoch": 0.02060310919647874,
+      "grad_norm": 0.5184299945831299,
+      "learning_rate": 2e-05,
+      "loss": 0.8403,
+      "step": 440
+    },
+    {
+      "epoch": 0.021071361678216896,
+      "grad_norm": 0.4794081449508667,
+      "learning_rate": 2e-05,
+      "loss": 0.8233,
+      "step": 450
+    },
+    {
+      "epoch": 0.021539614159955048,
+      "grad_norm": 0.7160170674324036,
+      "learning_rate": 2e-05,
+      "loss": 0.8302,
+      "step": 460
+    },
+    {
+      "epoch": 0.0220078666416932,
+      "grad_norm": 0.6666805148124695,
+      "learning_rate": 2e-05,
+      "loss": 0.8202,
+      "step": 470
+    },
+    {
+      "epoch": 0.022476119123431355,
+      "grad_norm": 0.5356866717338562,
+      "learning_rate": 2e-05,
+      "loss": 0.8418,
+      "step": 480
+    },
+    {
+      "epoch": 0.022944371605169506,
+      "grad_norm": 0.4900036156177521,
+      "learning_rate": 2e-05,
+      "loss": 0.829,
+      "step": 490
+    },
+    {
+      "epoch": 0.02341262408690766,
+      "grad_norm": 0.47087252140045166,
+      "learning_rate": 2e-05,
+      "loss": 0.8418,
+      "step": 500
+    },
+    {
+      "epoch": 0.023880876568645813,
+      "grad_norm": 0.5223408341407776,
+      "learning_rate": 2e-05,
+      "loss": 0.7874,
+      "step": 510
+    },
+    {
+      "epoch": 0.02434912905038397,
+      "grad_norm": 0.5723909735679626,
+      "learning_rate": 2e-05,
+      "loss": 0.8552,
+      "step": 520
+    },
+    {
+      "epoch": 0.02481738153212212,
+      "grad_norm": 0.4538605213165283,
+      "learning_rate": 2e-05,
+      "loss": 0.7783,
+      "step": 530
+    },
+    {
+      "epoch": 0.025285634013860272,
+      "grad_norm": 0.4878973960876465,
+      "learning_rate": 2e-05,
+      "loss": 0.8085,
+      "step": 540
+    },
+    {
+      "epoch": 0.025753886495598427,
+      "grad_norm": 0.5102939605712891,
+      "learning_rate": 2e-05,
+      "loss": 0.799,
+      "step": 550
+    },
+    {
+      "epoch": 0.02622213897733658,
+      "grad_norm": 0.5069881081581116,
+      "learning_rate": 2e-05,
+      "loss": 0.8201,
+      "step": 560
+    },
+    {
+      "epoch": 0.026690391459074734,
+      "grad_norm": 0.45733290910720825,
+      "learning_rate": 2e-05,
+      "loss": 0.844,
+      "step": 570
+    },
+    {
+      "epoch": 0.027158643940812886,
+      "grad_norm": 0.4658640921115875,
+      "learning_rate": 2e-05,
+      "loss": 0.8291,
+      "step": 580
+    },
+    {
+      "epoch": 0.02762689642255104,
+      "grad_norm": 0.48104459047317505,
+      "learning_rate": 2e-05,
+      "loss": 0.8432,
+      "step": 590
+    },
+    {
+      "epoch": 0.028095148904289192,
+      "grad_norm": 0.46297943592071533,
+      "learning_rate": 2e-05,
+      "loss": 0.8192,
+      "step": 600
+    },
+    {
+      "epoch": 0.028563401386027348,
+      "grad_norm": 0.450825959444046,
+      "learning_rate": 2e-05,
+      "loss": 0.7987,
+      "step": 610
+    },
+    {
+      "epoch": 0.0290316538677655,
+      "grad_norm": 0.4797734022140503,
+      "learning_rate": 2e-05,
+      "loss": 0.8325,
+      "step": 620
+    },
+    {
+      "epoch": 0.02949990634950365,
+      "grad_norm": 0.481893390417099,
+      "learning_rate": 2e-05,
+      "loss": 0.7837,
+      "step": 630
+    },
+    {
+      "epoch": 0.029968158831241806,
+      "grad_norm": 0.47477421164512634,
+      "learning_rate": 2e-05,
+      "loss": 0.8278,
+      "step": 640
+    },
+    {
+      "epoch": 0.030436411312979958,
+      "grad_norm": 0.5964585542678833,
+      "learning_rate": 2e-05,
+      "loss": 0.7969,
+      "step": 650
+    },
+    {
+      "epoch": 0.030904663794718113,
+      "grad_norm": 0.46593981981277466,
+      "learning_rate": 2e-05,
+      "loss": 0.8307,
+      "step": 660
+    },
+    {
+      "epoch": 0.03137291627645627,
+      "grad_norm": 0.48121365904808044,
+      "learning_rate": 2e-05,
+      "loss": 0.8174,
+      "step": 670
+    },
+    {
+      "epoch": 0.03184116875819442,
+      "grad_norm": 0.5038956999778748,
+      "learning_rate": 2e-05,
+      "loss": 0.8339,
+      "step": 680
+    },
+    {
+      "epoch": 0.03230942123993257,
+      "grad_norm": 0.5365706086158752,
+      "learning_rate": 2e-05,
+      "loss": 0.8291,
+      "step": 690
+    },
+    {
+      "epoch": 0.03277767372167072,
+      "grad_norm": 0.5319100618362427,
+      "learning_rate": 2e-05,
+      "loss": 0.7953,
+      "step": 700
+    },
+    {
+      "epoch": 0.033245926203408875,
+      "grad_norm": 0.4542364776134491,
+      "learning_rate": 2e-05,
+      "loss": 0.8263,
+      "step": 710
+    },
+    {
+      "epoch": 0.033714178685147034,
+      "grad_norm": 0.47826236486434937,
+      "learning_rate": 2e-05,
+      "loss": 0.8321,
+      "step": 720
+    },
+    {
+      "epoch": 0.034182431166885185,
+      "grad_norm": 0.44108861684799194,
+      "learning_rate": 2e-05,
+      "loss": 0.7989,
+      "step": 730
+    },
+    {
+      "epoch": 0.03465068364862334,
+      "grad_norm": 0.4653085172176361,
+      "learning_rate": 2e-05,
+      "loss": 0.7994,
+      "step": 740
+    },
+    {
+      "epoch": 0.03511893613036149,
+      "grad_norm": 0.5099039077758789,
+      "learning_rate": 2e-05,
+      "loss": 0.7591,
+      "step": 750
+    },
+    {
+      "epoch": 0.03558718861209965,
+      "grad_norm": 0.48215553164482117,
+      "learning_rate": 2e-05,
+      "loss": 0.7921,
+      "step": 760
+    },
+    {
+      "epoch": 0.0360554410938378,
+      "grad_norm": 0.46062806248664856,
+      "learning_rate": 2e-05,
+      "loss": 0.8244,
+      "step": 770
+    },
+    {
+      "epoch": 0.03652369357557595,
+      "grad_norm": 0.5108964443206787,
+      "learning_rate": 2e-05,
+      "loss": 0.8667,
+      "step": 780
+    },
+    {
+      "epoch": 0.0369919460573141,
+      "grad_norm": 0.47737154364585876,
+      "learning_rate": 2e-05,
+      "loss": 0.8246,
+      "step": 790
+    },
+    {
+      "epoch": 0.037460198539052254,
+      "grad_norm": 0.5114936828613281,
+      "learning_rate": 2e-05,
+      "loss": 0.8188,
+      "step": 800
+    },
+    {
+      "epoch": 0.03792845102079041,
+      "grad_norm": 0.47046583890914917,
+      "learning_rate": 2e-05,
+      "loss": 0.8393,
+      "step": 810
+    },
+    {
+      "epoch": 0.038396703502528565,
+      "grad_norm": 0.4314744472503662,
+      "learning_rate": 2e-05,
+      "loss": 0.7953,
+      "step": 820
+    },
+    {
+      "epoch": 0.038864955984266716,
+      "grad_norm": 0.4930090308189392,
+      "learning_rate": 2e-05,
+      "loss": 0.8048,
+      "step": 830
+    },
+    {
+      "epoch": 0.03933320846600487,
+      "grad_norm": 0.4331071078777313,
+      "learning_rate": 2e-05,
+      "loss": 0.8389,
+      "step": 840
+    },
+    {
+      "epoch": 0.03980146094774302,
+      "grad_norm": 0.4713480472564697,
+      "learning_rate": 2e-05,
+      "loss": 0.8165,
+      "step": 850
+    },
+    {
+      "epoch": 0.04026971342948118,
+      "grad_norm": 0.4679141938686371,
+      "learning_rate": 2e-05,
+      "loss": 0.8198,
+      "step": 860
+    },
+    {
+      "epoch": 0.04073796591121933,
+      "grad_norm": 0.7808457612991333,
+      "learning_rate": 2e-05,
+      "loss": 0.8528,
+      "step": 870
+    },
+    {
+      "epoch": 0.04120621839295748,
+      "grad_norm": 0.44788986444473267,
+      "learning_rate": 2e-05,
+      "loss": 0.8225,
+      "step": 880
+    },
+    {
+      "epoch": 0.041674470874695634,
+      "grad_norm": 0.480165034532547,
+      "learning_rate": 2e-05,
+      "loss": 0.8185,
+      "step": 890
+    },
+    {
+      "epoch": 0.04214272335643379,
+      "grad_norm": 0.46314555406570435,
+      "learning_rate": 2e-05,
+      "loss": 0.8116,
+      "step": 900
+    },
+    {
+      "epoch": 0.042610975838171944,
+      "grad_norm": 0.6263248920440674,
+      "learning_rate": 2e-05,
+      "loss": 0.8418,
+      "step": 910
+    },
+    {
+      "epoch": 0.043079228319910096,
+      "grad_norm": 0.4619986414909363,
+      "learning_rate": 2e-05,
+      "loss": 0.8378,
+      "step": 920
+    },
+    {
+      "epoch": 0.04354748080164825,
+      "grad_norm": 0.4389607906341553,
+      "learning_rate": 2e-05,
+      "loss": 0.8153,
+      "step": 930
+    },
+    {
+      "epoch": 0.0440157332833864,
+      "grad_norm": 0.5322599411010742,
+      "learning_rate": 2e-05,
+      "loss": 0.8049,
+      "step": 940
+    },
+    {
+      "epoch": 0.04448398576512456,
+      "grad_norm": 0.4362427890300751,
+      "learning_rate": 2e-05,
+      "loss": 0.7895,
+      "step": 950
+    },
+    {
+      "epoch": 0.04495223824686271,
+      "grad_norm": 0.560736358165741,
+      "learning_rate": 2e-05,
+      "loss": 0.7834,
+      "step": 960
+    },
+    {
+      "epoch": 0.04542049072860086,
+      "grad_norm": 0.49655383825302124,
+      "learning_rate": 2e-05,
+      "loss": 0.8419,
+      "step": 970
+    },
+    {
+      "epoch": 0.04588874321033901,
+      "grad_norm": 0.447719931602478,
+      "learning_rate": 2e-05,
+      "loss": 0.8268,
+      "step": 980
+    },
+    {
+      "epoch": 0.04635699569207717,
+      "grad_norm": 0.472380131483078,
+      "learning_rate": 2e-05,
+      "loss": 0.797,
+      "step": 990
+    },
+    {
+      "epoch": 0.04682524817381532,
+      "grad_norm": 0.4404251277446747,
+      "learning_rate": 2e-05,
+      "loss": 0.8216,
+      "step": 1000
+    },
+    {
+      "epoch": 0.047293500655553475,
+      "grad_norm": 0.8469703793525696,
+      "learning_rate": 2e-05,
+      "loss": 0.8061,
+      "step": 1010
+    },
+    {
+      "epoch": 0.047761753137291627,
+      "grad_norm": 0.49690261483192444,
+      "learning_rate": 2e-05,
+      "loss": 0.8739,
+      "step": 1020
+    },
+    {
+      "epoch": 0.04823000561902978,
+      "grad_norm": 0.4546132981777191,
+      "learning_rate": 2e-05,
+      "loss": 0.8611,
+      "step": 1030
+    },
+    {
+      "epoch": 0.04869825810076794,
+      "grad_norm": 0.9852249026298523,
+      "learning_rate": 2e-05,
+      "loss": 0.8151,
+      "step": 1040
+    },
+    {
+      "epoch": 0.04916651058250609,
+      "grad_norm": 0.4317361116409302,
+      "learning_rate": 2e-05,
+      "loss": 0.8253,
+      "step": 1050
+    },
+    {
+      "epoch": 0.04963476306424424,
+      "grad_norm": 0.48968589305877686,
+      "learning_rate": 2e-05,
+      "loss": 0.8241,
+      "step": 1060
+    },
+    {
+      "epoch": 0.05010301554598239,
+      "grad_norm": 0.5702976584434509,
+      "learning_rate": 2e-05,
+      "loss": 0.788,
+      "step": 1070
+    },
+    {
+      "epoch": 0.050571268027720544,
+      "grad_norm": 0.4381064474582672,
+      "learning_rate": 2e-05,
+      "loss": 0.7815,
+      "step": 1080
+    },
+    {
+      "epoch": 0.0510395205094587,
+      "grad_norm": 0.48637041449546814,
+      "learning_rate": 2e-05,
+      "loss": 0.8424,
+      "step": 1090
+    },
+    {
+      "epoch": 0.051507772991196854,
+      "grad_norm": 0.4259801506996155,
+      "learning_rate": 2e-05,
+      "loss": 0.817,
+      "step": 1100
+    },
+    {
+      "epoch": 0.051976025472935006,
+      "grad_norm": 0.4507712423801422,
+      "learning_rate": 2e-05,
+      "loss": 0.856,
+      "step": 1110
+    },
+    {
+      "epoch": 0.05244427795467316,
+      "grad_norm": 0.4860295057296753,
+      "learning_rate": 2e-05,
+      "loss": 0.8139,
+      "step": 1120
+    },
+    {
+      "epoch": 0.052912530436411316,
+      "grad_norm": 0.5244073271751404,
+      "learning_rate": 2e-05,
+      "loss": 0.8165,
+      "step": 1130
+    },
+    {
+      "epoch": 0.05338078291814947,
+      "grad_norm": 0.4211806654930115,
+      "learning_rate": 2e-05,
+      "loss": 0.7845,
+      "step": 1140
+    },
+    {
+      "epoch": 0.05384903539988762,
+      "grad_norm": 0.4540943205356598,
+      "learning_rate": 2e-05,
+      "loss": 0.7812,
+      "step": 1150
+    },
+    {
+      "epoch": 0.05431728788162577,
+      "grad_norm": 0.4845108985900879,
+      "learning_rate": 2e-05,
+      "loss": 0.8138,
+      "step": 1160
+    },
+    {
+      "epoch": 0.05478554036336392,
+      "grad_norm": 0.46812689304351807,
+      "learning_rate": 2e-05,
+      "loss": 0.8065,
+      "step": 1170
+    },
+    {
+      "epoch": 0.05525379284510208,
+      "grad_norm": 0.42959365248680115,
+      "learning_rate": 2e-05,
+      "loss": 0.8089,
+      "step": 1180
+    },
+    {
+      "epoch": 0.05572204532684023,
+      "grad_norm": 0.7998138070106506,
+      "learning_rate": 2e-05,
+      "loss": 0.8137,
+      "step": 1190
+    },
+    {
+      "epoch": 0.056190297808578385,
+      "grad_norm": 0.46024176478385925,
+      "learning_rate": 2e-05,
+      "loss": 0.8341,
+      "step": 1200
+    },
+    {
+      "epoch": 0.05665855029031654,
+      "grad_norm": 0.4920409023761749,
+      "learning_rate": 2e-05,
+      "loss": 0.8328,
+      "step": 1210
+    },
+    {
+      "epoch": 0.057126802772054695,
+      "grad_norm": 0.44345328211784363,
+      "learning_rate": 2e-05,
+      "loss": 0.8242,
+      "step": 1220
+    },
+    {
+      "epoch": 0.05759505525379285,
+      "grad_norm": 0.4638558030128479,
+      "learning_rate": 2e-05,
+      "loss": 0.8111,
+      "step": 1230
+    },
+    {
+      "epoch": 0.058063307735531,
+      "grad_norm": 0.6508961319923401,
+      "learning_rate": 2e-05,
+      "loss": 0.809,
+      "step": 1240
+    },
+    {
+      "epoch": 0.05853156021726915,
+      "grad_norm": 0.4465144872665405,
+      "learning_rate": 2e-05,
+      "loss": 0.8195,
+      "step": 1250
+    },
+    {
+      "epoch": 0.0589998126990073,
+      "grad_norm": 0.4405592978000641,
+      "learning_rate": 2e-05,
+      "loss": 0.8352,
+      "step": 1260
+    },
+    {
+      "epoch": 0.05946806518074546,
+      "grad_norm": 0.43743807077407837,
+      "learning_rate": 2e-05,
+      "loss": 0.8149,
+      "step": 1270
+    },
+    {
+      "epoch": 0.05993631766248361,
+      "grad_norm": 0.5173885226249695,
+      "learning_rate": 2e-05,
+      "loss": 0.8421,
+      "step": 1280
+    },
+    {
+      "epoch": 0.060404570144221764,
+      "grad_norm": 0.41101977229118347,
+      "learning_rate": 2e-05,
+      "loss": 0.8493,
+      "step": 1290
+    },
+    {
+      "epoch": 0.060872822625959916,
+      "grad_norm": 0.41480135917663574,
+      "learning_rate": 2e-05,
+      "loss": 0.7971,
+      "step": 1300
+    },
+    {
+      "epoch": 0.06134107510769807,
+      "grad_norm": 0.5274170637130737,
+      "learning_rate": 2e-05,
+      "loss": 0.8106,
+      "step": 1310
+    },
+    {
+      "epoch": 0.061809327589436226,
+      "grad_norm": 0.4326211214065552,
+      "learning_rate": 2e-05,
+      "loss": 0.7927,
+      "step": 1320
+    },
+    {
+      "epoch": 0.06227758007117438,
+      "grad_norm": 0.4117155373096466,
+      "learning_rate": 2e-05,
+      "loss": 0.7877,
+      "step": 1330
+    },
+    {
+      "epoch": 0.06274583255291254,
+      "grad_norm": 0.4453534483909607,
+      "learning_rate": 2e-05,
+      "loss": 0.8417,
+      "step": 1340
+    },
+    {
+      "epoch": 0.06321408503465069,
+      "grad_norm": 0.6158928871154785,
+      "learning_rate": 2e-05,
+      "loss": 0.7797,
+      "step": 1350
+    },
+    {
+      "epoch": 0.06368233751638884,
+      "grad_norm": 0.43932247161865234,
+      "learning_rate": 2e-05,
+      "loss": 0.8042,
+      "step": 1360
+    },
+    {
+      "epoch": 0.06415058999812699,
+      "grad_norm": 0.5323647856712341,
+      "learning_rate": 2e-05,
+      "loss": 0.798,
+      "step": 1370
+    },
+    {
+      "epoch": 0.06461884247986514,
+      "grad_norm": 0.4197414517402649,
+      "learning_rate": 2e-05,
+      "loss": 0.8223,
+      "step": 1380
+    },
+    {
+      "epoch": 0.0650870949616033,
+      "grad_norm": 0.48507630825042725,
+      "learning_rate": 2e-05,
+      "loss": 0.8105,
+      "step": 1390
+    },
+    {
+      "epoch": 0.06555534744334145,
+      "grad_norm": 0.47112739086151123,
+      "learning_rate": 2e-05,
+      "loss": 0.8249,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0660235999250796,
+      "grad_norm": 0.48371198773384094,
+      "learning_rate": 2e-05,
+      "loss": 0.8105,
+      "step": 1410
+    },
+    {
+      "epoch": 0.06649185240681775,
+      "grad_norm": 0.43702569603919983,
+      "learning_rate": 2e-05,
+      "loss": 0.7906,
+      "step": 1420
+    },
+    {
+      "epoch": 0.06696010488855592,
+      "grad_norm": 0.44430628418922424,
+      "learning_rate": 2e-05,
+      "loss": 0.8313,
+      "step": 1430
+    },
+    {
+      "epoch": 0.06742835737029407,
+      "grad_norm": 0.4579251706600189,
+      "learning_rate": 2e-05,
+      "loss": 0.8415,
+      "step": 1440
+    },
+    {
+      "epoch": 0.06789660985203222,
+      "grad_norm": 0.48323583602905273,
+      "learning_rate": 2e-05,
+      "loss": 0.8341,
+      "step": 1450
+    },
+    {
+      "epoch": 0.06836486233377037,
+      "grad_norm": 0.427022248506546,
+      "learning_rate": 2e-05,
+      "loss": 0.8007,
+      "step": 1460
+    },
+    {
+      "epoch": 0.06883311481550852,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 2e-05,
+      "loss": 0.8095,
+      "step": 1470
+    },
+    {
+      "epoch": 0.06930136729724667,
+      "grad_norm": 0.45807015895843506,
+      "learning_rate": 2e-05,
+      "loss": 0.7785,
+      "step": 1480
+    },
+    {
+      "epoch": 0.06976961977898483,
+      "grad_norm": 0.5102551579475403,
+      "learning_rate": 2e-05,
+      "loss": 0.806,
+      "step": 1490
+    },
+    {
+      "epoch": 0.07023787226072298,
+      "grad_norm": 0.42989158630371094,
+      "learning_rate": 2e-05,
+      "loss": 0.8295,
+      "step": 1500
+    },
+    {
+      "epoch": 0.07070612474246113,
+      "grad_norm": 0.5128605961799622,
+      "learning_rate": 2e-05,
+      "loss": 0.8218,
+      "step": 1510
+    },
+    {
+      "epoch": 0.0711743772241993,
+      "grad_norm": 0.4889835715293884,
+      "learning_rate": 2e-05,
+      "loss": 0.7938,
+      "step": 1520
+    },
+    {
+      "epoch": 0.07164262970593745,
+      "grad_norm": 0.4175378680229187,
+      "learning_rate": 2e-05,
+      "loss": 0.8033,
+      "step": 1530
+    },
+    {
+      "epoch": 0.0721108821876756,
+      "grad_norm": 0.4378540813922882,
+      "learning_rate": 2e-05,
+      "loss": 0.8042,
+      "step": 1540
+    },
+    {
+      "epoch": 0.07257913466941375,
+      "grad_norm": 0.4375297427177429,
+      "learning_rate": 2e-05,
+      "loss": 0.8218,
+      "step": 1550
+    },
+    {
+      "epoch": 0.0730473871511519,
+      "grad_norm": 0.49845996499061584,
+      "learning_rate": 2e-05,
+      "loss": 0.8044,
+      "step": 1560
+    },
+    {
+      "epoch": 0.07351563963289005,
+      "grad_norm": 0.46285390853881836,
+      "learning_rate": 2e-05,
+      "loss": 0.7989,
+      "step": 1570
+    },
+    {
+      "epoch": 0.0739838921146282,
+      "grad_norm": 0.46297210454940796,
+      "learning_rate": 2e-05,
+      "loss": 0.8065,
+      "step": 1580
+    },
+    {
+      "epoch": 0.07445214459636636,
+      "grad_norm": 0.5150440335273743,
+      "learning_rate": 2e-05,
+      "loss": 0.8284,
+      "step": 1590
+    },
+    {
+      "epoch": 0.07492039707810451,
+      "grad_norm": 0.47179800271987915,
+      "learning_rate": 2e-05,
+      "loss": 0.8059,
+      "step": 1600
+    },
+    {
+      "epoch": 0.07538864955984266,
+      "grad_norm": 0.4652591347694397,
+      "learning_rate": 2e-05,
+      "loss": 0.8229,
+      "step": 1610
+    },
+    {
+      "epoch": 0.07585690204158083,
+      "grad_norm": 0.4540858864784241,
+      "learning_rate": 2e-05,
+      "loss": 0.7697,
+      "step": 1620
+    },
+    {
+      "epoch": 0.07632515452331898,
+      "grad_norm": 0.4078024923801422,
+      "learning_rate": 2e-05,
+      "loss": 0.8106,
+      "step": 1630
+    },
+    {
+      "epoch": 0.07679340700505713,
+      "grad_norm": 0.44727492332458496,
+      "learning_rate": 2e-05,
+      "loss": 0.8216,
+      "step": 1640
+    },
+    {
+      "epoch": 0.07726165948679528,
+      "grad_norm": 0.46308594942092896,
+      "learning_rate": 2e-05,
+      "loss": 0.8184,
+      "step": 1650
+    },
+    {
+      "epoch": 0.07772991196853343,
+      "grad_norm": 0.4770665764808655,
+      "learning_rate": 2e-05,
+      "loss": 0.7977,
+      "step": 1660
+    },
+    {
+      "epoch": 0.07819816445027158,
+      "grad_norm": 0.4776230752468109,
+      "learning_rate": 2e-05,
+      "loss": 0.7921,
+      "step": 1670
+    },
+    {
+      "epoch": 0.07866641693200974,
+      "grad_norm": 0.5174942016601562,
+      "learning_rate": 2e-05,
+      "loss": 0.8066,
+      "step": 1680
+    },
+    {
+      "epoch": 0.07913466941374789,
+      "grad_norm": 0.43850815296173096,
+      "learning_rate": 2e-05,
+      "loss": 0.8068,
+      "step": 1690
+    },
+    {
+      "epoch": 0.07960292189548604,
+      "grad_norm": 1.0964583158493042,
+      "learning_rate": 2e-05,
+      "loss": 0.7769,
+      "step": 1700
+    },
+    {
+      "epoch": 0.0800711743772242,
+      "grad_norm": 0.4482307434082031,
+      "learning_rate": 2e-05,
+      "loss": 0.7822,
+      "step": 1710
+    },
+    {
+      "epoch": 0.08053942685896236,
+      "grad_norm": 0.5412369966506958,
+      "learning_rate": 2e-05,
+      "loss": 0.7915,
+      "step": 1720
+    },
+    {
+      "epoch": 0.08100767934070051,
+      "grad_norm": 0.4515257179737091,
+      "learning_rate": 2e-05,
+      "loss": 0.8215,
+      "step": 1730
+    },
+    {
+      "epoch": 0.08147593182243866,
+      "grad_norm": 0.4404001533985138,
+      "learning_rate": 2e-05,
+      "loss": 0.8162,
+      "step": 1740
+    },
+    {
+      "epoch": 0.08194418430417681,
+      "grad_norm": 0.4400689899921417,
+      "learning_rate": 2e-05,
+      "loss": 0.7876,
+      "step": 1750
+    },
+    {
+      "epoch": 0.08241243678591496,
+      "grad_norm": 0.4302707314491272,
+      "learning_rate": 2e-05,
+      "loss": 0.8352,
+      "step": 1760
+    },
+    {
+      "epoch": 0.08288068926765312,
+      "grad_norm": 0.4659354090690613,
+      "learning_rate": 2e-05,
+      "loss": 0.7758,
+      "step": 1770
+    },
+    {
+      "epoch": 0.08334894174939127,
+      "grad_norm": 0.4827459752559662,
+      "learning_rate": 2e-05,
+      "loss": 0.7892,
+      "step": 1780
+    },
+    {
+      "epoch": 0.08381719423112942,
+      "grad_norm": 1.0690308809280396,
+      "learning_rate": 2e-05,
+      "loss": 0.8228,
+      "step": 1790
+    },
+    {
+      "epoch": 0.08428544671286758,
+      "grad_norm": 0.4485591650009155,
+      "learning_rate": 2e-05,
+      "loss": 0.7583,
+      "step": 1800
+    },
+    {
+      "epoch": 0.08475369919460574,
+      "grad_norm": 0.44925209879875183,
+      "learning_rate": 2e-05,
+      "loss": 0.7587,
+      "step": 1810
+    },
+    {
+      "epoch": 0.08522195167634389,
+      "grad_norm": 0.4562433063983917,
+      "learning_rate": 2e-05,
+      "loss": 0.7677,
+      "step": 1820
+    },
+    {
+      "epoch": 0.08569020415808204,
+      "grad_norm": 0.45940324664115906,
+      "learning_rate": 2e-05,
+      "loss": 0.7985,
+      "step": 1830
+    },
+    {
+      "epoch": 0.08615845663982019,
+      "grad_norm": 0.4248304069042206,
+      "learning_rate": 2e-05,
+      "loss": 0.7445,
+      "step": 1840
+    },
+    {
+      "epoch": 0.08662670912155834,
+      "grad_norm": 0.48499906063079834,
+      "learning_rate": 2e-05,
+      "loss": 0.8037,
+      "step": 1850
+    },
+    {
+      "epoch": 0.0870949616032965,
+      "grad_norm": 0.43459802865982056,
+      "learning_rate": 2e-05,
+      "loss": 0.7893,
+      "step": 1860
+    },
+    {
+      "epoch": 0.08756321408503465,
+      "grad_norm": 0.521557629108429,
+      "learning_rate": 2e-05,
+      "loss": 0.79,
+      "step": 1870
+    },
+    {
+      "epoch": 0.0880314665667728,
+      "grad_norm": 0.424723744392395,
+      "learning_rate": 2e-05,
+      "loss": 0.7598,
+      "step": 1880
+    },
+    {
+      "epoch": 0.08849971904851096,
+      "grad_norm": 0.4430510401725769,
+      "learning_rate": 2e-05,
+      "loss": 0.8156,
+      "step": 1890
+    },
+    {
+      "epoch": 0.08896797153024912,
+      "grad_norm": 0.43703287839889526,
+      "learning_rate": 2e-05,
+      "loss": 0.8031,
+      "step": 1900
+    },
+    {
+      "epoch": 0.08943622401198727,
+      "grad_norm": 0.46375030279159546,
+      "learning_rate": 2e-05,
+      "loss": 0.7903,
+      "step": 1910
+    },
+    {
+      "epoch": 0.08990447649372542,
+      "grad_norm": 0.46522295475006104,
+      "learning_rate": 2e-05,
+      "loss": 0.7418,
+      "step": 1920
+    },
+    {
+      "epoch": 0.09037272897546357,
+      "grad_norm": 0.40295276045799255,
+      "learning_rate": 2e-05,
+      "loss": 0.781,
+      "step": 1930
+    },
+    {
+      "epoch": 0.09084098145720172,
+      "grad_norm": 0.42140400409698486,
+      "learning_rate": 2e-05,
+      "loss": 0.7899,
+      "step": 1940
+    },
+    {
+      "epoch": 0.09130923393893987,
+      "grad_norm": 0.6773248314857483,
+      "learning_rate": 2e-05,
+      "loss": 0.8514,
+      "step": 1950
+    },
+    {
+      "epoch": 0.09177748642067803,
+      "grad_norm": 0.46820682287216187,
+      "learning_rate": 2e-05,
+      "loss": 0.8016,
+      "step": 1960
+    },
+    {
+      "epoch": 0.09224573890241618,
+      "grad_norm": 0.4235709011554718,
+      "learning_rate": 2e-05,
+      "loss": 0.7933,
+      "step": 1970
+    },
+    {
+      "epoch": 0.09271399138415434,
+      "grad_norm": 0.43302154541015625,
+      "learning_rate": 2e-05,
+      "loss": 0.7481,
+      "step": 1980
+    },
+    {
+      "epoch": 0.0931822438658925,
+      "grad_norm": 0.4129074215888977,
+      "learning_rate": 2e-05,
+      "loss": 0.7644,
+      "step": 1990
+    },
+    {
+      "epoch": 0.09365049634763065,
+      "grad_norm": 0.47755202651023865,
+      "learning_rate": 2e-05,
+      "loss": 0.7979,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0941187488293688,
+      "grad_norm": 0.4275096356868744,
+      "learning_rate": 2e-05,
+      "loss": 0.7869,
+      "step": 2010
+    },
+    {
+      "epoch": 0.09458700131110695,
+      "grad_norm": 0.41398802399635315,
+      "learning_rate": 2e-05,
+      "loss": 0.7833,
+      "step": 2020
+    },
+    {
+      "epoch": 0.0950552537928451,
+      "grad_norm": 0.4200058877468109,
+      "learning_rate": 2e-05,
+      "loss": 0.791,
+      "step": 2030
+    },
+    {
+      "epoch": 0.09552350627458325,
+      "grad_norm": 0.4077129364013672,
+      "learning_rate": 2e-05,
+      "loss": 0.7645,
+      "step": 2040
+    },
+    {
+      "epoch": 0.0959917587563214,
+      "grad_norm": 0.416229248046875,
+      "learning_rate": 2e-05,
+      "loss": 0.7874,
+      "step": 2050
+    },
+    {
+      "epoch": 0.09646001123805956,
+      "grad_norm": 0.4201897382736206,
+      "learning_rate": 2e-05,
+      "loss": 0.7936,
+      "step": 2060
+    },
+    {
+      "epoch": 0.09692826371979771,
+      "grad_norm": 0.44387736916542053,
+      "learning_rate": 2e-05,
+      "loss": 0.7972,
+      "step": 2070
+    },
+    {
+      "epoch": 0.09739651620153587,
+      "grad_norm": 0.4564218521118164,
+      "learning_rate": 2e-05,
+      "loss": 0.8083,
+      "step": 2080
+    },
+    {
+      "epoch": 0.09786476868327403,
+      "grad_norm": 0.4306756854057312,
+      "learning_rate": 2e-05,
+      "loss": 0.7695,
+      "step": 2090
+    },
+    {
+      "epoch": 0.09833302116501218,
+      "grad_norm": 0.47157105803489685,
+      "learning_rate": 2e-05,
+      "loss": 0.7916,
+      "step": 2100
+    },
+    {
+      "epoch": 0.09880127364675033,
+      "grad_norm": 0.5025231838226318,
+      "learning_rate": 2e-05,
+      "loss": 0.7783,
+      "step": 2110
+    },
+    {
+      "epoch": 0.09926952612848848,
+      "grad_norm": 0.49327343702316284,
+      "learning_rate": 2e-05,
+      "loss": 0.7915,
+      "step": 2120
+    },
+    {
+      "epoch": 0.09973777861022663,
+      "grad_norm": 0.4390990734100342,
+      "learning_rate": 2e-05,
+      "loss": 0.7971,
+      "step": 2130
+    },
+    {
+      "epoch": 0.10020603109196478,
+      "grad_norm": 0.4255847930908203,
+      "learning_rate": 2e-05,
+      "loss": 0.7539,
+      "step": 2140
+    },
+    {
+      "epoch": 0.10067428357370294,
+      "grad_norm": 0.4064248502254486,
+      "learning_rate": 2e-05,
+      "loss": 0.8041,
+      "step": 2150
+    },
+    {
+      "epoch": 0.10114253605544109,
+      "grad_norm": 0.4446522891521454,
+      "learning_rate": 2e-05,
+      "loss": 0.7974,
+      "step": 2160
+    },
+    {
+      "epoch": 0.10161078853717925,
+      "grad_norm": 0.4395385980606079,
+      "learning_rate": 2e-05,
+      "loss": 0.7771,
+      "step": 2170
+    },
+    {
+      "epoch": 0.1020790410189174,
+      "grad_norm": 0.4272850751876831,
+      "learning_rate": 2e-05,
+      "loss": 0.8522,
+      "step": 2180
+    },
+    {
+      "epoch": 0.10254729350065556,
+      "grad_norm": 0.3931410014629364,
+      "learning_rate": 2e-05,
+      "loss": 0.8056,
+      "step": 2190
+    },
+    {
+      "epoch": 0.10301554598239371,
+      "grad_norm": 0.46096065640449524,
+      "learning_rate": 2e-05,
+      "loss": 0.7735,
+      "step": 2200
+    },
+    {
+      "epoch": 0.10348379846413186,
+      "grad_norm": 0.458321750164032,
+      "learning_rate": 2e-05,
+      "loss": 0.8037,
+      "step": 2210
+    },
+    {
+      "epoch": 0.10395205094587001,
+      "grad_norm": 0.4780912697315216,
+      "learning_rate": 2e-05,
+      "loss": 0.8117,
+      "step": 2220
+    },
+    {
+      "epoch": 0.10442030342760816,
+      "grad_norm": 0.4787966012954712,
+      "learning_rate": 2e-05,
+      "loss": 0.7722,
+      "step": 2230
+    },
+    {
+      "epoch": 0.10488855590934631,
+      "grad_norm": 0.44335323572158813,
+      "learning_rate": 2e-05,
+      "loss": 0.8006,
+      "step": 2240
+    },
+    {
+      "epoch": 0.10535680839108447,
+      "grad_norm": 0.46708425879478455,
+      "learning_rate": 2e-05,
+      "loss": 0.8177,
+      "step": 2250
+    },
+    {
+      "epoch": 0.10582506087282263,
+      "grad_norm": 0.41492828726768494,
+      "learning_rate": 2e-05,
+      "loss": 0.8078,
+      "step": 2260
+    },
+    {
+      "epoch": 0.10629331335456078,
+      "grad_norm": 0.4242907762527466,
+      "learning_rate": 2e-05,
+      "loss": 0.8162,
+      "step": 2270
+    },
+    {
+      "epoch": 0.10676156583629894,
+      "grad_norm": 0.43097883462905884,
+      "learning_rate": 2e-05,
+      "loss": 0.7563,
+      "step": 2280
+    },
+    {
+      "epoch": 0.10722981831803709,
+      "grad_norm": 0.3991326689720154,
+      "learning_rate": 2e-05,
+      "loss": 0.7908,
+      "step": 2290
+    },
+    {
+      "epoch": 0.10769807079977524,
+      "grad_norm": 0.5473389625549316,
+      "learning_rate": 2e-05,
+      "loss": 0.7945,
+      "step": 2300
+    },
+    {
+      "epoch": 0.10816632328151339,
+      "grad_norm": 0.46721047163009644,
+      "learning_rate": 2e-05,
+      "loss": 0.798,
+      "step": 2310
+    },
+    {
+      "epoch": 0.10863457576325154,
+      "grad_norm": 0.4458387792110443,
+      "learning_rate": 2e-05,
+      "loss": 0.8095,
+      "step": 2320
+    },
+    {
+      "epoch": 0.1091028282449897,
+      "grad_norm": 0.5851238369941711,
+      "learning_rate": 2e-05,
+      "loss": 0.79,
+      "step": 2330
+    },
+    {
+      "epoch": 0.10957108072672785,
+      "grad_norm": 0.46909311413764954,
+      "learning_rate": 2e-05,
+      "loss": 0.7908,
+      "step": 2340
+    },
+    {
+      "epoch": 0.11003933320846601,
+      "grad_norm": 0.5781607031822205,
+      "learning_rate": 2e-05,
+      "loss": 0.8256,
+      "step": 2350
+    },
+    {
+      "epoch": 0.11050758569020416,
+      "grad_norm": 0.4696139693260193,
+      "learning_rate": 2e-05,
+      "loss": 0.8044,
+      "step": 2360
+    },
+    {
+      "epoch": 0.11097583817194231,
+      "grad_norm": 0.4228568971157074,
+      "learning_rate": 2e-05,
+      "loss": 0.7684,
+      "step": 2370
+    },
+    {
+      "epoch": 0.11144409065368047,
+      "grad_norm": 0.4293256402015686,
+      "learning_rate": 2e-05,
+      "loss": 0.8011,
+      "step": 2380
+    },
+    {
+      "epoch": 0.11191234313541862,
+      "grad_norm": 0.4462338984012604,
+      "learning_rate": 2e-05,
+      "loss": 0.7655,
+      "step": 2390
+    },
+    {
+      "epoch": 0.11238059561715677,
+      "grad_norm": 0.47912371158599854,
+      "learning_rate": 2e-05,
+      "loss": 0.7984,
+      "step": 2400
+    },
+    {
+      "epoch": 0.11284884809889492,
+      "grad_norm": 0.9592866897583008,
+      "learning_rate": 2e-05,
+      "loss": 0.7766,
+      "step": 2410
+    },
+    {
+      "epoch": 0.11331710058063307,
+      "grad_norm": 0.39810967445373535,
+      "learning_rate": 2e-05,
+      "loss": 0.7604,
+      "step": 2420
+    },
+    {
+      "epoch": 0.11378535306237123,
+      "grad_norm": 0.45152178406715393,
+      "learning_rate": 2e-05,
+      "loss": 0.79,
+      "step": 2430
+    },
+    {
+      "epoch": 0.11425360554410939,
+      "grad_norm": 0.44523119926452637,
+      "learning_rate": 2e-05,
+      "loss": 0.8067,
+      "step": 2440
+    },
+    {
+      "epoch": 0.11472185802584754,
+      "grad_norm": 0.47627031803131104,
+      "learning_rate": 2e-05,
+      "loss": 0.7797,
+      "step": 2450
+    },
+    {
+      "epoch": 0.1151901105075857,
+      "grad_norm": 0.45713964104652405,
+      "learning_rate": 2e-05,
+      "loss": 0.7613,
+      "step": 2460
+    },
+    {
+      "epoch": 0.11565836298932385,
+      "grad_norm": 0.4603721499443054,
+      "learning_rate": 2e-05,
+      "loss": 0.7985,
+      "step": 2470
+    },
+    {
+      "epoch": 0.116126615471062,
+      "grad_norm": 0.5172587633132935,
+      "learning_rate": 2e-05,
+      "loss": 0.7631,
+      "step": 2480
+    },
+    {
+      "epoch": 0.11659486795280015,
+      "grad_norm": 0.4585573971271515,
+      "learning_rate": 2e-05,
+      "loss": 0.7675,
+      "step": 2490
+    },
+    {
+      "epoch": 0.1170631204345383,
+      "grad_norm": 0.4653816223144531,
+      "learning_rate": 2e-05,
+      "loss": 0.8136,
+      "step": 2500
+    },
+    {
+      "epoch": 0.11753137291627645,
+      "grad_norm": 0.45800113677978516,
+      "learning_rate": 2e-05,
+      "loss": 0.7873,
+      "step": 2510
+    },
+    {
+      "epoch": 0.1179996253980146,
+      "grad_norm": 1.0582246780395508,
+      "learning_rate": 2e-05,
+      "loss": 0.7743,
+      "step": 2520
+    },
+    {
+      "epoch": 0.11846787787975276,
+      "grad_norm": 0.4848767817020416,
+      "learning_rate": 2e-05,
+      "loss": 0.7817,
+      "step": 2530
+    },
+    {
+      "epoch": 0.11893613036149092,
+      "grad_norm": 0.45420584082603455,
+      "learning_rate": 2e-05,
+      "loss": 0.7787,
+      "step": 2540
+    },
+    {
+      "epoch": 0.11940438284322907,
+      "grad_norm": 0.446957528591156,
+      "learning_rate": 2e-05,
+      "loss": 0.7691,
+      "step": 2550
+    },
+    {
+      "epoch": 0.11987263532496722,
+      "grad_norm": 0.4325239956378937,
+      "learning_rate": 2e-05,
+      "loss": 0.7725,
+      "step": 2560
+    },
+    {
+      "epoch": 0.12034088780670538,
+      "grad_norm": 0.3984229266643524,
+      "learning_rate": 2e-05,
+      "loss": 0.7517,
+      "step": 2570
+    },
+    {
+      "epoch": 0.12080914028844353,
+      "grad_norm": 0.5047958493232727,
+      "learning_rate": 2e-05,
+      "loss": 0.7832,
+      "step": 2580
+    },
+    {
+      "epoch": 0.12127739277018168,
+      "grad_norm": 0.4237649142742157,
+      "learning_rate": 2e-05,
+      "loss": 0.7554,
+      "step": 2590
+    },
+    {
+      "epoch": 0.12174564525191983,
+      "grad_norm": 0.5109700560569763,
+      "learning_rate": 2e-05,
+      "loss": 0.791,
+      "step": 2600
+    },
+    {
+      "epoch": 0.12221389773365798,
+      "grad_norm": 0.47834986448287964,
+      "learning_rate": 2e-05,
+      "loss": 0.7781,
+      "step": 2610
+    },
+    {
+      "epoch": 0.12268215021539614,
+      "grad_norm": 0.43558385968208313,
+      "learning_rate": 2e-05,
+      "loss": 0.7887,
+      "step": 2620
+    },
+    {
+      "epoch": 0.1231504026971343,
+      "grad_norm": 0.46023640036582947,
+      "learning_rate": 2e-05,
+      "loss": 0.8184,
+      "step": 2630
+    },
+    {
+      "epoch": 0.12361865517887245,
+      "grad_norm": 0.43065863847732544,
+      "learning_rate": 2e-05,
+      "loss": 0.8087,
+      "step": 2640
+    },
+    {
+      "epoch": 0.1240869076606106,
+      "grad_norm": 0.46921634674072266,
+      "learning_rate": 2e-05,
+      "loss": 0.8023,
+      "step": 2650
+    },
+    {
+      "epoch": 0.12455516014234876,
+      "grad_norm": 0.45447105169296265,
+      "learning_rate": 2e-05,
+      "loss": 0.7865,
+      "step": 2660
+    },
+    {
+      "epoch": 0.12502341262408692,
+      "grad_norm": 0.5031870007514954,
+      "learning_rate": 2e-05,
+      "loss": 0.7982,
+      "step": 2670
+    },
+    {
+      "epoch": 0.12549166510582507,
+      "grad_norm": 0.4168241024017334,
+      "learning_rate": 2e-05,
+      "loss": 0.7755,
+      "step": 2680
+    },
+    {
+      "epoch": 0.12595991758756322,
+      "grad_norm": 0.489377498626709,
+      "learning_rate": 2e-05,
+      "loss": 0.797,
+      "step": 2690
+    },
+    {
+      "epoch": 0.12642817006930138,
+      "grad_norm": 0.42968428134918213,
+      "learning_rate": 2e-05,
+      "loss": 0.7752,
+      "step": 2700
+    },
+    {
+      "epoch": 0.12689642255103953,
+      "grad_norm": 0.45984914898872375,
+      "learning_rate": 2e-05,
+      "loss": 0.7716,
+      "step": 2710
+    },
+    {
+      "epoch": 0.12736467503277768,
+      "grad_norm": 0.47864603996276855,
+      "learning_rate": 2e-05,
+      "loss": 0.7735,
+      "step": 2720
+    },
+    {
+      "epoch": 0.12783292751451583,
+      "grad_norm": 0.4695641100406647,
+      "learning_rate": 2e-05,
+      "loss": 0.7924,
+      "step": 2730
+    },
+    {
+      "epoch": 0.12830117999625398,
+      "grad_norm": 0.42772170901298523,
+      "learning_rate": 2e-05,
+      "loss": 0.7798,
+      "step": 2740
+    },
+    {
+      "epoch": 0.12876943247799214,
+      "grad_norm": 0.526038408279419,
+      "learning_rate": 2e-05,
+      "loss": 0.8099,
+      "step": 2750
+    },
+    {
+      "epoch": 0.1292376849597303,
+      "grad_norm": 0.48115813732147217,
+      "learning_rate": 2e-05,
+      "loss": 0.7725,
+      "step": 2760
+    },
+    {
+      "epoch": 0.12970593744146844,
+      "grad_norm": 0.8196518421173096,
+      "learning_rate": 2e-05,
+      "loss": 0.7476,
+      "step": 2770
+    },
+    {
+      "epoch": 0.1301741899232066,
+      "grad_norm": 0.4384530186653137,
+      "learning_rate": 2e-05,
+      "loss": 0.7528,
+      "step": 2780
+    },
+    {
+      "epoch": 0.13064244240494474,
+      "grad_norm": 0.48463067412376404,
+      "learning_rate": 2e-05,
+      "loss": 0.7801,
+      "step": 2790
+    },
+    {
+      "epoch": 0.1311106948866829,
+      "grad_norm": 0.431721955537796,
+      "learning_rate": 2e-05,
+      "loss": 0.7843,
+      "step": 2800
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.4804224371910095,
+      "learning_rate": 2e-05,
+      "loss": 0.8155,
+      "step": 2810
+    },
+    {
+      "epoch": 0.1320471998501592,
+      "grad_norm": 0.4451720118522644,
+      "learning_rate": 2e-05,
+      "loss": 0.7953,
+      "step": 2820
+    },
+    {
+      "epoch": 0.13251545233189735,
+      "grad_norm": 0.5056591629981995,
+      "learning_rate": 2e-05,
+      "loss": 0.7696,
+      "step": 2830
+    },
+    {
+      "epoch": 0.1329837048136355,
+      "grad_norm": 0.40849485993385315,
+      "learning_rate": 2e-05,
+      "loss": 0.7782,
+      "step": 2840
+    },
+    {
+      "epoch": 0.13345195729537365,
+      "grad_norm": 0.4380452036857605,
+      "learning_rate": 2e-05,
+      "loss": 0.7444,
+      "step": 2850
+    },
+    {
+      "epoch": 0.13392020977711183,
+      "grad_norm": 0.4316031336784363,
+      "learning_rate": 2e-05,
+      "loss": 0.7728,
+      "step": 2860
+    },
+    {
+      "epoch": 0.13438846225884998,
+      "grad_norm": 0.46132344007492065,
+      "learning_rate": 2e-05,
+      "loss": 0.7649,
+      "step": 2870
+    },
+    {
+      "epoch": 0.13485671474058814,
+      "grad_norm": 0.4467066526412964,
+      "learning_rate": 2e-05,
+      "loss": 0.7802,
+      "step": 2880
+    },
+    {
+      "epoch": 0.1353249672223263,
+      "grad_norm": 0.4437260031700134,
+      "learning_rate": 2e-05,
+      "loss": 0.7728,
+      "step": 2890
+    },
+    {
+      "epoch": 0.13579321970406444,
+      "grad_norm": 0.41009271144866943,
+      "learning_rate": 2e-05,
+      "loss": 0.785,
+      "step": 2900
+    },
+    {
+      "epoch": 0.1362614721858026,
+      "grad_norm": 0.4567055106163025,
+      "learning_rate": 2e-05,
+      "loss": 0.7977,
+      "step": 2910
+    },
+    {
+      "epoch": 0.13672972466754074,
+      "grad_norm": 0.4779447019100189,
+      "learning_rate": 2e-05,
+      "loss": 0.786,
+      "step": 2920
+    },
+    {
+      "epoch": 0.1371979771492789,
+      "grad_norm": 0.4813325107097626,
+      "learning_rate": 2e-05,
+      "loss": 0.7602,
+      "step": 2930
+    },
+    {
+      "epoch": 0.13766622963101705,
+      "grad_norm": 0.46978309750556946,
+      "learning_rate": 2e-05,
+      "loss": 0.8055,
+      "step": 2940
+    },
+    {
+      "epoch": 0.1381344821127552,
+      "grad_norm": 0.436978816986084,
+      "learning_rate": 2e-05,
+      "loss": 0.7712,
+      "step": 2950
+    },
+    {
+      "epoch": 0.13860273459449335,
+      "grad_norm": 0.4569421410560608,
+      "learning_rate": 2e-05,
+      "loss": 0.7704,
+      "step": 2960
+    },
+    {
+      "epoch": 0.1390709870762315,
+      "grad_norm": 0.4956076443195343,
+      "learning_rate": 2e-05,
+      "loss": 0.7934,
+      "step": 2970
+    },
+    {
+      "epoch": 0.13953923955796965,
+      "grad_norm": 0.5110732913017273,
+      "learning_rate": 2e-05,
+      "loss": 0.7768,
+      "step": 2980
+    },
+    {
+      "epoch": 0.1400074920397078,
+      "grad_norm": 0.4133819043636322,
+      "learning_rate": 2e-05,
+      "loss": 0.7859,
+      "step": 2990
+    },
+    {
+      "epoch": 0.14047574452144596,
+      "grad_norm": 0.5259489417076111,
+      "learning_rate": 2e-05,
+      "loss": 0.7861,
+      "step": 3000
+    },
+    {
+      "epoch": 0.1409439970031841,
+      "grad_norm": 0.4838019013404846,
+      "learning_rate": 2e-05,
+      "loss": 0.7816,
+      "step": 3010
+    },
+    {
+      "epoch": 0.14141224948492226,
+      "grad_norm": 0.43243408203125,
+      "learning_rate": 2e-05,
+      "loss": 0.7951,
+      "step": 3020
+    },
+    {
+      "epoch": 0.1418805019666604,
+      "grad_norm": 0.4447523355484009,
+      "learning_rate": 2e-05,
+      "loss": 0.7745,
+      "step": 3030
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "grad_norm": 0.426066130399704,
+      "learning_rate": 2e-05,
+      "loss": 0.7306,
+      "step": 3040
+    },
+    {
+      "epoch": 0.14281700693013674,
+      "grad_norm": 0.4635065495967865,
+      "learning_rate": 2e-05,
+      "loss": 0.7769,
+      "step": 3050
+    },
+    {
+      "epoch": 0.1432852594118749,
+      "grad_norm": 0.4404882788658142,
+      "learning_rate": 2e-05,
+      "loss": 0.7852,
+      "step": 3060
+    },
+    {
+      "epoch": 0.14375351189361305,
+      "grad_norm": 0.4820006489753723,
+      "learning_rate": 2e-05,
+      "loss": 0.7805,
+      "step": 3070
+    },
+    {
+      "epoch": 0.1442217643753512,
+      "grad_norm": 1.9450064897537231,
+      "learning_rate": 2e-05,
+      "loss": 0.7459,
+      "step": 3080
+    },
+    {
+      "epoch": 0.14469001685708935,
+      "grad_norm": 0.4669210612773895,
+      "learning_rate": 2e-05,
+      "loss": 0.7594,
+      "step": 3090
+    },
+    {
+      "epoch": 0.1451582693388275,
+      "grad_norm": 0.4511769711971283,
+      "learning_rate": 2e-05,
+      "loss": 0.7574,
+      "step": 3100
+    },
+    {
+      "epoch": 0.14562652182056565,
+      "grad_norm": 0.4666540026664734,
+      "learning_rate": 2e-05,
+      "loss": 0.7624,
+      "step": 3110
+    },
+    {
+      "epoch": 0.1460947743023038,
+      "grad_norm": 0.4351053535938263,
+      "learning_rate": 2e-05,
+      "loss": 0.7786,
+      "step": 3120
+    },
+    {
+      "epoch": 0.14656302678404196,
+      "grad_norm": 0.48357275128364563,
+      "learning_rate": 2e-05,
+      "loss": 0.7756,
+      "step": 3130
+    },
+    {
+      "epoch": 0.1470312792657801,
+      "grad_norm": 0.4528772830963135,
+      "learning_rate": 2e-05,
+      "loss": 0.7812,
+      "step": 3140
+    },
+    {
+      "epoch": 0.14749953174751826,
+      "grad_norm": 0.43779534101486206,
+      "learning_rate": 2e-05,
+      "loss": 0.7698,
+      "step": 3150
+    },
+    {
+      "epoch": 0.1479677842292564,
+      "grad_norm": 0.4632822275161743,
+      "learning_rate": 2e-05,
+      "loss": 0.7414,
+      "step": 3160
+    },
+    {
+      "epoch": 0.14843603671099456,
+      "grad_norm": 0.4203107953071594,
+      "learning_rate": 2e-05,
+      "loss": 0.786,
+      "step": 3170
+    },
+    {
+      "epoch": 0.14890428919273271,
+      "grad_norm": 0.4951493740081787,
+      "learning_rate": 2e-05,
+      "loss": 0.7653,
+      "step": 3180
+    },
+    {
+      "epoch": 0.14937254167447087,
+      "grad_norm": 0.5392319560050964,
+      "learning_rate": 2e-05,
+      "loss": 0.7691,
+      "step": 3190
+    },
+    {
+      "epoch": 0.14984079415620902,
+      "grad_norm": 0.4392766058444977,
+      "learning_rate": 2e-05,
+      "loss": 0.7664,
+      "step": 3200
+    },
+    {
+      "epoch": 0.15030904663794717,
+      "grad_norm": 0.5064263939857483,
+      "learning_rate": 2e-05,
+      "loss": 0.7751,
+      "step": 3210
+    },
+    {
+      "epoch": 0.15077729911968532,
+      "grad_norm": 0.4974293112754822,
+      "learning_rate": 2e-05,
+      "loss": 0.7846,
+      "step": 3220
+    },
+    {
+      "epoch": 0.1512455516014235,
+      "grad_norm": 0.5040820240974426,
+      "learning_rate": 2e-05,
+      "loss": 0.7406,
+      "step": 3230
+    },
+    {
+      "epoch": 0.15171380408316165,
+      "grad_norm": 0.4319583475589752,
+      "learning_rate": 2e-05,
+      "loss": 0.7487,
+      "step": 3240
+    },
+    {
+      "epoch": 0.1521820565648998,
+      "grad_norm": 0.46588271856307983,
+      "learning_rate": 2e-05,
+      "loss": 0.773,
+      "step": 3250
+    },
+    {
+      "epoch": 0.15265030904663796,
+      "grad_norm": 0.41532087326049805,
+      "learning_rate": 2e-05,
+      "loss": 0.7661,
+      "step": 3260
+    },
+    {
+      "epoch": 0.1531185615283761,
+      "grad_norm": 0.5403257608413696,
+      "learning_rate": 2e-05,
+      "loss": 0.8033,
+      "step": 3270
+    },
+    {
+      "epoch": 0.15358681401011426,
+      "grad_norm": 0.4624592363834381,
+      "learning_rate": 2e-05,
+      "loss": 0.8036,
+      "step": 3280
+    },
+    {
+      "epoch": 0.1540550664918524,
+      "grad_norm": 0.4184800088405609,
+      "learning_rate": 2e-05,
+      "loss": 0.8141,
+      "step": 3290
+    },
+    {
+      "epoch": 0.15452331897359056,
+      "grad_norm": 0.41161057353019714,
+      "learning_rate": 2e-05,
+      "loss": 0.7622,
+      "step": 3300
+    },
+    {
+      "epoch": 0.1549915714553287,
+      "grad_norm": 0.41965046525001526,
+      "learning_rate": 2e-05,
+      "loss": 0.743,
+      "step": 3310
+    },
+    {
+      "epoch": 0.15545982393706687,
+      "grad_norm": 0.547100841999054,
+      "learning_rate": 2e-05,
+      "loss": 0.739,
+      "step": 3320
+    },
+    {
+      "epoch": 0.15592807641880502,
+      "grad_norm": 0.4471840262413025,
+      "learning_rate": 2e-05,
+      "loss": 0.7939,
+      "step": 3330
+    },
+    {
+      "epoch": 0.15639632890054317,
+      "grad_norm": 0.40980273485183716,
+      "learning_rate": 2e-05,
+      "loss": 0.7598,
+      "step": 3340
+    },
+    {
+      "epoch": 0.15686458138228132,
+      "grad_norm": 0.5068540573120117,
+      "learning_rate": 2e-05,
+      "loss": 0.7419,
+      "step": 3350
+    },
+    {
+      "epoch": 0.15733283386401947,
+      "grad_norm": 0.4310580790042877,
+      "learning_rate": 2e-05,
+      "loss": 0.7807,
+      "step": 3360
+    },
+    {
+      "epoch": 0.15780108634575762,
+      "grad_norm": 0.44191500544548035,
+      "learning_rate": 2e-05,
+      "loss": 0.7844,
+      "step": 3370
+    },
+    {
+      "epoch": 0.15826933882749578,
+      "grad_norm": 0.492794930934906,
+      "learning_rate": 2e-05,
+      "loss": 0.7829,
+      "step": 3380
+    },
+    {
+      "epoch": 0.15873759130923393,
+      "grad_norm": 0.46001243591308594,
+      "learning_rate": 2e-05,
+      "loss": 0.7616,
+      "step": 3390
+    },
+    {
+      "epoch": 0.15920584379097208,
+      "grad_norm": 0.452966570854187,
+      "learning_rate": 2e-05,
+      "loss": 0.8051,
+      "step": 3400
+    },
+    {
+      "epoch": 0.15967409627271026,
+      "grad_norm": 0.3855198621749878,
+      "learning_rate": 2e-05,
+      "loss": 0.7608,
+      "step": 3410
+    },
+    {
+      "epoch": 0.1601423487544484,
+      "grad_norm": 0.4697616398334503,
+      "learning_rate": 2e-05,
+      "loss": 0.7637,
+      "step": 3420
+    },
+    {
+      "epoch": 0.16061060123618656,
+      "grad_norm": 0.47525501251220703,
+      "learning_rate": 2e-05,
+      "loss": 0.7569,
+      "step": 3430
+    },
+    {
+      "epoch": 0.1610788537179247,
+      "grad_norm": 0.49193453788757324,
+      "learning_rate": 2e-05,
+      "loss": 0.7792,
+      "step": 3440
+    },
+    {
+      "epoch": 0.16154710619966287,
+      "grad_norm": 0.5018397569656372,
+      "learning_rate": 2e-05,
+      "loss": 0.8023,
+      "step": 3450
+    },
+    {
+      "epoch": 0.16201535868140102,
+      "grad_norm": 0.4693327248096466,
+      "learning_rate": 2e-05,
+      "loss": 0.7602,
+      "step": 3460
+    },
+    {
+      "epoch": 0.16248361116313917,
+      "grad_norm": 0.4147368371486664,
+      "learning_rate": 2e-05,
+      "loss": 0.7711,
+      "step": 3470
+    },
+    {
+      "epoch": 0.16295186364487732,
+      "grad_norm": 0.48835280537605286,
+      "learning_rate": 2e-05,
+      "loss": 0.8112,
+      "step": 3480
+    },
+    {
+      "epoch": 0.16342011612661547,
+      "grad_norm": 0.4873306155204773,
+      "learning_rate": 2e-05,
+      "loss": 0.8052,
+      "step": 3490
+    },
+    {
+      "epoch": 0.16388836860835362,
+      "grad_norm": 0.5845130681991577,
+      "learning_rate": 2e-05,
+      "loss": 0.7896,
+      "step": 3500
+    },
+    {
+      "epoch": 0.16435662109009178,
+      "grad_norm": 0.5305046439170837,
+      "learning_rate": 2e-05,
+      "loss": 0.7635,
+      "step": 3510
+    },
+    {
+      "epoch": 0.16482487357182993,
+      "grad_norm": 0.4971988797187805,
+      "learning_rate": 2e-05,
+      "loss": 0.7448,
+      "step": 3520
+    },
+    {
+      "epoch": 0.16529312605356808,
+      "grad_norm": 0.4730629026889801,
+      "learning_rate": 2e-05,
+      "loss": 0.7166,
+      "step": 3530
+    },
+    {
+      "epoch": 0.16576137853530623,
+      "grad_norm": 0.4115239381790161,
+      "learning_rate": 2e-05,
+      "loss": 0.7846,
+      "step": 3540
+    },
+    {
+      "epoch": 0.16622963101704438,
+      "grad_norm": 0.4584404528141022,
+      "learning_rate": 2e-05,
+      "loss": 0.744,
+      "step": 3550
+    },
+    {
+      "epoch": 0.16669788349878253,
+      "grad_norm": 0.4739014208316803,
+      "learning_rate": 2e-05,
+      "loss": 0.8232,
+      "step": 3560
+    },
+    {
+      "epoch": 0.16716613598052069,
+      "grad_norm": 0.44108620285987854,
+      "learning_rate": 2e-05,
+      "loss": 0.7595,
+      "step": 3570
+    },
+    {
+      "epoch": 0.16763438846225884,
+      "grad_norm": 0.4143202006816864,
+      "learning_rate": 2e-05,
+      "loss": 0.7571,
+      "step": 3580
+    },
+    {
+      "epoch": 0.168102640943997,
+      "grad_norm": 0.5289865136146545,
+      "learning_rate": 2e-05,
+      "loss": 0.7487,
+      "step": 3590
+    },
+    {
+      "epoch": 0.16857089342573517,
+      "grad_norm": 0.453819215297699,
+      "learning_rate": 2e-05,
+      "loss": 0.7516,
+      "step": 3600
+    },
+    {
+      "epoch": 0.16903914590747332,
+      "grad_norm": 0.4348923861980438,
+      "learning_rate": 2e-05,
+      "loss": 0.7767,
+      "step": 3610
+    },
+    {
+      "epoch": 0.16950739838921147,
+      "grad_norm": 0.4643234610557556,
+      "learning_rate": 2e-05,
+      "loss": 0.7945,
+      "step": 3620
+    },
+    {
+      "epoch": 0.16997565087094962,
+      "grad_norm": 0.47802820801734924,
+      "learning_rate": 2e-05,
+      "loss": 0.7327,
+      "step": 3630
+    },
+    {
+      "epoch": 0.17044390335268778,
+      "grad_norm": 0.4367299973964691,
+      "learning_rate": 2e-05,
+      "loss": 0.7923,
+      "step": 3640
+    },
+    {
+      "epoch": 0.17091215583442593,
+      "grad_norm": 0.4553154408931732,
+      "learning_rate": 2e-05,
+      "loss": 0.7655,
+      "step": 3650
+    },
+    {
+      "epoch": 0.17138040831616408,
+      "grad_norm": 0.4764273464679718,
+      "learning_rate": 2e-05,
+      "loss": 0.7554,
+      "step": 3660
+    },
+    {
+      "epoch": 0.17184866079790223,
+      "grad_norm": 0.44732391834259033,
+      "learning_rate": 2e-05,
+      "loss": 0.7692,
+      "step": 3670
+    },
+    {
+      "epoch": 0.17231691327964038,
+      "grad_norm": 0.5650924444198608,
+      "learning_rate": 2e-05,
+      "loss": 0.7731,
+      "step": 3680
+    },
+    {
+      "epoch": 0.17278516576137853,
+      "grad_norm": 0.6082085371017456,
+      "learning_rate": 2e-05,
+      "loss": 0.7769,
+      "step": 3690
+    },
+    {
+      "epoch": 0.17325341824311669,
+      "grad_norm": 0.5217570066452026,
+      "learning_rate": 2e-05,
+      "loss": 0.7568,
+      "step": 3700
+    },
+    {
+      "epoch": 0.17372167072485484,
+      "grad_norm": 0.46141839027404785,
+      "learning_rate": 2e-05,
+      "loss": 0.7528,
+      "step": 3710
+    },
+    {
+      "epoch": 0.174189923206593,
+      "grad_norm": 0.48429611325263977,
+      "learning_rate": 2e-05,
+      "loss": 0.797,
+      "step": 3720
+    },
+    {
+      "epoch": 0.17465817568833114,
+      "grad_norm": 0.5406231880187988,
+      "learning_rate": 2e-05,
+      "loss": 0.7687,
+      "step": 3730
+    },
+    {
+      "epoch": 0.1751264281700693,
+      "grad_norm": 0.42686790227890015,
+      "learning_rate": 2e-05,
+      "loss": 0.7706,
+      "step": 3740
+    },
+    {
+      "epoch": 0.17559468065180744,
+      "grad_norm": 0.44343850016593933,
+      "learning_rate": 2e-05,
+      "loss": 0.7863,
+      "step": 3750
+    },
+    {
+      "epoch": 0.1760629331335456,
+      "grad_norm": 0.4633735716342926,
+      "learning_rate": 2e-05,
+      "loss": 0.7569,
+      "step": 3760
+    },
+    {
+      "epoch": 0.17653118561528375,
+      "grad_norm": 0.4800039529800415,
+      "learning_rate": 2e-05,
+      "loss": 0.7502,
+      "step": 3770
+    },
+    {
+      "epoch": 0.17699943809702193,
+      "grad_norm": 0.4586217701435089,
+      "learning_rate": 2e-05,
+      "loss": 0.8227,
+      "step": 3780
+    },
+    {
+      "epoch": 0.17746769057876008,
+      "grad_norm": 0.4920169413089752,
+      "learning_rate": 2e-05,
+      "loss": 0.7901,
+      "step": 3790
+    },
+    {
+      "epoch": 0.17793594306049823,
+      "grad_norm": 0.47960785031318665,
+      "learning_rate": 2e-05,
+      "loss": 0.7633,
+      "step": 3800
+    },
+    {
+      "epoch": 0.17840419554223638,
+      "grad_norm": 0.4717206656932831,
+      "learning_rate": 2e-05,
+      "loss": 0.819,
+      "step": 3810
+    },
+    {
+      "epoch": 0.17887244802397453,
+      "grad_norm": 0.511841893196106,
+      "learning_rate": 2e-05,
+      "loss": 0.7732,
+      "step": 3820
+    },
+    {
+      "epoch": 0.17934070050571269,
+      "grad_norm": 0.47291046380996704,
+      "learning_rate": 2e-05,
+      "loss": 0.7682,
+      "step": 3830
+    },
+    {
+      "epoch": 0.17980895298745084,
+      "grad_norm": 0.40757039189338684,
+      "learning_rate": 2e-05,
+      "loss": 0.7546,
+      "step": 3840
+    },
+    {
+      "epoch": 0.180277205469189,
+      "grad_norm": 0.5135296583175659,
+      "learning_rate": 2e-05,
+      "loss": 0.7602,
+      "step": 3850
+    },
+    {
+      "epoch": 0.18074545795092714,
+      "grad_norm": 0.4503514766693115,
+      "learning_rate": 2e-05,
+      "loss": 0.738,
+      "step": 3860
+    },
+    {
+      "epoch": 0.1812137104326653,
+      "grad_norm": 0.49815234541893005,
+      "learning_rate": 2e-05,
+      "loss": 0.7765,
+      "step": 3870
+    },
+    {
+      "epoch": 0.18168196291440344,
+      "grad_norm": 0.4232896864414215,
+      "learning_rate": 2e-05,
+      "loss": 0.7836,
+      "step": 3880
+    },
+    {
+      "epoch": 0.1821502153961416,
+      "grad_norm": 0.4334942102432251,
+      "learning_rate": 2e-05,
+      "loss": 0.7253,
+      "step": 3890
+    },
+    {
+      "epoch": 0.18261846787787975,
+      "grad_norm": 0.43816936016082764,
+      "learning_rate": 2e-05,
+      "loss": 0.7814,
+      "step": 3900
+    },
+    {
+      "epoch": 0.1830867203596179,
+      "grad_norm": 0.4376625418663025,
+      "learning_rate": 2e-05,
+      "loss": 0.7547,
+      "step": 3910
+    },
+    {
+      "epoch": 0.18355497284135605,
+      "grad_norm": 0.4537307620048523,
+      "learning_rate": 2e-05,
+      "loss": 0.7475,
+      "step": 3920
+    },
+    {
+      "epoch": 0.1840232253230942,
+      "grad_norm": 0.4813627302646637,
+      "learning_rate": 2e-05,
+      "loss": 0.7681,
+      "step": 3930
+    },
+    {
+      "epoch": 0.18449147780483235,
+      "grad_norm": 0.5152831077575684,
+      "learning_rate": 2e-05,
+      "loss": 0.7151,
+      "step": 3940
+    },
+    {
+      "epoch": 0.1849597302865705,
+      "grad_norm": 0.4522545337677002,
+      "learning_rate": 2e-05,
+      "loss": 0.7779,
+      "step": 3950
+    },
+    {
+      "epoch": 0.18542798276830869,
+      "grad_norm": 0.6297553777694702,
+      "learning_rate": 2e-05,
+      "loss": 0.7902,
+      "step": 3960
+    },
+    {
+      "epoch": 0.18589623525004684,
+      "grad_norm": 0.4071296751499176,
+      "learning_rate": 2e-05,
+      "loss": 0.7563,
+      "step": 3970
+    },
+    {
+      "epoch": 0.186364487731785,
+      "grad_norm": 0.4333728849887848,
+      "learning_rate": 2e-05,
+      "loss": 0.7854,
+      "step": 3980
+    },
+    {
+      "epoch": 0.18683274021352314,
+      "grad_norm": 0.44967952370643616,
+      "learning_rate": 2e-05,
+      "loss": 0.7522,
+      "step": 3990
+    },
+    {
+      "epoch": 0.1873009926952613,
+      "grad_norm": 1.3324648141860962,
+      "learning_rate": 2e-05,
+      "loss": 0.7475,
+      "step": 4000
+    },
+    {
+      "epoch": 0.18776924517699944,
+      "grad_norm": 0.42225560545921326,
+      "learning_rate": 2e-05,
+      "loss": 0.7515,
+      "step": 4010
+    },
+    {
+      "epoch": 0.1882374976587376,
+      "grad_norm": 0.4295327365398407,
+      "learning_rate": 2e-05,
+      "loss": 0.7989,
+      "step": 4020
+    },
+    {
+      "epoch": 0.18870575014047575,
+      "grad_norm": 0.4431644380092621,
+      "learning_rate": 2e-05,
+      "loss": 0.7446,
+      "step": 4030
+    },
+    {
+      "epoch": 0.1891740026222139,
+      "grad_norm": 0.4686296880245209,
+      "learning_rate": 2e-05,
+      "loss": 0.7488,
+      "step": 4040
+    },
+    {
+      "epoch": 0.18964225510395205,
+      "grad_norm": 0.41146647930145264,
+      "learning_rate": 2e-05,
+      "loss": 0.7627,
+      "step": 4050
+    },
+    {
+      "epoch": 0.1901105075856902,
+      "grad_norm": 0.5990108847618103,
+      "learning_rate": 2e-05,
+      "loss": 0.7834,
+      "step": 4060
+    },
+    {
+      "epoch": 0.19057876006742835,
+      "grad_norm": 0.4420095682144165,
+      "learning_rate": 2e-05,
+      "loss": 0.7197,
+      "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:b97503725546d6c4b60d669e46c356e36f399e9537c14588ced62d2297d8a939
+size 7953