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 sha256:4e14627b05c58f9ea551937998c2c3e5e873db3cdfdc68b17f63992fc8418df0
+size 4902257696

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b53dd92fffd15b6745da8989a055cffa4b5cece5569de7a057387b3f50d4fc
+size 4915960368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c518f9c4ae04ab8a154694470dddb83c28c8714f0ecf1db0a2715912b6ba3051
+size 4983068496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72645f4b8a1da1093775eeb93b623c4548f1390b31c4213e0d12fdcc35d2f73
+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": 0.17383504890445478,
+  "eval_steps": 500,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00042711314227138767,
+      "grad_norm": 0.6801537275314331,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.6308,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008542262845427753,
+      "grad_norm": 0.7330222725868225,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.5921,
+      "step": 20
+    },
+    {
+      "epoch": 0.001281339426814163,
+      "grad_norm": 0.7190220952033997,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.6197,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017084525690855507,
+      "grad_norm": 0.6695777773857117,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.6225,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021355657113569385,
+      "grad_norm": 0.7244643568992615,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.5868,
+      "step": 50
+    },
+    {
+      "epoch": 0.002562678853628326,
+      "grad_norm": 0.7338688373565674,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.602,
+      "step": 60
+    },
+    {
+      "epoch": 0.0029897919958997137,
+      "grad_norm": 0.7063023447990417,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.5962,
+      "step": 70
+    },
+    {
+      "epoch": 0.0034169051381711013,
+      "grad_norm": 0.7280859351158142,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.5849,
+      "step": 80
+    },
+    {
+      "epoch": 0.0038440182804424894,
+      "grad_norm": 0.6686920523643494,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.5945,
+      "step": 90
+    },
+    {
+      "epoch": 0.004271131422713877,
+      "grad_norm": 0.6424954533576965,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.5742,
+      "step": 100
+    },
+    {
+      "epoch": 0.004698244564985265,
+      "grad_norm": 0.7504611015319824,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.6183,
+      "step": 110
+    },
+    {
+      "epoch": 0.005125357707256652,
+      "grad_norm": 0.7265036106109619,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.6288,
+      "step": 120
+    },
+    {
+      "epoch": 0.00555247084952804,
+      "grad_norm": 0.6728747487068176,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.5932,
+      "step": 130
+    },
+    {
+      "epoch": 0.005979583991799427,
+      "grad_norm": 0.5877931118011475,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.6073,
+      "step": 140
+    },
+    {
+      "epoch": 0.0064066971340708155,
+      "grad_norm": 0.9119960069656372,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.594,
+      "step": 150
+    },
+    {
+      "epoch": 0.006833810276342203,
+      "grad_norm": 0.6038461327552795,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.6186,
+      "step": 160
+    },
+    {
+      "epoch": 0.007260923418613591,
+      "grad_norm": 0.6067227125167847,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.608,
+      "step": 170
+    },
+    {
+      "epoch": 0.007688036560884979,
+      "grad_norm": 0.6028957962989807,
+      "learning_rate": 2e-05,
+      "loss": 0.5816,
+      "step": 180
+    },
+    {
+      "epoch": 0.008115149703156367,
+      "grad_norm": 0.5894806385040283,
+      "learning_rate": 2e-05,
+      "loss": 0.604,
+      "step": 190
+    },
+    {
+      "epoch": 0.008542262845427754,
+      "grad_norm": 0.5551896691322327,
+      "learning_rate": 2e-05,
+      "loss": 0.6181,
+      "step": 200
+    },
+    {
+      "epoch": 0.008969375987699141,
+      "grad_norm": 0.48914626240730286,
+      "learning_rate": 2e-05,
+      "loss": 0.6003,
+      "step": 210
+    },
+    {
+      "epoch": 0.00939648912997053,
+      "grad_norm": 0.5296058058738708,
+      "learning_rate": 2e-05,
+      "loss": 0.6201,
+      "step": 220
+    },
+    {
+      "epoch": 0.009823602272241917,
+      "grad_norm": 0.7409117221832275,
+      "learning_rate": 2e-05,
+      "loss": 0.5938,
+      "step": 230
+    },
+    {
+      "epoch": 0.010250715414513304,
+      "grad_norm": 0.5655877590179443,
+      "learning_rate": 2e-05,
+      "loss": 0.5714,
+      "step": 240
+    },
+    {
+      "epoch": 0.010677828556784692,
+      "grad_norm": 0.4660634696483612,
+      "learning_rate": 2e-05,
+      "loss": 0.5736,
+      "step": 250
+    },
+    {
+      "epoch": 0.01110494169905608,
+      "grad_norm": 0.437298059463501,
+      "learning_rate": 2e-05,
+      "loss": 0.5944,
+      "step": 260
+    },
+    {
+      "epoch": 0.011532054841327468,
+      "grad_norm": 0.7993448376655579,
+      "learning_rate": 2e-05,
+      "loss": 0.5918,
+      "step": 270
+    },
+    {
+      "epoch": 0.011959167983598855,
+      "grad_norm": 0.46986427903175354,
+      "learning_rate": 2e-05,
+      "loss": 0.6001,
+      "step": 280
+    },
+    {
+      "epoch": 0.012386281125870244,
+      "grad_norm": 0.4165823459625244,
+      "learning_rate": 2e-05,
+      "loss": 0.5817,
+      "step": 290
+    },
+    {
+      "epoch": 0.012813394268141631,
+      "grad_norm": 0.4695897102355957,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 300
+    },
+    {
+      "epoch": 0.013240507410413018,
+      "grad_norm": 0.46940892934799194,
+      "learning_rate": 2e-05,
+      "loss": 0.6293,
+      "step": 310
+    },
+    {
+      "epoch": 0.013667620552684405,
+      "grad_norm": 0.37120378017425537,
+      "learning_rate": 2e-05,
+      "loss": 0.6057,
+      "step": 320
+    },
+    {
+      "epoch": 0.014094733694955794,
+      "grad_norm": 0.4567081928253174,
+      "learning_rate": 2e-05,
+      "loss": 0.6088,
+      "step": 330
+    },
+    {
+      "epoch": 0.014521846837227181,
+      "grad_norm": 0.5053907036781311,
+      "learning_rate": 2e-05,
+      "loss": 0.575,
+      "step": 340
+    },
+    {
+      "epoch": 0.014948959979498569,
+      "grad_norm": 0.4822077453136444,
+      "learning_rate": 2e-05,
+      "loss": 0.6305,
+      "step": 350
+    },
+    {
+      "epoch": 0.015376073121769957,
+      "grad_norm": 0.42418718338012695,
+      "learning_rate": 2e-05,
+      "loss": 0.609,
+      "step": 360
+    },
+    {
+      "epoch": 0.015803186264041345,
+      "grad_norm": 0.4470791816711426,
+      "learning_rate": 2e-05,
+      "loss": 0.609,
+      "step": 370
+    },
+    {
+      "epoch": 0.016230299406312734,
+      "grad_norm": 0.4747907221317291,
+      "learning_rate": 2e-05,
+      "loss": 0.5753,
+      "step": 380
+    },
+    {
+      "epoch": 0.01665741254858412,
+      "grad_norm": 0.429513156414032,
+      "learning_rate": 2e-05,
+      "loss": 0.5757,
+      "step": 390
+    },
+    {
+      "epoch": 0.017084525690855508,
+      "grad_norm": 1.1115094423294067,
+      "learning_rate": 2e-05,
+      "loss": 0.5973,
+      "step": 400
+    },
+    {
+      "epoch": 0.017511638833126897,
+      "grad_norm": 0.4465528130531311,
+      "learning_rate": 2e-05,
+      "loss": 0.6135,
+      "step": 410
+    },
+    {
+      "epoch": 0.017938751975398282,
+      "grad_norm": 0.45542335510253906,
+      "learning_rate": 2e-05,
+      "loss": 0.5925,
+      "step": 420
+    },
+    {
+      "epoch": 0.01836586511766967,
+      "grad_norm": 0.4971701204776764,
+      "learning_rate": 2e-05,
+      "loss": 0.6015,
+      "step": 430
+    },
+    {
+      "epoch": 0.01879297825994106,
+      "grad_norm": 0.4876435101032257,
+      "learning_rate": 2e-05,
+      "loss": 0.612,
+      "step": 440
+    },
+    {
+      "epoch": 0.019220091402212446,
+      "grad_norm": 0.4507445693016052,
+      "learning_rate": 2e-05,
+      "loss": 0.6096,
+      "step": 450
+    },
+    {
+      "epoch": 0.019647204544483834,
+      "grad_norm": 0.48777464032173157,
+      "learning_rate": 2e-05,
+      "loss": 0.5804,
+      "step": 460
+    },
+    {
+      "epoch": 0.02007431768675522,
+      "grad_norm": 0.42354583740234375,
+      "learning_rate": 2e-05,
+      "loss": 0.6102,
+      "step": 470
+    },
+    {
+      "epoch": 0.02050143082902661,
+      "grad_norm": 0.4695739448070526,
+      "learning_rate": 2e-05,
+      "loss": 0.6343,
+      "step": 480
+    },
+    {
+      "epoch": 0.020928543971297998,
+      "grad_norm": 0.4769243896007538,
+      "learning_rate": 2e-05,
+      "loss": 0.5989,
+      "step": 490
+    },
+    {
+      "epoch": 0.021355657113569383,
+      "grad_norm": 0.44087329506874084,
+      "learning_rate": 2e-05,
+      "loss": 0.5978,
+      "step": 500
+    },
+    {
+      "epoch": 0.021782770255840772,
+      "grad_norm": 0.42501866817474365,
+      "learning_rate": 2e-05,
+      "loss": 0.6133,
+      "step": 510
+    },
+    {
+      "epoch": 0.02220988339811216,
+      "grad_norm": 0.38661816716194153,
+      "learning_rate": 2e-05,
+      "loss": 0.6056,
+      "step": 520
+    },
+    {
+      "epoch": 0.022636996540383546,
+      "grad_norm": 0.43126940727233887,
+      "learning_rate": 2e-05,
+      "loss": 0.5679,
+      "step": 530
+    },
+    {
+      "epoch": 0.023064109682654935,
+      "grad_norm": 0.433454304933548,
+      "learning_rate": 2e-05,
+      "loss": 0.6074,
+      "step": 540
+    },
+    {
+      "epoch": 0.023491222824926324,
+      "grad_norm": 0.3950791656970978,
+      "learning_rate": 2e-05,
+      "loss": 0.6267,
+      "step": 550
+    },
+    {
+      "epoch": 0.02391833596719771,
+      "grad_norm": 0.42388349771499634,
+      "learning_rate": 2e-05,
+      "loss": 0.6457,
+      "step": 560
+    },
+    {
+      "epoch": 0.0243454491094691,
+      "grad_norm": 0.4391220510005951,
+      "learning_rate": 2e-05,
+      "loss": 0.6222,
+      "step": 570
+    },
+    {
+      "epoch": 0.024772562251740488,
+      "grad_norm": 0.4486788213253021,
+      "learning_rate": 2e-05,
+      "loss": 0.6232,
+      "step": 580
+    },
+    {
+      "epoch": 0.025199675394011873,
+      "grad_norm": 0.5258558988571167,
+      "learning_rate": 2e-05,
+      "loss": 0.6157,
+      "step": 590
+    },
+    {
+      "epoch": 0.025626788536283262,
+      "grad_norm": 0.3985844552516937,
+      "learning_rate": 2e-05,
+      "loss": 0.5623,
+      "step": 600
+    },
+    {
+      "epoch": 0.02605390167855465,
+      "grad_norm": 0.4276188910007477,
+      "learning_rate": 2e-05,
+      "loss": 0.589,
+      "step": 610
+    },
+    {
+      "epoch": 0.026481014820826036,
+      "grad_norm": 0.36040425300598145,
+      "learning_rate": 2e-05,
+      "loss": 0.5889,
+      "step": 620
+    },
+    {
+      "epoch": 0.026908127963097425,
+      "grad_norm": 0.43689343333244324,
+      "learning_rate": 2e-05,
+      "loss": 0.586,
+      "step": 630
+    },
+    {
+      "epoch": 0.02733524110536881,
+      "grad_norm": 0.38051506876945496,
+      "learning_rate": 2e-05,
+      "loss": 0.6155,
+      "step": 640
+    },
+    {
+      "epoch": 0.0277623542476402,
+      "grad_norm": 0.375367134809494,
+      "learning_rate": 2e-05,
+      "loss": 0.6267,
+      "step": 650
+    },
+    {
+      "epoch": 0.02818946738991159,
+      "grad_norm": 0.40035131573677063,
+      "learning_rate": 2e-05,
+      "loss": 0.6035,
+      "step": 660
+    },
+    {
+      "epoch": 0.028616580532182974,
+      "grad_norm": 0.429284006357193,
+      "learning_rate": 2e-05,
+      "loss": 0.5957,
+      "step": 670
+    },
+    {
+      "epoch": 0.029043693674454363,
+      "grad_norm": 0.4076769948005676,
+      "learning_rate": 2e-05,
+      "loss": 0.599,
+      "step": 680
+    },
+    {
+      "epoch": 0.02947080681672575,
+      "grad_norm": 0.39563876390457153,
+      "learning_rate": 2e-05,
+      "loss": 0.5906,
+      "step": 690
+    },
+    {
+      "epoch": 0.029897919958997137,
+      "grad_norm": 0.39621901512145996,
+      "learning_rate": 2e-05,
+      "loss": 0.615,
+      "step": 700
+    },
+    {
+      "epoch": 0.030325033101268526,
+      "grad_norm": 0.43017053604125977,
+      "learning_rate": 2e-05,
+      "loss": 0.6114,
+      "step": 710
+    },
+    {
+      "epoch": 0.030752146243539915,
+      "grad_norm": 0.3699895143508911,
+      "learning_rate": 2e-05,
+      "loss": 0.6024,
+      "step": 720
+    },
+    {
+      "epoch": 0.0311792593858113,
+      "grad_norm": 0.39387860894203186,
+      "learning_rate": 2e-05,
+      "loss": 0.5797,
+      "step": 730
+    },
+    {
+      "epoch": 0.03160637252808269,
+      "grad_norm": 0.36330047249794006,
+      "learning_rate": 2e-05,
+      "loss": 0.5641,
+      "step": 740
+    },
+    {
+      "epoch": 0.03203348567035408,
+      "grad_norm": 0.3734346628189087,
+      "learning_rate": 2e-05,
+      "loss": 0.6066,
+      "step": 750
+    },
+    {
+      "epoch": 0.03246059881262547,
+      "grad_norm": 0.3981451690196991,
+      "learning_rate": 2e-05,
+      "loss": 0.5708,
+      "step": 760
+    },
+    {
+      "epoch": 0.03288771195489685,
+      "grad_norm": 0.5013331770896912,
+      "learning_rate": 2e-05,
+      "loss": 0.5786,
+      "step": 770
+    },
+    {
+      "epoch": 0.03331482509716824,
+      "grad_norm": 0.4515092968940735,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 780
+    },
+    {
+      "epoch": 0.03374193823943963,
+      "grad_norm": 0.4270780682563782,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 790
+    },
+    {
+      "epoch": 0.034169051381711016,
+      "grad_norm": 0.40977057814598083,
+      "learning_rate": 2e-05,
+      "loss": 0.5903,
+      "step": 800
+    },
+    {
+      "epoch": 0.034596164523982405,
+      "grad_norm": 0.3862808644771576,
+      "learning_rate": 2e-05,
+      "loss": 0.591,
+      "step": 810
+    },
+    {
+      "epoch": 0.035023277666253794,
+      "grad_norm": 0.3566862642765045,
+      "learning_rate": 2e-05,
+      "loss": 0.5822,
+      "step": 820
+    },
+    {
+      "epoch": 0.035450390808525176,
+      "grad_norm": 0.47487324476242065,
+      "learning_rate": 2e-05,
+      "loss": 0.6037,
+      "step": 830
+    },
+    {
+      "epoch": 0.035877503950796565,
+      "grad_norm": 0.6204171180725098,
+      "learning_rate": 2e-05,
+      "loss": 0.606,
+      "step": 840
+    },
+    {
+      "epoch": 0.036304617093067953,
+      "grad_norm": 0.38122642040252686,
+      "learning_rate": 2e-05,
+      "loss": 0.6022,
+      "step": 850
+    },
+    {
+      "epoch": 0.03673173023533934,
+      "grad_norm": 0.45812979340553284,
+      "learning_rate": 2e-05,
+      "loss": 0.6134,
+      "step": 860
+    },
+    {
+      "epoch": 0.03715884337761073,
+      "grad_norm": 0.38281163573265076,
+      "learning_rate": 2e-05,
+      "loss": 0.5692,
+      "step": 870
+    },
+    {
+      "epoch": 0.03758595651988212,
+      "grad_norm": 0.44842684268951416,
+      "learning_rate": 2e-05,
+      "loss": 0.6195,
+      "step": 880
+    },
+    {
+      "epoch": 0.0380130696621535,
+      "grad_norm": 0.3978036642074585,
+      "learning_rate": 2e-05,
+      "loss": 0.5872,
+      "step": 890
+    },
+    {
+      "epoch": 0.03844018280442489,
+      "grad_norm": 0.40599605441093445,
+      "learning_rate": 2e-05,
+      "loss": 0.5896,
+      "step": 900
+    },
+    {
+      "epoch": 0.03886729594669628,
+      "grad_norm": 0.4849986732006073,
+      "learning_rate": 2e-05,
+      "loss": 0.5679,
+      "step": 910
+    },
+    {
+      "epoch": 0.03929440908896767,
+      "grad_norm": 0.3729165196418762,
+      "learning_rate": 2e-05,
+      "loss": 0.5941,
+      "step": 920
+    },
+    {
+      "epoch": 0.03972152223123906,
+      "grad_norm": 0.3839932680130005,
+      "learning_rate": 2e-05,
+      "loss": 0.5809,
+      "step": 930
+    },
+    {
+      "epoch": 0.04014863537351044,
+      "grad_norm": 0.3133138120174408,
+      "learning_rate": 2e-05,
+      "loss": 0.5909,
+      "step": 940
+    },
+    {
+      "epoch": 0.04057574851578183,
+      "grad_norm": 0.37946876883506775,
+      "learning_rate": 2e-05,
+      "loss": 0.5791,
+      "step": 950
+    },
+    {
+      "epoch": 0.04100286165805322,
+      "grad_norm": 0.3639635741710663,
+      "learning_rate": 2e-05,
+      "loss": 0.6028,
+      "step": 960
+    },
+    {
+      "epoch": 0.04142997480032461,
+      "grad_norm": 0.39474979043006897,
+      "learning_rate": 2e-05,
+      "loss": 0.5927,
+      "step": 970
+    },
+    {
+      "epoch": 0.041857087942595995,
+      "grad_norm": 0.39630550146102905,
+      "learning_rate": 2e-05,
+      "loss": 0.5861,
+      "step": 980
+    },
+    {
+      "epoch": 0.042284201084867384,
+      "grad_norm": 0.4038623571395874,
+      "learning_rate": 2e-05,
+      "loss": 0.5991,
+      "step": 990
+    },
+    {
+      "epoch": 0.042711314227138766,
+      "grad_norm": 0.46558162569999695,
+      "learning_rate": 2e-05,
+      "loss": 0.5842,
+      "step": 1000
+    },
+    {
+      "epoch": 0.043138427369410155,
+      "grad_norm": 0.4309065043926239,
+      "learning_rate": 2e-05,
+      "loss": 0.6021,
+      "step": 1010
+    },
+    {
+      "epoch": 0.043565540511681544,
+      "grad_norm": 0.3698565363883972,
+      "learning_rate": 2e-05,
+      "loss": 0.607,
+      "step": 1020
+    },
+    {
+      "epoch": 0.04399265365395293,
+      "grad_norm": 0.40514087677001953,
+      "learning_rate": 2e-05,
+      "loss": 0.5933,
+      "step": 1030
+    },
+    {
+      "epoch": 0.04441976679622432,
+      "grad_norm": 0.7474258542060852,
+      "learning_rate": 2e-05,
+      "loss": 0.5946,
+      "step": 1040
+    },
+    {
+      "epoch": 0.04484687993849571,
+      "grad_norm": 0.38786014914512634,
+      "learning_rate": 2e-05,
+      "loss": 0.6132,
+      "step": 1050
+    },
+    {
+      "epoch": 0.04527399308076709,
+      "grad_norm": 0.38152816891670227,
+      "learning_rate": 2e-05,
+      "loss": 0.5799,
+      "step": 1060
+    },
+    {
+      "epoch": 0.04570110622303848,
+      "grad_norm": 0.5136268734931946,
+      "learning_rate": 2e-05,
+      "loss": 0.6335,
+      "step": 1070
+    },
+    {
+      "epoch": 0.04612821936530987,
+      "grad_norm": 0.37756872177124023,
+      "learning_rate": 2e-05,
+      "loss": 0.5794,
+      "step": 1080
+    },
+    {
+      "epoch": 0.04655533250758126,
+      "grad_norm": 0.41157087683677673,
+      "learning_rate": 2e-05,
+      "loss": 0.6129,
+      "step": 1090
+    },
+    {
+      "epoch": 0.04698244564985265,
+      "grad_norm": 0.45449504256248474,
+      "learning_rate": 2e-05,
+      "loss": 0.6074,
+      "step": 1100
+    },
+    {
+      "epoch": 0.04740955879212403,
+      "grad_norm": 0.36440810561180115,
+      "learning_rate": 2e-05,
+      "loss": 0.5905,
+      "step": 1110
+    },
+    {
+      "epoch": 0.04783667193439542,
+      "grad_norm": 0.40203210711479187,
+      "learning_rate": 2e-05,
+      "loss": 0.5772,
+      "step": 1120
+    },
+    {
+      "epoch": 0.04826378507666681,
+      "grad_norm": 0.4374965727329254,
+      "learning_rate": 2e-05,
+      "loss": 0.6033,
+      "step": 1130
+    },
+    {
+      "epoch": 0.0486908982189382,
+      "grad_norm": 0.37814727425575256,
+      "learning_rate": 2e-05,
+      "loss": 0.6051,
+      "step": 1140
+    },
+    {
+      "epoch": 0.049118011361209586,
+      "grad_norm": 0.3608170449733734,
+      "learning_rate": 2e-05,
+      "loss": 0.6036,
+      "step": 1150
+    },
+    {
+      "epoch": 0.049545124503480975,
+      "grad_norm": 0.5163088440895081,
+      "learning_rate": 2e-05,
+      "loss": 0.5888,
+      "step": 1160
+    },
+    {
+      "epoch": 0.04997223764575236,
+      "grad_norm": 0.6338587403297424,
+      "learning_rate": 2e-05,
+      "loss": 0.5846,
+      "step": 1170
+    },
+    {
+      "epoch": 0.050399350788023746,
+      "grad_norm": 0.3570212125778198,
+      "learning_rate": 2e-05,
+      "loss": 0.5997,
+      "step": 1180
+    },
+    {
+      "epoch": 0.050826463930295135,
+      "grad_norm": 0.4730677604675293,
+      "learning_rate": 2e-05,
+      "loss": 0.5666,
+      "step": 1190
+    },
+    {
+      "epoch": 0.051253577072566524,
+      "grad_norm": 0.4634343683719635,
+      "learning_rate": 2e-05,
+      "loss": 0.6167,
+      "step": 1200
+    },
+    {
+      "epoch": 0.05168069021483791,
+      "grad_norm": 0.4279061555862427,
+      "learning_rate": 2e-05,
+      "loss": 0.5984,
+      "step": 1210
+    },
+    {
+      "epoch": 0.0521078033571093,
+      "grad_norm": 0.42280420660972595,
+      "learning_rate": 2e-05,
+      "loss": 0.5715,
+      "step": 1220
+    },
+    {
+      "epoch": 0.052534916499380684,
+      "grad_norm": 0.34051749110221863,
+      "learning_rate": 2e-05,
+      "loss": 0.577,
+      "step": 1230
+    },
+    {
+      "epoch": 0.05296202964165207,
+      "grad_norm": 0.3963359296321869,
+      "learning_rate": 2e-05,
+      "loss": 0.6313,
+      "step": 1240
+    },
+    {
+      "epoch": 0.05338914278392346,
+      "grad_norm": 0.5236133933067322,
+      "learning_rate": 2e-05,
+      "loss": 0.6187,
+      "step": 1250
+    },
+    {
+      "epoch": 0.05381625592619485,
+      "grad_norm": 0.40057671070098877,
+      "learning_rate": 2e-05,
+      "loss": 0.6118,
+      "step": 1260
+    },
+    {
+      "epoch": 0.05424336906846624,
+      "grad_norm": 0.4331953227519989,
+      "learning_rate": 2e-05,
+      "loss": 0.5933,
+      "step": 1270
+    },
+    {
+      "epoch": 0.05467048221073762,
+      "grad_norm": 0.35897260904312134,
+      "learning_rate": 2e-05,
+      "loss": 0.5776,
+      "step": 1280
+    },
+    {
+      "epoch": 0.05509759535300901,
+      "grad_norm": 0.40010058879852295,
+      "learning_rate": 2e-05,
+      "loss": 0.58,
+      "step": 1290
+    },
+    {
+      "epoch": 0.0555247084952804,
+      "grad_norm": 0.49022912979125977,
+      "learning_rate": 2e-05,
+      "loss": 0.5747,
+      "step": 1300
+    },
+    {
+      "epoch": 0.05595182163755179,
+      "grad_norm": 0.4582119584083557,
+      "learning_rate": 2e-05,
+      "loss": 0.5994,
+      "step": 1310
+    },
+    {
+      "epoch": 0.05637893477982318,
+      "grad_norm": 0.4133841097354889,
+      "learning_rate": 2e-05,
+      "loss": 0.5856,
+      "step": 1320
+    },
+    {
+      "epoch": 0.056806047922094566,
+      "grad_norm": 0.40341418981552124,
+      "learning_rate": 2e-05,
+      "loss": 0.615,
+      "step": 1330
+    },
+    {
+      "epoch": 0.05723316106436595,
+      "grad_norm": 0.3729898929595947,
+      "learning_rate": 2e-05,
+      "loss": 0.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 0.05766027420663734,
+      "grad_norm": 0.36487877368927,
+      "learning_rate": 2e-05,
+      "loss": 0.6087,
+      "step": 1350
+    },
+    {
+      "epoch": 0.058087387348908726,
+      "grad_norm": 0.410173237323761,
+      "learning_rate": 2e-05,
+      "loss": 0.6106,
+      "step": 1360
+    },
+    {
+      "epoch": 0.058514500491180114,
+      "grad_norm": 0.4052298367023468,
+      "learning_rate": 2e-05,
+      "loss": 0.5794,
+      "step": 1370
+    },
+    {
+      "epoch": 0.0589416136334515,
+      "grad_norm": 0.35845524072647095,
+      "learning_rate": 2e-05,
+      "loss": 0.5818,
+      "step": 1380
+    },
+    {
+      "epoch": 0.05936872677572289,
+      "grad_norm": 0.39520588517189026,
+      "learning_rate": 2e-05,
+      "loss": 0.5724,
+      "step": 1390
+    },
+    {
+      "epoch": 0.059795839917994274,
+      "grad_norm": 0.3926452696323395,
+      "learning_rate": 2e-05,
+      "loss": 0.5787,
+      "step": 1400
+    },
+    {
+      "epoch": 0.06022295306026566,
+      "grad_norm": 0.3984834551811218,
+      "learning_rate": 2e-05,
+      "loss": 0.6149,
+      "step": 1410
+    },
+    {
+      "epoch": 0.06065006620253705,
+      "grad_norm": 0.4060869514942169,
+      "learning_rate": 2e-05,
+      "loss": 0.623,
+      "step": 1420
+    },
+    {
+      "epoch": 0.06107717934480844,
+      "grad_norm": 0.3899109661579132,
+      "learning_rate": 2e-05,
+      "loss": 0.606,
+      "step": 1430
+    },
+    {
+      "epoch": 0.06150429248707983,
+      "grad_norm": 0.41343048214912415,
+      "learning_rate": 2e-05,
+      "loss": 0.62,
+      "step": 1440
+    },
+    {
+      "epoch": 0.06193140562935121,
+      "grad_norm": 0.5486384630203247,
+      "learning_rate": 2e-05,
+      "loss": 0.5888,
+      "step": 1450
+    },
+    {
+      "epoch": 0.0623585187716226,
+      "grad_norm": 0.4260222017765045,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 1460
+    },
+    {
+      "epoch": 0.062785631913894,
+      "grad_norm": 0.5510641932487488,
+      "learning_rate": 2e-05,
+      "loss": 0.5917,
+      "step": 1470
+    },
+    {
+      "epoch": 0.06321274505616538,
+      "grad_norm": 0.3307860791683197,
+      "learning_rate": 2e-05,
+      "loss": 0.5966,
+      "step": 1480
+    },
+    {
+      "epoch": 0.06363985819843676,
+      "grad_norm": 0.37774041295051575,
+      "learning_rate": 2e-05,
+      "loss": 0.5928,
+      "step": 1490
+    },
+    {
+      "epoch": 0.06406697134070816,
+      "grad_norm": 0.40287962555885315,
+      "learning_rate": 2e-05,
+      "loss": 0.6018,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06449408448297954,
+      "grad_norm": 0.3765062987804413,
+      "learning_rate": 2e-05,
+      "loss": 0.5868,
+      "step": 1510
+    },
+    {
+      "epoch": 0.06492119762525093,
+      "grad_norm": 0.3866639733314514,
+      "learning_rate": 2e-05,
+      "loss": 0.5918,
+      "step": 1520
+    },
+    {
+      "epoch": 0.06534831076752232,
+      "grad_norm": 0.3452185392379761,
+      "learning_rate": 2e-05,
+      "loss": 0.6006,
+      "step": 1530
+    },
+    {
+      "epoch": 0.0657754239097937,
+      "grad_norm": 0.3757578730583191,
+      "learning_rate": 2e-05,
+      "loss": 0.5885,
+      "step": 1540
+    },
+    {
+      "epoch": 0.0662025370520651,
+      "grad_norm": 0.6169503927230835,
+      "learning_rate": 2e-05,
+      "loss": 0.5942,
+      "step": 1550
+    },
+    {
+      "epoch": 0.06662965019433648,
+      "grad_norm": 0.40690863132476807,
+      "learning_rate": 2e-05,
+      "loss": 0.5846,
+      "step": 1560
+    },
+    {
+      "epoch": 0.06705676333660787,
+      "grad_norm": 0.40239500999450684,
+      "learning_rate": 2e-05,
+      "loss": 0.6043,
+      "step": 1570
+    },
+    {
+      "epoch": 0.06748387647887925,
+      "grad_norm": 0.6150453090667725,
+      "learning_rate": 2e-05,
+      "loss": 0.5687,
+      "step": 1580
+    },
+    {
+      "epoch": 0.06791098962115065,
+      "grad_norm": 0.3692316710948944,
+      "learning_rate": 2e-05,
+      "loss": 0.5934,
+      "step": 1590
+    },
+    {
+      "epoch": 0.06833810276342203,
+      "grad_norm": 0.4124865233898163,
+      "learning_rate": 2e-05,
+      "loss": 0.5784,
+      "step": 1600
+    },
+    {
+      "epoch": 0.06876521590569341,
+      "grad_norm": 0.40603578090667725,
+      "learning_rate": 2e-05,
+      "loss": 0.5536,
+      "step": 1610
+    },
+    {
+      "epoch": 0.06919232904796481,
+      "grad_norm": 0.3672163188457489,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 1620
+    },
+    {
+      "epoch": 0.06961944219023619,
+      "grad_norm": 0.4111248850822449,
+      "learning_rate": 2e-05,
+      "loss": 0.6168,
+      "step": 1630
+    },
+    {
+      "epoch": 0.07004655533250759,
+      "grad_norm": 0.3349396288394928,
+      "learning_rate": 2e-05,
+      "loss": 0.6096,
+      "step": 1640
+    },
+    {
+      "epoch": 0.07047366847477897,
+      "grad_norm": 0.35192081332206726,
+      "learning_rate": 2e-05,
+      "loss": 0.6309,
+      "step": 1650
+    },
+    {
+      "epoch": 0.07090078161705035,
+      "grad_norm": 0.46462368965148926,
+      "learning_rate": 2e-05,
+      "loss": 0.5827,
+      "step": 1660
+    },
+    {
+      "epoch": 0.07132789475932175,
+      "grad_norm": 0.4099385440349579,
+      "learning_rate": 2e-05,
+      "loss": 0.6093,
+      "step": 1670
+    },
+    {
+      "epoch": 0.07175500790159313,
+      "grad_norm": 0.39262962341308594,
+      "learning_rate": 2e-05,
+      "loss": 0.5959,
+      "step": 1680
+    },
+    {
+      "epoch": 0.07218212104386452,
+      "grad_norm": 0.4145928919315338,
+      "learning_rate": 2e-05,
+      "loss": 0.5776,
+      "step": 1690
+    },
+    {
+      "epoch": 0.07260923418613591,
+      "grad_norm": 0.33485323190689087,
+      "learning_rate": 2e-05,
+      "loss": 0.5864,
+      "step": 1700
+    },
+    {
+      "epoch": 0.07303634732840729,
+      "grad_norm": 0.3448295295238495,
+      "learning_rate": 2e-05,
+      "loss": 0.6077,
+      "step": 1710
+    },
+    {
+      "epoch": 0.07346346047067868,
+      "grad_norm": 0.3951145112514496,
+      "learning_rate": 2e-05,
+      "loss": 0.5667,
+      "step": 1720
+    },
+    {
+      "epoch": 0.07389057361295007,
+      "grad_norm": 0.36090508103370667,
+      "learning_rate": 2e-05,
+      "loss": 0.6006,
+      "step": 1730
+    },
+    {
+      "epoch": 0.07431768675522146,
+      "grad_norm": 0.35783612728118896,
+      "learning_rate": 2e-05,
+      "loss": 0.5698,
+      "step": 1740
+    },
+    {
+      "epoch": 0.07474479989749284,
+      "grad_norm": 0.4051808714866638,
+      "learning_rate": 2e-05,
+      "loss": 0.5841,
+      "step": 1750
+    },
+    {
+      "epoch": 0.07517191303976424,
+      "grad_norm": 0.36852049827575684,
+      "learning_rate": 2e-05,
+      "loss": 0.5812,
+      "step": 1760
+    },
+    {
+      "epoch": 0.07559902618203562,
+      "grad_norm": 0.47315099835395813,
+      "learning_rate": 2e-05,
+      "loss": 0.5867,
+      "step": 1770
+    },
+    {
+      "epoch": 0.076026139324307,
+      "grad_norm": 0.370299756526947,
+      "learning_rate": 2e-05,
+      "loss": 0.5944,
+      "step": 1780
+    },
+    {
+      "epoch": 0.0764532524665784,
+      "grad_norm": 0.3629041314125061,
+      "learning_rate": 2e-05,
+      "loss": 0.5895,
+      "step": 1790
+    },
+    {
+      "epoch": 0.07688036560884978,
+      "grad_norm": 0.4631352722644806,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 1800
+    },
+    {
+      "epoch": 0.07730747875112118,
+      "grad_norm": 0.3893195390701294,
+      "learning_rate": 2e-05,
+      "loss": 0.579,
+      "step": 1810
+    },
+    {
+      "epoch": 0.07773459189339256,
+      "grad_norm": 0.4197307825088501,
+      "learning_rate": 2e-05,
+      "loss": 0.6022,
+      "step": 1820
+    },
+    {
+      "epoch": 0.07816170503566394,
+      "grad_norm": 0.5316178798675537,
+      "learning_rate": 2e-05,
+      "loss": 0.6127,
+      "step": 1830
+    },
+    {
+      "epoch": 0.07858881817793534,
+      "grad_norm": 0.4087827801704407,
+      "learning_rate": 2e-05,
+      "loss": 0.6148,
+      "step": 1840
+    },
+    {
+      "epoch": 0.07901593132020672,
+      "grad_norm": 0.9132181406021118,
+      "learning_rate": 2e-05,
+      "loss": 0.5675,
+      "step": 1850
+    },
+    {
+      "epoch": 0.07944304446247812,
+      "grad_norm": 0.42939144372940063,
+      "learning_rate": 2e-05,
+      "loss": 0.5827,
+      "step": 1860
+    },
+    {
+      "epoch": 0.0798701576047495,
+      "grad_norm": 0.5866528749465942,
+      "learning_rate": 2e-05,
+      "loss": 0.5984,
+      "step": 1870
+    },
+    {
+      "epoch": 0.08029727074702088,
+      "grad_norm": 0.38625794649124146,
+      "learning_rate": 2e-05,
+      "loss": 0.5712,
+      "step": 1880
+    },
+    {
+      "epoch": 0.08072438388929228,
+      "grad_norm": 0.3775944411754608,
+      "learning_rate": 2e-05,
+      "loss": 0.5633,
+      "step": 1890
+    },
+    {
+      "epoch": 0.08115149703156366,
+      "grad_norm": 0.37404197454452515,
+      "learning_rate": 2e-05,
+      "loss": 0.5944,
+      "step": 1900
+    },
+    {
+      "epoch": 0.08157861017383505,
+      "grad_norm": 0.4127039611339569,
+      "learning_rate": 2e-05,
+      "loss": 0.5685,
+      "step": 1910
+    },
+    {
+      "epoch": 0.08200572331610644,
+      "grad_norm": 0.4228227734565735,
+      "learning_rate": 2e-05,
+      "loss": 0.5907,
+      "step": 1920
+    },
+    {
+      "epoch": 0.08243283645837783,
+      "grad_norm": 0.3642731010913849,
+      "learning_rate": 2e-05,
+      "loss": 0.5926,
+      "step": 1930
+    },
+    {
+      "epoch": 0.08285994960064921,
+      "grad_norm": 0.3753544092178345,
+      "learning_rate": 2e-05,
+      "loss": 0.598,
+      "step": 1940
+    },
+    {
+      "epoch": 0.0832870627429206,
+      "grad_norm": 0.35891029238700867,
+      "learning_rate": 2e-05,
+      "loss": 0.5862,
+      "step": 1950
+    },
+    {
+      "epoch": 0.08371417588519199,
+      "grad_norm": 0.3859628438949585,
+      "learning_rate": 2e-05,
+      "loss": 0.5787,
+      "step": 1960
+    },
+    {
+      "epoch": 0.08414128902746337,
+      "grad_norm": 0.3352157473564148,
+      "learning_rate": 2e-05,
+      "loss": 0.5677,
+      "step": 1970
+    },
+    {
+      "epoch": 0.08456840216973477,
+      "grad_norm": 0.38465848565101624,
+      "learning_rate": 2e-05,
+      "loss": 0.5651,
+      "step": 1980
+    },
+    {
+      "epoch": 0.08499551531200615,
+      "grad_norm": 0.8394455313682556,
+      "learning_rate": 2e-05,
+      "loss": 0.5683,
+      "step": 1990
+    },
+    {
+      "epoch": 0.08542262845427753,
+      "grad_norm": 0.39962485432624817,
+      "learning_rate": 2e-05,
+      "loss": 0.5793,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08584974159654893,
+      "grad_norm": 0.3594360649585724,
+      "learning_rate": 2e-05,
+      "loss": 0.6158,
+      "step": 2010
+    },
+    {
+      "epoch": 0.08627685473882031,
+      "grad_norm": 0.388683557510376,
+      "learning_rate": 2e-05,
+      "loss": 0.5829,
+      "step": 2020
+    },
+    {
+      "epoch": 0.0867039678810917,
+      "grad_norm": 0.33351218700408936,
+      "learning_rate": 2e-05,
+      "loss": 0.5698,
+      "step": 2030
+    },
+    {
+      "epoch": 0.08713108102336309,
+      "grad_norm": 0.41887760162353516,
+      "learning_rate": 2e-05,
+      "loss": 0.5688,
+      "step": 2040
+    },
+    {
+      "epoch": 0.08755819416563447,
+      "grad_norm": 0.41641342639923096,
+      "learning_rate": 2e-05,
+      "loss": 0.6138,
+      "step": 2050
+    },
+    {
+      "epoch": 0.08798530730790587,
+      "grad_norm": 0.39547309279441833,
+      "learning_rate": 2e-05,
+      "loss": 0.5687,
+      "step": 2060
+    },
+    {
+      "epoch": 0.08841242045017725,
+      "grad_norm": 0.37472912669181824,
+      "learning_rate": 2e-05,
+      "loss": 0.5866,
+      "step": 2070
+    },
+    {
+      "epoch": 0.08883953359244864,
+      "grad_norm": 0.32959887385368347,
+      "learning_rate": 2e-05,
+      "loss": 0.5634,
+      "step": 2080
+    },
+    {
+      "epoch": 0.08926664673472003,
+      "grad_norm": 0.3440960943698883,
+      "learning_rate": 2e-05,
+      "loss": 0.5966,
+      "step": 2090
+    },
+    {
+      "epoch": 0.08969375987699142,
+      "grad_norm": 0.3621431291103363,
+      "learning_rate": 2e-05,
+      "loss": 0.5454,
+      "step": 2100
+    },
+    {
+      "epoch": 0.0901208730192628,
+      "grad_norm": 0.3840614855289459,
+      "learning_rate": 2e-05,
+      "loss": 0.583,
+      "step": 2110
+    },
+    {
+      "epoch": 0.09054798616153419,
+      "grad_norm": 0.4339292049407959,
+      "learning_rate": 2e-05,
+      "loss": 0.5729,
+      "step": 2120
+    },
+    {
+      "epoch": 0.09097509930380558,
+      "grad_norm": 0.3641127943992615,
+      "learning_rate": 2e-05,
+      "loss": 0.5484,
+      "step": 2130
+    },
+    {
+      "epoch": 0.09140221244607696,
+      "grad_norm": 0.3554155230522156,
+      "learning_rate": 2e-05,
+      "loss": 0.6231,
+      "step": 2140
+    },
+    {
+      "epoch": 0.09182932558834836,
+      "grad_norm": 0.5909919142723083,
+      "learning_rate": 2e-05,
+      "loss": 0.5631,
+      "step": 2150
+    },
+    {
+      "epoch": 0.09225643873061974,
+      "grad_norm": 0.39234042167663574,
+      "learning_rate": 2e-05,
+      "loss": 0.5526,
+      "step": 2160
+    },
+    {
+      "epoch": 0.09268355187289112,
+      "grad_norm": 0.399471640586853,
+      "learning_rate": 2e-05,
+      "loss": 0.578,
+      "step": 2170
+    },
+    {
+      "epoch": 0.09311066501516252,
+      "grad_norm": 0.3671838939189911,
+      "learning_rate": 2e-05,
+      "loss": 0.5632,
+      "step": 2180
+    },
+    {
+      "epoch": 0.0935377781574339,
+      "grad_norm": 0.41628867387771606,
+      "learning_rate": 2e-05,
+      "loss": 0.5823,
+      "step": 2190
+    },
+    {
+      "epoch": 0.0939648912997053,
+      "grad_norm": 0.36250025033950806,
+      "learning_rate": 2e-05,
+      "loss": 0.5564,
+      "step": 2200
+    },
+    {
+      "epoch": 0.09439200444197668,
+      "grad_norm": 0.38223734498023987,
+      "learning_rate": 2e-05,
+      "loss": 0.581,
+      "step": 2210
+    },
+    {
+      "epoch": 0.09481911758424806,
+      "grad_norm": 0.39655935764312744,
+      "learning_rate": 2e-05,
+      "loss": 0.538,
+      "step": 2220
+    },
+    {
+      "epoch": 0.09524623072651946,
+      "grad_norm": 0.47572919726371765,
+      "learning_rate": 2e-05,
+      "loss": 0.5916,
+      "step": 2230
+    },
+    {
+      "epoch": 0.09567334386879084,
+      "grad_norm": 0.34458720684051514,
+      "learning_rate": 2e-05,
+      "loss": 0.552,
+      "step": 2240
+    },
+    {
+      "epoch": 0.09610045701106223,
+      "grad_norm": 0.3788979649543762,
+      "learning_rate": 2e-05,
+      "loss": 0.5879,
+      "step": 2250
+    },
+    {
+      "epoch": 0.09652757015333362,
+      "grad_norm": 0.4104970395565033,
+      "learning_rate": 2e-05,
+      "loss": 0.5314,
+      "step": 2260
+    },
+    {
+      "epoch": 0.09695468329560501,
+      "grad_norm": 0.3858654499053955,
+      "learning_rate": 2e-05,
+      "loss": 0.5674,
+      "step": 2270
+    },
+    {
+      "epoch": 0.0973817964378764,
+      "grad_norm": 0.5043524503707886,
+      "learning_rate": 2e-05,
+      "loss": 0.5868,
+      "step": 2280
+    },
+    {
+      "epoch": 0.09780890958014778,
+      "grad_norm": 0.4935309886932373,
+      "learning_rate": 2e-05,
+      "loss": 0.614,
+      "step": 2290
+    },
+    {
+      "epoch": 0.09823602272241917,
+      "grad_norm": 0.3307911455631256,
+      "learning_rate": 2e-05,
+      "loss": 0.5855,
+      "step": 2300
+    },
+    {
+      "epoch": 0.09866313586469055,
+      "grad_norm": 0.4159630835056305,
+      "learning_rate": 2e-05,
+      "loss": 0.5617,
+      "step": 2310
+    },
+    {
+      "epoch": 0.09909024900696195,
+      "grad_norm": 0.35000452399253845,
+      "learning_rate": 2e-05,
+      "loss": 0.5416,
+      "step": 2320
+    },
+    {
+      "epoch": 0.09951736214923333,
+      "grad_norm": 0.35403895378112793,
+      "learning_rate": 2e-05,
+      "loss": 0.6036,
+      "step": 2330
+    },
+    {
+      "epoch": 0.09994447529150471,
+      "grad_norm": 0.426325261592865,
+      "learning_rate": 2e-05,
+      "loss": 0.5982,
+      "step": 2340
+    },
+    {
+      "epoch": 0.10037158843377611,
+      "grad_norm": 0.3617796003818512,
+      "learning_rate": 2e-05,
+      "loss": 0.5854,
+      "step": 2350
+    },
+    {
+      "epoch": 0.10079870157604749,
+      "grad_norm": 0.38468244671821594,
+      "learning_rate": 2e-05,
+      "loss": 0.5581,
+      "step": 2360
+    },
+    {
+      "epoch": 0.10122581471831889,
+      "grad_norm": 0.368740051984787,
+      "learning_rate": 2e-05,
+      "loss": 0.585,
+      "step": 2370
+    },
+    {
+      "epoch": 0.10165292786059027,
+      "grad_norm": 0.3715099096298218,
+      "learning_rate": 2e-05,
+      "loss": 0.5484,
+      "step": 2380
+    },
+    {
+      "epoch": 0.10208004100286165,
+      "grad_norm": 0.3937329649925232,
+      "learning_rate": 2e-05,
+      "loss": 0.5733,
+      "step": 2390
+    },
+    {
+      "epoch": 0.10250715414513305,
+      "grad_norm": 0.4053308963775635,
+      "learning_rate": 2e-05,
+      "loss": 0.5752,
+      "step": 2400
+    },
+    {
+      "epoch": 0.10293426728740443,
+      "grad_norm": 0.45390602946281433,
+      "learning_rate": 2e-05,
+      "loss": 0.6029,
+      "step": 2410
+    },
+    {
+      "epoch": 0.10336138042967583,
+      "grad_norm": 0.41054967045783997,
+      "learning_rate": 2e-05,
+      "loss": 0.5808,
+      "step": 2420
+    },
+    {
+      "epoch": 0.10378849357194721,
+      "grad_norm": 0.40561535954475403,
+      "learning_rate": 2e-05,
+      "loss": 0.5406,
+      "step": 2430
+    },
+    {
+      "epoch": 0.1042156067142186,
+      "grad_norm": 0.3592640161514282,
+      "learning_rate": 2e-05,
+      "loss": 0.5658,
+      "step": 2440
+    },
+    {
+      "epoch": 0.10464271985648999,
+      "grad_norm": 0.353193074464798,
+      "learning_rate": 2e-05,
+      "loss": 0.5636,
+      "step": 2450
+    },
+    {
+      "epoch": 0.10506983299876137,
+      "grad_norm": 0.37722814083099365,
+      "learning_rate": 2e-05,
+      "loss": 0.5908,
+      "step": 2460
+    },
+    {
+      "epoch": 0.10549694614103276,
+      "grad_norm": 0.40230175852775574,
+      "learning_rate": 2e-05,
+      "loss": 0.5749,
+      "step": 2470
+    },
+    {
+      "epoch": 0.10592405928330414,
+      "grad_norm": 0.325605183839798,
+      "learning_rate": 2e-05,
+      "loss": 0.5561,
+      "step": 2480
+    },
+    {
+      "epoch": 0.10635117242557554,
+      "grad_norm": 0.4106343984603882,
+      "learning_rate": 2e-05,
+      "loss": 0.5952,
+      "step": 2490
+    },
+    {
+      "epoch": 0.10677828556784692,
+      "grad_norm": 0.5286628603935242,
+      "learning_rate": 2e-05,
+      "loss": 0.5644,
+      "step": 2500
+    },
+    {
+      "epoch": 0.1072053987101183,
+      "grad_norm": 0.39102843403816223,
+      "learning_rate": 2e-05,
+      "loss": 0.5852,
+      "step": 2510
+    },
+    {
+      "epoch": 0.1076325118523897,
+      "grad_norm": 0.3884442150592804,
+      "learning_rate": 2e-05,
+      "loss": 0.5841,
+      "step": 2520
+    },
+    {
+      "epoch": 0.10805962499466108,
+      "grad_norm": 0.34783875942230225,
+      "learning_rate": 2e-05,
+      "loss": 0.5746,
+      "step": 2530
+    },
+    {
+      "epoch": 0.10848673813693248,
+      "grad_norm": 0.3849523365497589,
+      "learning_rate": 2e-05,
+      "loss": 0.5609,
+      "step": 2540
+    },
+    {
+      "epoch": 0.10891385127920386,
+      "grad_norm": 0.3732714056968689,
+      "learning_rate": 2e-05,
+      "loss": 0.575,
+      "step": 2550
+    },
+    {
+      "epoch": 0.10934096442147524,
+      "grad_norm": 0.45154619216918945,
+      "learning_rate": 2e-05,
+      "loss": 0.5841,
+      "step": 2560
+    },
+    {
+      "epoch": 0.10976807756374664,
+      "grad_norm": 0.44157183170318604,
+      "learning_rate": 2e-05,
+      "loss": 0.5715,
+      "step": 2570
+    },
+    {
+      "epoch": 0.11019519070601802,
+      "grad_norm": 0.36760470271110535,
+      "learning_rate": 2e-05,
+      "loss": 0.5753,
+      "step": 2580
+    },
+    {
+      "epoch": 0.11062230384828942,
+      "grad_norm": 0.5752866268157959,
+      "learning_rate": 2e-05,
+      "loss": 0.58,
+      "step": 2590
+    },
+    {
+      "epoch": 0.1110494169905608,
+      "grad_norm": 0.4019835591316223,
+      "learning_rate": 2e-05,
+      "loss": 0.5901,
+      "step": 2600
+    },
+    {
+      "epoch": 0.1114765301328322,
+      "grad_norm": 0.39717164635658264,
+      "learning_rate": 2e-05,
+      "loss": 0.5621,
+      "step": 2610
+    },
+    {
+      "epoch": 0.11190364327510358,
+      "grad_norm": 0.38785597681999207,
+      "learning_rate": 2e-05,
+      "loss": 0.5594,
+      "step": 2620
+    },
+    {
+      "epoch": 0.11233075641737496,
+      "grad_norm": 0.466998815536499,
+      "learning_rate": 2e-05,
+      "loss": 0.5613,
+      "step": 2630
+    },
+    {
+      "epoch": 0.11275786955964635,
+      "grad_norm": 0.4325760304927826,
+      "learning_rate": 2e-05,
+      "loss": 0.6015,
+      "step": 2640
+    },
+    {
+      "epoch": 0.11318498270191774,
+      "grad_norm": 0.4164709150791168,
+      "learning_rate": 2e-05,
+      "loss": 0.5762,
+      "step": 2650
+    },
+    {
+      "epoch": 0.11361209584418913,
+      "grad_norm": 0.3899877071380615,
+      "learning_rate": 2e-05,
+      "loss": 0.5868,
+      "step": 2660
+    },
+    {
+      "epoch": 0.11403920898646051,
+      "grad_norm": 0.38004082441329956,
+      "learning_rate": 2e-05,
+      "loss": 0.5701,
+      "step": 2670
+    },
+    {
+      "epoch": 0.1144663221287319,
+      "grad_norm": 0.42381832003593445,
+      "learning_rate": 2e-05,
+      "loss": 0.5593,
+      "step": 2680
+    },
+    {
+      "epoch": 0.11489343527100329,
+      "grad_norm": 0.42195361852645874,
+      "learning_rate": 2e-05,
+      "loss": 0.5937,
+      "step": 2690
+    },
+    {
+      "epoch": 0.11532054841327467,
+      "grad_norm": 0.3784947991371155,
+      "learning_rate": 2e-05,
+      "loss": 0.5773,
+      "step": 2700
+    },
+    {
+      "epoch": 0.11574766155554607,
+      "grad_norm": 0.35190480947494507,
+      "learning_rate": 2e-05,
+      "loss": 0.6169,
+      "step": 2710
+    },
+    {
+      "epoch": 0.11617477469781745,
+      "grad_norm": 0.43207699060440063,
+      "learning_rate": 2e-05,
+      "loss": 0.5772,
+      "step": 2720
+    },
+    {
+      "epoch": 0.11660188784008883,
+      "grad_norm": 0.463670551776886,
+      "learning_rate": 2e-05,
+      "loss": 0.5405,
+      "step": 2730
+    },
+    {
+      "epoch": 0.11702900098236023,
+      "grad_norm": 0.32041552662849426,
+      "learning_rate": 2e-05,
+      "loss": 0.5539,
+      "step": 2740
+    },
+    {
+      "epoch": 0.11745611412463161,
+      "grad_norm": 0.3760058283805847,
+      "learning_rate": 2e-05,
+      "loss": 0.5791,
+      "step": 2750
+    },
+    {
+      "epoch": 0.117883227266903,
+      "grad_norm": 0.6083221435546875,
+      "learning_rate": 2e-05,
+      "loss": 0.5613,
+      "step": 2760
+    },
+    {
+      "epoch": 0.11831034040917439,
+      "grad_norm": 0.38147875666618347,
+      "learning_rate": 2e-05,
+      "loss": 0.5617,
+      "step": 2770
+    },
+    {
+      "epoch": 0.11873745355144578,
+      "grad_norm": 0.4536650478839874,
+      "learning_rate": 2e-05,
+      "loss": 0.5583,
+      "step": 2780
+    },
+    {
+      "epoch": 0.11916456669371717,
+      "grad_norm": 0.4079718291759491,
+      "learning_rate": 2e-05,
+      "loss": 0.5792,
+      "step": 2790
+    },
+    {
+      "epoch": 0.11959167983598855,
+      "grad_norm": 0.5897331237792969,
+      "learning_rate": 2e-05,
+      "loss": 0.6039,
+      "step": 2800
+    },
+    {
+      "epoch": 0.12001879297825994,
+      "grad_norm": 0.37805119156837463,
+      "learning_rate": 2e-05,
+      "loss": 0.592,
+      "step": 2810
+    },
+    {
+      "epoch": 0.12044590612053133,
+      "grad_norm": 0.3962540030479431,
+      "learning_rate": 2e-05,
+      "loss": 0.5411,
+      "step": 2820
+    },
+    {
+      "epoch": 0.12087301926280272,
+      "grad_norm": 0.35660144686698914,
+      "learning_rate": 2e-05,
+      "loss": 0.5665,
+      "step": 2830
+    },
+    {
+      "epoch": 0.1213001324050741,
+      "grad_norm": 0.34495723247528076,
+      "learning_rate": 2e-05,
+      "loss": 0.549,
+      "step": 2840
+    },
+    {
+      "epoch": 0.12172724554734549,
+      "grad_norm": 0.34002381563186646,
+      "learning_rate": 2e-05,
+      "loss": 0.6298,
+      "step": 2850
+    },
+    {
+      "epoch": 0.12215435868961688,
+      "grad_norm": 0.37899792194366455,
+      "learning_rate": 2e-05,
+      "loss": 0.591,
+      "step": 2860
+    },
+    {
+      "epoch": 0.12258147183188826,
+      "grad_norm": 0.4109525978565216,
+      "learning_rate": 2e-05,
+      "loss": 0.5772,
+      "step": 2870
+    },
+    {
+      "epoch": 0.12300858497415966,
+      "grad_norm": 0.3907710313796997,
+      "learning_rate": 2e-05,
+      "loss": 0.5741,
+      "step": 2880
+    },
+    {
+      "epoch": 0.12343569811643104,
+      "grad_norm": 0.3784787952899933,
+      "learning_rate": 2e-05,
+      "loss": 0.5665,
+      "step": 2890
+    },
+    {
+      "epoch": 0.12386281125870242,
+      "grad_norm": 0.37501630187034607,
+      "learning_rate": 2e-05,
+      "loss": 0.5366,
+      "step": 2900
+    },
+    {
+      "epoch": 0.12428992440097382,
+      "grad_norm": 0.3924628794193268,
+      "learning_rate": 2e-05,
+      "loss": 0.5797,
+      "step": 2910
+    },
+    {
+      "epoch": 0.1247170375432452,
+      "grad_norm": 0.43658187985420227,
+      "learning_rate": 2e-05,
+      "loss": 0.565,
+      "step": 2920
+    },
+    {
+      "epoch": 0.1251441506855166,
+      "grad_norm": 0.38225287199020386,
+      "learning_rate": 2e-05,
+      "loss": 0.5413,
+      "step": 2930
+    },
+    {
+      "epoch": 0.125571263827788,
+      "grad_norm": 0.4072240889072418,
+      "learning_rate": 2e-05,
+      "loss": 0.5728,
+      "step": 2940
+    },
+    {
+      "epoch": 0.12599837697005936,
+      "grad_norm": 0.4064178168773651,
+      "learning_rate": 2e-05,
+      "loss": 0.6005,
+      "step": 2950
+    },
+    {
+      "epoch": 0.12642549011233076,
+      "grad_norm": 0.4391927123069763,
+      "learning_rate": 2e-05,
+      "loss": 0.6141,
+      "step": 2960
+    },
+    {
+      "epoch": 0.12685260325460215,
+      "grad_norm": 0.42472970485687256,
+      "learning_rate": 2e-05,
+      "loss": 0.5428,
+      "step": 2970
+    },
+    {
+      "epoch": 0.12727971639687352,
+      "grad_norm": 0.38745298981666565,
+      "learning_rate": 2e-05,
+      "loss": 0.5734,
+      "step": 2980
+    },
+    {
+      "epoch": 0.12770682953914492,
+      "grad_norm": 0.4173530042171478,
+      "learning_rate": 2e-05,
+      "loss": 0.5653,
+      "step": 2990
+    },
+    {
+      "epoch": 0.1281339426814163,
+      "grad_norm": 0.3415777087211609,
+      "learning_rate": 2e-05,
+      "loss": 0.6015,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12856105582368768,
+      "grad_norm": 0.3713918924331665,
+      "learning_rate": 2e-05,
+      "loss": 0.5837,
+      "step": 3010
+    },
+    {
+      "epoch": 0.12898816896595908,
+      "grad_norm": 0.3744640648365021,
+      "learning_rate": 2e-05,
+      "loss": 0.5736,
+      "step": 3020
+    },
+    {
+      "epoch": 0.12941528210823047,
+      "grad_norm": 0.4359869360923767,
+      "learning_rate": 2e-05,
+      "loss": 0.5568,
+      "step": 3030
+    },
+    {
+      "epoch": 0.12984239525050187,
+      "grad_norm": 0.3905504047870636,
+      "learning_rate": 2e-05,
+      "loss": 0.562,
+      "step": 3040
+    },
+    {
+      "epoch": 0.13026950839277324,
+      "grad_norm": 0.39894676208496094,
+      "learning_rate": 2e-05,
+      "loss": 0.5511,
+      "step": 3050
+    },
+    {
+      "epoch": 0.13069662153504463,
+      "grad_norm": 0.5057910084724426,
+      "learning_rate": 2e-05,
+      "loss": 0.5816,
+      "step": 3060
+    },
+    {
+      "epoch": 0.13112373467731603,
+      "grad_norm": 0.43427377939224243,
+      "learning_rate": 2e-05,
+      "loss": 0.5639,
+      "step": 3070
+    },
+    {
+      "epoch": 0.1315508478195874,
+      "grad_norm": 0.45989125967025757,
+      "learning_rate": 2e-05,
+      "loss": 0.5492,
+      "step": 3080
+    },
+    {
+      "epoch": 0.1319779609618588,
+      "grad_norm": 0.35695382952690125,
+      "learning_rate": 2e-05,
+      "loss": 0.5678,
+      "step": 3090
+    },
+    {
+      "epoch": 0.1324050741041302,
+      "grad_norm": 0.37269893288612366,
+      "learning_rate": 2e-05,
+      "loss": 0.5653,
+      "step": 3100
+    },
+    {
+      "epoch": 0.13283218724640158,
+      "grad_norm": 0.36502060294151306,
+      "learning_rate": 2e-05,
+      "loss": 0.5695,
+      "step": 3110
+    },
+    {
+      "epoch": 0.13325930038867295,
+      "grad_norm": 0.475284606218338,
+      "learning_rate": 2e-05,
+      "loss": 0.6043,
+      "step": 3120
+    },
+    {
+      "epoch": 0.13368641353094435,
+      "grad_norm": 0.48649531602859497,
+      "learning_rate": 2e-05,
+      "loss": 0.5853,
+      "step": 3130
+    },
+    {
+      "epoch": 0.13411352667321574,
+      "grad_norm": 0.39084985852241516,
+      "learning_rate": 2e-05,
+      "loss": 0.5962,
+      "step": 3140
+    },
+    {
+      "epoch": 0.1345406398154871,
+      "grad_norm": 0.38478323817253113,
+      "learning_rate": 2e-05,
+      "loss": 0.5616,
+      "step": 3150
+    },
+    {
+      "epoch": 0.1349677529577585,
+      "grad_norm": 0.5824605822563171,
+      "learning_rate": 2e-05,
+      "loss": 0.6054,
+      "step": 3160
+    },
+    {
+      "epoch": 0.1353948661000299,
+      "grad_norm": 0.4485900402069092,
+      "learning_rate": 2e-05,
+      "loss": 0.5707,
+      "step": 3170
+    },
+    {
+      "epoch": 0.1358219792423013,
+      "grad_norm": 0.375914990901947,
+      "learning_rate": 2e-05,
+      "loss": 0.5465,
+      "step": 3180
+    },
+    {
+      "epoch": 0.13624909238457267,
+      "grad_norm": 0.5320949554443359,
+      "learning_rate": 2e-05,
+      "loss": 0.5351,
+      "step": 3190
+    },
+    {
+      "epoch": 0.13667620552684406,
+      "grad_norm": 0.41607433557510376,
+      "learning_rate": 2e-05,
+      "loss": 0.5902,
+      "step": 3200
+    },
+    {
+      "epoch": 0.13710331866911546,
+      "grad_norm": 0.5325413346290588,
+      "learning_rate": 2e-05,
+      "loss": 0.5458,
+      "step": 3210
+    },
+    {
+      "epoch": 0.13753043181138683,
+      "grad_norm": 0.42464679479599,
+      "learning_rate": 2e-05,
+      "loss": 0.569,
+      "step": 3220
+    },
+    {
+      "epoch": 0.13795754495365822,
+      "grad_norm": 0.39139604568481445,
+      "learning_rate": 2e-05,
+      "loss": 0.5908,
+      "step": 3230
+    },
+    {
+      "epoch": 0.13838465809592962,
+      "grad_norm": 0.33918386697769165,
+      "learning_rate": 2e-05,
+      "loss": 0.5487,
+      "step": 3240
+    },
+    {
+      "epoch": 0.138811771238201,
+      "grad_norm": 0.36727094650268555,
+      "learning_rate": 2e-05,
+      "loss": 0.5517,
+      "step": 3250
+    },
+    {
+      "epoch": 0.13923888438047238,
+      "grad_norm": 0.4186103343963623,
+      "learning_rate": 2e-05,
+      "loss": 0.578,
+      "step": 3260
+    },
+    {
+      "epoch": 0.13966599752274378,
+      "grad_norm": 0.3756353259086609,
+      "learning_rate": 2e-05,
+      "loss": 0.5763,
+      "step": 3270
+    },
+    {
+      "epoch": 0.14009311066501517,
+      "grad_norm": 0.4280708432197571,
+      "learning_rate": 2e-05,
+      "loss": 0.6045,
+      "step": 3280
+    },
+    {
+      "epoch": 0.14052022380728654,
+      "grad_norm": 0.35054245591163635,
+      "learning_rate": 2e-05,
+      "loss": 0.6027,
+      "step": 3290
+    },
+    {
+      "epoch": 0.14094733694955794,
+      "grad_norm": 0.43539586663246155,
+      "learning_rate": 2e-05,
+      "loss": 0.6017,
+      "step": 3300
+    },
+    {
+      "epoch": 0.14137445009182933,
+      "grad_norm": 0.34701254963874817,
+      "learning_rate": 2e-05,
+      "loss": 0.5463,
+      "step": 3310
+    },
+    {
+      "epoch": 0.1418015632341007,
+      "grad_norm": 0.4053698778152466,
+      "learning_rate": 2e-05,
+      "loss": 0.6133,
+      "step": 3320
+    },
+    {
+      "epoch": 0.1422286763763721,
+      "grad_norm": 0.3809550404548645,
+      "learning_rate": 2e-05,
+      "loss": 0.55,
+      "step": 3330
+    },
+    {
+      "epoch": 0.1426557895186435,
+      "grad_norm": 0.3274977505207062,
+      "learning_rate": 2e-05,
+      "loss": 0.6049,
+      "step": 3340
+    },
+    {
+      "epoch": 0.1430829026609149,
+      "grad_norm": 0.3431304693222046,
+      "learning_rate": 2e-05,
+      "loss": 0.5482,
+      "step": 3350
+    },
+    {
+      "epoch": 0.14351001580318626,
+      "grad_norm": 0.34091097116470337,
+      "learning_rate": 2e-05,
+      "loss": 0.5533,
+      "step": 3360
+    },
+    {
+      "epoch": 0.14393712894545765,
+      "grad_norm": 0.4111207127571106,
+      "learning_rate": 2e-05,
+      "loss": 0.5553,
+      "step": 3370
+    },
+    {
+      "epoch": 0.14436424208772905,
+      "grad_norm": 0.4225037693977356,
+      "learning_rate": 2e-05,
+      "loss": 0.5631,
+      "step": 3380
+    },
+    {
+      "epoch": 0.14479135523000042,
+      "grad_norm": 0.30720216035842896,
+      "learning_rate": 2e-05,
+      "loss": 0.5672,
+      "step": 3390
+    },
+    {
+      "epoch": 0.14521846837227181,
+      "grad_norm": 0.48781946301460266,
+      "learning_rate": 2e-05,
+      "loss": 0.5506,
+      "step": 3400
+    },
+    {
+      "epoch": 0.1456455815145432,
+      "grad_norm": 0.47484657168388367,
+      "learning_rate": 2e-05,
+      "loss": 0.5671,
+      "step": 3410
+    },
+    {
+      "epoch": 0.14607269465681458,
+      "grad_norm": 0.3884461522102356,
+      "learning_rate": 2e-05,
+      "loss": 0.6055,
+      "step": 3420
+    },
+    {
+      "epoch": 0.14649980779908597,
+      "grad_norm": 0.4190621078014374,
+      "learning_rate": 2e-05,
+      "loss": 0.5712,
+      "step": 3430
+    },
+    {
+      "epoch": 0.14692692094135737,
+      "grad_norm": 0.4329921007156372,
+      "learning_rate": 2e-05,
+      "loss": 0.5785,
+      "step": 3440
+    },
+    {
+      "epoch": 0.14735403408362877,
+      "grad_norm": 0.3370278775691986,
+      "learning_rate": 2e-05,
+      "loss": 0.5372,
+      "step": 3450
+    },
+    {
+      "epoch": 0.14778114722590013,
+      "grad_norm": 0.45355620980262756,
+      "learning_rate": 2e-05,
+      "loss": 0.5367,
+      "step": 3460
+    },
+    {
+      "epoch": 0.14820826036817153,
+      "grad_norm": 0.3436107933521271,
+      "learning_rate": 2e-05,
+      "loss": 0.5738,
+      "step": 3470
+    },
+    {
+      "epoch": 0.14863537351044293,
+      "grad_norm": 0.37410539388656616,
+      "learning_rate": 2e-05,
+      "loss": 0.5551,
+      "step": 3480
+    },
+    {
+      "epoch": 0.1490624866527143,
+      "grad_norm": 0.4082183241844177,
+      "learning_rate": 2e-05,
+      "loss": 0.5552,
+      "step": 3490
+    },
+    {
+      "epoch": 0.1494895997949857,
+      "grad_norm": 0.3776927888393402,
+      "learning_rate": 2e-05,
+      "loss": 0.5556,
+      "step": 3500
+    },
+    {
+      "epoch": 0.14991671293725709,
+      "grad_norm": 0.42349398136138916,
+      "learning_rate": 2e-05,
+      "loss": 0.5685,
+      "step": 3510
+    },
+    {
+      "epoch": 0.15034382607952848,
+      "grad_norm": 0.33163750171661377,
+      "learning_rate": 2e-05,
+      "loss": 0.5862,
+      "step": 3520
+    },
+    {
+      "epoch": 0.15077093922179985,
+      "grad_norm": 0.4498125910758972,
+      "learning_rate": 2e-05,
+      "loss": 0.5716,
+      "step": 3530
+    },
+    {
+      "epoch": 0.15119805236407124,
+      "grad_norm": 0.3540550172328949,
+      "learning_rate": 2e-05,
+      "loss": 0.5663,
+      "step": 3540
+    },
+    {
+      "epoch": 0.15162516550634264,
+      "grad_norm": 0.37196221947669983,
+      "learning_rate": 2e-05,
+      "loss": 0.5344,
+      "step": 3550
+    },
+    {
+      "epoch": 0.152052278648614,
+      "grad_norm": 0.37784308195114136,
+      "learning_rate": 2e-05,
+      "loss": 0.577,
+      "step": 3560
+    },
+    {
+      "epoch": 0.1524793917908854,
+      "grad_norm": 0.33470308780670166,
+      "learning_rate": 2e-05,
+      "loss": 0.5408,
+      "step": 3570
+    },
+    {
+      "epoch": 0.1529065049331568,
+      "grad_norm": 0.48294422030448914,
+      "learning_rate": 2e-05,
+      "loss": 0.5472,
+      "step": 3580
+    },
+    {
+      "epoch": 0.15333361807542817,
+      "grad_norm": 0.38164424896240234,
+      "learning_rate": 2e-05,
+      "loss": 0.5884,
+      "step": 3590
+    },
+    {
+      "epoch": 0.15376073121769956,
+      "grad_norm": 0.37437787652015686,
+      "learning_rate": 2e-05,
+      "loss": 0.5879,
+      "step": 3600
+    },
+    {
+      "epoch": 0.15418784435997096,
+      "grad_norm": 0.39613077044487,
+      "learning_rate": 2e-05,
+      "loss": 0.5727,
+      "step": 3610
+    },
+    {
+      "epoch": 0.15461495750224236,
+      "grad_norm": 0.5033529996871948,
+      "learning_rate": 2e-05,
+      "loss": 0.5542,
+      "step": 3620
+    },
+    {
+      "epoch": 0.15504207064451372,
+      "grad_norm": 0.5393747687339783,
+      "learning_rate": 2e-05,
+      "loss": 0.5642,
+      "step": 3630
+    },
+    {
+      "epoch": 0.15546918378678512,
+      "grad_norm": 0.40253424644470215,
+      "learning_rate": 2e-05,
+      "loss": 0.5542,
+      "step": 3640
+    },
+    {
+      "epoch": 0.15589629692905652,
+      "grad_norm": 0.36225783824920654,
+      "learning_rate": 2e-05,
+      "loss": 0.5668,
+      "step": 3650
+    },
+    {
+      "epoch": 0.15632341007132788,
+      "grad_norm": 0.3562473952770233,
+      "learning_rate": 2e-05,
+      "loss": 0.5654,
+      "step": 3660
+    },
+    {
+      "epoch": 0.15675052321359928,
+      "grad_norm": 0.40967217087745667,
+      "learning_rate": 2e-05,
+      "loss": 0.5663,
+      "step": 3670
+    },
+    {
+      "epoch": 0.15717763635587068,
+      "grad_norm": 0.3644748032093048,
+      "learning_rate": 2e-05,
+      "loss": 0.5599,
+      "step": 3680
+    },
+    {
+      "epoch": 0.15760474949814207,
+      "grad_norm": 0.4053981304168701,
+      "learning_rate": 2e-05,
+      "loss": 0.5457,
+      "step": 3690
+    },
+    {
+      "epoch": 0.15803186264041344,
+      "grad_norm": 0.41403481364250183,
+      "learning_rate": 2e-05,
+      "loss": 0.5639,
+      "step": 3700
+    },
+    {
+      "epoch": 0.15845897578268484,
+      "grad_norm": 0.38169658184051514,
+      "learning_rate": 2e-05,
+      "loss": 0.5451,
+      "step": 3710
+    },
+    {
+      "epoch": 0.15888608892495623,
+      "grad_norm": 0.4290609359741211,
+      "learning_rate": 2e-05,
+      "loss": 0.6034,
+      "step": 3720
+    },
+    {
+      "epoch": 0.1593132020672276,
+      "grad_norm": 0.3592872619628906,
+      "learning_rate": 2e-05,
+      "loss": 0.5511,
+      "step": 3730
+    },
+    {
+      "epoch": 0.159740315209499,
+      "grad_norm": 0.4039403796195984,
+      "learning_rate": 2e-05,
+      "loss": 0.5588,
+      "step": 3740
+    },
+    {
+      "epoch": 0.1601674283517704,
+      "grad_norm": 0.44793298840522766,
+      "learning_rate": 2e-05,
+      "loss": 0.5509,
+      "step": 3750
+    },
+    {
+      "epoch": 0.16059454149404176,
+      "grad_norm": 0.3872862160205841,
+      "learning_rate": 2e-05,
+      "loss": 0.5735,
+      "step": 3760
+    },
+    {
+      "epoch": 0.16102165463631316,
+      "grad_norm": 0.4395015239715576,
+      "learning_rate": 2e-05,
+      "loss": 0.589,
+      "step": 3770
+    },
+    {
+      "epoch": 0.16144876777858455,
+      "grad_norm": 0.4228643774986267,
+      "learning_rate": 2e-05,
+      "loss": 0.5546,
+      "step": 3780
+    },
+    {
+      "epoch": 0.16187588092085595,
+      "grad_norm": 0.46395066380500793,
+      "learning_rate": 2e-05,
+      "loss": 0.5642,
+      "step": 3790
+    },
+    {
+      "epoch": 0.16230299406312731,
+      "grad_norm": 0.415254145860672,
+      "learning_rate": 2e-05,
+      "loss": 0.5434,
+      "step": 3800
+    },
+    {
+      "epoch": 0.1627301072053987,
+      "grad_norm": 0.8578656315803528,
+      "learning_rate": 2e-05,
+      "loss": 0.5251,
+      "step": 3810
+    },
+    {
+      "epoch": 0.1631572203476701,
+      "grad_norm": 0.3627680838108063,
+      "learning_rate": 2e-05,
+      "loss": 0.5547,
+      "step": 3820
+    },
+    {
+      "epoch": 0.16358433348994147,
+      "grad_norm": 0.37490200996398926,
+      "learning_rate": 2e-05,
+      "loss": 0.5601,
+      "step": 3830
+    },
+    {
+      "epoch": 0.16401144663221287,
+      "grad_norm": 0.5282700061798096,
+      "learning_rate": 2e-05,
+      "loss": 0.5605,
+      "step": 3840
+    },
+    {
+      "epoch": 0.16443855977448427,
+      "grad_norm": 0.39495882391929626,
+      "learning_rate": 2e-05,
+      "loss": 0.5799,
+      "step": 3850
+    },
+    {
+      "epoch": 0.16486567291675566,
+      "grad_norm": 0.42333877086639404,
+      "learning_rate": 2e-05,
+      "loss": 0.5534,
+      "step": 3860
+    },
+    {
+      "epoch": 0.16529278605902703,
+      "grad_norm": 0.6054421663284302,
+      "learning_rate": 2e-05,
+      "loss": 0.5676,
+      "step": 3870
+    },
+    {
+      "epoch": 0.16571989920129843,
+      "grad_norm": 0.380671888589859,
+      "learning_rate": 2e-05,
+      "loss": 0.5676,
+      "step": 3880
+    },
+    {
+      "epoch": 0.16614701234356982,
+      "grad_norm": 0.39355093240737915,
+      "learning_rate": 2e-05,
+      "loss": 0.5397,
+      "step": 3890
+    },
+    {
+      "epoch": 0.1665741254858412,
+      "grad_norm": 0.38664868474006653,
+      "learning_rate": 2e-05,
+      "loss": 0.529,
+      "step": 3900
+    },
+    {
+      "epoch": 0.16700123862811259,
+      "grad_norm": 0.3793322443962097,
+      "learning_rate": 2e-05,
+      "loss": 0.5529,
+      "step": 3910
+    },
+    {
+      "epoch": 0.16742835177038398,
+      "grad_norm": 0.3703729212284088,
+      "learning_rate": 2e-05,
+      "loss": 0.5504,
+      "step": 3920
+    },
+    {
+      "epoch": 0.16785546491265535,
+      "grad_norm": 0.3335875868797302,
+      "learning_rate": 2e-05,
+      "loss": 0.5619,
+      "step": 3930
+    },
+    {
+      "epoch": 0.16828257805492675,
+      "grad_norm": 0.3511432409286499,
+      "learning_rate": 2e-05,
+      "loss": 0.5464,
+      "step": 3940
+    },
+    {
+      "epoch": 0.16870969119719814,
+      "grad_norm": 0.4855042099952698,
+      "learning_rate": 2e-05,
+      "loss": 0.5644,
+      "step": 3950
+    },
+    {
+      "epoch": 0.16913680433946954,
+      "grad_norm": 0.4055890738964081,
+      "learning_rate": 2e-05,
+      "loss": 0.5676,
+      "step": 3960
+    },
+    {
+      "epoch": 0.1695639174817409,
+      "grad_norm": 0.3778741657733917,
+      "learning_rate": 2e-05,
+      "loss": 0.5442,
+      "step": 3970
+    },
+    {
+      "epoch": 0.1699910306240123,
+      "grad_norm": 0.41490328311920166,
+      "learning_rate": 2e-05,
+      "loss": 0.5577,
+      "step": 3980
+    },
+    {
+      "epoch": 0.1704181437662837,
+      "grad_norm": 0.5095113515853882,
+      "learning_rate": 2e-05,
+      "loss": 0.581,
+      "step": 3990
+    },
+    {
+      "epoch": 0.17084525690855507,
+      "grad_norm": 0.37108686566352844,
+      "learning_rate": 2e-05,
+      "loss": 0.5947,
+      "step": 4000
+    },
+    {
+      "epoch": 0.17127237005082646,
+      "grad_norm": 0.4250836968421936,
+      "learning_rate": 2e-05,
+      "loss": 0.51,
+      "step": 4010
+    },
+    {
+      "epoch": 0.17169948319309786,
+      "grad_norm": 0.40347006916999817,
+      "learning_rate": 2e-05,
+      "loss": 0.5629,
+      "step": 4020
+    },
+    {
+      "epoch": 0.17212659633536925,
+      "grad_norm": 0.37307119369506836,
+      "learning_rate": 2e-05,
+      "loss": 0.5598,
+      "step": 4030
+    },
+    {
+      "epoch": 0.17255370947764062,
+      "grad_norm": 0.3558986186981201,
+      "learning_rate": 2e-05,
+      "loss": 0.5684,
+      "step": 4040
+    },
+    {
+      "epoch": 0.17298082261991202,
+      "grad_norm": 0.40337949991226196,
+      "learning_rate": 2e-05,
+      "loss": 0.5578,
+      "step": 4050
+    },
+    {
+      "epoch": 0.1734079357621834,
+      "grad_norm": 0.34226059913635254,
+      "learning_rate": 2e-05,
+      "loss": 0.5652,
+      "step": 4060
+    },
+    {
+      "epoch": 0.17383504890445478,
+      "grad_norm": 0.3506963849067688,
+      "learning_rate": 2e-05,
+      "loss": 0.5598,
+      "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 sha256:50bce28aa60b5e52e815b7feb16c8a64a1dbca440f3f650b1debb1f3844ff3e1
+size 7953