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 sha256:88393ee826ef53c82e0c299fc8e3c02c60974ee2a581943f708fec4596cc8a60
+size 4902257696

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eff30a37d3f5add14a4e10789c0406bb6d671ea746f75d1cd1e9d110acdc7c6
+size 4915960368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5735e8cf0dd92e56539560f300ecbded1457689956ec1d39525407373527ac0
+size 4983068496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0901b5dee8979300cc377d75fa70a923157b78f71723c0caf983ff6d5787c387
+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": 0.21301093839953944,
+  "eval_steps": 500,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005233683990160674,
+      "grad_norm": 1.1370724439620972,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.8003,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010467367980321349,
+      "grad_norm": 0.9877656102180481,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.7587,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015701051970482022,
+      "grad_norm": 0.8628589510917664,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.7476,
+      "step": 30
+    },
+    {
+      "epoch": 0.0020934735960642698,
+      "grad_norm": 0.7837583422660828,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.7334,
+      "step": 40
+    },
+    {
+      "epoch": 0.002616841995080337,
+      "grad_norm": 0.7342932224273682,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.7397,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031402103940964044,
+      "grad_norm": 0.9271304607391357,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.7296,
+      "step": 60
+    },
+    {
+      "epoch": 0.0036635787931124718,
+      "grad_norm": 0.8066033720970154,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.6864,
+      "step": 70
+    },
+    {
+      "epoch": 0.0041869471921285395,
+      "grad_norm": 0.8114457726478577,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.6792,
+      "step": 80
+    },
+    {
+      "epoch": 0.004710315591144607,
+      "grad_norm": 0.8880093097686768,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.7508,
+      "step": 90
+    },
+    {
+      "epoch": 0.005233683990160674,
+      "grad_norm": 1.1273611783981323,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.6849,
+      "step": 100
+    },
+    {
+      "epoch": 0.0057570523891767415,
+      "grad_norm": 0.7791317701339722,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.698,
+      "step": 110
+    },
+    {
+      "epoch": 0.006280420788192809,
+      "grad_norm": 0.8140974044799805,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.6947,
+      "step": 120
+    },
+    {
+      "epoch": 0.006803789187208876,
+      "grad_norm": 0.8656443357467651,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.7158,
+      "step": 130
+    },
+    {
+      "epoch": 0.0073271575862249435,
+      "grad_norm": 0.744526743888855,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.6701,
+      "step": 140
+    },
+    {
+      "epoch": 0.00785052598524101,
+      "grad_norm": 0.7715036273002625,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.6794,
+      "step": 150
+    },
+    {
+      "epoch": 0.008373894384257079,
+      "grad_norm": 0.7816882729530334,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.7059,
+      "step": 160
+    },
+    {
+      "epoch": 0.008897262783273146,
+      "grad_norm": 0.7964625954627991,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.6954,
+      "step": 170
+    },
+    {
+      "epoch": 0.009420631182289214,
+      "grad_norm": 1.0829215049743652,
+      "learning_rate": 2e-05,
+      "loss": 0.6888,
+      "step": 180
+    },
+    {
+      "epoch": 0.00994399958130528,
+      "grad_norm": 0.6891264319419861,
+      "learning_rate": 2e-05,
+      "loss": 0.6539,
+      "step": 190
+    },
+    {
+      "epoch": 0.010467367980321348,
+      "grad_norm": 0.7293897867202759,
+      "learning_rate": 2e-05,
+      "loss": 0.7164,
+      "step": 200
+    },
+    {
+      "epoch": 0.010990736379337415,
+      "grad_norm": 0.6318921446800232,
+      "learning_rate": 2e-05,
+      "loss": 0.7084,
+      "step": 210
+    },
+    {
+      "epoch": 0.011514104778353483,
+      "grad_norm": 0.6405470371246338,
+      "learning_rate": 2e-05,
+      "loss": 0.6812,
+      "step": 220
+    },
+    {
+      "epoch": 0.012037473177369551,
+      "grad_norm": 0.6632219552993774,
+      "learning_rate": 2e-05,
+      "loss": 0.6733,
+      "step": 230
+    },
+    {
+      "epoch": 0.012560841576385618,
+      "grad_norm": 0.7196585536003113,
+      "learning_rate": 2e-05,
+      "loss": 0.6835,
+      "step": 240
+    },
+    {
+      "epoch": 0.013084209975401686,
+      "grad_norm": 0.5942214131355286,
+      "learning_rate": 2e-05,
+      "loss": 0.6613,
+      "step": 250
+    },
+    {
+      "epoch": 0.013607578374417752,
+      "grad_norm": 0.5716996788978577,
+      "learning_rate": 2e-05,
+      "loss": 0.6759,
+      "step": 260
+    },
+    {
+      "epoch": 0.01413094677343382,
+      "grad_norm": 0.5713549256324768,
+      "learning_rate": 2e-05,
+      "loss": 0.7041,
+      "step": 270
+    },
+    {
+      "epoch": 0.014654315172449887,
+      "grad_norm": 0.5658433437347412,
+      "learning_rate": 2e-05,
+      "loss": 0.6866,
+      "step": 280
+    },
+    {
+      "epoch": 0.015177683571465955,
+      "grad_norm": 0.5381125211715698,
+      "learning_rate": 2e-05,
+      "loss": 0.7024,
+      "step": 290
+    },
+    {
+      "epoch": 0.01570105197048202,
+      "grad_norm": 0.5079479217529297,
+      "learning_rate": 2e-05,
+      "loss": 0.686,
+      "step": 300
+    },
+    {
+      "epoch": 0.016224420369498088,
+      "grad_norm": 0.5530030727386475,
+      "learning_rate": 2e-05,
+      "loss": 0.6912,
+      "step": 310
+    },
+    {
+      "epoch": 0.016747788768514158,
+      "grad_norm": 0.5396811962127686,
+      "learning_rate": 2e-05,
+      "loss": 0.6751,
+      "step": 320
+    },
+    {
+      "epoch": 0.017271157167530225,
+      "grad_norm": 0.4894005060195923,
+      "learning_rate": 2e-05,
+      "loss": 0.6649,
+      "step": 330
+    },
+    {
+      "epoch": 0.01779452556654629,
+      "grad_norm": 0.5230134129524231,
+      "learning_rate": 2e-05,
+      "loss": 0.684,
+      "step": 340
+    },
+    {
+      "epoch": 0.01831789396556236,
+      "grad_norm": 0.5332402586936951,
+      "learning_rate": 2e-05,
+      "loss": 0.6767,
+      "step": 350
+    },
+    {
+      "epoch": 0.018841262364578427,
+      "grad_norm": 0.5048417448997498,
+      "learning_rate": 2e-05,
+      "loss": 0.6922,
+      "step": 360
+    },
+    {
+      "epoch": 0.019364630763594494,
+      "grad_norm": 0.5345087051391602,
+      "learning_rate": 2e-05,
+      "loss": 0.6976,
+      "step": 370
+    },
+    {
+      "epoch": 0.01988799916261056,
+      "grad_norm": 0.511880099773407,
+      "learning_rate": 2e-05,
+      "loss": 0.6814,
+      "step": 380
+    },
+    {
+      "epoch": 0.02041136756162663,
+      "grad_norm": 0.46280574798583984,
+      "learning_rate": 2e-05,
+      "loss": 0.6566,
+      "step": 390
+    },
+    {
+      "epoch": 0.020934735960642697,
+      "grad_norm": 0.464054137468338,
+      "learning_rate": 2e-05,
+      "loss": 0.6483,
+      "step": 400
+    },
+    {
+      "epoch": 0.021458104359658763,
+      "grad_norm": 0.5449008941650391,
+      "learning_rate": 2e-05,
+      "loss": 0.6841,
+      "step": 410
+    },
+    {
+      "epoch": 0.02198147275867483,
+      "grad_norm": 0.5352079272270203,
+      "learning_rate": 2e-05,
+      "loss": 0.6604,
+      "step": 420
+    },
+    {
+      "epoch": 0.0225048411576909,
+      "grad_norm": 0.5088271498680115,
+      "learning_rate": 2e-05,
+      "loss": 0.6683,
+      "step": 430
+    },
+    {
+      "epoch": 0.023028209556706966,
+      "grad_norm": 0.5593430399894714,
+      "learning_rate": 2e-05,
+      "loss": 0.6795,
+      "step": 440
+    },
+    {
+      "epoch": 0.023551577955723033,
+      "grad_norm": 0.507481575012207,
+      "learning_rate": 2e-05,
+      "loss": 0.6654,
+      "step": 450
+    },
+    {
+      "epoch": 0.024074946354739103,
+      "grad_norm": 0.4815616011619568,
+      "learning_rate": 2e-05,
+      "loss": 0.6843,
+      "step": 460
+    },
+    {
+      "epoch": 0.02459831475375517,
+      "grad_norm": 0.5703353881835938,
+      "learning_rate": 2e-05,
+      "loss": 0.6598,
+      "step": 470
+    },
+    {
+      "epoch": 0.025121683152771235,
+      "grad_norm": 0.48705339431762695,
+      "learning_rate": 2e-05,
+      "loss": 0.6614,
+      "step": 480
+    },
+    {
+      "epoch": 0.025645051551787302,
+      "grad_norm": 0.547533392906189,
+      "learning_rate": 2e-05,
+      "loss": 0.6585,
+      "step": 490
+    },
+    {
+      "epoch": 0.026168419950803372,
+      "grad_norm": 0.6569129228591919,
+      "learning_rate": 2e-05,
+      "loss": 0.6716,
+      "step": 500
+    },
+    {
+      "epoch": 0.02669178834981944,
+      "grad_norm": 0.5733374357223511,
+      "learning_rate": 2e-05,
+      "loss": 0.6465,
+      "step": 510
+    },
+    {
+      "epoch": 0.027215156748835505,
+      "grad_norm": 0.4885842502117157,
+      "learning_rate": 2e-05,
+      "loss": 0.682,
+      "step": 520
+    },
+    {
+      "epoch": 0.02773852514785157,
+      "grad_norm": 0.42785435914993286,
+      "learning_rate": 2e-05,
+      "loss": 0.6594,
+      "step": 530
+    },
+    {
+      "epoch": 0.02826189354686764,
+      "grad_norm": 0.4955022931098938,
+      "learning_rate": 2e-05,
+      "loss": 0.6674,
+      "step": 540
+    },
+    {
+      "epoch": 0.028785261945883708,
+      "grad_norm": 0.48021453619003296,
+      "learning_rate": 2e-05,
+      "loss": 0.6796,
+      "step": 550
+    },
+    {
+      "epoch": 0.029308630344899774,
+      "grad_norm": 0.4767313301563263,
+      "learning_rate": 2e-05,
+      "loss": 0.6865,
+      "step": 560
+    },
+    {
+      "epoch": 0.029831998743915844,
+      "grad_norm": 0.5284311771392822,
+      "learning_rate": 2e-05,
+      "loss": 0.6489,
+      "step": 570
+    },
+    {
+      "epoch": 0.03035536714293191,
+      "grad_norm": 0.4461924731731415,
+      "learning_rate": 2e-05,
+      "loss": 0.686,
+      "step": 580
+    },
+    {
+      "epoch": 0.030878735541947977,
+      "grad_norm": 0.45115983486175537,
+      "learning_rate": 2e-05,
+      "loss": 0.6539,
+      "step": 590
+    },
+    {
+      "epoch": 0.03140210394096404,
+      "grad_norm": 0.5064119100570679,
+      "learning_rate": 2e-05,
+      "loss": 0.6946,
+      "step": 600
+    },
+    {
+      "epoch": 0.03192547233998011,
+      "grad_norm": 0.5319550037384033,
+      "learning_rate": 2e-05,
+      "loss": 0.645,
+      "step": 610
+    },
+    {
+      "epoch": 0.032448840738996176,
+      "grad_norm": 0.4419703781604767,
+      "learning_rate": 2e-05,
+      "loss": 0.7003,
+      "step": 620
+    },
+    {
+      "epoch": 0.03297220913801225,
+      "grad_norm": 0.42887452244758606,
+      "learning_rate": 2e-05,
+      "loss": 0.6783,
+      "step": 630
+    },
+    {
+      "epoch": 0.033495577537028316,
+      "grad_norm": 0.46661144495010376,
+      "learning_rate": 2e-05,
+      "loss": 0.6686,
+      "step": 640
+    },
+    {
+      "epoch": 0.03401894593604438,
+      "grad_norm": 0.5283986330032349,
+      "learning_rate": 2e-05,
+      "loss": 0.6679,
+      "step": 650
+    },
+    {
+      "epoch": 0.03454231433506045,
+      "grad_norm": 0.5113454461097717,
+      "learning_rate": 2e-05,
+      "loss": 0.6506,
+      "step": 660
+    },
+    {
+      "epoch": 0.035065682734076516,
+      "grad_norm": 0.4744948148727417,
+      "learning_rate": 2e-05,
+      "loss": 0.6724,
+      "step": 670
+    },
+    {
+      "epoch": 0.03558905113309258,
+      "grad_norm": 0.49696066975593567,
+      "learning_rate": 2e-05,
+      "loss": 0.6652,
+      "step": 680
+    },
+    {
+      "epoch": 0.03611241953210865,
+      "grad_norm": 0.7813011407852173,
+      "learning_rate": 2e-05,
+      "loss": 0.6621,
+      "step": 690
+    },
+    {
+      "epoch": 0.03663578793112472,
+      "grad_norm": 0.49424248933792114,
+      "learning_rate": 2e-05,
+      "loss": 0.6727,
+      "step": 700
+    },
+    {
+      "epoch": 0.03715915633014079,
+      "grad_norm": 0.4447154104709625,
+      "learning_rate": 2e-05,
+      "loss": 0.6659,
+      "step": 710
+    },
+    {
+      "epoch": 0.037682524729156855,
+      "grad_norm": 0.44892066717147827,
+      "learning_rate": 2e-05,
+      "loss": 0.6554,
+      "step": 720
+    },
+    {
+      "epoch": 0.03820589312817292,
+      "grad_norm": 0.49734535813331604,
+      "learning_rate": 2e-05,
+      "loss": 0.6779,
+      "step": 730
+    },
+    {
+      "epoch": 0.03872926152718899,
+      "grad_norm": 0.5591990947723389,
+      "learning_rate": 2e-05,
+      "loss": 0.6927,
+      "step": 740
+    },
+    {
+      "epoch": 0.039252629926205054,
+      "grad_norm": 0.45224255323410034,
+      "learning_rate": 2e-05,
+      "loss": 0.6398,
+      "step": 750
+    },
+    {
+      "epoch": 0.03977599832522112,
+      "grad_norm": 0.41793182492256165,
+      "learning_rate": 2e-05,
+      "loss": 0.6668,
+      "step": 760
+    },
+    {
+      "epoch": 0.04029936672423719,
+      "grad_norm": 0.43993815779685974,
+      "learning_rate": 2e-05,
+      "loss": 0.6456,
+      "step": 770
+    },
+    {
+      "epoch": 0.04082273512325326,
+      "grad_norm": 0.44372230768203735,
+      "learning_rate": 2e-05,
+      "loss": 0.6669,
+      "step": 780
+    },
+    {
+      "epoch": 0.04134610352226933,
+      "grad_norm": 0.4827944040298462,
+      "learning_rate": 2e-05,
+      "loss": 0.657,
+      "step": 790
+    },
+    {
+      "epoch": 0.041869471921285394,
+      "grad_norm": 0.4187488257884979,
+      "learning_rate": 2e-05,
+      "loss": 0.6456,
+      "step": 800
+    },
+    {
+      "epoch": 0.04239284032030146,
+      "grad_norm": 0.47213008999824524,
+      "learning_rate": 2e-05,
+      "loss": 0.6555,
+      "step": 810
+    },
+    {
+      "epoch": 0.042916208719317527,
+      "grad_norm": 0.43557852506637573,
+      "learning_rate": 2e-05,
+      "loss": 0.6545,
+      "step": 820
+    },
+    {
+      "epoch": 0.04343957711833359,
+      "grad_norm": 0.45871806144714355,
+      "learning_rate": 2e-05,
+      "loss": 0.6538,
+      "step": 830
+    },
+    {
+      "epoch": 0.04396294551734966,
+      "grad_norm": 0.46028947830200195,
+      "learning_rate": 2e-05,
+      "loss": 0.6356,
+      "step": 840
+    },
+    {
+      "epoch": 0.04448631391636573,
+      "grad_norm": 0.548116147518158,
+      "learning_rate": 2e-05,
+      "loss": 0.6872,
+      "step": 850
+    },
+    {
+      "epoch": 0.0450096823153818,
+      "grad_norm": 0.49427151679992676,
+      "learning_rate": 2e-05,
+      "loss": 0.6372,
+      "step": 860
+    },
+    {
+      "epoch": 0.045533050714397866,
+      "grad_norm": 0.46103739738464355,
+      "learning_rate": 2e-05,
+      "loss": 0.6991,
+      "step": 870
+    },
+    {
+      "epoch": 0.04605641911341393,
+      "grad_norm": 0.4400480091571808,
+      "learning_rate": 2e-05,
+      "loss": 0.667,
+      "step": 880
+    },
+    {
+      "epoch": 0.04657978751243,
+      "grad_norm": 0.45002153515815735,
+      "learning_rate": 2e-05,
+      "loss": 0.6582,
+      "step": 890
+    },
+    {
+      "epoch": 0.047103155911446065,
+      "grad_norm": 0.44472604990005493,
+      "learning_rate": 2e-05,
+      "loss": 0.6706,
+      "step": 900
+    },
+    {
+      "epoch": 0.04762652431046213,
+      "grad_norm": 0.4121211767196655,
+      "learning_rate": 2e-05,
+      "loss": 0.6602,
+      "step": 910
+    },
+    {
+      "epoch": 0.048149892709478205,
+      "grad_norm": 0.5010108351707458,
+      "learning_rate": 2e-05,
+      "loss": 0.6761,
+      "step": 920
+    },
+    {
+      "epoch": 0.04867326110849427,
+      "grad_norm": 0.45920342206954956,
+      "learning_rate": 2e-05,
+      "loss": 0.6671,
+      "step": 930
+    },
+    {
+      "epoch": 0.04919662950751034,
+      "grad_norm": 0.5177173018455505,
+      "learning_rate": 2e-05,
+      "loss": 0.652,
+      "step": 940
+    },
+    {
+      "epoch": 0.049719997906526404,
+      "grad_norm": 0.49086499214172363,
+      "learning_rate": 2e-05,
+      "loss": 0.6795,
+      "step": 950
+    },
+    {
+      "epoch": 0.05024336630554247,
+      "grad_norm": 0.582841157913208,
+      "learning_rate": 2e-05,
+      "loss": 0.6376,
+      "step": 960
+    },
+    {
+      "epoch": 0.05076673470455854,
+      "grad_norm": 0.4690440595149994,
+      "learning_rate": 2e-05,
+      "loss": 0.6465,
+      "step": 970
+    },
+    {
+      "epoch": 0.051290103103574604,
+      "grad_norm": 0.45363402366638184,
+      "learning_rate": 2e-05,
+      "loss": 0.6511,
+      "step": 980
+    },
+    {
+      "epoch": 0.05181347150259067,
+      "grad_norm": 0.43920376896858215,
+      "learning_rate": 2e-05,
+      "loss": 0.6943,
+      "step": 990
+    },
+    {
+      "epoch": 0.052336839901606744,
+      "grad_norm": 0.421144038438797,
+      "learning_rate": 2e-05,
+      "loss": 0.6434,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05286020830062281,
+      "grad_norm": 0.45188188552856445,
+      "learning_rate": 2e-05,
+      "loss": 0.6467,
+      "step": 1010
+    },
+    {
+      "epoch": 0.05338357669963888,
+      "grad_norm": 0.4339853823184967,
+      "learning_rate": 2e-05,
+      "loss": 0.6596,
+      "step": 1020
+    },
+    {
+      "epoch": 0.05390694509865494,
+      "grad_norm": 0.4234607517719269,
+      "learning_rate": 2e-05,
+      "loss": 0.674,
+      "step": 1030
+    },
+    {
+      "epoch": 0.05443031349767101,
+      "grad_norm": 0.46552717685699463,
+      "learning_rate": 2e-05,
+      "loss": 0.6649,
+      "step": 1040
+    },
+    {
+      "epoch": 0.054953681896687076,
+      "grad_norm": 0.4405843913555145,
+      "learning_rate": 2e-05,
+      "loss": 0.6577,
+      "step": 1050
+    },
+    {
+      "epoch": 0.05547705029570314,
+      "grad_norm": 0.5044958591461182,
+      "learning_rate": 2e-05,
+      "loss": 0.6152,
+      "step": 1060
+    },
+    {
+      "epoch": 0.056000418694719216,
+      "grad_norm": 0.43265852332115173,
+      "learning_rate": 2e-05,
+      "loss": 0.6317,
+      "step": 1070
+    },
+    {
+      "epoch": 0.05652378709373528,
+      "grad_norm": 0.41526952385902405,
+      "learning_rate": 2e-05,
+      "loss": 0.6501,
+      "step": 1080
+    },
+    {
+      "epoch": 0.05704715549275135,
+      "grad_norm": 0.43947693705558777,
+      "learning_rate": 2e-05,
+      "loss": 0.6542,
+      "step": 1090
+    },
+    {
+      "epoch": 0.057570523891767415,
+      "grad_norm": 0.4375130534172058,
+      "learning_rate": 2e-05,
+      "loss": 0.671,
+      "step": 1100
+    },
+    {
+      "epoch": 0.05809389229078348,
+      "grad_norm": 0.4554004371166229,
+      "learning_rate": 2e-05,
+      "loss": 0.6507,
+      "step": 1110
+    },
+    {
+      "epoch": 0.05861726068979955,
+      "grad_norm": 0.5064834356307983,
+      "learning_rate": 2e-05,
+      "loss": 0.6467,
+      "step": 1120
+    },
+    {
+      "epoch": 0.059140629088815615,
+      "grad_norm": 0.446809321641922,
+      "learning_rate": 2e-05,
+      "loss": 0.6751,
+      "step": 1130
+    },
+    {
+      "epoch": 0.05966399748783169,
+      "grad_norm": 0.4745899736881256,
+      "learning_rate": 2e-05,
+      "loss": 0.6564,
+      "step": 1140
+    },
+    {
+      "epoch": 0.060187365886847755,
+      "grad_norm": 0.5119066834449768,
+      "learning_rate": 2e-05,
+      "loss": 0.6618,
+      "step": 1150
+    },
+    {
+      "epoch": 0.06071073428586382,
+      "grad_norm": 0.41898113489151,
+      "learning_rate": 2e-05,
+      "loss": 0.6622,
+      "step": 1160
+    },
+    {
+      "epoch": 0.06123410268487989,
+      "grad_norm": 0.6409226059913635,
+      "learning_rate": 2e-05,
+      "loss": 0.6708,
+      "step": 1170
+    },
+    {
+      "epoch": 0.061757471083895954,
+      "grad_norm": 0.439377099275589,
+      "learning_rate": 2e-05,
+      "loss": 0.6473,
+      "step": 1180
+    },
+    {
+      "epoch": 0.06228083948291202,
+      "grad_norm": 0.4160749316215515,
+      "learning_rate": 2e-05,
+      "loss": 0.6798,
+      "step": 1190
+    },
+    {
+      "epoch": 0.06280420788192809,
+      "grad_norm": 0.5204553604125977,
+      "learning_rate": 2e-05,
+      "loss": 0.6866,
+      "step": 1200
+    },
+    {
+      "epoch": 0.06332757628094415,
+      "grad_norm": 0.48897305130958557,
+      "learning_rate": 2e-05,
+      "loss": 0.6618,
+      "step": 1210
+    },
+    {
+      "epoch": 0.06385094467996022,
+      "grad_norm": 0.45014750957489014,
+      "learning_rate": 2e-05,
+      "loss": 0.6647,
+      "step": 1220
+    },
+    {
+      "epoch": 0.06437431307897629,
+      "grad_norm": 0.4595189690589905,
+      "learning_rate": 2e-05,
+      "loss": 0.6625,
+      "step": 1230
+    },
+    {
+      "epoch": 0.06489768147799235,
+      "grad_norm": 0.49671754240989685,
+      "learning_rate": 2e-05,
+      "loss": 0.663,
+      "step": 1240
+    },
+    {
+      "epoch": 0.06542104987700843,
+      "grad_norm": 0.44070637226104736,
+      "learning_rate": 2e-05,
+      "loss": 0.6613,
+      "step": 1250
+    },
+    {
+      "epoch": 0.0659444182760245,
+      "grad_norm": 0.45897576212882996,
+      "learning_rate": 2e-05,
+      "loss": 0.6516,
+      "step": 1260
+    },
+    {
+      "epoch": 0.06646778667504057,
+      "grad_norm": 0.4450547695159912,
+      "learning_rate": 2e-05,
+      "loss": 0.641,
+      "step": 1270
+    },
+    {
+      "epoch": 0.06699115507405663,
+      "grad_norm": 0.4288750886917114,
+      "learning_rate": 2e-05,
+      "loss": 0.6656,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0675145234730727,
+      "grad_norm": 0.47525206208229065,
+      "learning_rate": 2e-05,
+      "loss": 0.6915,
+      "step": 1290
+    },
+    {
+      "epoch": 0.06803789187208877,
+      "grad_norm": 0.41285258531570435,
+      "learning_rate": 2e-05,
+      "loss": 0.6401,
+      "step": 1300
+    },
+    {
+      "epoch": 0.06856126027110483,
+      "grad_norm": 0.46445295214653015,
+      "learning_rate": 2e-05,
+      "loss": 0.6692,
+      "step": 1310
+    },
+    {
+      "epoch": 0.0690846286701209,
+      "grad_norm": 0.44153061509132385,
+      "learning_rate": 2e-05,
+      "loss": 0.6291,
+      "step": 1320
+    },
+    {
+      "epoch": 0.06960799706913696,
+      "grad_norm": 0.7016943693161011,
+      "learning_rate": 2e-05,
+      "loss": 0.6405,
+      "step": 1330
+    },
+    {
+      "epoch": 0.07013136546815303,
+      "grad_norm": 0.498710572719574,
+      "learning_rate": 2e-05,
+      "loss": 0.6433,
+      "step": 1340
+    },
+    {
+      "epoch": 0.0706547338671691,
+      "grad_norm": 0.4415338337421417,
+      "learning_rate": 2e-05,
+      "loss": 0.673,
+      "step": 1350
+    },
+    {
+      "epoch": 0.07117810226618516,
+      "grad_norm": 0.5377183556556702,
+      "learning_rate": 2e-05,
+      "loss": 0.6556,
+      "step": 1360
+    },
+    {
+      "epoch": 0.07170147066520123,
+      "grad_norm": 0.40461525321006775,
+      "learning_rate": 2e-05,
+      "loss": 0.6384,
+      "step": 1370
+    },
+    {
+      "epoch": 0.0722248390642173,
+      "grad_norm": 0.4240797758102417,
+      "learning_rate": 2e-05,
+      "loss": 0.6467,
+      "step": 1380
+    },
+    {
+      "epoch": 0.07274820746323336,
+      "grad_norm": 0.4052056074142456,
+      "learning_rate": 2e-05,
+      "loss": 0.6448,
+      "step": 1390
+    },
+    {
+      "epoch": 0.07327157586224944,
+      "grad_norm": 0.41825127601623535,
+      "learning_rate": 2e-05,
+      "loss": 0.6465,
+      "step": 1400
+    },
+    {
+      "epoch": 0.07379494426126551,
+      "grad_norm": 0.41024652123451233,
+      "learning_rate": 2e-05,
+      "loss": 0.6428,
+      "step": 1410
+    },
+    {
+      "epoch": 0.07431831266028158,
+      "grad_norm": 0.38469892740249634,
+      "learning_rate": 2e-05,
+      "loss": 0.6652,
+      "step": 1420
+    },
+    {
+      "epoch": 0.07484168105929764,
+      "grad_norm": 0.4639175236225128,
+      "learning_rate": 2e-05,
+      "loss": 0.6503,
+      "step": 1430
+    },
+    {
+      "epoch": 0.07536504945831371,
+      "grad_norm": 0.4508153200149536,
+      "learning_rate": 2e-05,
+      "loss": 0.6464,
+      "step": 1440
+    },
+    {
+      "epoch": 0.07588841785732978,
+      "grad_norm": 0.5173973441123962,
+      "learning_rate": 2e-05,
+      "loss": 0.6475,
+      "step": 1450
+    },
+    {
+      "epoch": 0.07641178625634584,
+      "grad_norm": 0.47181883454322815,
+      "learning_rate": 2e-05,
+      "loss": 0.6662,
+      "step": 1460
+    },
+    {
+      "epoch": 0.07693515465536191,
+      "grad_norm": 0.43690988421440125,
+      "learning_rate": 2e-05,
+      "loss": 0.6459,
+      "step": 1470
+    },
+    {
+      "epoch": 0.07745852305437798,
+      "grad_norm": 0.40047961473464966,
+      "learning_rate": 2e-05,
+      "loss": 0.6808,
+      "step": 1480
+    },
+    {
+      "epoch": 0.07798189145339404,
+      "grad_norm": 0.3962308466434479,
+      "learning_rate": 2e-05,
+      "loss": 0.6249,
+      "step": 1490
+    },
+    {
+      "epoch": 0.07850525985241011,
+      "grad_norm": 0.5075916051864624,
+      "learning_rate": 2e-05,
+      "loss": 0.6562,
+      "step": 1500
+    },
+    {
+      "epoch": 0.07902862825142618,
+      "grad_norm": 0.44439756870269775,
+      "learning_rate": 2e-05,
+      "loss": 0.6744,
+      "step": 1510
+    },
+    {
+      "epoch": 0.07955199665044224,
+      "grad_norm": 0.4172062575817108,
+      "learning_rate": 2e-05,
+      "loss": 0.6328,
+      "step": 1520
+    },
+    {
+      "epoch": 0.08007536504945831,
+      "grad_norm": 0.9272112250328064,
+      "learning_rate": 2e-05,
+      "loss": 0.6554,
+      "step": 1530
+    },
+    {
+      "epoch": 0.08059873344847437,
+      "grad_norm": 0.44365498423576355,
+      "learning_rate": 2e-05,
+      "loss": 0.6567,
+      "step": 1540
+    },
+    {
+      "epoch": 0.08112210184749045,
+      "grad_norm": 0.5808505415916443,
+      "learning_rate": 2e-05,
+      "loss": 0.6671,
+      "step": 1550
+    },
+    {
+      "epoch": 0.08164547024650652,
+      "grad_norm": 0.4238007068634033,
+      "learning_rate": 2e-05,
+      "loss": 0.6655,
+      "step": 1560
+    },
+    {
+      "epoch": 0.08216883864552259,
+      "grad_norm": 0.4158059358596802,
+      "learning_rate": 2e-05,
+      "loss": 0.6502,
+      "step": 1570
+    },
+    {
+      "epoch": 0.08269220704453865,
+      "grad_norm": 0.4266833961009979,
+      "learning_rate": 2e-05,
+      "loss": 0.6389,
+      "step": 1580
+    },
+    {
+      "epoch": 0.08321557544355472,
+      "grad_norm": 0.4183817505836487,
+      "learning_rate": 2e-05,
+      "loss": 0.6297,
+      "step": 1590
+    },
+    {
+      "epoch": 0.08373894384257079,
+      "grad_norm": 0.4242572784423828,
+      "learning_rate": 2e-05,
+      "loss": 0.6575,
+      "step": 1600
+    },
+    {
+      "epoch": 0.08426231224158685,
+      "grad_norm": 0.42805418372154236,
+      "learning_rate": 2e-05,
+      "loss": 0.6316,
+      "step": 1610
+    },
+    {
+      "epoch": 0.08478568064060292,
+      "grad_norm": 0.441866010427475,
+      "learning_rate": 2e-05,
+      "loss": 0.6702,
+      "step": 1620
+    },
+    {
+      "epoch": 0.08530904903961899,
+      "grad_norm": 0.4371151626110077,
+      "learning_rate": 2e-05,
+      "loss": 0.6623,
+      "step": 1630
+    },
+    {
+      "epoch": 0.08583241743863505,
+      "grad_norm": 0.43131211400032043,
+      "learning_rate": 2e-05,
+      "loss": 0.6448,
+      "step": 1640
+    },
+    {
+      "epoch": 0.08635578583765112,
+      "grad_norm": 0.4316512644290924,
+      "learning_rate": 2e-05,
+      "loss": 0.6374,
+      "step": 1650
+    },
+    {
+      "epoch": 0.08687915423666719,
+      "grad_norm": 0.48419904708862305,
+      "learning_rate": 2e-05,
+      "loss": 0.6224,
+      "step": 1660
+    },
+    {
+      "epoch": 0.08740252263568325,
+      "grad_norm": 0.3933804929256439,
+      "learning_rate": 2e-05,
+      "loss": 0.6522,
+      "step": 1670
+    },
+    {
+      "epoch": 0.08792589103469932,
+      "grad_norm": 0.4437639117240906,
+      "learning_rate": 2e-05,
+      "loss": 0.6237,
+      "step": 1680
+    },
+    {
+      "epoch": 0.08844925943371539,
+      "grad_norm": 0.4899040460586548,
+      "learning_rate": 2e-05,
+      "loss": 0.6321,
+      "step": 1690
+    },
+    {
+      "epoch": 0.08897262783273147,
+      "grad_norm": 0.4382249712944031,
+      "learning_rate": 2e-05,
+      "loss": 0.6469,
+      "step": 1700
+    },
+    {
+      "epoch": 0.08949599623174753,
+      "grad_norm": 0.4095931053161621,
+      "learning_rate": 2e-05,
+      "loss": 0.6588,
+      "step": 1710
+    },
+    {
+      "epoch": 0.0900193646307636,
+      "grad_norm": 0.43513184785842896,
+      "learning_rate": 2e-05,
+      "loss": 0.6569,
+      "step": 1720
+    },
+    {
+      "epoch": 0.09054273302977967,
+      "grad_norm": 0.46793821454048157,
+      "learning_rate": 2e-05,
+      "loss": 0.6322,
+      "step": 1730
+    },
+    {
+      "epoch": 0.09106610142879573,
+      "grad_norm": 0.430164098739624,
+      "learning_rate": 2e-05,
+      "loss": 0.6224,
+      "step": 1740
+    },
+    {
+      "epoch": 0.0915894698278118,
+      "grad_norm": 0.3761891722679138,
+      "learning_rate": 2e-05,
+      "loss": 0.606,
+      "step": 1750
+    },
+    {
+      "epoch": 0.09211283822682786,
+      "grad_norm": 0.373146116733551,
+      "learning_rate": 2e-05,
+      "loss": 0.6329,
+      "step": 1760
+    },
+    {
+      "epoch": 0.09263620662584393,
+      "grad_norm": 0.42644017934799194,
+      "learning_rate": 2e-05,
+      "loss": 0.6466,
+      "step": 1770
+    },
+    {
+      "epoch": 0.09315957502486,
+      "grad_norm": 0.40171223878860474,
+      "learning_rate": 2e-05,
+      "loss": 0.6567,
+      "step": 1780
+    },
+    {
+      "epoch": 0.09368294342387606,
+      "grad_norm": 0.5002732872962952,
+      "learning_rate": 2e-05,
+      "loss": 0.6645,
+      "step": 1790
+    },
+    {
+      "epoch": 0.09420631182289213,
+      "grad_norm": 0.45148345828056335,
+      "learning_rate": 2e-05,
+      "loss": 0.6735,
+      "step": 1800
+    },
+    {
+      "epoch": 0.0947296802219082,
+      "grad_norm": 0.4408950209617615,
+      "learning_rate": 2e-05,
+      "loss": 0.64,
+      "step": 1810
+    },
+    {
+      "epoch": 0.09525304862092426,
+      "grad_norm": 0.41224032640457153,
+      "learning_rate": 2e-05,
+      "loss": 0.6483,
+      "step": 1820
+    },
+    {
+      "epoch": 0.09577641701994033,
+      "grad_norm": 0.3857000768184662,
+      "learning_rate": 2e-05,
+      "loss": 0.6591,
+      "step": 1830
+    },
+    {
+      "epoch": 0.09629978541895641,
+      "grad_norm": 0.5142344832420349,
+      "learning_rate": 2e-05,
+      "loss": 0.6613,
+      "step": 1840
+    },
+    {
+      "epoch": 0.09682315381797248,
+      "grad_norm": 0.43707653880119324,
+      "learning_rate": 2e-05,
+      "loss": 0.6463,
+      "step": 1850
+    },
+    {
+      "epoch": 0.09734652221698854,
+      "grad_norm": 0.5951546430587769,
+      "learning_rate": 2e-05,
+      "loss": 0.6634,
+      "step": 1860
+    },
+    {
+      "epoch": 0.09786989061600461,
+      "grad_norm": 0.451498419046402,
+      "learning_rate": 2e-05,
+      "loss": 0.6228,
+      "step": 1870
+    },
+    {
+      "epoch": 0.09839325901502068,
+      "grad_norm": 0.43872302770614624,
+      "learning_rate": 2e-05,
+      "loss": 0.6417,
+      "step": 1880
+    },
+    {
+      "epoch": 0.09891662741403674,
+      "grad_norm": 0.3905869722366333,
+      "learning_rate": 2e-05,
+      "loss": 0.6195,
+      "step": 1890
+    },
+    {
+      "epoch": 0.09943999581305281,
+      "grad_norm": 0.46226704120635986,
+      "learning_rate": 2e-05,
+      "loss": 0.652,
+      "step": 1900
+    },
+    {
+      "epoch": 0.09996336421206888,
+      "grad_norm": 0.4350249469280243,
+      "learning_rate": 2e-05,
+      "loss": 0.6814,
+      "step": 1910
+    },
+    {
+      "epoch": 0.10048673261108494,
+      "grad_norm": 0.547003448009491,
+      "learning_rate": 2e-05,
+      "loss": 0.6376,
+      "step": 1920
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 0.40520697832107544,
+      "learning_rate": 2e-05,
+      "loss": 0.6281,
+      "step": 1930
+    },
+    {
+      "epoch": 0.10153346940911707,
+      "grad_norm": 0.3886966109275818,
+      "learning_rate": 2e-05,
+      "loss": 0.6349,
+      "step": 1940
+    },
+    {
+      "epoch": 0.10205683780813314,
+      "grad_norm": 0.4416722059249878,
+      "learning_rate": 2e-05,
+      "loss": 0.6626,
+      "step": 1950
+    },
+    {
+      "epoch": 0.10258020620714921,
+      "grad_norm": 0.4272310137748718,
+      "learning_rate": 2e-05,
+      "loss": 0.627,
+      "step": 1960
+    },
+    {
+      "epoch": 0.10310357460616527,
+      "grad_norm": 0.4342178404331207,
+      "learning_rate": 2e-05,
+      "loss": 0.6616,
+      "step": 1970
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.4413588047027588,
+      "learning_rate": 2e-05,
+      "loss": 0.6602,
+      "step": 1980
+    },
+    {
+      "epoch": 0.10415031140419742,
+      "grad_norm": 0.39807382225990295,
+      "learning_rate": 2e-05,
+      "loss": 0.6184,
+      "step": 1990
+    },
+    {
+      "epoch": 0.10467367980321349,
+      "grad_norm": 0.39922189712524414,
+      "learning_rate": 2e-05,
+      "loss": 0.6348,
+      "step": 2000
+    },
+    {
+      "epoch": 0.10519704820222955,
+      "grad_norm": 0.4405508041381836,
+      "learning_rate": 2e-05,
+      "loss": 0.6527,
+      "step": 2010
+    },
+    {
+      "epoch": 0.10572041660124562,
+      "grad_norm": 0.4154644310474396,
+      "learning_rate": 2e-05,
+      "loss": 0.6383,
+      "step": 2020
+    },
+    {
+      "epoch": 0.10624378500026169,
+      "grad_norm": 0.4121659994125366,
+      "learning_rate": 2e-05,
+      "loss": 0.6337,
+      "step": 2030
+    },
+    {
+      "epoch": 0.10676715339927775,
+      "grad_norm": 0.4231645166873932,
+      "learning_rate": 2e-05,
+      "loss": 0.6648,
+      "step": 2040
+    },
+    {
+      "epoch": 0.10729052179829382,
+      "grad_norm": 0.5495308041572571,
+      "learning_rate": 2e-05,
+      "loss": 0.6655,
+      "step": 2050
+    },
+    {
+      "epoch": 0.10781389019730989,
+      "grad_norm": 0.4083961546421051,
+      "learning_rate": 2e-05,
+      "loss": 0.6091,
+      "step": 2060
+    },
+    {
+      "epoch": 0.10833725859632595,
+      "grad_norm": 0.394467830657959,
+      "learning_rate": 2e-05,
+      "loss": 0.6472,
+      "step": 2070
+    },
+    {
+      "epoch": 0.10886062699534202,
+      "grad_norm": 0.4051300585269928,
+      "learning_rate": 2e-05,
+      "loss": 0.6295,
+      "step": 2080
+    },
+    {
+      "epoch": 0.10938399539435809,
+      "grad_norm": 0.44103720784187317,
+      "learning_rate": 2e-05,
+      "loss": 0.6316,
+      "step": 2090
+    },
+    {
+      "epoch": 0.10990736379337415,
+      "grad_norm": 0.4452396333217621,
+      "learning_rate": 2e-05,
+      "loss": 0.6367,
+      "step": 2100
+    },
+    {
+      "epoch": 0.11043073219239022,
+      "grad_norm": 0.5510708689689636,
+      "learning_rate": 2e-05,
+      "loss": 0.6258,
+      "step": 2110
+    },
+    {
+      "epoch": 0.11095410059140629,
+      "grad_norm": 0.5372933149337769,
+      "learning_rate": 2e-05,
+      "loss": 0.6476,
+      "step": 2120
+    },
+    {
+      "epoch": 0.11147746899042235,
+      "grad_norm": 0.4383063316345215,
+      "learning_rate": 2e-05,
+      "loss": 0.6605,
+      "step": 2130
+    },
+    {
+      "epoch": 0.11200083738943843,
+      "grad_norm": 0.4241836667060852,
+      "learning_rate": 2e-05,
+      "loss": 0.6362,
+      "step": 2140
+    },
+    {
+      "epoch": 0.1125242057884545,
+      "grad_norm": 0.442451149225235,
+      "learning_rate": 2e-05,
+      "loss": 0.6433,
+      "step": 2150
+    },
+    {
+      "epoch": 0.11304757418747056,
+      "grad_norm": 0.41505861282348633,
+      "learning_rate": 2e-05,
+      "loss": 0.6239,
+      "step": 2160
+    },
+    {
+      "epoch": 0.11357094258648663,
+      "grad_norm": 0.43439918756484985,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 2170
+    },
+    {
+      "epoch": 0.1140943109855027,
+      "grad_norm": 0.43937069177627563,
+      "learning_rate": 2e-05,
+      "loss": 0.6414,
+      "step": 2180
+    },
+    {
+      "epoch": 0.11461767938451876,
+      "grad_norm": 0.43210020661354065,
+      "learning_rate": 2e-05,
+      "loss": 0.6257,
+      "step": 2190
+    },
+    {
+      "epoch": 0.11514104778353483,
+      "grad_norm": 0.49416911602020264,
+      "learning_rate": 2e-05,
+      "loss": 0.6442,
+      "step": 2200
+    },
+    {
+      "epoch": 0.1156644161825509,
+      "grad_norm": 0.40978503227233887,
+      "learning_rate": 2e-05,
+      "loss": 0.6329,
+      "step": 2210
+    },
+    {
+      "epoch": 0.11618778458156696,
+      "grad_norm": 0.4340236485004425,
+      "learning_rate": 2e-05,
+      "loss": 0.6347,
+      "step": 2220
+    },
+    {
+      "epoch": 0.11671115298058303,
+      "grad_norm": 0.41441839933395386,
+      "learning_rate": 2e-05,
+      "loss": 0.6205,
+      "step": 2230
+    },
+    {
+      "epoch": 0.1172345213795991,
+      "grad_norm": 0.4365447461605072,
+      "learning_rate": 2e-05,
+      "loss": 0.6329,
+      "step": 2240
+    },
+    {
+      "epoch": 0.11775788977861516,
+      "grad_norm": 0.44118615984916687,
+      "learning_rate": 2e-05,
+      "loss": 0.6549,
+      "step": 2250
+    },
+    {
+      "epoch": 0.11828125817763123,
+      "grad_norm": 0.40321072936058044,
+      "learning_rate": 2e-05,
+      "loss": 0.6284,
+      "step": 2260
+    },
+    {
+      "epoch": 0.1188046265766473,
+      "grad_norm": 0.4358213543891907,
+      "learning_rate": 2e-05,
+      "loss": 0.6375,
+      "step": 2270
+    },
+    {
+      "epoch": 0.11932799497566338,
+      "grad_norm": 0.42884060740470886,
+      "learning_rate": 2e-05,
+      "loss": 0.6452,
+      "step": 2280
+    },
+    {
+      "epoch": 0.11985136337467944,
+      "grad_norm": 0.43688151240348816,
+      "learning_rate": 2e-05,
+      "loss": 0.6433,
+      "step": 2290
+    },
+    {
+      "epoch": 0.12037473177369551,
+      "grad_norm": 0.42834022641181946,
+      "learning_rate": 2e-05,
+      "loss": 0.6461,
+      "step": 2300
+    },
+    {
+      "epoch": 0.12089810017271158,
+      "grad_norm": 0.44969525933265686,
+      "learning_rate": 2e-05,
+      "loss": 0.6704,
+      "step": 2310
+    },
+    {
+      "epoch": 0.12142146857172764,
+      "grad_norm": 0.4053316116333008,
+      "learning_rate": 2e-05,
+      "loss": 0.6188,
+      "step": 2320
+    },
+    {
+      "epoch": 0.12194483697074371,
+      "grad_norm": 0.3716852366924286,
+      "learning_rate": 2e-05,
+      "loss": 0.6249,
+      "step": 2330
+    },
+    {
+      "epoch": 0.12246820536975978,
+      "grad_norm": 0.4359619617462158,
+      "learning_rate": 2e-05,
+      "loss": 0.6571,
+      "step": 2340
+    },
+    {
+      "epoch": 0.12299157376877584,
+      "grad_norm": 0.38862133026123047,
+      "learning_rate": 2e-05,
+      "loss": 0.641,
+      "step": 2350
+    },
+    {
+      "epoch": 0.12351494216779191,
+      "grad_norm": 0.4286133646965027,
+      "learning_rate": 2e-05,
+      "loss": 0.6514,
+      "step": 2360
+    },
+    {
+      "epoch": 0.12403831056680797,
+      "grad_norm": 0.4758356809616089,
+      "learning_rate": 2e-05,
+      "loss": 0.628,
+      "step": 2370
+    },
+    {
+      "epoch": 0.12456167896582404,
+      "grad_norm": 0.4074471592903137,
+      "learning_rate": 2e-05,
+      "loss": 0.6161,
+      "step": 2380
+    },
+    {
+      "epoch": 0.1250850473648401,
+      "grad_norm": 0.4395975172519684,
+      "learning_rate": 2e-05,
+      "loss": 0.6514,
+      "step": 2390
+    },
+    {
+      "epoch": 0.12560841576385617,
+      "grad_norm": 0.4212956130504608,
+      "learning_rate": 2e-05,
+      "loss": 0.6459,
+      "step": 2400
+    },
+    {
+      "epoch": 0.12613178416287224,
+      "grad_norm": 0.43518325686454773,
+      "learning_rate": 2e-05,
+      "loss": 0.6631,
+      "step": 2410
+    },
+    {
+      "epoch": 0.1266551525618883,
+      "grad_norm": 0.41669315099716187,
+      "learning_rate": 2e-05,
+      "loss": 0.6433,
+      "step": 2420
+    },
+    {
+      "epoch": 0.12717852096090437,
+      "grad_norm": 0.47521886229515076,
+      "learning_rate": 2e-05,
+      "loss": 0.6008,
+      "step": 2430
+    },
+    {
+      "epoch": 0.12770188935992044,
+      "grad_norm": 0.5306794047355652,
+      "learning_rate": 2e-05,
+      "loss": 0.6499,
+      "step": 2440
+    },
+    {
+      "epoch": 0.1282252577589365,
+      "grad_norm": 0.4078957438468933,
+      "learning_rate": 2e-05,
+      "loss": 0.632,
+      "step": 2450
+    },
+    {
+      "epoch": 0.12874862615795257,
+      "grad_norm": 0.4263654351234436,
+      "learning_rate": 2e-05,
+      "loss": 0.6367,
+      "step": 2460
+    },
+    {
+      "epoch": 0.12927199455696864,
+      "grad_norm": 0.4139572083950043,
+      "learning_rate": 2e-05,
+      "loss": 0.642,
+      "step": 2470
+    },
+    {
+      "epoch": 0.1297953629559847,
+      "grad_norm": 0.38871797919273376,
+      "learning_rate": 2e-05,
+      "loss": 0.6342,
+      "step": 2480
+    },
+    {
+      "epoch": 0.13031873135500077,
+      "grad_norm": 0.429225891828537,
+      "learning_rate": 2e-05,
+      "loss": 0.6249,
+      "step": 2490
+    },
+    {
+      "epoch": 0.13084209975401687,
+      "grad_norm": 0.45410633087158203,
+      "learning_rate": 2e-05,
+      "loss": 0.6395,
+      "step": 2500
+    },
+    {
+      "epoch": 0.13136546815303293,
+      "grad_norm": 0.45400431752204895,
+      "learning_rate": 2e-05,
+      "loss": 0.6244,
+      "step": 2510
+    },
+    {
+      "epoch": 0.131888836552049,
+      "grad_norm": 0.4065890312194824,
+      "learning_rate": 2e-05,
+      "loss": 0.6394,
+      "step": 2520
+    },
+    {
+      "epoch": 0.13241220495106507,
+      "grad_norm": 0.4191737771034241,
+      "learning_rate": 2e-05,
+      "loss": 0.6409,
+      "step": 2530
+    },
+    {
+      "epoch": 0.13293557335008113,
+      "grad_norm": 0.45096731185913086,
+      "learning_rate": 2e-05,
+      "loss": 0.6208,
+      "step": 2540
+    },
+    {
+      "epoch": 0.1334589417490972,
+      "grad_norm": 0.46258044242858887,
+      "learning_rate": 2e-05,
+      "loss": 0.6395,
+      "step": 2550
+    },
+    {
+      "epoch": 0.13398231014811327,
+      "grad_norm": 0.4282276928424835,
+      "learning_rate": 2e-05,
+      "loss": 0.601,
+      "step": 2560
+    },
+    {
+      "epoch": 0.13450567854712933,
+      "grad_norm": 0.41605663299560547,
+      "learning_rate": 2e-05,
+      "loss": 0.6501,
+      "step": 2570
+    },
+    {
+      "epoch": 0.1350290469461454,
+      "grad_norm": 0.41660454869270325,
+      "learning_rate": 2e-05,
+      "loss": 0.6546,
+      "step": 2580
+    },
+    {
+      "epoch": 0.13555241534516146,
+      "grad_norm": 0.4275190234184265,
+      "learning_rate": 2e-05,
+      "loss": 0.6458,
+      "step": 2590
+    },
+    {
+      "epoch": 0.13607578374417753,
+      "grad_norm": 0.4305119514465332,
+      "learning_rate": 2e-05,
+      "loss": 0.6403,
+      "step": 2600
+    },
+    {
+      "epoch": 0.1365991521431936,
+      "grad_norm": 0.42454832792282104,
+      "learning_rate": 2e-05,
+      "loss": 0.6368,
+      "step": 2610
+    },
+    {
+      "epoch": 0.13712252054220966,
+      "grad_norm": 0.44257181882858276,
+      "learning_rate": 2e-05,
+      "loss": 0.6343,
+      "step": 2620
+    },
+    {
+      "epoch": 0.13764588894122573,
+      "grad_norm": 0.3995290696620941,
+      "learning_rate": 2e-05,
+      "loss": 0.6616,
+      "step": 2630
+    },
+    {
+      "epoch": 0.1381692573402418,
+      "grad_norm": 0.4199754297733307,
+      "learning_rate": 2e-05,
+      "loss": 0.6286,
+      "step": 2640
+    },
+    {
+      "epoch": 0.13869262573925786,
+      "grad_norm": 0.42020726203918457,
+      "learning_rate": 2e-05,
+      "loss": 0.6371,
+      "step": 2650
+    },
+    {
+      "epoch": 0.13921599413827393,
+      "grad_norm": 0.39368361234664917,
+      "learning_rate": 2e-05,
+      "loss": 0.6517,
+      "step": 2660
+    },
+    {
+      "epoch": 0.13973936253729,
+      "grad_norm": 0.4302023947238922,
+      "learning_rate": 2e-05,
+      "loss": 0.6139,
+      "step": 2670
+    },
+    {
+      "epoch": 0.14026273093630606,
+      "grad_norm": 0.49658092856407166,
+      "learning_rate": 2e-05,
+      "loss": 0.6565,
+      "step": 2680
+    },
+    {
+      "epoch": 0.14078609933532213,
+      "grad_norm": 0.3941155672073364,
+      "learning_rate": 2e-05,
+      "loss": 0.6527,
+      "step": 2690
+    },
+    {
+      "epoch": 0.1413094677343382,
+      "grad_norm": 0.43608132004737854,
+      "learning_rate": 2e-05,
+      "loss": 0.6309,
+      "step": 2700
+    },
+    {
+      "epoch": 0.14183283613335426,
+      "grad_norm": 0.4120804965496063,
+      "learning_rate": 2e-05,
+      "loss": 0.6326,
+      "step": 2710
+    },
+    {
+      "epoch": 0.14235620453237033,
+      "grad_norm": 0.4378657639026642,
+      "learning_rate": 2e-05,
+      "loss": 0.6479,
+      "step": 2720
+    },
+    {
+      "epoch": 0.1428795729313864,
+      "grad_norm": 0.39626598358154297,
+      "learning_rate": 2e-05,
+      "loss": 0.6537,
+      "step": 2730
+    },
+    {
+      "epoch": 0.14340294133040246,
+      "grad_norm": 0.40195828676223755,
+      "learning_rate": 2e-05,
+      "loss": 0.6075,
+      "step": 2740
+    },
+    {
+      "epoch": 0.14392630972941853,
+      "grad_norm": 0.3953752815723419,
+      "learning_rate": 2e-05,
+      "loss": 0.6179,
+      "step": 2750
+    },
+    {
+      "epoch": 0.1444496781284346,
+      "grad_norm": 0.4433000385761261,
+      "learning_rate": 2e-05,
+      "loss": 0.6743,
+      "step": 2760
+    },
+    {
+      "epoch": 0.14497304652745066,
+      "grad_norm": 0.42893922328948975,
+      "learning_rate": 2e-05,
+      "loss": 0.6272,
+      "step": 2770
+    },
+    {
+      "epoch": 0.14549641492646673,
+      "grad_norm": 0.4065708518028259,
+      "learning_rate": 2e-05,
+      "loss": 0.6417,
+      "step": 2780
+    },
+    {
+      "epoch": 0.1460197833254828,
+      "grad_norm": 0.4181337058544159,
+      "learning_rate": 2e-05,
+      "loss": 0.6392,
+      "step": 2790
+    },
+    {
+      "epoch": 0.1465431517244989,
+      "grad_norm": 0.4179243743419647,
+      "learning_rate": 2e-05,
+      "loss": 0.6026,
+      "step": 2800
+    },
+    {
+      "epoch": 0.14706652012351495,
+      "grad_norm": 0.46388933062553406,
+      "learning_rate": 2e-05,
+      "loss": 0.6335,
+      "step": 2810
+    },
+    {
+      "epoch": 0.14758988852253102,
+      "grad_norm": 0.4350208640098572,
+      "learning_rate": 2e-05,
+      "loss": 0.6349,
+      "step": 2820
+    },
+    {
+      "epoch": 0.1481132569215471,
+      "grad_norm": 0.4281371831893921,
+      "learning_rate": 2e-05,
+      "loss": 0.5927,
+      "step": 2830
+    },
+    {
+      "epoch": 0.14863662532056315,
+      "grad_norm": 0.3796765208244324,
+      "learning_rate": 2e-05,
+      "loss": 0.6244,
+      "step": 2840
+    },
+    {
+      "epoch": 0.14915999371957922,
+      "grad_norm": 0.400057315826416,
+      "learning_rate": 2e-05,
+      "loss": 0.6083,
+      "step": 2850
+    },
+    {
+      "epoch": 0.1496833621185953,
+      "grad_norm": 0.5580277442932129,
+      "learning_rate": 2e-05,
+      "loss": 0.6088,
+      "step": 2860
+    },
+    {
+      "epoch": 0.15020673051761135,
+      "grad_norm": 0.4220695197582245,
+      "learning_rate": 2e-05,
+      "loss": 0.6339,
+      "step": 2870
+    },
+    {
+      "epoch": 0.15073009891662742,
+      "grad_norm": 0.4196612536907196,
+      "learning_rate": 2e-05,
+      "loss": 0.6415,
+      "step": 2880
+    },
+    {
+      "epoch": 0.1512534673156435,
+      "grad_norm": 0.4167044162750244,
+      "learning_rate": 2e-05,
+      "loss": 0.6276,
+      "step": 2890
+    },
+    {
+      "epoch": 0.15177683571465955,
+      "grad_norm": 0.4121061861515045,
+      "learning_rate": 2e-05,
+      "loss": 0.6311,
+      "step": 2900
+    },
+    {
+      "epoch": 0.15230020411367562,
+      "grad_norm": 0.4583412706851959,
+      "learning_rate": 2e-05,
+      "loss": 0.6415,
+      "step": 2910
+    },
+    {
+      "epoch": 0.15282357251269169,
+      "grad_norm": 0.4203738272190094,
+      "learning_rate": 2e-05,
+      "loss": 0.657,
+      "step": 2920
+    },
+    {
+      "epoch": 0.15334694091170775,
+      "grad_norm": 0.4278572201728821,
+      "learning_rate": 2e-05,
+      "loss": 0.6457,
+      "step": 2930
+    },
+    {
+      "epoch": 0.15387030931072382,
+      "grad_norm": 0.41517725586891174,
+      "learning_rate": 2e-05,
+      "loss": 0.6506,
+      "step": 2940
+    },
+    {
+      "epoch": 0.15439367770973988,
+      "grad_norm": 0.39440619945526123,
+      "learning_rate": 2e-05,
+      "loss": 0.6247,
+      "step": 2950
+    },
+    {
+      "epoch": 0.15491704610875595,
+      "grad_norm": 0.3762326240539551,
+      "learning_rate": 2e-05,
+      "loss": 0.6464,
+      "step": 2960
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 0.43617796897888184,
+      "learning_rate": 2e-05,
+      "loss": 0.6162,
+      "step": 2970
+    },
+    {
+      "epoch": 0.15596378290678808,
+      "grad_norm": 0.41636911034584045,
+      "learning_rate": 2e-05,
+      "loss": 0.6327,
+      "step": 2980
+    },
+    {
+      "epoch": 0.15648715130580415,
+      "grad_norm": 0.4136853814125061,
+      "learning_rate": 2e-05,
+      "loss": 0.6292,
+      "step": 2990
+    },
+    {
+      "epoch": 0.15701051970482022,
+      "grad_norm": 0.44505634903907776,
+      "learning_rate": 2e-05,
+      "loss": 0.646,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15753388810383628,
+      "grad_norm": 0.42681798338890076,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 3010
+    },
+    {
+      "epoch": 0.15805725650285235,
+      "grad_norm": 0.3740960657596588,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 3020
+    },
+    {
+      "epoch": 0.15858062490186842,
+      "grad_norm": 0.4044531285762787,
+      "learning_rate": 2e-05,
+      "loss": 0.655,
+      "step": 3030
+    },
+    {
+      "epoch": 0.15910399330088448,
+      "grad_norm": 0.38664835691452026,
+      "learning_rate": 2e-05,
+      "loss": 0.6201,
+      "step": 3040
+    },
+    {
+      "epoch": 0.15962736169990055,
+      "grad_norm": 0.5274628400802612,
+      "learning_rate": 2e-05,
+      "loss": 0.6374,
+      "step": 3050
+    },
+    {
+      "epoch": 0.16015073009891662,
+      "grad_norm": 0.4279114305973053,
+      "learning_rate": 2e-05,
+      "loss": 0.6433,
+      "step": 3060
+    },
+    {
+      "epoch": 0.16067409849793268,
+      "grad_norm": 0.396634578704834,
+      "learning_rate": 2e-05,
+      "loss": 0.6155,
+      "step": 3070
+    },
+    {
+      "epoch": 0.16119746689694875,
+      "grad_norm": 0.41256171464920044,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 3080
+    },
+    {
+      "epoch": 0.16172083529596484,
+      "grad_norm": 0.47806742787361145,
+      "learning_rate": 2e-05,
+      "loss": 0.6288,
+      "step": 3090
+    },
+    {
+      "epoch": 0.1622442036949809,
+      "grad_norm": 0.41482001543045044,
+      "learning_rate": 2e-05,
+      "loss": 0.6097,
+      "step": 3100
+    },
+    {
+      "epoch": 0.16276757209399698,
+      "grad_norm": 0.4124285876750946,
+      "learning_rate": 2e-05,
+      "loss": 0.6381,
+      "step": 3110
+    },
+    {
+      "epoch": 0.16329094049301304,
+      "grad_norm": 0.39308762550354004,
+      "learning_rate": 2e-05,
+      "loss": 0.6418,
+      "step": 3120
+    },
+    {
+      "epoch": 0.1638143088920291,
+      "grad_norm": 0.5976954698562622,
+      "learning_rate": 2e-05,
+      "loss": 0.6403,
+      "step": 3130
+    },
+    {
+      "epoch": 0.16433767729104518,
+      "grad_norm": 0.4556901752948761,
+      "learning_rate": 2e-05,
+      "loss": 0.6415,
+      "step": 3140
+    },
+    {
+      "epoch": 0.16486104569006124,
+      "grad_norm": 0.4634074866771698,
+      "learning_rate": 2e-05,
+      "loss": 0.6142,
+      "step": 3150
+    },
+    {
+      "epoch": 0.1653844140890773,
+      "grad_norm": 0.4238816797733307,
+      "learning_rate": 2e-05,
+      "loss": 0.6528,
+      "step": 3160
+    },
+    {
+      "epoch": 0.16590778248809337,
+      "grad_norm": 0.5388637185096741,
+      "learning_rate": 2e-05,
+      "loss": 0.6723,
+      "step": 3170
+    },
+    {
+      "epoch": 0.16643115088710944,
+      "grad_norm": 0.3934621512889862,
+      "learning_rate": 2e-05,
+      "loss": 0.6347,
+      "step": 3180
+    },
+    {
+      "epoch": 0.1669545192861255,
+      "grad_norm": 0.3961109519004822,
+      "learning_rate": 2e-05,
+      "loss": 0.6345,
+      "step": 3190
+    },
+    {
+      "epoch": 0.16747788768514157,
+      "grad_norm": 0.41134336590766907,
+      "learning_rate": 2e-05,
+      "loss": 0.6227,
+      "step": 3200
+    },
+    {
+      "epoch": 0.16800125608415764,
+      "grad_norm": 0.4064910411834717,
+      "learning_rate": 2e-05,
+      "loss": 0.6087,
+      "step": 3210
+    },
+    {
+      "epoch": 0.1685246244831737,
+      "grad_norm": 0.411873459815979,
+      "learning_rate": 2e-05,
+      "loss": 0.6291,
+      "step": 3220
+    },
+    {
+      "epoch": 0.16904799288218977,
+      "grad_norm": 0.41122299432754517,
+      "learning_rate": 2e-05,
+      "loss": 0.6217,
+      "step": 3230
+    },
+    {
+      "epoch": 0.16957136128120584,
+      "grad_norm": 0.4552735686302185,
+      "learning_rate": 2e-05,
+      "loss": 0.6334,
+      "step": 3240
+    },
+    {
+      "epoch": 0.1700947296802219,
+      "grad_norm": 0.457132488489151,
+      "learning_rate": 2e-05,
+      "loss": 0.6213,
+      "step": 3250
+    },
+    {
+      "epoch": 0.17061809807923797,
+      "grad_norm": 0.38603243231773376,
+      "learning_rate": 2e-05,
+      "loss": 0.6363,
+      "step": 3260
+    },
+    {
+      "epoch": 0.17114146647825404,
+      "grad_norm": 0.4321597218513489,
+      "learning_rate": 2e-05,
+      "loss": 0.6194,
+      "step": 3270
+    },
+    {
+      "epoch": 0.1716648348772701,
+      "grad_norm": 0.43034639954566956,
+      "learning_rate": 2e-05,
+      "loss": 0.6409,
+      "step": 3280
+    },
+    {
+      "epoch": 0.17218820327628617,
+      "grad_norm": 0.42103973031044006,
+      "learning_rate": 2e-05,
+      "loss": 0.6154,
+      "step": 3290
+    },
+    {
+      "epoch": 0.17271157167530224,
+      "grad_norm": 0.3927100896835327,
+      "learning_rate": 2e-05,
+      "loss": 0.6313,
+      "step": 3300
+    },
+    {
+      "epoch": 0.1732349400743183,
+      "grad_norm": 0.4339587688446045,
+      "learning_rate": 2e-05,
+      "loss": 0.614,
+      "step": 3310
+    },
+    {
+      "epoch": 0.17375830847333437,
+      "grad_norm": 0.40991151332855225,
+      "learning_rate": 2e-05,
+      "loss": 0.6456,
+      "step": 3320
+    },
+    {
+      "epoch": 0.17428167687235044,
+      "grad_norm": 0.4325578808784485,
+      "learning_rate": 2e-05,
+      "loss": 0.6041,
+      "step": 3330
+    },
+    {
+      "epoch": 0.1748050452713665,
+      "grad_norm": 0.41213691234588623,
+      "learning_rate": 2e-05,
+      "loss": 0.6349,
+      "step": 3340
+    },
+    {
+      "epoch": 0.17532841367038257,
+      "grad_norm": 0.47782137989997864,
+      "learning_rate": 2e-05,
+      "loss": 0.636,
+      "step": 3350
+    },
+    {
+      "epoch": 0.17585178206939864,
+      "grad_norm": 0.42506250739097595,
+      "learning_rate": 2e-05,
+      "loss": 0.626,
+      "step": 3360
+    },
+    {
+      "epoch": 0.1763751504684147,
+      "grad_norm": 0.3940761983394623,
+      "learning_rate": 2e-05,
+      "loss": 0.6193,
+      "step": 3370
+    },
+    {
+      "epoch": 0.17689851886743077,
+      "grad_norm": 0.4069708287715912,
+      "learning_rate": 2e-05,
+      "loss": 0.6365,
+      "step": 3380
+    },
+    {
+      "epoch": 0.17742188726644686,
+      "grad_norm": 0.504355788230896,
+      "learning_rate": 2e-05,
+      "loss": 0.5985,
+      "step": 3390
+    },
+    {
+      "epoch": 0.17794525566546293,
+      "grad_norm": 0.3881029486656189,
+      "learning_rate": 2e-05,
+      "loss": 0.6328,
+      "step": 3400
+    },
+    {
+      "epoch": 0.178468624064479,
+      "grad_norm": 2.036409854888916,
+      "learning_rate": 2e-05,
+      "loss": 0.6237,
+      "step": 3410
+    },
+    {
+      "epoch": 0.17899199246349506,
+      "grad_norm": 0.41256919503211975,
+      "learning_rate": 2e-05,
+      "loss": 0.6066,
+      "step": 3420
+    },
+    {
+      "epoch": 0.17951536086251113,
+      "grad_norm": 0.4488495886325836,
+      "learning_rate": 2e-05,
+      "loss": 0.6247,
+      "step": 3430
+    },
+    {
+      "epoch": 0.1800387292615272,
+      "grad_norm": 0.4205232560634613,
+      "learning_rate": 2e-05,
+      "loss": 0.6094,
+      "step": 3440
+    },
+    {
+      "epoch": 0.18056209766054326,
+      "grad_norm": 0.4089616537094116,
+      "learning_rate": 2e-05,
+      "loss": 0.6264,
+      "step": 3450
+    },
+    {
+      "epoch": 0.18108546605955933,
+      "grad_norm": 0.37557995319366455,
+      "learning_rate": 2e-05,
+      "loss": 0.6322,
+      "step": 3460
+    },
+    {
+      "epoch": 0.1816088344585754,
+      "grad_norm": 0.39397501945495605,
+      "learning_rate": 2e-05,
+      "loss": 0.6647,
+      "step": 3470
+    },
+    {
+      "epoch": 0.18213220285759146,
+      "grad_norm": 0.4009655714035034,
+      "learning_rate": 2e-05,
+      "loss": 0.6203,
+      "step": 3480
+    },
+    {
+      "epoch": 0.18265557125660753,
+      "grad_norm": 0.40983593463897705,
+      "learning_rate": 2e-05,
+      "loss": 0.6684,
+      "step": 3490
+    },
+    {
+      "epoch": 0.1831789396556236,
+      "grad_norm": 0.41632992029190063,
+      "learning_rate": 2e-05,
+      "loss": 0.6055,
+      "step": 3500
+    },
+    {
+      "epoch": 0.18370230805463966,
+      "grad_norm": 0.42826464772224426,
+      "learning_rate": 2e-05,
+      "loss": 0.6114,
+      "step": 3510
+    },
+    {
+      "epoch": 0.18422567645365573,
+      "grad_norm": 0.4451156556606293,
+      "learning_rate": 2e-05,
+      "loss": 0.6164,
+      "step": 3520
+    },
+    {
+      "epoch": 0.1847490448526718,
+      "grad_norm": 0.7244383692741394,
+      "learning_rate": 2e-05,
+      "loss": 0.643,
+      "step": 3530
+    },
+    {
+      "epoch": 0.18527241325168786,
+      "grad_norm": 0.41192492842674255,
+      "learning_rate": 2e-05,
+      "loss": 0.6389,
+      "step": 3540
+    },
+    {
+      "epoch": 0.18579578165070393,
+      "grad_norm": 0.42937004566192627,
+      "learning_rate": 2e-05,
+      "loss": 0.6449,
+      "step": 3550
+    },
+    {
+      "epoch": 0.18631915004972,
+      "grad_norm": 0.4111078977584839,
+      "learning_rate": 2e-05,
+      "loss": 0.6202,
+      "step": 3560
+    },
+    {
+      "epoch": 0.18684251844873606,
+      "grad_norm": 0.4172969460487366,
+      "learning_rate": 2e-05,
+      "loss": 0.6188,
+      "step": 3570
+    },
+    {
+      "epoch": 0.18736588684775213,
+      "grad_norm": 0.38246381282806396,
+      "learning_rate": 2e-05,
+      "loss": 0.609,
+      "step": 3580
+    },
+    {
+      "epoch": 0.1878892552467682,
+      "grad_norm": 0.467737078666687,
+      "learning_rate": 2e-05,
+      "loss": 0.6177,
+      "step": 3590
+    },
+    {
+      "epoch": 0.18841262364578426,
+      "grad_norm": 0.3787391185760498,
+      "learning_rate": 2e-05,
+      "loss": 0.6156,
+      "step": 3600
+    },
+    {
+      "epoch": 0.18893599204480033,
+      "grad_norm": 0.39074644446372986,
+      "learning_rate": 2e-05,
+      "loss": 0.6275,
+      "step": 3610
+    },
+    {
+      "epoch": 0.1894593604438164,
+      "grad_norm": 0.4353400468826294,
+      "learning_rate": 2e-05,
+      "loss": 0.613,
+      "step": 3620
+    },
+    {
+      "epoch": 0.18998272884283246,
+      "grad_norm": 0.4572504758834839,
+      "learning_rate": 2e-05,
+      "loss": 0.6243,
+      "step": 3630
+    },
+    {
+      "epoch": 0.19050609724184853,
+      "grad_norm": 0.3868942856788635,
+      "learning_rate": 2e-05,
+      "loss": 0.6303,
+      "step": 3640
+    },
+    {
+      "epoch": 0.1910294656408646,
+      "grad_norm": 0.41320866346359253,
+      "learning_rate": 2e-05,
+      "loss": 0.6255,
+      "step": 3650
+    },
+    {
+      "epoch": 0.19155283403988066,
+      "grad_norm": 0.39754143357276917,
+      "learning_rate": 2e-05,
+      "loss": 0.6064,
+      "step": 3660
+    },
+    {
+      "epoch": 0.19207620243889673,
+      "grad_norm": 0.45954880118370056,
+      "learning_rate": 2e-05,
+      "loss": 0.6355,
+      "step": 3670
+    },
+    {
+      "epoch": 0.19259957083791282,
+      "grad_norm": 0.42518895864486694,
+      "learning_rate": 2e-05,
+      "loss": 0.6339,
+      "step": 3680
+    },
+    {
+      "epoch": 0.1931229392369289,
+      "grad_norm": 0.40126708149909973,
+      "learning_rate": 2e-05,
+      "loss": 0.6226,
+      "step": 3690
+    },
+    {
+      "epoch": 0.19364630763594495,
+      "grad_norm": 0.5110933184623718,
+      "learning_rate": 2e-05,
+      "loss": 0.6236,
+      "step": 3700
+    },
+    {
+      "epoch": 0.19416967603496102,
+      "grad_norm": 0.4530631899833679,
+      "learning_rate": 2e-05,
+      "loss": 0.6132,
+      "step": 3710
+    },
+    {
+      "epoch": 0.19469304443397709,
+      "grad_norm": 0.40570759773254395,
+      "learning_rate": 2e-05,
+      "loss": 0.6205,
+      "step": 3720
+    },
+    {
+      "epoch": 0.19521641283299315,
+      "grad_norm": 0.4424304962158203,
+      "learning_rate": 2e-05,
+      "loss": 0.6318,
+      "step": 3730
+    },
+    {
+      "epoch": 0.19573978123200922,
+      "grad_norm": 0.4104612171649933,
+      "learning_rate": 2e-05,
+      "loss": 0.6112,
+      "step": 3740
+    },
+    {
+      "epoch": 0.19626314963102529,
+      "grad_norm": 0.4605982303619385,
+      "learning_rate": 2e-05,
+      "loss": 0.63,
+      "step": 3750
+    },
+    {
+      "epoch": 0.19678651803004135,
+      "grad_norm": 0.41476568579673767,
+      "learning_rate": 2e-05,
+      "loss": 0.6301,
+      "step": 3760
+    },
+    {
+      "epoch": 0.19730988642905742,
+      "grad_norm": 0.4510325491428375,
+      "learning_rate": 2e-05,
+      "loss": 0.6311,
+      "step": 3770
+    },
+    {
+      "epoch": 0.19783325482807348,
+      "grad_norm": 0.3622564673423767,
+      "learning_rate": 2e-05,
+      "loss": 0.6028,
+      "step": 3780
+    },
+    {
+      "epoch": 0.19835662322708955,
+      "grad_norm": 0.40758174657821655,
+      "learning_rate": 2e-05,
+      "loss": 0.6328,
+      "step": 3790
+    },
+    {
+      "epoch": 0.19887999162610562,
+      "grad_norm": 0.42536821961402893,
+      "learning_rate": 2e-05,
+      "loss": 0.6343,
+      "step": 3800
+    },
+    {
+      "epoch": 0.19940336002512168,
+      "grad_norm": 0.4246145486831665,
+      "learning_rate": 2e-05,
+      "loss": 0.617,
+      "step": 3810
+    },
+    {
+      "epoch": 0.19992672842413775,
+      "grad_norm": 0.4054490327835083,
+      "learning_rate": 2e-05,
+      "loss": 0.6374,
+      "step": 3820
+    },
+    {
+      "epoch": 0.20045009682315382,
+      "grad_norm": 0.4975704848766327,
+      "learning_rate": 2e-05,
+      "loss": 0.6006,
+      "step": 3830
+    },
+    {
+      "epoch": 0.20097346522216988,
+      "grad_norm": 0.5053114891052246,
+      "learning_rate": 2e-05,
+      "loss": 0.6319,
+      "step": 3840
+    },
+    {
+      "epoch": 0.20149683362118595,
+      "grad_norm": 0.41113340854644775,
+      "learning_rate": 2e-05,
+      "loss": 0.6342,
+      "step": 3850
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.3836223781108856,
+      "learning_rate": 2e-05,
+      "loss": 0.6196,
+      "step": 3860
+    },
+    {
+      "epoch": 0.20254357041921808,
+      "grad_norm": 0.3937544822692871,
+      "learning_rate": 2e-05,
+      "loss": 0.641,
+      "step": 3870
+    },
+    {
+      "epoch": 0.20306693881823415,
+      "grad_norm": 0.4237481951713562,
+      "learning_rate": 2e-05,
+      "loss": 0.6125,
+      "step": 3880
+    },
+    {
+      "epoch": 0.20359030721725022,
+      "grad_norm": 0.3751864731311798,
+      "learning_rate": 2e-05,
+      "loss": 0.6197,
+      "step": 3890
+    },
+    {
+      "epoch": 0.20411367561626628,
+      "grad_norm": 0.5081929564476013,
+      "learning_rate": 2e-05,
+      "loss": 0.6203,
+      "step": 3900
+    },
+    {
+      "epoch": 0.20463704401528235,
+      "grad_norm": 0.4540235698223114,
+      "learning_rate": 2e-05,
+      "loss": 0.6168,
+      "step": 3910
+    },
+    {
+      "epoch": 0.20516041241429842,
+      "grad_norm": 0.41905754804611206,
+      "learning_rate": 2e-05,
+      "loss": 0.616,
+      "step": 3920
+    },
+    {
+      "epoch": 0.20568378081331448,
+      "grad_norm": 0.5326279997825623,
+      "learning_rate": 2e-05,
+      "loss": 0.6211,
+      "step": 3930
+    },
+    {
+      "epoch": 0.20620714921233055,
+      "grad_norm": 0.41054078936576843,
+      "learning_rate": 2e-05,
+      "loss": 0.6113,
+      "step": 3940
+    },
+    {
+      "epoch": 0.20673051761134661,
+      "grad_norm": 0.4346046447753906,
+      "learning_rate": 2e-05,
+      "loss": 0.6495,
+      "step": 3950
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.410095751285553,
+      "learning_rate": 2e-05,
+      "loss": 0.62,
+      "step": 3960
+    },
+    {
+      "epoch": 0.20777725440937878,
+      "grad_norm": 0.40288132429122925,
+      "learning_rate": 2e-05,
+      "loss": 0.6214,
+      "step": 3970
+    },
+    {
+      "epoch": 0.20830062280839484,
+      "grad_norm": 0.40218082070350647,
+      "learning_rate": 2e-05,
+      "loss": 0.6318,
+      "step": 3980
+    },
+    {
+      "epoch": 0.2088239912074109,
+      "grad_norm": 0.43279343843460083,
+      "learning_rate": 2e-05,
+      "loss": 0.6341,
+      "step": 3990
+    },
+    {
+      "epoch": 0.20934735960642697,
+      "grad_norm": 0.39592084288597107,
+      "learning_rate": 2e-05,
+      "loss": 0.6042,
+      "step": 4000
+    },
+    {
+      "epoch": 0.20987072800544304,
+      "grad_norm": 0.4071950912475586,
+      "learning_rate": 2e-05,
+      "loss": 0.5843,
+      "step": 4010
+    },
+    {
+      "epoch": 0.2103940964044591,
+      "grad_norm": 0.3897649347782135,
+      "learning_rate": 2e-05,
+      "loss": 0.6269,
+      "step": 4020
+    },
+    {
+      "epoch": 0.21091746480347517,
+      "grad_norm": 0.7160203456878662,
+      "learning_rate": 2e-05,
+      "loss": 0.6499,
+      "step": 4030
+    },
+    {
+      "epoch": 0.21144083320249124,
+      "grad_norm": 0.38851386308670044,
+      "learning_rate": 2e-05,
+      "loss": 0.6142,
+      "step": 4040
+    },
+    {
+      "epoch": 0.2119642016015073,
+      "grad_norm": 0.3943970799446106,
+      "learning_rate": 2e-05,
+      "loss": 0.5983,
+      "step": 4050
+    },
+    {
+      "epoch": 0.21248757000052337,
+      "grad_norm": 0.41590937972068787,
+      "learning_rate": 2e-05,
+      "loss": 0.6363,
+      "step": 4060
+    },
+    {
+      "epoch": 0.21301093839953944,
+      "grad_norm": 0.38856077194213867,
+      "learning_rate": 2e-05,
+      "loss": 0.611,
+      "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 sha256:819eaf54c4f7b1176f385051a75457bbad1c187949592b1a470bb647227be1c7
+size 7953