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:f644286ff3dc6aade309db6e908cc8e62a89ad575b7ce833d41199ee2ea5b54d
+size 4902257696

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d627e4567700c2d811c6771066717db17f6a912798019bd4fc9b1f7a1549790f
+size 4915960368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434807d0be5bc9dd70ac68e26df2b6efa01aec00de0abc94ca2bad21f3f6ed57
+size 4983068496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e7970db45b68004d2bc67a59f88acfd838da9cc5df8acd536ab97fd9dab52a
+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": 0.2524813895781638,
+  "eval_steps": 500,
+  "global_step": 4070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006203473945409429,
+      "grad_norm": 1.103378415107727,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.8492,
+      "step": 10
+    },
+    {
+      "epoch": 0.0012406947890818859,
+      "grad_norm": 0.9267538189888,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.7944,
+      "step": 20
+    },
+    {
+      "epoch": 0.0018610421836228288,
+      "grad_norm": 0.8842476606369019,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.7628,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024813895781637717,
+      "grad_norm": 0.8289238810539246,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.7342,
+      "step": 40
+    },
+    {
+      "epoch": 0.003101736972704715,
+      "grad_norm": 0.9065801501274109,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.7217,
+      "step": 50
+    },
+    {
+      "epoch": 0.0037220843672456576,
+      "grad_norm": 0.8170527815818787,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.73,
+      "step": 60
+    },
+    {
+      "epoch": 0.004342431761786601,
+      "grad_norm": 0.8123277425765991,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.7154,
+      "step": 70
+    },
+    {
+      "epoch": 0.004962779156327543,
+      "grad_norm": 0.7789028882980347,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.7083,
+      "step": 80
+    },
+    {
+      "epoch": 0.005583126550868486,
+      "grad_norm": 0.7920109033584595,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.7252,
+      "step": 90
+    },
+    {
+      "epoch": 0.00620347394540943,
+      "grad_norm": 0.9307668209075928,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.6857,
+      "step": 100
+    },
+    {
+      "epoch": 0.006823821339950372,
+      "grad_norm": 0.8309650421142578,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.7,
+      "step": 110
+    },
+    {
+      "epoch": 0.007444168734491315,
+      "grad_norm": 0.907129168510437,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.7132,
+      "step": 120
+    },
+    {
+      "epoch": 0.008064516129032258,
+      "grad_norm": 0.8221721649169922,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.7001,
+      "step": 130
+    },
+    {
+      "epoch": 0.008684863523573201,
+      "grad_norm": 0.701308012008667,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.699,
+      "step": 140
+    },
+    {
+      "epoch": 0.009305210918114143,
+      "grad_norm": 0.7170705199241638,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.6725,
+      "step": 150
+    },
+    {
+      "epoch": 0.009925558312655087,
+      "grad_norm": 0.8029273152351379,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.6839,
+      "step": 160
+    },
+    {
+      "epoch": 0.01054590570719603,
+      "grad_norm": 0.7059943079948425,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.6963,
+      "step": 170
+    },
+    {
+      "epoch": 0.011166253101736972,
+      "grad_norm": 0.7652074694633484,
+      "learning_rate": 2e-05,
+      "loss": 0.6906,
+      "step": 180
+    },
+    {
+      "epoch": 0.011786600496277916,
+      "grad_norm": 0.777823269367218,
+      "learning_rate": 2e-05,
+      "loss": 0.6697,
+      "step": 190
+    },
+    {
+      "epoch": 0.01240694789081886,
+      "grad_norm": 0.7011638879776001,
+      "learning_rate": 2e-05,
+      "loss": 0.6886,
+      "step": 200
+    },
+    {
+      "epoch": 0.013027295285359801,
+      "grad_norm": 0.7449702024459839,
+      "learning_rate": 2e-05,
+      "loss": 0.6957,
+      "step": 210
+    },
+    {
+      "epoch": 0.013647642679900745,
+      "grad_norm": 0.7148544192314148,
+      "learning_rate": 2e-05,
+      "loss": 0.6679,
+      "step": 220
+    },
+    {
+      "epoch": 0.014267990074441687,
+      "grad_norm": 0.6491106748580933,
+      "learning_rate": 2e-05,
+      "loss": 0.6916,
+      "step": 230
+    },
+    {
+      "epoch": 0.01488833746898263,
+      "grad_norm": 0.5647692084312439,
+      "learning_rate": 2e-05,
+      "loss": 0.6986,
+      "step": 240
+    },
+    {
+      "epoch": 0.015508684863523574,
+      "grad_norm": 0.5894495844841003,
+      "learning_rate": 2e-05,
+      "loss": 0.7308,
+      "step": 250
+    },
+    {
+      "epoch": 0.016129032258064516,
+      "grad_norm": 0.5743111371994019,
+      "learning_rate": 2e-05,
+      "loss": 0.6988,
+      "step": 260
+    },
+    {
+      "epoch": 0.016749379652605458,
+      "grad_norm": 0.5293608903884888,
+      "learning_rate": 2e-05,
+      "loss": 0.6821,
+      "step": 270
+    },
+    {
+      "epoch": 0.017369727047146403,
+      "grad_norm": 0.5631842613220215,
+      "learning_rate": 2e-05,
+      "loss": 0.6701,
+      "step": 280
+    },
+    {
+      "epoch": 0.017990074441687345,
+      "grad_norm": 0.5677319765090942,
+      "learning_rate": 2e-05,
+      "loss": 0.7191,
+      "step": 290
+    },
+    {
+      "epoch": 0.018610421836228287,
+      "grad_norm": 0.5547688603401184,
+      "learning_rate": 2e-05,
+      "loss": 0.7094,
+      "step": 300
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 0.5547721982002258,
+      "learning_rate": 2e-05,
+      "loss": 0.6783,
+      "step": 310
+    },
+    {
+      "epoch": 0.019851116625310174,
+      "grad_norm": 0.5873662829399109,
+      "learning_rate": 2e-05,
+      "loss": 0.707,
+      "step": 320
+    },
+    {
+      "epoch": 0.020471464019851116,
+      "grad_norm": 0.5058910846710205,
+      "learning_rate": 2e-05,
+      "loss": 0.663,
+      "step": 330
+    },
+    {
+      "epoch": 0.02109181141439206,
+      "grad_norm": 0.4962847828865051,
+      "learning_rate": 2e-05,
+      "loss": 0.6727,
+      "step": 340
+    },
+    {
+      "epoch": 0.021712158808933003,
+      "grad_norm": 0.49221107363700867,
+      "learning_rate": 2e-05,
+      "loss": 0.666,
+      "step": 350
+    },
+    {
+      "epoch": 0.022332506203473945,
+      "grad_norm": 0.4796120822429657,
+      "learning_rate": 2e-05,
+      "loss": 0.6665,
+      "step": 360
+    },
+    {
+      "epoch": 0.02295285359801489,
+      "grad_norm": 0.5007806420326233,
+      "learning_rate": 2e-05,
+      "loss": 0.6865,
+      "step": 370
+    },
+    {
+      "epoch": 0.02357320099255583,
+      "grad_norm": 0.5052497386932373,
+      "learning_rate": 2e-05,
+      "loss": 0.67,
+      "step": 380
+    },
+    {
+      "epoch": 0.024193548387096774,
+      "grad_norm": 0.4976111948490143,
+      "learning_rate": 2e-05,
+      "loss": 0.6971,
+      "step": 390
+    },
+    {
+      "epoch": 0.02481389578163772,
+      "grad_norm": 0.489734947681427,
+      "learning_rate": 2e-05,
+      "loss": 0.7244,
+      "step": 400
+    },
+    {
+      "epoch": 0.02543424317617866,
+      "grad_norm": 0.504808783531189,
+      "learning_rate": 2e-05,
+      "loss": 0.6574,
+      "step": 410
+    },
+    {
+      "epoch": 0.026054590570719603,
+      "grad_norm": 0.5242099761962891,
+      "learning_rate": 2e-05,
+      "loss": 0.6793,
+      "step": 420
+    },
+    {
+      "epoch": 0.026674937965260544,
+      "grad_norm": 0.48700666427612305,
+      "learning_rate": 2e-05,
+      "loss": 0.6733,
+      "step": 430
+    },
+    {
+      "epoch": 0.02729528535980149,
+      "grad_norm": 0.5279196500778198,
+      "learning_rate": 2e-05,
+      "loss": 0.6807,
+      "step": 440
+    },
+    {
+      "epoch": 0.02791563275434243,
+      "grad_norm": 1.6781505346298218,
+      "learning_rate": 2e-05,
+      "loss": 0.7033,
+      "step": 450
+    },
+    {
+      "epoch": 0.028535980148883373,
+      "grad_norm": 0.589901328086853,
+      "learning_rate": 2e-05,
+      "loss": 0.7007,
+      "step": 460
+    },
+    {
+      "epoch": 0.02915632754342432,
+      "grad_norm": 0.9268983006477356,
+      "learning_rate": 2e-05,
+      "loss": 0.6832,
+      "step": 470
+    },
+    {
+      "epoch": 0.02977667493796526,
+      "grad_norm": 0.47625434398651123,
+      "learning_rate": 2e-05,
+      "loss": 0.6953,
+      "step": 480
+    },
+    {
+      "epoch": 0.030397022332506202,
+      "grad_norm": 0.5042843818664551,
+      "learning_rate": 2e-05,
+      "loss": 0.6592,
+      "step": 490
+    },
+    {
+      "epoch": 0.031017369727047148,
+      "grad_norm": 0.44941166043281555,
+      "learning_rate": 2e-05,
+      "loss": 0.695,
+      "step": 500
+    },
+    {
+      "epoch": 0.03163771712158809,
+      "grad_norm": 0.477464497089386,
+      "learning_rate": 2e-05,
+      "loss": 0.6707,
+      "step": 510
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 0.4819585680961609,
+      "learning_rate": 2e-05,
+      "loss": 0.6708,
+      "step": 520
+    },
+    {
+      "epoch": 0.03287841191066997,
+      "grad_norm": 0.4723353981971741,
+      "learning_rate": 2e-05,
+      "loss": 0.6615,
+      "step": 530
+    },
+    {
+      "epoch": 0.033498759305210915,
+      "grad_norm": 0.4481304883956909,
+      "learning_rate": 2e-05,
+      "loss": 0.6716,
+      "step": 540
+    },
+    {
+      "epoch": 0.034119106699751864,
+      "grad_norm": 0.4634115993976593,
+      "learning_rate": 2e-05,
+      "loss": 0.6564,
+      "step": 550
+    },
+    {
+      "epoch": 0.034739454094292806,
+      "grad_norm": 0.4898909628391266,
+      "learning_rate": 2e-05,
+      "loss": 0.6783,
+      "step": 560
+    },
+    {
+      "epoch": 0.03535980148883375,
+      "grad_norm": 0.49201110005378723,
+      "learning_rate": 2e-05,
+      "loss": 0.6679,
+      "step": 570
+    },
+    {
+      "epoch": 0.03598014888337469,
+      "grad_norm": 0.4393959045410156,
+      "learning_rate": 2e-05,
+      "loss": 0.6984,
+      "step": 580
+    },
+    {
+      "epoch": 0.03660049627791563,
+      "grad_norm": 0.4818369746208191,
+      "learning_rate": 2e-05,
+      "loss": 0.6841,
+      "step": 590
+    },
+    {
+      "epoch": 0.03722084367245657,
+      "grad_norm": 0.4339914917945862,
+      "learning_rate": 2e-05,
+      "loss": 0.6787,
+      "step": 600
+    },
+    {
+      "epoch": 0.03784119106699752,
+      "grad_norm": 0.43327295780181885,
+      "learning_rate": 2e-05,
+      "loss": 0.6796,
+      "step": 610
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 0.4560607969760895,
+      "learning_rate": 2e-05,
+      "loss": 0.6468,
+      "step": 620
+    },
+    {
+      "epoch": 0.039081885856079406,
+      "grad_norm": 0.47957178950309753,
+      "learning_rate": 2e-05,
+      "loss": 0.6495,
+      "step": 630
+    },
+    {
+      "epoch": 0.03970223325062035,
+      "grad_norm": 0.4618580639362335,
+      "learning_rate": 2e-05,
+      "loss": 0.669,
+      "step": 640
+    },
+    {
+      "epoch": 0.04032258064516129,
+      "grad_norm": 0.505342423915863,
+      "learning_rate": 2e-05,
+      "loss": 0.6767,
+      "step": 650
+    },
+    {
+      "epoch": 0.04094292803970223,
+      "grad_norm": 0.48456406593322754,
+      "learning_rate": 2e-05,
+      "loss": 0.6804,
+      "step": 660
+    },
+    {
+      "epoch": 0.04156327543424317,
+      "grad_norm": 0.44942647218704224,
+      "learning_rate": 2e-05,
+      "loss": 0.6661,
+      "step": 670
+    },
+    {
+      "epoch": 0.04218362282878412,
+      "grad_norm": 0.4639962315559387,
+      "learning_rate": 2e-05,
+      "loss": 0.6796,
+      "step": 680
+    },
+    {
+      "epoch": 0.042803970223325064,
+      "grad_norm": 0.46533408761024475,
+      "learning_rate": 2e-05,
+      "loss": 0.6875,
+      "step": 690
+    },
+    {
+      "epoch": 0.043424317617866005,
+      "grad_norm": 0.42894449830055237,
+      "learning_rate": 2e-05,
+      "loss": 0.6436,
+      "step": 700
+    },
+    {
+      "epoch": 0.04404466501240695,
+      "grad_norm": 0.5065799951553345,
+      "learning_rate": 2e-05,
+      "loss": 0.6714,
+      "step": 710
+    },
+    {
+      "epoch": 0.04466501240694789,
+      "grad_norm": 0.4446672797203064,
+      "learning_rate": 2e-05,
+      "loss": 0.6871,
+      "step": 720
+    },
+    {
+      "epoch": 0.04528535980148883,
+      "grad_norm": 0.4434851109981537,
+      "learning_rate": 2e-05,
+      "loss": 0.6584,
+      "step": 730
+    },
+    {
+      "epoch": 0.04590570719602978,
+      "grad_norm": 0.5027102828025818,
+      "learning_rate": 2e-05,
+      "loss": 0.6791,
+      "step": 740
+    },
+    {
+      "epoch": 0.04652605459057072,
+      "grad_norm": 0.4595511853694916,
+      "learning_rate": 2e-05,
+      "loss": 0.6911,
+      "step": 750
+    },
+    {
+      "epoch": 0.04714640198511166,
+      "grad_norm": 0.4787590801715851,
+      "learning_rate": 2e-05,
+      "loss": 0.6868,
+      "step": 760
+    },
+    {
+      "epoch": 0.047766749379652605,
+      "grad_norm": 0.4960077106952667,
+      "learning_rate": 2e-05,
+      "loss": 0.6664,
+      "step": 770
+    },
+    {
+      "epoch": 0.04838709677419355,
+      "grad_norm": 0.4341469705104828,
+      "learning_rate": 2e-05,
+      "loss": 0.6501,
+      "step": 780
+    },
+    {
+      "epoch": 0.04900744416873449,
+      "grad_norm": 0.4147971272468567,
+      "learning_rate": 2e-05,
+      "loss": 0.6439,
+      "step": 790
+    },
+    {
+      "epoch": 0.04962779156327544,
+      "grad_norm": 0.4606212377548218,
+      "learning_rate": 2e-05,
+      "loss": 0.6964,
+      "step": 800
+    },
+    {
+      "epoch": 0.05024813895781638,
+      "grad_norm": 0.4221757650375366,
+      "learning_rate": 2e-05,
+      "loss": 0.6598,
+      "step": 810
+    },
+    {
+      "epoch": 0.05086848635235732,
+      "grad_norm": 0.46451857686042786,
+      "learning_rate": 2e-05,
+      "loss": 0.6503,
+      "step": 820
+    },
+    {
+      "epoch": 0.05148883374689826,
+      "grad_norm": 0.4234520196914673,
+      "learning_rate": 2e-05,
+      "loss": 0.6702,
+      "step": 830
+    },
+    {
+      "epoch": 0.052109181141439205,
+      "grad_norm": 0.5181183218955994,
+      "learning_rate": 2e-05,
+      "loss": 0.703,
+      "step": 840
+    },
+    {
+      "epoch": 0.05272952853598015,
+      "grad_norm": 0.43921777606010437,
+      "learning_rate": 2e-05,
+      "loss": 0.6777,
+      "step": 850
+    },
+    {
+      "epoch": 0.05334987593052109,
+      "grad_norm": 0.4488343894481659,
+      "learning_rate": 2e-05,
+      "loss": 0.6661,
+      "step": 860
+    },
+    {
+      "epoch": 0.05397022332506204,
+      "grad_norm": 0.45838460326194763,
+      "learning_rate": 2e-05,
+      "loss": 0.6438,
+      "step": 870
+    },
+    {
+      "epoch": 0.05459057071960298,
+      "grad_norm": 0.42543938755989075,
+      "learning_rate": 2e-05,
+      "loss": 0.6781,
+      "step": 880
+    },
+    {
+      "epoch": 0.05521091811414392,
+      "grad_norm": 0.44000378251075745,
+      "learning_rate": 2e-05,
+      "loss": 0.656,
+      "step": 890
+    },
+    {
+      "epoch": 0.05583126550868486,
+      "grad_norm": 0.4415980279445648,
+      "learning_rate": 2e-05,
+      "loss": 0.66,
+      "step": 900
+    },
+    {
+      "epoch": 0.056451612903225805,
+      "grad_norm": 0.4455133378505707,
+      "learning_rate": 2e-05,
+      "loss": 0.6633,
+      "step": 910
+    },
+    {
+      "epoch": 0.05707196029776675,
+      "grad_norm": 0.44925546646118164,
+      "learning_rate": 2e-05,
+      "loss": 0.6833,
+      "step": 920
+    },
+    {
+      "epoch": 0.057692307692307696,
+      "grad_norm": 0.7831513285636902,
+      "learning_rate": 2e-05,
+      "loss": 0.6649,
+      "step": 930
+    },
+    {
+      "epoch": 0.05831265508684864,
+      "grad_norm": 0.5281955003738403,
+      "learning_rate": 2e-05,
+      "loss": 0.66,
+      "step": 940
+    },
+    {
+      "epoch": 0.05893300248138958,
+      "grad_norm": 0.43578600883483887,
+      "learning_rate": 2e-05,
+      "loss": 0.6886,
+      "step": 950
+    },
+    {
+      "epoch": 0.05955334987593052,
+      "grad_norm": 0.43332430720329285,
+      "learning_rate": 2e-05,
+      "loss": 0.6617,
+      "step": 960
+    },
+    {
+      "epoch": 0.06017369727047146,
+      "grad_norm": 0.46484294533729553,
+      "learning_rate": 2e-05,
+      "loss": 0.6435,
+      "step": 970
+    },
+    {
+      "epoch": 0.060794044665012405,
+      "grad_norm": 0.41882455348968506,
+      "learning_rate": 2e-05,
+      "loss": 0.6602,
+      "step": 980
+    },
+    {
+      "epoch": 0.06141439205955335,
+      "grad_norm": 0.4295177757740021,
+      "learning_rate": 2e-05,
+      "loss": 0.6784,
+      "step": 990
+    },
+    {
+      "epoch": 0.062034739454094295,
+      "grad_norm": 0.4727322459220886,
+      "learning_rate": 2e-05,
+      "loss": 0.6818,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06265508684863523,
+      "grad_norm": 0.430388480424881,
+      "learning_rate": 2e-05,
+      "loss": 0.6579,
+      "step": 1010
+    },
+    {
+      "epoch": 0.06327543424317618,
+      "grad_norm": 0.3914746642112732,
+      "learning_rate": 2e-05,
+      "loss": 0.6793,
+      "step": 1020
+    },
+    {
+      "epoch": 0.06389578163771713,
+      "grad_norm": 0.4640097916126251,
+      "learning_rate": 2e-05,
+      "loss": 0.6454,
+      "step": 1030
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.43572962284088135,
+      "learning_rate": 2e-05,
+      "loss": 0.6644,
+      "step": 1040
+    },
+    {
+      "epoch": 0.06513647642679901,
+      "grad_norm": 0.42249470949172974,
+      "learning_rate": 2e-05,
+      "loss": 0.659,
+      "step": 1050
+    },
+    {
+      "epoch": 0.06575682382133995,
+      "grad_norm": 0.45737001299858093,
+      "learning_rate": 2e-05,
+      "loss": 0.6563,
+      "step": 1060
+    },
+    {
+      "epoch": 0.0663771712158809,
+      "grad_norm": 0.39258211851119995,
+      "learning_rate": 2e-05,
+      "loss": 0.67,
+      "step": 1070
+    },
+    {
+      "epoch": 0.06699751861042183,
+      "grad_norm": 0.4379409849643707,
+      "learning_rate": 2e-05,
+      "loss": 0.6729,
+      "step": 1080
+    },
+    {
+      "epoch": 0.06761786600496278,
+      "grad_norm": 0.3982328474521637,
+      "learning_rate": 2e-05,
+      "loss": 0.659,
+      "step": 1090
+    },
+    {
+      "epoch": 0.06823821339950373,
+      "grad_norm": 0.42903372645378113,
+      "learning_rate": 2e-05,
+      "loss": 0.6594,
+      "step": 1100
+    },
+    {
+      "epoch": 0.06885856079404466,
+      "grad_norm": 0.4348221719264984,
+      "learning_rate": 2e-05,
+      "loss": 0.6313,
+      "step": 1110
+    },
+    {
+      "epoch": 0.06947890818858561,
+      "grad_norm": 0.43977659940719604,
+      "learning_rate": 2e-05,
+      "loss": 0.7013,
+      "step": 1120
+    },
+    {
+      "epoch": 0.07009925558312655,
+      "grad_norm": 0.41244375705718994,
+      "learning_rate": 2e-05,
+      "loss": 0.6474,
+      "step": 1130
+    },
+    {
+      "epoch": 0.0707196029776675,
+      "grad_norm": 0.4200294613838196,
+      "learning_rate": 2e-05,
+      "loss": 0.6853,
+      "step": 1140
+    },
+    {
+      "epoch": 0.07133995037220843,
+      "grad_norm": 0.4071672856807709,
+      "learning_rate": 2e-05,
+      "loss": 0.6773,
+      "step": 1150
+    },
+    {
+      "epoch": 0.07196029776674938,
+      "grad_norm": 0.4591241776943207,
+      "learning_rate": 2e-05,
+      "loss": 0.6901,
+      "step": 1160
+    },
+    {
+      "epoch": 0.07258064516129033,
+      "grad_norm": 0.4510512948036194,
+      "learning_rate": 2e-05,
+      "loss": 0.6751,
+      "step": 1170
+    },
+    {
+      "epoch": 0.07320099255583126,
+      "grad_norm": 0.4550836980342865,
+      "learning_rate": 2e-05,
+      "loss": 0.6745,
+      "step": 1180
+    },
+    {
+      "epoch": 0.07382133995037221,
+      "grad_norm": 0.42455634474754333,
+      "learning_rate": 2e-05,
+      "loss": 0.6852,
+      "step": 1190
+    },
+    {
+      "epoch": 0.07444168734491315,
+      "grad_norm": 0.4288151264190674,
+      "learning_rate": 2e-05,
+      "loss": 0.6362,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0750620347394541,
+      "grad_norm": 0.41488656401634216,
+      "learning_rate": 2e-05,
+      "loss": 0.6555,
+      "step": 1210
+    },
+    {
+      "epoch": 0.07568238213399504,
+      "grad_norm": 0.41888904571533203,
+      "learning_rate": 2e-05,
+      "loss": 0.6405,
+      "step": 1220
+    },
+    {
+      "epoch": 0.07630272952853598,
+      "grad_norm": 0.42407098412513733,
+      "learning_rate": 2e-05,
+      "loss": 0.6869,
+      "step": 1230
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.43882668018341064,
+      "learning_rate": 2e-05,
+      "loss": 0.6697,
+      "step": 1240
+    },
+    {
+      "epoch": 0.07754342431761786,
+      "grad_norm": 0.463724285364151,
+      "learning_rate": 2e-05,
+      "loss": 0.6606,
+      "step": 1250
+    },
+    {
+      "epoch": 0.07816377171215881,
+      "grad_norm": 0.4122724235057831,
+      "learning_rate": 2e-05,
+      "loss": 0.683,
+      "step": 1260
+    },
+    {
+      "epoch": 0.07878411910669975,
+      "grad_norm": 0.4170853793621063,
+      "learning_rate": 2e-05,
+      "loss": 0.6469,
+      "step": 1270
+    },
+    {
+      "epoch": 0.0794044665012407,
+      "grad_norm": 0.41887524724006653,
+      "learning_rate": 2e-05,
+      "loss": 0.6613,
+      "step": 1280
+    },
+    {
+      "epoch": 0.08002481389578164,
+      "grad_norm": 0.5110520720481873,
+      "learning_rate": 2e-05,
+      "loss": 0.6481,
+      "step": 1290
+    },
+    {
+      "epoch": 0.08064516129032258,
+      "grad_norm": 0.5727337002754211,
+      "learning_rate": 2e-05,
+      "loss": 0.6602,
+      "step": 1300
+    },
+    {
+      "epoch": 0.08126550868486353,
+      "grad_norm": 0.45020315051078796,
+      "learning_rate": 2e-05,
+      "loss": 0.6905,
+      "step": 1310
+    },
+    {
+      "epoch": 0.08188585607940446,
+      "grad_norm": 0.41866007447242737,
+      "learning_rate": 2e-05,
+      "loss": 0.6458,
+      "step": 1320
+    },
+    {
+      "epoch": 0.08250620347394541,
+      "grad_norm": 0.4124995768070221,
+      "learning_rate": 2e-05,
+      "loss": 0.6476,
+      "step": 1330
+    },
+    {
+      "epoch": 0.08312655086848635,
+      "grad_norm": 0.45238474011421204,
+      "learning_rate": 2e-05,
+      "loss": 0.6722,
+      "step": 1340
+    },
+    {
+      "epoch": 0.0837468982630273,
+      "grad_norm": 0.44636914134025574,
+      "learning_rate": 2e-05,
+      "loss": 0.6828,
+      "step": 1350
+    },
+    {
+      "epoch": 0.08436724565756824,
+      "grad_norm": 0.42632195353507996,
+      "learning_rate": 2e-05,
+      "loss": 0.6974,
+      "step": 1360
+    },
+    {
+      "epoch": 0.08498759305210918,
+      "grad_norm": 0.4126355051994324,
+      "learning_rate": 2e-05,
+      "loss": 0.6542,
+      "step": 1370
+    },
+    {
+      "epoch": 0.08560794044665013,
+      "grad_norm": 0.4650143086910248,
+      "learning_rate": 2e-05,
+      "loss": 0.6402,
+      "step": 1380
+    },
+    {
+      "epoch": 0.08622828784119106,
+      "grad_norm": 0.4254385530948639,
+      "learning_rate": 2e-05,
+      "loss": 0.6196,
+      "step": 1390
+    },
+    {
+      "epoch": 0.08684863523573201,
+      "grad_norm": 0.5174993872642517,
+      "learning_rate": 2e-05,
+      "loss": 0.6566,
+      "step": 1400
+    },
+    {
+      "epoch": 0.08746898263027296,
+      "grad_norm": 0.4466327428817749,
+      "learning_rate": 2e-05,
+      "loss": 0.6777,
+      "step": 1410
+    },
+    {
+      "epoch": 0.0880893300248139,
+      "grad_norm": 0.4639355540275574,
+      "learning_rate": 2e-05,
+      "loss": 0.6518,
+      "step": 1420
+    },
+    {
+      "epoch": 0.08870967741935484,
+      "grad_norm": 0.49918368458747864,
+      "learning_rate": 2e-05,
+      "loss": 0.666,
+      "step": 1430
+    },
+    {
+      "epoch": 0.08933002481389578,
+      "grad_norm": 0.45220839977264404,
+      "learning_rate": 2e-05,
+      "loss": 0.6626,
+      "step": 1440
+    },
+    {
+      "epoch": 0.08995037220843673,
+      "grad_norm": 0.40696123242378235,
+      "learning_rate": 2e-05,
+      "loss": 0.6591,
+      "step": 1450
+    },
+    {
+      "epoch": 0.09057071960297766,
+      "grad_norm": 0.42498070001602173,
+      "learning_rate": 2e-05,
+      "loss": 0.6532,
+      "step": 1460
+    },
+    {
+      "epoch": 0.09119106699751861,
+      "grad_norm": 0.4117129147052765,
+      "learning_rate": 2e-05,
+      "loss": 0.6272,
+      "step": 1470
+    },
+    {
+      "epoch": 0.09181141439205956,
+      "grad_norm": 0.4506339132785797,
+      "learning_rate": 2e-05,
+      "loss": 0.6609,
+      "step": 1480
+    },
+    {
+      "epoch": 0.0924317617866005,
+      "grad_norm": 0.40215933322906494,
+      "learning_rate": 2e-05,
+      "loss": 0.6653,
+      "step": 1490
+    },
+    {
+      "epoch": 0.09305210918114144,
+      "grad_norm": 0.4949316382408142,
+      "learning_rate": 2e-05,
+      "loss": 0.6583,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09367245657568238,
+      "grad_norm": 0.45883846282958984,
+      "learning_rate": 2e-05,
+      "loss": 0.6553,
+      "step": 1510
+    },
+    {
+      "epoch": 0.09429280397022333,
+      "grad_norm": 0.41736656427383423,
+      "learning_rate": 2e-05,
+      "loss": 0.6727,
+      "step": 1520
+    },
+    {
+      "epoch": 0.09491315136476426,
+      "grad_norm": 0.45958396792411804,
+      "learning_rate": 2e-05,
+      "loss": 0.6402,
+      "step": 1530
+    },
+    {
+      "epoch": 0.09553349875930521,
+      "grad_norm": 0.41696447134017944,
+      "learning_rate": 2e-05,
+      "loss": 0.669,
+      "step": 1540
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 0.45699238777160645,
+      "learning_rate": 2e-05,
+      "loss": 0.6421,
+      "step": 1550
+    },
+    {
+      "epoch": 0.0967741935483871,
+      "grad_norm": 0.46844539046287537,
+      "learning_rate": 2e-05,
+      "loss": 0.6628,
+      "step": 1560
+    },
+    {
+      "epoch": 0.09739454094292804,
+      "grad_norm": 0.4296782612800598,
+      "learning_rate": 2e-05,
+      "loss": 0.6468,
+      "step": 1570
+    },
+    {
+      "epoch": 0.09801488833746898,
+      "grad_norm": 0.43794864416122437,
+      "learning_rate": 2e-05,
+      "loss": 0.6708,
+      "step": 1580
+    },
+    {
+      "epoch": 0.09863523573200993,
+      "grad_norm": 0.4485463500022888,
+      "learning_rate": 2e-05,
+      "loss": 0.6537,
+      "step": 1590
+    },
+    {
+      "epoch": 0.09925558312655088,
+      "grad_norm": 0.44051381945610046,
+      "learning_rate": 2e-05,
+      "loss": 0.6378,
+      "step": 1600
+    },
+    {
+      "epoch": 0.09987593052109181,
+      "grad_norm": 0.44119101762771606,
+      "learning_rate": 2e-05,
+      "loss": 0.6503,
+      "step": 1610
+    },
+    {
+      "epoch": 0.10049627791563276,
+      "grad_norm": 0.4515126049518585,
+      "learning_rate": 2e-05,
+      "loss": 0.6647,
+      "step": 1620
+    },
+    {
+      "epoch": 0.1011166253101737,
+      "grad_norm": 0.4214085042476654,
+      "learning_rate": 2e-05,
+      "loss": 0.6483,
+      "step": 1630
+    },
+    {
+      "epoch": 0.10173697270471464,
+      "grad_norm": 0.4193068742752075,
+      "learning_rate": 2e-05,
+      "loss": 0.6685,
+      "step": 1640
+    },
+    {
+      "epoch": 0.10235732009925558,
+      "grad_norm": 0.4890860319137573,
+      "learning_rate": 2e-05,
+      "loss": 0.6529,
+      "step": 1650
+    },
+    {
+      "epoch": 0.10297766749379653,
+      "grad_norm": 0.5013541579246521,
+      "learning_rate": 2e-05,
+      "loss": 0.7078,
+      "step": 1660
+    },
+    {
+      "epoch": 0.10359801488833748,
+      "grad_norm": 0.4772087335586548,
+      "learning_rate": 2e-05,
+      "loss": 0.6574,
+      "step": 1670
+    },
+    {
+      "epoch": 0.10421836228287841,
+      "grad_norm": 0.5918506979942322,
+      "learning_rate": 2e-05,
+      "loss": 0.6668,
+      "step": 1680
+    },
+    {
+      "epoch": 0.10483870967741936,
+      "grad_norm": 0.42867156863212585,
+      "learning_rate": 2e-05,
+      "loss": 0.6556,
+      "step": 1690
+    },
+    {
+      "epoch": 0.1054590570719603,
+      "grad_norm": 0.4230250418186188,
+      "learning_rate": 2e-05,
+      "loss": 0.6564,
+      "step": 1700
+    },
+    {
+      "epoch": 0.10607940446650124,
+      "grad_norm": 0.4046623110771179,
+      "learning_rate": 2e-05,
+      "loss": 0.6691,
+      "step": 1710
+    },
+    {
+      "epoch": 0.10669975186104218,
+      "grad_norm": 0.4210417568683624,
+      "learning_rate": 2e-05,
+      "loss": 0.6675,
+      "step": 1720
+    },
+    {
+      "epoch": 0.10732009925558313,
+      "grad_norm": 0.4010581970214844,
+      "learning_rate": 2e-05,
+      "loss": 0.6402,
+      "step": 1730
+    },
+    {
+      "epoch": 0.10794044665012408,
+      "grad_norm": 0.4336850643157959,
+      "learning_rate": 2e-05,
+      "loss": 0.6568,
+      "step": 1740
+    },
+    {
+      "epoch": 0.10856079404466501,
+      "grad_norm": 0.43575379252433777,
+      "learning_rate": 2e-05,
+      "loss": 0.6493,
+      "step": 1750
+    },
+    {
+      "epoch": 0.10918114143920596,
+      "grad_norm": 0.42740049958229065,
+      "learning_rate": 2e-05,
+      "loss": 0.6571,
+      "step": 1760
+    },
+    {
+      "epoch": 0.1098014888337469,
+      "grad_norm": 0.4169295132160187,
+      "learning_rate": 2e-05,
+      "loss": 0.6611,
+      "step": 1770
+    },
+    {
+      "epoch": 0.11042183622828784,
+      "grad_norm": 0.5564378499984741,
+      "learning_rate": 2e-05,
+      "loss": 0.6532,
+      "step": 1780
+    },
+    {
+      "epoch": 0.11104218362282878,
+      "grad_norm": 0.45990580320358276,
+      "learning_rate": 2e-05,
+      "loss": 0.6262,
+      "step": 1790
+    },
+    {
+      "epoch": 0.11166253101736973,
+      "grad_norm": 0.4232894778251648,
+      "learning_rate": 2e-05,
+      "loss": 0.6729,
+      "step": 1800
+    },
+    {
+      "epoch": 0.11228287841191067,
+      "grad_norm": 0.49535107612609863,
+      "learning_rate": 2e-05,
+      "loss": 0.6808,
+      "step": 1810
+    },
+    {
+      "epoch": 0.11290322580645161,
+      "grad_norm": 0.4231373965740204,
+      "learning_rate": 2e-05,
+      "loss": 0.6731,
+      "step": 1820
+    },
+    {
+      "epoch": 0.11352357320099256,
+      "grad_norm": 0.42381367087364197,
+      "learning_rate": 2e-05,
+      "loss": 0.6672,
+      "step": 1830
+    },
+    {
+      "epoch": 0.1141439205955335,
+      "grad_norm": 0.40873488783836365,
+      "learning_rate": 2e-05,
+      "loss": 0.6471,
+      "step": 1840
+    },
+    {
+      "epoch": 0.11476426799007444,
+      "grad_norm": 0.4330880641937256,
+      "learning_rate": 2e-05,
+      "loss": 0.6653,
+      "step": 1850
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 0.47087201476097107,
+      "learning_rate": 2e-05,
+      "loss": 0.6865,
+      "step": 1860
+    },
+    {
+      "epoch": 0.11600496277915633,
+      "grad_norm": 0.49161598086357117,
+      "learning_rate": 2e-05,
+      "loss": 0.6625,
+      "step": 1870
+    },
+    {
+      "epoch": 0.11662531017369727,
+      "grad_norm": 0.40995311737060547,
+      "learning_rate": 2e-05,
+      "loss": 0.6421,
+      "step": 1880
+    },
+    {
+      "epoch": 0.11724565756823821,
+      "grad_norm": 0.40415555238723755,
+      "learning_rate": 2e-05,
+      "loss": 0.6407,
+      "step": 1890
+    },
+    {
+      "epoch": 0.11786600496277916,
+      "grad_norm": 0.42309048771858215,
+      "learning_rate": 2e-05,
+      "loss": 0.6524,
+      "step": 1900
+    },
+    {
+      "epoch": 0.1184863523573201,
+      "grad_norm": 0.428654283285141,
+      "learning_rate": 2e-05,
+      "loss": 0.6473,
+      "step": 1910
+    },
+    {
+      "epoch": 0.11910669975186104,
+      "grad_norm": 0.46681228280067444,
+      "learning_rate": 2e-05,
+      "loss": 0.665,
+      "step": 1920
+    },
+    {
+      "epoch": 0.11972704714640199,
+      "grad_norm": 0.5378752946853638,
+      "learning_rate": 2e-05,
+      "loss": 0.6888,
+      "step": 1930
+    },
+    {
+      "epoch": 0.12034739454094293,
+      "grad_norm": 0.3942810297012329,
+      "learning_rate": 2e-05,
+      "loss": 0.6693,
+      "step": 1940
+    },
+    {
+      "epoch": 0.12096774193548387,
+      "grad_norm": 0.40872716903686523,
+      "learning_rate": 2e-05,
+      "loss": 0.6564,
+      "step": 1950
+    },
+    {
+      "epoch": 0.12158808933002481,
+      "grad_norm": 0.4505879580974579,
+      "learning_rate": 2e-05,
+      "loss": 0.6651,
+      "step": 1960
+    },
+    {
+      "epoch": 0.12220843672456576,
+      "grad_norm": 0.46347737312316895,
+      "learning_rate": 2e-05,
+      "loss": 0.6682,
+      "step": 1970
+    },
+    {
+      "epoch": 0.1228287841191067,
+      "grad_norm": 0.4220800995826721,
+      "learning_rate": 2e-05,
+      "loss": 0.6633,
+      "step": 1980
+    },
+    {
+      "epoch": 0.12344913151364764,
+      "grad_norm": 0.39984744787216187,
+      "learning_rate": 2e-05,
+      "loss": 0.6379,
+      "step": 1990
+    },
+    {
+      "epoch": 0.12406947890818859,
+      "grad_norm": 0.42455461621284485,
+      "learning_rate": 2e-05,
+      "loss": 0.6442,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12468982630272953,
+      "grad_norm": 0.4262460768222809,
+      "learning_rate": 2e-05,
+      "loss": 0.6385,
+      "step": 2010
+    },
+    {
+      "epoch": 0.12531017369727046,
+      "grad_norm": 0.42343422770500183,
+      "learning_rate": 2e-05,
+      "loss": 0.6541,
+      "step": 2020
+    },
+    {
+      "epoch": 0.1259305210918114,
+      "grad_norm": 0.4029340147972107,
+      "learning_rate": 2e-05,
+      "loss": 0.6776,
+      "step": 2030
+    },
+    {
+      "epoch": 0.12655086848635236,
+      "grad_norm": 0.44888031482696533,
+      "learning_rate": 2e-05,
+      "loss": 0.6232,
+      "step": 2040
+    },
+    {
+      "epoch": 0.1271712158808933,
+      "grad_norm": 0.4395098388195038,
+      "learning_rate": 2e-05,
+      "loss": 0.6447,
+      "step": 2050
+    },
+    {
+      "epoch": 0.12779156327543426,
+      "grad_norm": 0.40587204694747925,
+      "learning_rate": 2e-05,
+      "loss": 0.6616,
+      "step": 2060
+    },
+    {
+      "epoch": 0.12841191066997518,
+      "grad_norm": 0.4486628472805023,
+      "learning_rate": 2e-05,
+      "loss": 0.6639,
+      "step": 2070
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 0.4576110243797302,
+      "learning_rate": 2e-05,
+      "loss": 0.6597,
+      "step": 2080
+    },
+    {
+      "epoch": 0.12965260545905707,
+      "grad_norm": 0.4019532799720764,
+      "learning_rate": 2e-05,
+      "loss": 0.6469,
+      "step": 2090
+    },
+    {
+      "epoch": 0.13027295285359802,
+      "grad_norm": 0.43723776936531067,
+      "learning_rate": 2e-05,
+      "loss": 0.6332,
+      "step": 2100
+    },
+    {
+      "epoch": 0.13089330024813894,
+      "grad_norm": 0.40787678956985474,
+      "learning_rate": 2e-05,
+      "loss": 0.6356,
+      "step": 2110
+    },
+    {
+      "epoch": 0.1315136476426799,
+      "grad_norm": 0.4124930799007416,
+      "learning_rate": 2e-05,
+      "loss": 0.6523,
+      "step": 2120
+    },
+    {
+      "epoch": 0.13213399503722084,
+      "grad_norm": 0.4150378108024597,
+      "learning_rate": 2e-05,
+      "loss": 0.6694,
+      "step": 2130
+    },
+    {
+      "epoch": 0.1327543424317618,
+      "grad_norm": 0.41935351490974426,
+      "learning_rate": 2e-05,
+      "loss": 0.6745,
+      "step": 2140
+    },
+    {
+      "epoch": 0.13337468982630274,
+      "grad_norm": 0.6122373938560486,
+      "learning_rate": 2e-05,
+      "loss": 0.6566,
+      "step": 2150
+    },
+    {
+      "epoch": 0.13399503722084366,
+      "grad_norm": 0.518964409828186,
+      "learning_rate": 2e-05,
+      "loss": 0.6281,
+      "step": 2160
+    },
+    {
+      "epoch": 0.1346153846153846,
+      "grad_norm": 0.45327648520469666,
+      "learning_rate": 2e-05,
+      "loss": 0.6431,
+      "step": 2170
+    },
+    {
+      "epoch": 0.13523573200992556,
+      "grad_norm": 0.41766470670700073,
+      "learning_rate": 2e-05,
+      "loss": 0.6707,
+      "step": 2180
+    },
+    {
+      "epoch": 0.1358560794044665,
+      "grad_norm": 0.43843910098075867,
+      "learning_rate": 2e-05,
+      "loss": 0.6698,
+      "step": 2190
+    },
+    {
+      "epoch": 0.13647642679900746,
+      "grad_norm": 0.5084978342056274,
+      "learning_rate": 2e-05,
+      "loss": 0.6347,
+      "step": 2200
+    },
+    {
+      "epoch": 0.13709677419354838,
+      "grad_norm": 0.4238511919975281,
+      "learning_rate": 2e-05,
+      "loss": 0.6459,
+      "step": 2210
+    },
+    {
+      "epoch": 0.13771712158808933,
+      "grad_norm": 0.4075576961040497,
+      "learning_rate": 2e-05,
+      "loss": 0.6248,
+      "step": 2220
+    },
+    {
+      "epoch": 0.13833746898263027,
+      "grad_norm": 0.4354841411113739,
+      "learning_rate": 2e-05,
+      "loss": 0.6718,
+      "step": 2230
+    },
+    {
+      "epoch": 0.13895781637717122,
+      "grad_norm": 0.5108729004859924,
+      "learning_rate": 2e-05,
+      "loss": 0.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 0.13957816377171217,
+      "grad_norm": 0.4199222922325134,
+      "learning_rate": 2e-05,
+      "loss": 0.6543,
+      "step": 2250
+    },
+    {
+      "epoch": 0.1401985111662531,
+      "grad_norm": 0.4035865068435669,
+      "learning_rate": 2e-05,
+      "loss": 0.6269,
+      "step": 2260
+    },
+    {
+      "epoch": 0.14081885856079404,
+      "grad_norm": 0.4430849254131317,
+      "learning_rate": 2e-05,
+      "loss": 0.626,
+      "step": 2270
+    },
+    {
+      "epoch": 0.141439205955335,
+      "grad_norm": 0.4501071274280548,
+      "learning_rate": 2e-05,
+      "loss": 0.6373,
+      "step": 2280
+    },
+    {
+      "epoch": 0.14205955334987594,
+      "grad_norm": 0.47260135412216187,
+      "learning_rate": 2e-05,
+      "loss": 0.6503,
+      "step": 2290
+    },
+    {
+      "epoch": 0.14267990074441686,
+      "grad_norm": 0.3968529999256134,
+      "learning_rate": 2e-05,
+      "loss": 0.6401,
+      "step": 2300
+    },
+    {
+      "epoch": 0.1433002481389578,
+      "grad_norm": 0.41558271646499634,
+      "learning_rate": 2e-05,
+      "loss": 0.6624,
+      "step": 2310
+    },
+    {
+      "epoch": 0.14392059553349876,
+      "grad_norm": 0.46250858902931213,
+      "learning_rate": 2e-05,
+      "loss": 0.6678,
+      "step": 2320
+    },
+    {
+      "epoch": 0.1445409429280397,
+      "grad_norm": 0.40959519147872925,
+      "learning_rate": 2e-05,
+      "loss": 0.6381,
+      "step": 2330
+    },
+    {
+      "epoch": 0.14516129032258066,
+      "grad_norm": 0.431772917509079,
+      "learning_rate": 2e-05,
+      "loss": 0.6485,
+      "step": 2340
+    },
+    {
+      "epoch": 0.14578163771712158,
+      "grad_norm": 0.42857933044433594,
+      "learning_rate": 2e-05,
+      "loss": 0.6469,
+      "step": 2350
+    },
+    {
+      "epoch": 0.14640198511166252,
+      "grad_norm": 0.4006024897098541,
+      "learning_rate": 2e-05,
+      "loss": 0.6752,
+      "step": 2360
+    },
+    {
+      "epoch": 0.14702233250620347,
+      "grad_norm": 0.4340827763080597,
+      "learning_rate": 2e-05,
+      "loss": 0.6407,
+      "step": 2370
+    },
+    {
+      "epoch": 0.14764267990074442,
+      "grad_norm": 0.43578338623046875,
+      "learning_rate": 2e-05,
+      "loss": 0.6463,
+      "step": 2380
+    },
+    {
+      "epoch": 0.14826302729528537,
+      "grad_norm": 0.4057551920413971,
+      "learning_rate": 2e-05,
+      "loss": 0.6295,
+      "step": 2390
+    },
+    {
+      "epoch": 0.1488833746898263,
+      "grad_norm": 0.405994713306427,
+      "learning_rate": 2e-05,
+      "loss": 0.6639,
+      "step": 2400
+    },
+    {
+      "epoch": 0.14950372208436724,
+      "grad_norm": 0.4021854102611542,
+      "learning_rate": 2e-05,
+      "loss": 0.6542,
+      "step": 2410
+    },
+    {
+      "epoch": 0.1501240694789082,
+      "grad_norm": 0.4120284914970398,
+      "learning_rate": 2e-05,
+      "loss": 0.6456,
+      "step": 2420
+    },
+    {
+      "epoch": 0.15074441687344914,
+      "grad_norm": 0.4367629289627075,
+      "learning_rate": 2e-05,
+      "loss": 0.6334,
+      "step": 2430
+    },
+    {
+      "epoch": 0.1513647642679901,
+      "grad_norm": 0.39025968313217163,
+      "learning_rate": 2e-05,
+      "loss": 0.634,
+      "step": 2440
+    },
+    {
+      "epoch": 0.151985111662531,
+      "grad_norm": 0.44010090827941895,
+      "learning_rate": 2e-05,
+      "loss": 0.6346,
+      "step": 2450
+    },
+    {
+      "epoch": 0.15260545905707196,
+      "grad_norm": 0.4358943998813629,
+      "learning_rate": 2e-05,
+      "loss": 0.6556,
+      "step": 2460
+    },
+    {
+      "epoch": 0.1532258064516129,
+      "grad_norm": 0.40464046597480774,
+      "learning_rate": 2e-05,
+      "loss": 0.6405,
+      "step": 2470
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.43297019600868225,
+      "learning_rate": 2e-05,
+      "loss": 0.6618,
+      "step": 2480
+    },
+    {
+      "epoch": 0.15446650124069478,
+      "grad_norm": 0.37946197390556335,
+      "learning_rate": 2e-05,
+      "loss": 0.6338,
+      "step": 2490
+    },
+    {
+      "epoch": 0.15508684863523572,
+      "grad_norm": 0.44986578822135925,
+      "learning_rate": 2e-05,
+      "loss": 0.6654,
+      "step": 2500
+    },
+    {
+      "epoch": 0.15570719602977667,
+      "grad_norm": 0.40377217531204224,
+      "learning_rate": 2e-05,
+      "loss": 0.6261,
+      "step": 2510
+    },
+    {
+      "epoch": 0.15632754342431762,
+      "grad_norm": 0.4069921374320984,
+      "learning_rate": 2e-05,
+      "loss": 0.6543,
+      "step": 2520
+    },
+    {
+      "epoch": 0.15694789081885857,
+      "grad_norm": 0.3909223675727844,
+      "learning_rate": 2e-05,
+      "loss": 0.6449,
+      "step": 2530
+    },
+    {
+      "epoch": 0.1575682382133995,
+      "grad_norm": 0.37389710545539856,
+      "learning_rate": 2e-05,
+      "loss": 0.6352,
+      "step": 2540
+    },
+    {
+      "epoch": 0.15818858560794044,
+      "grad_norm": 0.4050366282463074,
+      "learning_rate": 2e-05,
+      "loss": 0.6554,
+      "step": 2550
+    },
+    {
+      "epoch": 0.1588089330024814,
+      "grad_norm": 0.41864311695098877,
+      "learning_rate": 2e-05,
+      "loss": 0.6403,
+      "step": 2560
+    },
+    {
+      "epoch": 0.15942928039702234,
+      "grad_norm": 0.404889315366745,
+      "learning_rate": 2e-05,
+      "loss": 0.6523,
+      "step": 2570
+    },
+    {
+      "epoch": 0.1600496277915633,
+      "grad_norm": 0.480149507522583,
+      "learning_rate": 2e-05,
+      "loss": 0.6254,
+      "step": 2580
+    },
+    {
+      "epoch": 0.1606699751861042,
+      "grad_norm": 0.41777101159095764,
+      "learning_rate": 2e-05,
+      "loss": 0.6392,
+      "step": 2590
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 0.41992273926734924,
+      "learning_rate": 2e-05,
+      "loss": 0.6283,
+      "step": 2600
+    },
+    {
+      "epoch": 0.1619106699751861,
+      "grad_norm": 0.3978483974933624,
+      "learning_rate": 2e-05,
+      "loss": 0.6415,
+      "step": 2610
+    },
+    {
+      "epoch": 0.16253101736972705,
+      "grad_norm": 0.4051460027694702,
+      "learning_rate": 2e-05,
+      "loss": 0.6325,
+      "step": 2620
+    },
+    {
+      "epoch": 0.163151364764268,
+      "grad_norm": 0.38797181844711304,
+      "learning_rate": 2e-05,
+      "loss": 0.6538,
+      "step": 2630
+    },
+    {
+      "epoch": 0.16377171215880892,
+      "grad_norm": 0.4264223575592041,
+      "learning_rate": 2e-05,
+      "loss": 0.6079,
+      "step": 2640
+    },
+    {
+      "epoch": 0.16439205955334987,
+      "grad_norm": 0.6309807300567627,
+      "learning_rate": 2e-05,
+      "loss": 0.6443,
+      "step": 2650
+    },
+    {
+      "epoch": 0.16501240694789082,
+      "grad_norm": 0.4043954610824585,
+      "learning_rate": 2e-05,
+      "loss": 0.6587,
+      "step": 2660
+    },
+    {
+      "epoch": 0.16563275434243177,
+      "grad_norm": 0.433071106672287,
+      "learning_rate": 2e-05,
+      "loss": 0.6458,
+      "step": 2670
+    },
+    {
+      "epoch": 0.1662531017369727,
+      "grad_norm": 0.43372464179992676,
+      "learning_rate": 2e-05,
+      "loss": 0.6228,
+      "step": 2680
+    },
+    {
+      "epoch": 0.16687344913151364,
+      "grad_norm": 0.4626196324825287,
+      "learning_rate": 2e-05,
+      "loss": 0.6406,
+      "step": 2690
+    },
+    {
+      "epoch": 0.1674937965260546,
+      "grad_norm": 0.379689484834671,
+      "learning_rate": 2e-05,
+      "loss": 0.6368,
+      "step": 2700
+    },
+    {
+      "epoch": 0.16811414392059554,
+      "grad_norm": 0.43384963274002075,
+      "learning_rate": 2e-05,
+      "loss": 0.6421,
+      "step": 2710
+    },
+    {
+      "epoch": 0.1687344913151365,
+      "grad_norm": 0.5025782585144043,
+      "learning_rate": 2e-05,
+      "loss": 0.6644,
+      "step": 2720
+    },
+    {
+      "epoch": 0.1693548387096774,
+      "grad_norm": 0.398337185382843,
+      "learning_rate": 2e-05,
+      "loss": 0.6242,
+      "step": 2730
+    },
+    {
+      "epoch": 0.16997518610421836,
+      "grad_norm": 0.4152053892612457,
+      "learning_rate": 2e-05,
+      "loss": 0.674,
+      "step": 2740
+    },
+    {
+      "epoch": 0.1705955334987593,
+      "grad_norm": 0.40534213185310364,
+      "learning_rate": 2e-05,
+      "loss": 0.6372,
+      "step": 2750
+    },
+    {
+      "epoch": 0.17121588089330025,
+      "grad_norm": 0.44497600197792053,
+      "learning_rate": 2e-05,
+      "loss": 0.6453,
+      "step": 2760
+    },
+    {
+      "epoch": 0.1718362282878412,
+      "grad_norm": 0.4441177546977997,
+      "learning_rate": 2e-05,
+      "loss": 0.6467,
+      "step": 2770
+    },
+    {
+      "epoch": 0.17245657568238212,
+      "grad_norm": 0.39838549494743347,
+      "learning_rate": 2e-05,
+      "loss": 0.6359,
+      "step": 2780
+    },
+    {
+      "epoch": 0.17307692307692307,
+      "grad_norm": 0.6976585984230042,
+      "learning_rate": 2e-05,
+      "loss": 0.6335,
+      "step": 2790
+    },
+    {
+      "epoch": 0.17369727047146402,
+      "grad_norm": 0.48044341802597046,
+      "learning_rate": 2e-05,
+      "loss": 0.6604,
+      "step": 2800
+    },
+    {
+      "epoch": 0.17431761786600497,
+      "grad_norm": 0.3987114131450653,
+      "learning_rate": 2e-05,
+      "loss": 0.6348,
+      "step": 2810
+    },
+    {
+      "epoch": 0.17493796526054592,
+      "grad_norm": 0.37417376041412354,
+      "learning_rate": 2e-05,
+      "loss": 0.6302,
+      "step": 2820
+    },
+    {
+      "epoch": 0.17555831265508684,
+      "grad_norm": 0.4066050946712494,
+      "learning_rate": 2e-05,
+      "loss": 0.6319,
+      "step": 2830
+    },
+    {
+      "epoch": 0.1761786600496278,
+      "grad_norm": 0.45394909381866455,
+      "learning_rate": 2e-05,
+      "loss": 0.6278,
+      "step": 2840
+    },
+    {
+      "epoch": 0.17679900744416874,
+      "grad_norm": 0.414578378200531,
+      "learning_rate": 2e-05,
+      "loss": 0.6317,
+      "step": 2850
+    },
+    {
+      "epoch": 0.1774193548387097,
+      "grad_norm": 0.4722119867801666,
+      "learning_rate": 2e-05,
+      "loss": 0.622,
+      "step": 2860
+    },
+    {
+      "epoch": 0.1780397022332506,
+      "grad_norm": 0.42602238059043884,
+      "learning_rate": 2e-05,
+      "loss": 0.6631,
+      "step": 2870
+    },
+    {
+      "epoch": 0.17866004962779156,
+      "grad_norm": 0.43522897362709045,
+      "learning_rate": 2e-05,
+      "loss": 0.6288,
+      "step": 2880
+    },
+    {
+      "epoch": 0.1792803970223325,
+      "grad_norm": 0.4144858121871948,
+      "learning_rate": 2e-05,
+      "loss": 0.6401,
+      "step": 2890
+    },
+    {
+      "epoch": 0.17990074441687345,
+      "grad_norm": 0.4240042567253113,
+      "learning_rate": 2e-05,
+      "loss": 0.6183,
+      "step": 2900
+    },
+    {
+      "epoch": 0.1805210918114144,
+      "grad_norm": 0.4313690662384033,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 2910
+    },
+    {
+      "epoch": 0.18114143920595532,
+      "grad_norm": 0.40647462010383606,
+      "learning_rate": 2e-05,
+      "loss": 0.6423,
+      "step": 2920
+    },
+    {
+      "epoch": 0.18176178660049627,
+      "grad_norm": 0.40608322620391846,
+      "learning_rate": 2e-05,
+      "loss": 0.6345,
+      "step": 2930
+    },
+    {
+      "epoch": 0.18238213399503722,
+      "grad_norm": 0.5110368132591248,
+      "learning_rate": 2e-05,
+      "loss": 0.6505,
+      "step": 2940
+    },
+    {
+      "epoch": 0.18300248138957817,
+      "grad_norm": 1.3996773958206177,
+      "learning_rate": 2e-05,
+      "loss": 0.6334,
+      "step": 2950
+    },
+    {
+      "epoch": 0.18362282878411912,
+      "grad_norm": 0.4118184745311737,
+      "learning_rate": 2e-05,
+      "loss": 0.6325,
+      "step": 2960
+    },
+    {
+      "epoch": 0.18424317617866004,
+      "grad_norm": 0.4443102777004242,
+      "learning_rate": 2e-05,
+      "loss": 0.6667,
+      "step": 2970
+    },
+    {
+      "epoch": 0.184863523573201,
+      "grad_norm": 0.39859694242477417,
+      "learning_rate": 2e-05,
+      "loss": 0.6389,
+      "step": 2980
+    },
+    {
+      "epoch": 0.18548387096774194,
+      "grad_norm": 0.42832204699516296,
+      "learning_rate": 2e-05,
+      "loss": 0.6789,
+      "step": 2990
+    },
+    {
+      "epoch": 0.18610421836228289,
+      "grad_norm": 0.43463531136512756,
+      "learning_rate": 2e-05,
+      "loss": 0.6296,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18672456575682383,
+      "grad_norm": 0.441102534532547,
+      "learning_rate": 2e-05,
+      "loss": 0.6127,
+      "step": 3010
+    },
+    {
+      "epoch": 0.18734491315136476,
+      "grad_norm": 0.419390469789505,
+      "learning_rate": 2e-05,
+      "loss": 0.6483,
+      "step": 3020
+    },
+    {
+      "epoch": 0.1879652605459057,
+      "grad_norm": 0.41196301579475403,
+      "learning_rate": 2e-05,
+      "loss": 0.6404,
+      "step": 3030
+    },
+    {
+      "epoch": 0.18858560794044665,
+      "grad_norm": 0.3819664418697357,
+      "learning_rate": 2e-05,
+      "loss": 0.6516,
+      "step": 3040
+    },
+    {
+      "epoch": 0.1892059553349876,
+      "grad_norm": 0.40153929591178894,
+      "learning_rate": 2e-05,
+      "loss": 0.6237,
+      "step": 3050
+    },
+    {
+      "epoch": 0.18982630272952852,
+      "grad_norm": 0.4139013886451721,
+      "learning_rate": 2e-05,
+      "loss": 0.6392,
+      "step": 3060
+    },
+    {
+      "epoch": 0.19044665012406947,
+      "grad_norm": 0.40049391984939575,
+      "learning_rate": 2e-05,
+      "loss": 0.6432,
+      "step": 3070
+    },
+    {
+      "epoch": 0.19106699751861042,
+      "grad_norm": 0.4137687385082245,
+      "learning_rate": 2e-05,
+      "loss": 0.6211,
+      "step": 3080
+    },
+    {
+      "epoch": 0.19168734491315137,
+      "grad_norm": 0.43249863386154175,
+      "learning_rate": 2e-05,
+      "loss": 0.6478,
+      "step": 3090
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 0.4651578664779663,
+      "learning_rate": 2e-05,
+      "loss": 0.643,
+      "step": 3100
+    },
+    {
+      "epoch": 0.19292803970223324,
+      "grad_norm": 0.44925519824028015,
+      "learning_rate": 2e-05,
+      "loss": 0.6378,
+      "step": 3110
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 0.38708093762397766,
+      "learning_rate": 2e-05,
+      "loss": 0.6335,
+      "step": 3120
+    },
+    {
+      "epoch": 0.19416873449131514,
+      "grad_norm": 0.42161768674850464,
+      "learning_rate": 2e-05,
+      "loss": 0.6569,
+      "step": 3130
+    },
+    {
+      "epoch": 0.19478908188585609,
+      "grad_norm": 0.6364923119544983,
+      "learning_rate": 2e-05,
+      "loss": 0.617,
+      "step": 3140
+    },
+    {
+      "epoch": 0.19540942928039703,
+      "grad_norm": 0.43241891264915466,
+      "learning_rate": 2e-05,
+      "loss": 0.6428,
+      "step": 3150
+    },
+    {
+      "epoch": 0.19602977667493796,
+      "grad_norm": 0.41662028431892395,
+      "learning_rate": 2e-05,
+      "loss": 0.6495,
+      "step": 3160
+    },
+    {
+      "epoch": 0.1966501240694789,
+      "grad_norm": 0.4269491732120514,
+      "learning_rate": 2e-05,
+      "loss": 0.6473,
+      "step": 3170
+    },
+    {
+      "epoch": 0.19727047146401985,
+      "grad_norm": 0.412458211183548,
+      "learning_rate": 2e-05,
+      "loss": 0.6477,
+      "step": 3180
+    },
+    {
+      "epoch": 0.1978908188585608,
+      "grad_norm": 0.43503549695014954,
+      "learning_rate": 2e-05,
+      "loss": 0.6629,
+      "step": 3190
+    },
+    {
+      "epoch": 0.19851116625310175,
+      "grad_norm": 0.41298508644104004,
+      "learning_rate": 2e-05,
+      "loss": 0.6117,
+      "step": 3200
+    },
+    {
+      "epoch": 0.19913151364764267,
+      "grad_norm": 0.3883150815963745,
+      "learning_rate": 2e-05,
+      "loss": 0.628,
+      "step": 3210
+    },
+    {
+      "epoch": 0.19975186104218362,
+      "grad_norm": 0.4110269248485565,
+      "learning_rate": 2e-05,
+      "loss": 0.6373,
+      "step": 3220
+    },
+    {
+      "epoch": 0.20037220843672457,
+      "grad_norm": 0.4852235019207001,
+      "learning_rate": 2e-05,
+      "loss": 0.6269,
+      "step": 3230
+    },
+    {
+      "epoch": 0.20099255583126552,
+      "grad_norm": 0.3968954384326935,
+      "learning_rate": 2e-05,
+      "loss": 0.6461,
+      "step": 3240
+    },
+    {
+      "epoch": 0.20161290322580644,
+      "grad_norm": 0.45685458183288574,
+      "learning_rate": 2e-05,
+      "loss": 0.648,
+      "step": 3250
+    },
+    {
+      "epoch": 0.2022332506203474,
+      "grad_norm": 0.40747106075286865,
+      "learning_rate": 2e-05,
+      "loss": 0.6546,
+      "step": 3260
+    },
+    {
+      "epoch": 0.20285359801488834,
+      "grad_norm": 0.3848201632499695,
+      "learning_rate": 2e-05,
+      "loss": 0.6281,
+      "step": 3270
+    },
+    {
+      "epoch": 0.20347394540942929,
+      "grad_norm": 0.38959604501724243,
+      "learning_rate": 2e-05,
+      "loss": 0.6208,
+      "step": 3280
+    },
+    {
+      "epoch": 0.20409429280397023,
+      "grad_norm": 0.4149569571018219,
+      "learning_rate": 2e-05,
+      "loss": 0.6293,
+      "step": 3290
+    },
+    {
+      "epoch": 0.20471464019851116,
+      "grad_norm": 0.46731993556022644,
+      "learning_rate": 2e-05,
+      "loss": 0.6641,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2053349875930521,
+      "grad_norm": 0.4299260675907135,
+      "learning_rate": 2e-05,
+      "loss": 0.6057,
+      "step": 3310
+    },
+    {
+      "epoch": 0.20595533498759305,
+      "grad_norm": 0.4170496463775635,
+      "learning_rate": 2e-05,
+      "loss": 0.6457,
+      "step": 3320
+    },
+    {
+      "epoch": 0.206575682382134,
+      "grad_norm": 0.43017125129699707,
+      "learning_rate": 2e-05,
+      "loss": 0.6224,
+      "step": 3330
+    },
+    {
+      "epoch": 0.20719602977667495,
+      "grad_norm": 0.39833810925483704,
+      "learning_rate": 2e-05,
+      "loss": 0.6397,
+      "step": 3340
+    },
+    {
+      "epoch": 0.20781637717121587,
+      "grad_norm": 0.4055391848087311,
+      "learning_rate": 2e-05,
+      "loss": 0.6209,
+      "step": 3350
+    },
+    {
+      "epoch": 0.20843672456575682,
+      "grad_norm": 0.4533246159553528,
+      "learning_rate": 2e-05,
+      "loss": 0.6224,
+      "step": 3360
+    },
+    {
+      "epoch": 0.20905707196029777,
+      "grad_norm": 0.3952649235725403,
+      "learning_rate": 2e-05,
+      "loss": 0.6493,
+      "step": 3370
+    },
+    {
+      "epoch": 0.20967741935483872,
+      "grad_norm": 0.4192732870578766,
+      "learning_rate": 2e-05,
+      "loss": 0.6293,
+      "step": 3380
+    },
+    {
+      "epoch": 0.21029776674937964,
+      "grad_norm": 0.40987828373908997,
+      "learning_rate": 2e-05,
+      "loss": 0.6222,
+      "step": 3390
+    },
+    {
+      "epoch": 0.2109181141439206,
+      "grad_norm": 0.41994917392730713,
+      "learning_rate": 2e-05,
+      "loss": 0.6556,
+      "step": 3400
+    },
+    {
+      "epoch": 0.21153846153846154,
+      "grad_norm": 0.42132651805877686,
+      "learning_rate": 2e-05,
+      "loss": 0.6443,
+      "step": 3410
+    },
+    {
+      "epoch": 0.21215880893300249,
+      "grad_norm": 0.4320928156375885,
+      "learning_rate": 2e-05,
+      "loss": 0.6461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.21277915632754343,
+      "grad_norm": 0.435435950756073,
+      "learning_rate": 2e-05,
+      "loss": 0.6255,
+      "step": 3430
+    },
+    {
+      "epoch": 0.21339950372208435,
+      "grad_norm": 0.41047704219818115,
+      "learning_rate": 2e-05,
+      "loss": 0.6422,
+      "step": 3440
+    },
+    {
+      "epoch": 0.2140198511166253,
+      "grad_norm": 0.3944700062274933,
+      "learning_rate": 2e-05,
+      "loss": 0.621,
+      "step": 3450
+    },
+    {
+      "epoch": 0.21464019851116625,
+      "grad_norm": 0.42940741777420044,
+      "learning_rate": 2e-05,
+      "loss": 0.6196,
+      "step": 3460
+    },
+    {
+      "epoch": 0.2152605459057072,
+      "grad_norm": 0.3980760872364044,
+      "learning_rate": 2e-05,
+      "loss": 0.6412,
+      "step": 3470
+    },
+    {
+      "epoch": 0.21588089330024815,
+      "grad_norm": 0.39118990302085876,
+      "learning_rate": 2e-05,
+      "loss": 0.6249,
+      "step": 3480
+    },
+    {
+      "epoch": 0.21650124069478907,
+      "grad_norm": 0.44674456119537354,
+      "learning_rate": 2e-05,
+      "loss": 0.6394,
+      "step": 3490
+    },
+    {
+      "epoch": 0.21712158808933002,
+      "grad_norm": 0.42848122119903564,
+      "learning_rate": 2e-05,
+      "loss": 0.6354,
+      "step": 3500
+    },
+    {
+      "epoch": 0.21774193548387097,
+      "grad_norm": 0.44583410024642944,
+      "learning_rate": 2e-05,
+      "loss": 0.6453,
+      "step": 3510
+    },
+    {
+      "epoch": 0.21836228287841192,
+      "grad_norm": 0.44389545917510986,
+      "learning_rate": 2e-05,
+      "loss": 0.6652,
+      "step": 3520
+    },
+    {
+      "epoch": 0.21898263027295287,
+      "grad_norm": 0.38134288787841797,
+      "learning_rate": 2e-05,
+      "loss": 0.6203,
+      "step": 3530
+    },
+    {
+      "epoch": 0.2196029776674938,
+      "grad_norm": 0.4165913462638855,
+      "learning_rate": 2e-05,
+      "loss": 0.643,
+      "step": 3540
+    },
+    {
+      "epoch": 0.22022332506203474,
+      "grad_norm": 0.4155155420303345,
+      "learning_rate": 2e-05,
+      "loss": 0.6491,
+      "step": 3550
+    },
+    {
+      "epoch": 0.22084367245657568,
+      "grad_norm": 0.390639066696167,
+      "learning_rate": 2e-05,
+      "loss": 0.6182,
+      "step": 3560
+    },
+    {
+      "epoch": 0.22146401985111663,
+      "grad_norm": 0.43849295377731323,
+      "learning_rate": 2e-05,
+      "loss": 0.6379,
+      "step": 3570
+    },
+    {
+      "epoch": 0.22208436724565755,
+      "grad_norm": 0.3993423283100128,
+      "learning_rate": 2e-05,
+      "loss": 0.6588,
+      "step": 3580
+    },
+    {
+      "epoch": 0.2227047146401985,
+      "grad_norm": 0.4390069246292114,
+      "learning_rate": 2e-05,
+      "loss": 0.6071,
+      "step": 3590
+    },
+    {
+      "epoch": 0.22332506203473945,
+      "grad_norm": 0.37074384093284607,
+      "learning_rate": 2e-05,
+      "loss": 0.6336,
+      "step": 3600
+    },
+    {
+      "epoch": 0.2239454094292804,
+      "grad_norm": 0.4541170597076416,
+      "learning_rate": 2e-05,
+      "loss": 0.65,
+      "step": 3610
+    },
+    {
+      "epoch": 0.22456575682382135,
+      "grad_norm": 0.41161370277404785,
+      "learning_rate": 2e-05,
+      "loss": 0.6127,
+      "step": 3620
+    },
+    {
+      "epoch": 0.22518610421836227,
+      "grad_norm": 0.39428696036338806,
+      "learning_rate": 2e-05,
+      "loss": 0.6452,
+      "step": 3630
+    },
+    {
+      "epoch": 0.22580645161290322,
+      "grad_norm": 0.3822895586490631,
+      "learning_rate": 2e-05,
+      "loss": 0.625,
+      "step": 3640
+    },
+    {
+      "epoch": 0.22642679900744417,
+      "grad_norm": 0.5086479783058167,
+      "learning_rate": 2e-05,
+      "loss": 0.6069,
+      "step": 3650
+    },
+    {
+      "epoch": 0.22704714640198512,
+      "grad_norm": 0.43685758113861084,
+      "learning_rate": 2e-05,
+      "loss": 0.6357,
+      "step": 3660
+    },
+    {
+      "epoch": 0.22766749379652607,
+      "grad_norm": 0.44833698868751526,
+      "learning_rate": 2e-05,
+      "loss": 0.6288,
+      "step": 3670
+    },
+    {
+      "epoch": 0.228287841191067,
+      "grad_norm": 0.695853590965271,
+      "learning_rate": 2e-05,
+      "loss": 0.631,
+      "step": 3680
+    },
+    {
+      "epoch": 0.22890818858560794,
+      "grad_norm": 0.403007835149765,
+      "learning_rate": 2e-05,
+      "loss": 0.6306,
+      "step": 3690
+    },
+    {
+      "epoch": 0.22952853598014888,
+      "grad_norm": 0.45625439286231995,
+      "learning_rate": 2e-05,
+      "loss": 0.6404,
+      "step": 3700
+    },
+    {
+      "epoch": 0.23014888337468983,
+      "grad_norm": 0.4494592249393463,
+      "learning_rate": 2e-05,
+      "loss": 0.6482,
+      "step": 3710
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.39842021465301514,
+      "learning_rate": 2e-05,
+      "loss": 0.6518,
+      "step": 3720
+    },
+    {
+      "epoch": 0.2313895781637717,
+      "grad_norm": 0.45455050468444824,
+      "learning_rate": 2e-05,
+      "loss": 0.6392,
+      "step": 3730
+    },
+    {
+      "epoch": 0.23200992555831265,
+      "grad_norm": 0.40073955059051514,
+      "learning_rate": 2e-05,
+      "loss": 0.6239,
+      "step": 3740
+    },
+    {
+      "epoch": 0.2326302729528536,
+      "grad_norm": 0.40425387024879456,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 3750
+    },
+    {
+      "epoch": 0.23325062034739455,
+      "grad_norm": 0.38586944341659546,
+      "learning_rate": 2e-05,
+      "loss": 0.6236,
+      "step": 3760
+    },
+    {
+      "epoch": 0.23387096774193547,
+      "grad_norm": 0.4220291078090668,
+      "learning_rate": 2e-05,
+      "loss": 0.6245,
+      "step": 3770
+    },
+    {
+      "epoch": 0.23449131513647642,
+      "grad_norm": 0.39111921191215515,
+      "learning_rate": 2e-05,
+      "loss": 0.6206,
+      "step": 3780
+    },
+    {
+      "epoch": 0.23511166253101737,
+      "grad_norm": 0.4438347816467285,
+      "learning_rate": 2e-05,
+      "loss": 0.626,
+      "step": 3790
+    },
+    {
+      "epoch": 0.23573200992555832,
+      "grad_norm": 0.4105881154537201,
+      "learning_rate": 2e-05,
+      "loss": 0.6152,
+      "step": 3800
+    },
+    {
+      "epoch": 0.23635235732009927,
+      "grad_norm": 0.5986375212669373,
+      "learning_rate": 2e-05,
+      "loss": 0.6332,
+      "step": 3810
+    },
+    {
+      "epoch": 0.2369727047146402,
+      "grad_norm": 0.42196112871170044,
+      "learning_rate": 2e-05,
+      "loss": 0.6344,
+      "step": 3820
+    },
+    {
+      "epoch": 0.23759305210918114,
+      "grad_norm": 0.4690241813659668,
+      "learning_rate": 2e-05,
+      "loss": 0.6326,
+      "step": 3830
+    },
+    {
+      "epoch": 0.23821339950372208,
+      "grad_norm": 0.39249280095100403,
+      "learning_rate": 2e-05,
+      "loss": 0.644,
+      "step": 3840
+    },
+    {
+      "epoch": 0.23883374689826303,
+      "grad_norm": 0.3836807310581207,
+      "learning_rate": 2e-05,
+      "loss": 0.643,
+      "step": 3850
+    },
+    {
+      "epoch": 0.23945409429280398,
+      "grad_norm": 0.39411523938179016,
+      "learning_rate": 2e-05,
+      "loss": 0.6168,
+      "step": 3860
+    },
+    {
+      "epoch": 0.2400744416873449,
+      "grad_norm": 0.39570122957229614,
+      "learning_rate": 2e-05,
+      "loss": 0.6458,
+      "step": 3870
+    },
+    {
+      "epoch": 0.24069478908188585,
+      "grad_norm": 0.4410209059715271,
+      "learning_rate": 2e-05,
+      "loss": 0.6357,
+      "step": 3880
+    },
+    {
+      "epoch": 0.2413151364764268,
+      "grad_norm": 0.41891351342201233,
+      "learning_rate": 2e-05,
+      "loss": 0.645,
+      "step": 3890
+    },
+    {
+      "epoch": 0.24193548387096775,
+      "grad_norm": 0.3815721273422241,
+      "learning_rate": 2e-05,
+      "loss": 0.6197,
+      "step": 3900
+    },
+    {
+      "epoch": 0.2425558312655087,
+      "grad_norm": 0.42668625712394714,
+      "learning_rate": 2e-05,
+      "loss": 0.6512,
+      "step": 3910
+    },
+    {
+      "epoch": 0.24317617866004962,
+      "grad_norm": 0.44440335035324097,
+      "learning_rate": 2e-05,
+      "loss": 0.6286,
+      "step": 3920
+    },
+    {
+      "epoch": 0.24379652605459057,
+      "grad_norm": 0.4490135908126831,
+      "learning_rate": 2e-05,
+      "loss": 0.6429,
+      "step": 3930
+    },
+    {
+      "epoch": 0.24441687344913152,
+      "grad_norm": 0.3730720281600952,
+      "learning_rate": 2e-05,
+      "loss": 0.6178,
+      "step": 3940
+    },
+    {
+      "epoch": 0.24503722084367247,
+      "grad_norm": 0.4244785010814667,
+      "learning_rate": 2e-05,
+      "loss": 0.667,
+      "step": 3950
+    },
+    {
+      "epoch": 0.2456575682382134,
+      "grad_norm": 0.38650715351104736,
+      "learning_rate": 2e-05,
+      "loss": 0.6116,
+      "step": 3960
+    },
+    {
+      "epoch": 0.24627791563275434,
+      "grad_norm": 0.38137051463127136,
+      "learning_rate": 2e-05,
+      "loss": 0.6411,
+      "step": 3970
+    },
+    {
+      "epoch": 0.24689826302729528,
+      "grad_norm": 0.4392582178115845,
+      "learning_rate": 2e-05,
+      "loss": 0.6296,
+      "step": 3980
+    },
+    {
+      "epoch": 0.24751861042183623,
+      "grad_norm": 0.40702107548713684,
+      "learning_rate": 2e-05,
+      "loss": 0.6369,
+      "step": 3990
+    },
+    {
+      "epoch": 0.24813895781637718,
+      "grad_norm": 0.3724535405635834,
+      "learning_rate": 2e-05,
+      "loss": 0.6209,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2487593052109181,
+      "grad_norm": 0.38708439469337463,
+      "learning_rate": 2e-05,
+      "loss": 0.6208,
+      "step": 4010
+    },
+    {
+      "epoch": 0.24937965260545905,
+      "grad_norm": 0.46000051498413086,
+      "learning_rate": 2e-05,
+      "loss": 0.6162,
+      "step": 4020
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.41148972511291504,
+      "learning_rate": 2e-05,
+      "loss": 0.589,
+      "step": 4030
+    },
+    {
+      "epoch": 0.2506203473945409,
+      "grad_norm": 0.40816742181777954,
+      "learning_rate": 2e-05,
+      "loss": 0.6286,
+      "step": 4040
+    },
+    {
+      "epoch": 0.2512406947890819,
+      "grad_norm": 0.3669893741607666,
+      "learning_rate": 2e-05,
+      "loss": 0.6382,
+      "step": 4050
+    },
+    {
+      "epoch": 0.2518610421836228,
+      "grad_norm": 0.4152558743953705,
+      "learning_rate": 2e-05,
+      "loss": 0.6367,
+      "step": 4060
+    },
+    {
+      "epoch": 0.2524813895781638,
+      "grad_norm": 0.4094124734401703,
+      "learning_rate": 2e-05,
+      "loss": 0.6322,
+      "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 sha256:13f3f13da2e5ca567b4f8a9a0c2e0acafa771d616b1aefeea391df39d83d57a5
+size 7953