Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip 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

200M/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
+}

200M/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 %}

200M/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
+}

200M/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

200M/latest

@@ -0,0 +1 @@
+global_step2035

200M/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27242b4c8ed87d596ceebb4b0791d3fcc69de0d2e06fe610e8b0401c95040f38
+size 4902257696

200M/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218da080dc90fc47905118dddbf5061655e0d3b7c868c9e5fc50cce2b0ca0852
+size 4915960368

200M/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113f56a92d099737cade0071b83ba444ade51facce73364a782a673998f88c0f
+size 4983068496

200M/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e00135bef6597c648d40b77d1369df04c8c783f2b74ab7e3de64b205dd8260
+size 1580230264

200M/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"
+  }
+}

200M/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7dcf54a8dbd1fff243640ddc034149fbe7c90ed70b8a95a6bb093e989a7577
+size 14469

200M/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a2b0b9d330140afd742a57df45106276d425d38a78e53b0fd43dba9559f8d4
+size 14469

200M/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce222f8f11fd62fd6cb82264500aefbc9e7ef16907ed3e4aa3a8a99c21d95d3
+size 14476

200M/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07144bfc4ed675dda70ab66923d17d6f9233560b2db09689cbe1f262c590c88
+size 14476

200M/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5db634f6ed5151d3c898fbe3c365f950516c404bed926de16b253b26e63c7cf
+size 14469

200M/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad774eade44525098fff2d5910e3d16565fca4c2af29ed0bc4d9315a8ac9607a
+size 14469

200M/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdee1b37be2238764bcfeed9dad268e938248152b0fba60eaf89adda99eac0f
+size 14469

200M/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6046157bd3d69a7cf6ee508b7359b30cb71488a11b11b07a614041b06813c553
+size 14469

200M/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc9300f101a324d0361f01aec1d57e26b57a703b4e536f4fe982c8ba57a9144
+size 14469

200M/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357df7b609d6ffd7f22b998281f7856a711ee83505e5ed2835959554b0185df7
+size 14469

200M/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb33667d752a94ade6841f62b8b8fcc22256b4712bd568b141bc690d4a42e11
+size 14469

200M/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354a7a38e97ba11b8ad29bf4d00d74f92295b32124cff0ef46baa862aa9b0f2f
+size 14469

200M/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea084231345496123a1e2e3e6e6377891838cfabbf1b42517ab7575e5966916e
+size 1465

200M/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
+  }
+}

200M/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

200M/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
+}

200M/trainer_state.json

@@ -0,0 +1,1455 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1262406947890819,
+  "eval_steps": 500,
+  "global_step": 2035,
+  "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
+    }
+  ],
+  "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": 9.084295122442519e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

200M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f3f13da2e5ca567b4f8a9a0c2e0acafa771d616b1aefeea391df39d83d57a5
+size 7953