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 sha256:692ce5823f05d965b9f1734eb0c89b53dd4b995de150b163c14a6c7a5db1615c
+size 4902257696

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427d8ebf3bba9fd0aed4a26314b50ffbfaba86e0704b7f22709d6bbf28ef9683
+size 4915960368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d18fb1180f216be3c6abfe40496032246335385f00ee870be49b771efc5d274
+size 4983068496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86da431bc08222c45f3174bf9962e2aecb688b07729111830bc22edf61bbd9f
+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": 0.08691752445222739,
+  "eval_steps": 500,
+  "global_step": 2035,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00042711314227138767,
+      "grad_norm": 0.6801537275314331,
+      "learning_rate": 2.910112359550562e-06,
+      "loss": 0.6308,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008542262845427753,
+      "grad_norm": 0.7330222725868225,
+      "learning_rate": 3.921348314606742e-06,
+      "loss": 0.5921,
+      "step": 20
+    },
+    {
+      "epoch": 0.001281339426814163,
+      "grad_norm": 0.7190220952033997,
+      "learning_rate": 4.932584269662922e-06,
+      "loss": 0.6197,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017084525690855507,
+      "grad_norm": 0.6695777773857117,
+      "learning_rate": 5.943820224719102e-06,
+      "loss": 0.6225,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021355657113569385,
+      "grad_norm": 0.7244643568992615,
+      "learning_rate": 6.955056179775282e-06,
+      "loss": 0.5868,
+      "step": 50
+    },
+    {
+      "epoch": 0.002562678853628326,
+      "grad_norm": 0.7338688373565674,
+      "learning_rate": 7.966292134831462e-06,
+      "loss": 0.602,
+      "step": 60
+    },
+    {
+      "epoch": 0.0029897919958997137,
+      "grad_norm": 0.7063023447990417,
+      "learning_rate": 8.977528089887641e-06,
+      "loss": 0.5962,
+      "step": 70
+    },
+    {
+      "epoch": 0.0034169051381711013,
+      "grad_norm": 0.7280859351158142,
+      "learning_rate": 9.988764044943822e-06,
+      "loss": 0.5849,
+      "step": 80
+    },
+    {
+      "epoch": 0.0038440182804424894,
+      "grad_norm": 0.6686920523643494,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.5945,
+      "step": 90
+    },
+    {
+      "epoch": 0.004271131422713877,
+      "grad_norm": 0.6424954533576965,
+      "learning_rate": 1.2011235955056182e-05,
+      "loss": 0.5742,
+      "step": 100
+    },
+    {
+      "epoch": 0.004698244564985265,
+      "grad_norm": 0.7504611015319824,
+      "learning_rate": 1.3022471910112362e-05,
+      "loss": 0.6183,
+      "step": 110
+    },
+    {
+      "epoch": 0.005125357707256652,
+      "grad_norm": 0.7265036106109619,
+      "learning_rate": 1.403370786516854e-05,
+      "loss": 0.6288,
+      "step": 120
+    },
+    {
+      "epoch": 0.00555247084952804,
+      "grad_norm": 0.6728747487068176,
+      "learning_rate": 1.504494382022472e-05,
+      "loss": 0.5932,
+      "step": 130
+    },
+    {
+      "epoch": 0.005979583991799427,
+      "grad_norm": 0.5877931118011475,
+      "learning_rate": 1.60561797752809e-05,
+      "loss": 0.6073,
+      "step": 140
+    },
+    {
+      "epoch": 0.0064066971340708155,
+      "grad_norm": 0.9119960069656372,
+      "learning_rate": 1.706741573033708e-05,
+      "loss": 0.594,
+      "step": 150
+    },
+    {
+      "epoch": 0.006833810276342203,
+      "grad_norm": 0.6038461327552795,
+      "learning_rate": 1.8078651685393256e-05,
+      "loss": 0.6186,
+      "step": 160
+    },
+    {
+      "epoch": 0.007260923418613591,
+      "grad_norm": 0.6067227125167847,
+      "learning_rate": 1.908988764044944e-05,
+      "loss": 0.608,
+      "step": 170
+    },
+    {
+      "epoch": 0.007688036560884979,
+      "grad_norm": 0.6028957962989807,
+      "learning_rate": 2e-05,
+      "loss": 0.5816,
+      "step": 180
+    },
+    {
+      "epoch": 0.008115149703156367,
+      "grad_norm": 0.5894806385040283,
+      "learning_rate": 2e-05,
+      "loss": 0.604,
+      "step": 190
+    },
+    {
+      "epoch": 0.008542262845427754,
+      "grad_norm": 0.5551896691322327,
+      "learning_rate": 2e-05,
+      "loss": 0.6181,
+      "step": 200
+    },
+    {
+      "epoch": 0.008969375987699141,
+      "grad_norm": 0.48914626240730286,
+      "learning_rate": 2e-05,
+      "loss": 0.6003,
+      "step": 210
+    },
+    {
+      "epoch": 0.00939648912997053,
+      "grad_norm": 0.5296058058738708,
+      "learning_rate": 2e-05,
+      "loss": 0.6201,
+      "step": 220
+    },
+    {
+      "epoch": 0.009823602272241917,
+      "grad_norm": 0.7409117221832275,
+      "learning_rate": 2e-05,
+      "loss": 0.5938,
+      "step": 230
+    },
+    {
+      "epoch": 0.010250715414513304,
+      "grad_norm": 0.5655877590179443,
+      "learning_rate": 2e-05,
+      "loss": 0.5714,
+      "step": 240
+    },
+    {
+      "epoch": 0.010677828556784692,
+      "grad_norm": 0.4660634696483612,
+      "learning_rate": 2e-05,
+      "loss": 0.5736,
+      "step": 250
+    },
+    {
+      "epoch": 0.01110494169905608,
+      "grad_norm": 0.437298059463501,
+      "learning_rate": 2e-05,
+      "loss": 0.5944,
+      "step": 260
+    },
+    {
+      "epoch": 0.011532054841327468,
+      "grad_norm": 0.7993448376655579,
+      "learning_rate": 2e-05,
+      "loss": 0.5918,
+      "step": 270
+    },
+    {
+      "epoch": 0.011959167983598855,
+      "grad_norm": 0.46986427903175354,
+      "learning_rate": 2e-05,
+      "loss": 0.6001,
+      "step": 280
+    },
+    {
+      "epoch": 0.012386281125870244,
+      "grad_norm": 0.4165823459625244,
+      "learning_rate": 2e-05,
+      "loss": 0.5817,
+      "step": 290
+    },
+    {
+      "epoch": 0.012813394268141631,
+      "grad_norm": 0.4695897102355957,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 300
+    },
+    {
+      "epoch": 0.013240507410413018,
+      "grad_norm": 0.46940892934799194,
+      "learning_rate": 2e-05,
+      "loss": 0.6293,
+      "step": 310
+    },
+    {
+      "epoch": 0.013667620552684405,
+      "grad_norm": 0.37120378017425537,
+      "learning_rate": 2e-05,
+      "loss": 0.6057,
+      "step": 320
+    },
+    {
+      "epoch": 0.014094733694955794,
+      "grad_norm": 0.4567081928253174,
+      "learning_rate": 2e-05,
+      "loss": 0.6088,
+      "step": 330
+    },
+    {
+      "epoch": 0.014521846837227181,
+      "grad_norm": 0.5053907036781311,
+      "learning_rate": 2e-05,
+      "loss": 0.575,
+      "step": 340
+    },
+    {
+      "epoch": 0.014948959979498569,
+      "grad_norm": 0.4822077453136444,
+      "learning_rate": 2e-05,
+      "loss": 0.6305,
+      "step": 350
+    },
+    {
+      "epoch": 0.015376073121769957,
+      "grad_norm": 0.42418718338012695,
+      "learning_rate": 2e-05,
+      "loss": 0.609,
+      "step": 360
+    },
+    {
+      "epoch": 0.015803186264041345,
+      "grad_norm": 0.4470791816711426,
+      "learning_rate": 2e-05,
+      "loss": 0.609,
+      "step": 370
+    },
+    {
+      "epoch": 0.016230299406312734,
+      "grad_norm": 0.4747907221317291,
+      "learning_rate": 2e-05,
+      "loss": 0.5753,
+      "step": 380
+    },
+    {
+      "epoch": 0.01665741254858412,
+      "grad_norm": 0.429513156414032,
+      "learning_rate": 2e-05,
+      "loss": 0.5757,
+      "step": 390
+    },
+    {
+      "epoch": 0.017084525690855508,
+      "grad_norm": 1.1115094423294067,
+      "learning_rate": 2e-05,
+      "loss": 0.5973,
+      "step": 400
+    },
+    {
+      "epoch": 0.017511638833126897,
+      "grad_norm": 0.4465528130531311,
+      "learning_rate": 2e-05,
+      "loss": 0.6135,
+      "step": 410
+    },
+    {
+      "epoch": 0.017938751975398282,
+      "grad_norm": 0.45542335510253906,
+      "learning_rate": 2e-05,
+      "loss": 0.5925,
+      "step": 420
+    },
+    {
+      "epoch": 0.01836586511766967,
+      "grad_norm": 0.4971701204776764,
+      "learning_rate": 2e-05,
+      "loss": 0.6015,
+      "step": 430
+    },
+    {
+      "epoch": 0.01879297825994106,
+      "grad_norm": 0.4876435101032257,
+      "learning_rate": 2e-05,
+      "loss": 0.612,
+      "step": 440
+    },
+    {
+      "epoch": 0.019220091402212446,
+      "grad_norm": 0.4507445693016052,
+      "learning_rate": 2e-05,
+      "loss": 0.6096,
+      "step": 450
+    },
+    {
+      "epoch": 0.019647204544483834,
+      "grad_norm": 0.48777464032173157,
+      "learning_rate": 2e-05,
+      "loss": 0.5804,
+      "step": 460
+    },
+    {
+      "epoch": 0.02007431768675522,
+      "grad_norm": 0.42354583740234375,
+      "learning_rate": 2e-05,
+      "loss": 0.6102,
+      "step": 470
+    },
+    {
+      "epoch": 0.02050143082902661,
+      "grad_norm": 0.4695739448070526,
+      "learning_rate": 2e-05,
+      "loss": 0.6343,
+      "step": 480
+    },
+    {
+      "epoch": 0.020928543971297998,
+      "grad_norm": 0.4769243896007538,
+      "learning_rate": 2e-05,
+      "loss": 0.5989,
+      "step": 490
+    },
+    {
+      "epoch": 0.021355657113569383,
+      "grad_norm": 0.44087329506874084,
+      "learning_rate": 2e-05,
+      "loss": 0.5978,
+      "step": 500
+    },
+    {
+      "epoch": 0.021782770255840772,
+      "grad_norm": 0.42501866817474365,
+      "learning_rate": 2e-05,
+      "loss": 0.6133,
+      "step": 510
+    },
+    {
+      "epoch": 0.02220988339811216,
+      "grad_norm": 0.38661816716194153,
+      "learning_rate": 2e-05,
+      "loss": 0.6056,
+      "step": 520
+    },
+    {
+      "epoch": 0.022636996540383546,
+      "grad_norm": 0.43126940727233887,
+      "learning_rate": 2e-05,
+      "loss": 0.5679,
+      "step": 530
+    },
+    {
+      "epoch": 0.023064109682654935,
+      "grad_norm": 0.433454304933548,
+      "learning_rate": 2e-05,
+      "loss": 0.6074,
+      "step": 540
+    },
+    {
+      "epoch": 0.023491222824926324,
+      "grad_norm": 0.3950791656970978,
+      "learning_rate": 2e-05,
+      "loss": 0.6267,
+      "step": 550
+    },
+    {
+      "epoch": 0.02391833596719771,
+      "grad_norm": 0.42388349771499634,
+      "learning_rate": 2e-05,
+      "loss": 0.6457,
+      "step": 560
+    },
+    {
+      "epoch": 0.0243454491094691,
+      "grad_norm": 0.4391220510005951,
+      "learning_rate": 2e-05,
+      "loss": 0.6222,
+      "step": 570
+    },
+    {
+      "epoch": 0.024772562251740488,
+      "grad_norm": 0.4486788213253021,
+      "learning_rate": 2e-05,
+      "loss": 0.6232,
+      "step": 580
+    },
+    {
+      "epoch": 0.025199675394011873,
+      "grad_norm": 0.5258558988571167,
+      "learning_rate": 2e-05,
+      "loss": 0.6157,
+      "step": 590
+    },
+    {
+      "epoch": 0.025626788536283262,
+      "grad_norm": 0.3985844552516937,
+      "learning_rate": 2e-05,
+      "loss": 0.5623,
+      "step": 600
+    },
+    {
+      "epoch": 0.02605390167855465,
+      "grad_norm": 0.4276188910007477,
+      "learning_rate": 2e-05,
+      "loss": 0.589,
+      "step": 610
+    },
+    {
+      "epoch": 0.026481014820826036,
+      "grad_norm": 0.36040425300598145,
+      "learning_rate": 2e-05,
+      "loss": 0.5889,
+      "step": 620
+    },
+    {
+      "epoch": 0.026908127963097425,
+      "grad_norm": 0.43689343333244324,
+      "learning_rate": 2e-05,
+      "loss": 0.586,
+      "step": 630
+    },
+    {
+      "epoch": 0.02733524110536881,
+      "grad_norm": 0.38051506876945496,
+      "learning_rate": 2e-05,
+      "loss": 0.6155,
+      "step": 640
+    },
+    {
+      "epoch": 0.0277623542476402,
+      "grad_norm": 0.375367134809494,
+      "learning_rate": 2e-05,
+      "loss": 0.6267,
+      "step": 650
+    },
+    {
+      "epoch": 0.02818946738991159,
+      "grad_norm": 0.40035131573677063,
+      "learning_rate": 2e-05,
+      "loss": 0.6035,
+      "step": 660
+    },
+    {
+      "epoch": 0.028616580532182974,
+      "grad_norm": 0.429284006357193,
+      "learning_rate": 2e-05,
+      "loss": 0.5957,
+      "step": 670
+    },
+    {
+      "epoch": 0.029043693674454363,
+      "grad_norm": 0.4076769948005676,
+      "learning_rate": 2e-05,
+      "loss": 0.599,
+      "step": 680
+    },
+    {
+      "epoch": 0.02947080681672575,
+      "grad_norm": 0.39563876390457153,
+      "learning_rate": 2e-05,
+      "loss": 0.5906,
+      "step": 690
+    },
+    {
+      "epoch": 0.029897919958997137,
+      "grad_norm": 0.39621901512145996,
+      "learning_rate": 2e-05,
+      "loss": 0.615,
+      "step": 700
+    },
+    {
+      "epoch": 0.030325033101268526,
+      "grad_norm": 0.43017053604125977,
+      "learning_rate": 2e-05,
+      "loss": 0.6114,
+      "step": 710
+    },
+    {
+      "epoch": 0.030752146243539915,
+      "grad_norm": 0.3699895143508911,
+      "learning_rate": 2e-05,
+      "loss": 0.6024,
+      "step": 720
+    },
+    {
+      "epoch": 0.0311792593858113,
+      "grad_norm": 0.39387860894203186,
+      "learning_rate": 2e-05,
+      "loss": 0.5797,
+      "step": 730
+    },
+    {
+      "epoch": 0.03160637252808269,
+      "grad_norm": 0.36330047249794006,
+      "learning_rate": 2e-05,
+      "loss": 0.5641,
+      "step": 740
+    },
+    {
+      "epoch": 0.03203348567035408,
+      "grad_norm": 0.3734346628189087,
+      "learning_rate": 2e-05,
+      "loss": 0.6066,
+      "step": 750
+    },
+    {
+      "epoch": 0.03246059881262547,
+      "grad_norm": 0.3981451690196991,
+      "learning_rate": 2e-05,
+      "loss": 0.5708,
+      "step": 760
+    },
+    {
+      "epoch": 0.03288771195489685,
+      "grad_norm": 0.5013331770896912,
+      "learning_rate": 2e-05,
+      "loss": 0.5786,
+      "step": 770
+    },
+    {
+      "epoch": 0.03331482509716824,
+      "grad_norm": 0.4515092968940735,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 780
+    },
+    {
+      "epoch": 0.03374193823943963,
+      "grad_norm": 0.4270780682563782,
+      "learning_rate": 2e-05,
+      "loss": 0.6274,
+      "step": 790
+    },
+    {
+      "epoch": 0.034169051381711016,
+      "grad_norm": 0.40977057814598083,
+      "learning_rate": 2e-05,
+      "loss": 0.5903,
+      "step": 800
+    },
+    {
+      "epoch": 0.034596164523982405,
+      "grad_norm": 0.3862808644771576,
+      "learning_rate": 2e-05,
+      "loss": 0.591,
+      "step": 810
+    },
+    {
+      "epoch": 0.035023277666253794,
+      "grad_norm": 0.3566862642765045,
+      "learning_rate": 2e-05,
+      "loss": 0.5822,
+      "step": 820
+    },
+    {
+      "epoch": 0.035450390808525176,
+      "grad_norm": 0.47487324476242065,
+      "learning_rate": 2e-05,
+      "loss": 0.6037,
+      "step": 830
+    },
+    {
+      "epoch": 0.035877503950796565,
+      "grad_norm": 0.6204171180725098,
+      "learning_rate": 2e-05,
+      "loss": 0.606,
+      "step": 840
+    },
+    {
+      "epoch": 0.036304617093067953,
+      "grad_norm": 0.38122642040252686,
+      "learning_rate": 2e-05,
+      "loss": 0.6022,
+      "step": 850
+    },
+    {
+      "epoch": 0.03673173023533934,
+      "grad_norm": 0.45812979340553284,
+      "learning_rate": 2e-05,
+      "loss": 0.6134,
+      "step": 860
+    },
+    {
+      "epoch": 0.03715884337761073,
+      "grad_norm": 0.38281163573265076,
+      "learning_rate": 2e-05,
+      "loss": 0.5692,
+      "step": 870
+    },
+    {
+      "epoch": 0.03758595651988212,
+      "grad_norm": 0.44842684268951416,
+      "learning_rate": 2e-05,
+      "loss": 0.6195,
+      "step": 880
+    },
+    {
+      "epoch": 0.0380130696621535,
+      "grad_norm": 0.3978036642074585,
+      "learning_rate": 2e-05,
+      "loss": 0.5872,
+      "step": 890
+    },
+    {
+      "epoch": 0.03844018280442489,
+      "grad_norm": 0.40599605441093445,
+      "learning_rate": 2e-05,
+      "loss": 0.5896,
+      "step": 900
+    },
+    {
+      "epoch": 0.03886729594669628,
+      "grad_norm": 0.4849986732006073,
+      "learning_rate": 2e-05,
+      "loss": 0.5679,
+      "step": 910
+    },
+    {
+      "epoch": 0.03929440908896767,
+      "grad_norm": 0.3729165196418762,
+      "learning_rate": 2e-05,
+      "loss": 0.5941,
+      "step": 920
+    },
+    {
+      "epoch": 0.03972152223123906,
+      "grad_norm": 0.3839932680130005,
+      "learning_rate": 2e-05,
+      "loss": 0.5809,
+      "step": 930
+    },
+    {
+      "epoch": 0.04014863537351044,
+      "grad_norm": 0.3133138120174408,
+      "learning_rate": 2e-05,
+      "loss": 0.5909,
+      "step": 940
+    },
+    {
+      "epoch": 0.04057574851578183,
+      "grad_norm": 0.37946876883506775,
+      "learning_rate": 2e-05,
+      "loss": 0.5791,
+      "step": 950
+    },
+    {
+      "epoch": 0.04100286165805322,
+      "grad_norm": 0.3639635741710663,
+      "learning_rate": 2e-05,
+      "loss": 0.6028,
+      "step": 960
+    },
+    {
+      "epoch": 0.04142997480032461,
+      "grad_norm": 0.39474979043006897,
+      "learning_rate": 2e-05,
+      "loss": 0.5927,
+      "step": 970
+    },
+    {
+      "epoch": 0.041857087942595995,
+      "grad_norm": 0.39630550146102905,
+      "learning_rate": 2e-05,
+      "loss": 0.5861,
+      "step": 980
+    },
+    {
+      "epoch": 0.042284201084867384,
+      "grad_norm": 0.4038623571395874,
+      "learning_rate": 2e-05,
+      "loss": 0.5991,
+      "step": 990
+    },
+    {
+      "epoch": 0.042711314227138766,
+      "grad_norm": 0.46558162569999695,
+      "learning_rate": 2e-05,
+      "loss": 0.5842,
+      "step": 1000
+    },
+    {
+      "epoch": 0.043138427369410155,
+      "grad_norm": 0.4309065043926239,
+      "learning_rate": 2e-05,
+      "loss": 0.6021,
+      "step": 1010
+    },
+    {
+      "epoch": 0.043565540511681544,
+      "grad_norm": 0.3698565363883972,
+      "learning_rate": 2e-05,
+      "loss": 0.607,
+      "step": 1020
+    },
+    {
+      "epoch": 0.04399265365395293,
+      "grad_norm": 0.40514087677001953,
+      "learning_rate": 2e-05,
+      "loss": 0.5933,
+      "step": 1030
+    },
+    {
+      "epoch": 0.04441976679622432,
+      "grad_norm": 0.7474258542060852,
+      "learning_rate": 2e-05,
+      "loss": 0.5946,
+      "step": 1040
+    },
+    {
+      "epoch": 0.04484687993849571,
+      "grad_norm": 0.38786014914512634,
+      "learning_rate": 2e-05,
+      "loss": 0.6132,
+      "step": 1050
+    },
+    {
+      "epoch": 0.04527399308076709,
+      "grad_norm": 0.38152816891670227,
+      "learning_rate": 2e-05,
+      "loss": 0.5799,
+      "step": 1060
+    },
+    {
+      "epoch": 0.04570110622303848,
+      "grad_norm": 0.5136268734931946,
+      "learning_rate": 2e-05,
+      "loss": 0.6335,
+      "step": 1070
+    },
+    {
+      "epoch": 0.04612821936530987,
+      "grad_norm": 0.37756872177124023,
+      "learning_rate": 2e-05,
+      "loss": 0.5794,
+      "step": 1080
+    },
+    {
+      "epoch": 0.04655533250758126,
+      "grad_norm": 0.41157087683677673,
+      "learning_rate": 2e-05,
+      "loss": 0.6129,
+      "step": 1090
+    },
+    {
+      "epoch": 0.04698244564985265,
+      "grad_norm": 0.45449504256248474,
+      "learning_rate": 2e-05,
+      "loss": 0.6074,
+      "step": 1100
+    },
+    {
+      "epoch": 0.04740955879212403,
+      "grad_norm": 0.36440810561180115,
+      "learning_rate": 2e-05,
+      "loss": 0.5905,
+      "step": 1110
+    },
+    {
+      "epoch": 0.04783667193439542,
+      "grad_norm": 0.40203210711479187,
+      "learning_rate": 2e-05,
+      "loss": 0.5772,
+      "step": 1120
+    },
+    {
+      "epoch": 0.04826378507666681,
+      "grad_norm": 0.4374965727329254,
+      "learning_rate": 2e-05,
+      "loss": 0.6033,
+      "step": 1130
+    },
+    {
+      "epoch": 0.0486908982189382,
+      "grad_norm": 0.37814727425575256,
+      "learning_rate": 2e-05,
+      "loss": 0.6051,
+      "step": 1140
+    },
+    {
+      "epoch": 0.049118011361209586,
+      "grad_norm": 0.3608170449733734,
+      "learning_rate": 2e-05,
+      "loss": 0.6036,
+      "step": 1150
+    },
+    {
+      "epoch": 0.049545124503480975,
+      "grad_norm": 0.5163088440895081,
+      "learning_rate": 2e-05,
+      "loss": 0.5888,
+      "step": 1160
+    },
+    {
+      "epoch": 0.04997223764575236,
+      "grad_norm": 0.6338587403297424,
+      "learning_rate": 2e-05,
+      "loss": 0.5846,
+      "step": 1170
+    },
+    {
+      "epoch": 0.050399350788023746,
+      "grad_norm": 0.3570212125778198,
+      "learning_rate": 2e-05,
+      "loss": 0.5997,
+      "step": 1180
+    },
+    {
+      "epoch": 0.050826463930295135,
+      "grad_norm": 0.4730677604675293,
+      "learning_rate": 2e-05,
+      "loss": 0.5666,
+      "step": 1190
+    },
+    {
+      "epoch": 0.051253577072566524,
+      "grad_norm": 0.4634343683719635,
+      "learning_rate": 2e-05,
+      "loss": 0.6167,
+      "step": 1200
+    },
+    {
+      "epoch": 0.05168069021483791,
+      "grad_norm": 0.4279061555862427,
+      "learning_rate": 2e-05,
+      "loss": 0.5984,
+      "step": 1210
+    },
+    {
+      "epoch": 0.0521078033571093,
+      "grad_norm": 0.42280420660972595,
+      "learning_rate": 2e-05,
+      "loss": 0.5715,
+      "step": 1220
+    },
+    {
+      "epoch": 0.052534916499380684,
+      "grad_norm": 0.34051749110221863,
+      "learning_rate": 2e-05,
+      "loss": 0.577,
+      "step": 1230
+    },
+    {
+      "epoch": 0.05296202964165207,
+      "grad_norm": 0.3963359296321869,
+      "learning_rate": 2e-05,
+      "loss": 0.6313,
+      "step": 1240
+    },
+    {
+      "epoch": 0.05338914278392346,
+      "grad_norm": 0.5236133933067322,
+      "learning_rate": 2e-05,
+      "loss": 0.6187,
+      "step": 1250
+    },
+    {
+      "epoch": 0.05381625592619485,
+      "grad_norm": 0.40057671070098877,
+      "learning_rate": 2e-05,
+      "loss": 0.6118,
+      "step": 1260
+    },
+    {
+      "epoch": 0.05424336906846624,
+      "grad_norm": 0.4331953227519989,
+      "learning_rate": 2e-05,
+      "loss": 0.5933,
+      "step": 1270
+    },
+    {
+      "epoch": 0.05467048221073762,
+      "grad_norm": 0.35897260904312134,
+      "learning_rate": 2e-05,
+      "loss": 0.5776,
+      "step": 1280
+    },
+    {
+      "epoch": 0.05509759535300901,
+      "grad_norm": 0.40010058879852295,
+      "learning_rate": 2e-05,
+      "loss": 0.58,
+      "step": 1290
+    },
+    {
+      "epoch": 0.0555247084952804,
+      "grad_norm": 0.49022912979125977,
+      "learning_rate": 2e-05,
+      "loss": 0.5747,
+      "step": 1300
+    },
+    {
+      "epoch": 0.05595182163755179,
+      "grad_norm": 0.4582119584083557,
+      "learning_rate": 2e-05,
+      "loss": 0.5994,
+      "step": 1310
+    },
+    {
+      "epoch": 0.05637893477982318,
+      "grad_norm": 0.4133841097354889,
+      "learning_rate": 2e-05,
+      "loss": 0.5856,
+      "step": 1320
+    },
+    {
+      "epoch": 0.056806047922094566,
+      "grad_norm": 0.40341418981552124,
+      "learning_rate": 2e-05,
+      "loss": 0.615,
+      "step": 1330
+    },
+    {
+      "epoch": 0.05723316106436595,
+      "grad_norm": 0.3729898929595947,
+      "learning_rate": 2e-05,
+      "loss": 0.5871,
+      "step": 1340
+    },
+    {
+      "epoch": 0.05766027420663734,
+      "grad_norm": 0.36487877368927,
+      "learning_rate": 2e-05,
+      "loss": 0.6087,
+      "step": 1350
+    },
+    {
+      "epoch": 0.058087387348908726,
+      "grad_norm": 0.410173237323761,
+      "learning_rate": 2e-05,
+      "loss": 0.6106,
+      "step": 1360
+    },
+    {
+      "epoch": 0.058514500491180114,
+      "grad_norm": 0.4052298367023468,
+      "learning_rate": 2e-05,
+      "loss": 0.5794,
+      "step": 1370
+    },
+    {
+      "epoch": 0.0589416136334515,
+      "grad_norm": 0.35845524072647095,
+      "learning_rate": 2e-05,
+      "loss": 0.5818,
+      "step": 1380
+    },
+    {
+      "epoch": 0.05936872677572289,
+      "grad_norm": 0.39520588517189026,
+      "learning_rate": 2e-05,
+      "loss": 0.5724,
+      "step": 1390
+    },
+    {
+      "epoch": 0.059795839917994274,
+      "grad_norm": 0.3926452696323395,
+      "learning_rate": 2e-05,
+      "loss": 0.5787,
+      "step": 1400
+    },
+    {
+      "epoch": 0.06022295306026566,
+      "grad_norm": 0.3984834551811218,
+      "learning_rate": 2e-05,
+      "loss": 0.6149,
+      "step": 1410
+    },
+    {
+      "epoch": 0.06065006620253705,
+      "grad_norm": 0.4060869514942169,
+      "learning_rate": 2e-05,
+      "loss": 0.623,
+      "step": 1420
+    },
+    {
+      "epoch": 0.06107717934480844,
+      "grad_norm": 0.3899109661579132,
+      "learning_rate": 2e-05,
+      "loss": 0.606,
+      "step": 1430
+    },
+    {
+      "epoch": 0.06150429248707983,
+      "grad_norm": 0.41343048214912415,
+      "learning_rate": 2e-05,
+      "loss": 0.62,
+      "step": 1440
+    },
+    {
+      "epoch": 0.06193140562935121,
+      "grad_norm": 0.5486384630203247,
+      "learning_rate": 2e-05,
+      "loss": 0.5888,
+      "step": 1450
+    },
+    {
+      "epoch": 0.0623585187716226,
+      "grad_norm": 0.4260222017765045,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 1460
+    },
+    {
+      "epoch": 0.062785631913894,
+      "grad_norm": 0.5510641932487488,
+      "learning_rate": 2e-05,
+      "loss": 0.5917,
+      "step": 1470
+    },
+    {
+      "epoch": 0.06321274505616538,
+      "grad_norm": 0.3307860791683197,
+      "learning_rate": 2e-05,
+      "loss": 0.5966,
+      "step": 1480
+    },
+    {
+      "epoch": 0.06363985819843676,
+      "grad_norm": 0.37774041295051575,
+      "learning_rate": 2e-05,
+      "loss": 0.5928,
+      "step": 1490
+    },
+    {
+      "epoch": 0.06406697134070816,
+      "grad_norm": 0.40287962555885315,
+      "learning_rate": 2e-05,
+      "loss": 0.6018,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06449408448297954,
+      "grad_norm": 0.3765062987804413,
+      "learning_rate": 2e-05,
+      "loss": 0.5868,
+      "step": 1510
+    },
+    {
+      "epoch": 0.06492119762525093,
+      "grad_norm": 0.3866639733314514,
+      "learning_rate": 2e-05,
+      "loss": 0.5918,
+      "step": 1520
+    },
+    {
+      "epoch": 0.06534831076752232,
+      "grad_norm": 0.3452185392379761,
+      "learning_rate": 2e-05,
+      "loss": 0.6006,
+      "step": 1530
+    },
+    {
+      "epoch": 0.0657754239097937,
+      "grad_norm": 0.3757578730583191,
+      "learning_rate": 2e-05,
+      "loss": 0.5885,
+      "step": 1540
+    },
+    {
+      "epoch": 0.0662025370520651,
+      "grad_norm": 0.6169503927230835,
+      "learning_rate": 2e-05,
+      "loss": 0.5942,
+      "step": 1550
+    },
+    {
+      "epoch": 0.06662965019433648,
+      "grad_norm": 0.40690863132476807,
+      "learning_rate": 2e-05,
+      "loss": 0.5846,
+      "step": 1560
+    },
+    {
+      "epoch": 0.06705676333660787,
+      "grad_norm": 0.40239500999450684,
+      "learning_rate": 2e-05,
+      "loss": 0.6043,
+      "step": 1570
+    },
+    {
+      "epoch": 0.06748387647887925,
+      "grad_norm": 0.6150453090667725,
+      "learning_rate": 2e-05,
+      "loss": 0.5687,
+      "step": 1580
+    },
+    {
+      "epoch": 0.06791098962115065,
+      "grad_norm": 0.3692316710948944,
+      "learning_rate": 2e-05,
+      "loss": 0.5934,
+      "step": 1590
+    },
+    {
+      "epoch": 0.06833810276342203,
+      "grad_norm": 0.4124865233898163,
+      "learning_rate": 2e-05,
+      "loss": 0.5784,
+      "step": 1600
+    },
+    {
+      "epoch": 0.06876521590569341,
+      "grad_norm": 0.40603578090667725,
+      "learning_rate": 2e-05,
+      "loss": 0.5536,
+      "step": 1610
+    },
+    {
+      "epoch": 0.06919232904796481,
+      "grad_norm": 0.3672163188457489,
+      "learning_rate": 2e-05,
+      "loss": 0.5949,
+      "step": 1620
+    },
+    {
+      "epoch": 0.06961944219023619,
+      "grad_norm": 0.4111248850822449,
+      "learning_rate": 2e-05,
+      "loss": 0.6168,
+      "step": 1630
+    },
+    {
+      "epoch": 0.07004655533250759,
+      "grad_norm": 0.3349396288394928,
+      "learning_rate": 2e-05,
+      "loss": 0.6096,
+      "step": 1640
+    },
+    {
+      "epoch": 0.07047366847477897,
+      "grad_norm": 0.35192081332206726,
+      "learning_rate": 2e-05,
+      "loss": 0.6309,
+      "step": 1650
+    },
+    {
+      "epoch": 0.07090078161705035,
+      "grad_norm": 0.46462368965148926,
+      "learning_rate": 2e-05,
+      "loss": 0.5827,
+      "step": 1660
+    },
+    {
+      "epoch": 0.07132789475932175,
+      "grad_norm": 0.4099385440349579,
+      "learning_rate": 2e-05,
+      "loss": 0.6093,
+      "step": 1670
+    },
+    {
+      "epoch": 0.07175500790159313,
+      "grad_norm": 0.39262962341308594,
+      "learning_rate": 2e-05,
+      "loss": 0.5959,
+      "step": 1680
+    },
+    {
+      "epoch": 0.07218212104386452,
+      "grad_norm": 0.4145928919315338,
+      "learning_rate": 2e-05,
+      "loss": 0.5776,
+      "step": 1690
+    },
+    {
+      "epoch": 0.07260923418613591,
+      "grad_norm": 0.33485323190689087,
+      "learning_rate": 2e-05,
+      "loss": 0.5864,
+      "step": 1700
+    },
+    {
+      "epoch": 0.07303634732840729,
+      "grad_norm": 0.3448295295238495,
+      "learning_rate": 2e-05,
+      "loss": 0.6077,
+      "step": 1710
+    },
+    {
+      "epoch": 0.07346346047067868,
+      "grad_norm": 0.3951145112514496,
+      "learning_rate": 2e-05,
+      "loss": 0.5667,
+      "step": 1720
+    },
+    {
+      "epoch": 0.07389057361295007,
+      "grad_norm": 0.36090508103370667,
+      "learning_rate": 2e-05,
+      "loss": 0.6006,
+      "step": 1730
+    },
+    {
+      "epoch": 0.07431768675522146,
+      "grad_norm": 0.35783612728118896,
+      "learning_rate": 2e-05,
+      "loss": 0.5698,
+      "step": 1740
+    },
+    {
+      "epoch": 0.07474479989749284,
+      "grad_norm": 0.4051808714866638,
+      "learning_rate": 2e-05,
+      "loss": 0.5841,
+      "step": 1750
+    },
+    {
+      "epoch": 0.07517191303976424,
+      "grad_norm": 0.36852049827575684,
+      "learning_rate": 2e-05,
+      "loss": 0.5812,
+      "step": 1760
+    },
+    {
+      "epoch": 0.07559902618203562,
+      "grad_norm": 0.47315099835395813,
+      "learning_rate": 2e-05,
+      "loss": 0.5867,
+      "step": 1770
+    },
+    {
+      "epoch": 0.076026139324307,
+      "grad_norm": 0.370299756526947,
+      "learning_rate": 2e-05,
+      "loss": 0.5944,
+      "step": 1780
+    },
+    {
+      "epoch": 0.0764532524665784,
+      "grad_norm": 0.3629041314125061,
+      "learning_rate": 2e-05,
+      "loss": 0.5895,
+      "step": 1790
+    },
+    {
+      "epoch": 0.07688036560884978,
+      "grad_norm": 0.4631352722644806,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 1800
+    },
+    {
+      "epoch": 0.07730747875112118,
+      "grad_norm": 0.3893195390701294,
+      "learning_rate": 2e-05,
+      "loss": 0.579,
+      "step": 1810
+    },
+    {
+      "epoch": 0.07773459189339256,
+      "grad_norm": 0.4197307825088501,
+      "learning_rate": 2e-05,
+      "loss": 0.6022,
+      "step": 1820
+    },
+    {
+      "epoch": 0.07816170503566394,
+      "grad_norm": 0.5316178798675537,
+      "learning_rate": 2e-05,
+      "loss": 0.6127,
+      "step": 1830
+    },
+    {
+      "epoch": 0.07858881817793534,
+      "grad_norm": 0.4087827801704407,
+      "learning_rate": 2e-05,
+      "loss": 0.6148,
+      "step": 1840
+    },
+    {
+      "epoch": 0.07901593132020672,
+      "grad_norm": 0.9132181406021118,
+      "learning_rate": 2e-05,
+      "loss": 0.5675,
+      "step": 1850
+    },
+    {
+      "epoch": 0.07944304446247812,
+      "grad_norm": 0.42939144372940063,
+      "learning_rate": 2e-05,
+      "loss": 0.5827,
+      "step": 1860
+    },
+    {
+      "epoch": 0.0798701576047495,
+      "grad_norm": 0.5866528749465942,
+      "learning_rate": 2e-05,
+      "loss": 0.5984,
+      "step": 1870
+    },
+    {
+      "epoch": 0.08029727074702088,
+      "grad_norm": 0.38625794649124146,
+      "learning_rate": 2e-05,
+      "loss": 0.5712,
+      "step": 1880
+    },
+    {
+      "epoch": 0.08072438388929228,
+      "grad_norm": 0.3775944411754608,
+      "learning_rate": 2e-05,
+      "loss": 0.5633,
+      "step": 1890
+    },
+    {
+      "epoch": 0.08115149703156366,
+      "grad_norm": 0.37404197454452515,
+      "learning_rate": 2e-05,
+      "loss": 0.5944,
+      "step": 1900
+    },
+    {
+      "epoch": 0.08157861017383505,
+      "grad_norm": 0.4127039611339569,
+      "learning_rate": 2e-05,
+      "loss": 0.5685,
+      "step": 1910
+    },
+    {
+      "epoch": 0.08200572331610644,
+      "grad_norm": 0.4228227734565735,
+      "learning_rate": 2e-05,
+      "loss": 0.5907,
+      "step": 1920
+    },
+    {
+      "epoch": 0.08243283645837783,
+      "grad_norm": 0.3642731010913849,
+      "learning_rate": 2e-05,
+      "loss": 0.5926,
+      "step": 1930
+    },
+    {
+      "epoch": 0.08285994960064921,
+      "grad_norm": 0.3753544092178345,
+      "learning_rate": 2e-05,
+      "loss": 0.598,
+      "step": 1940
+    },
+    {
+      "epoch": 0.0832870627429206,
+      "grad_norm": 0.35891029238700867,
+      "learning_rate": 2e-05,
+      "loss": 0.5862,
+      "step": 1950
+    },
+    {
+      "epoch": 0.08371417588519199,
+      "grad_norm": 0.3859628438949585,
+      "learning_rate": 2e-05,
+      "loss": 0.5787,
+      "step": 1960
+    },
+    {
+      "epoch": 0.08414128902746337,
+      "grad_norm": 0.3352157473564148,
+      "learning_rate": 2e-05,
+      "loss": 0.5677,
+      "step": 1970
+    },
+    {
+      "epoch": 0.08456840216973477,
+      "grad_norm": 0.38465848565101624,
+      "learning_rate": 2e-05,
+      "loss": 0.5651,
+      "step": 1980
+    },
+    {
+      "epoch": 0.08499551531200615,
+      "grad_norm": 0.8394455313682556,
+      "learning_rate": 2e-05,
+      "loss": 0.5683,
+      "step": 1990
+    },
+    {
+      "epoch": 0.08542262845427753,
+      "grad_norm": 0.39962485432624817,
+      "learning_rate": 2e-05,
+      "loss": 0.5793,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08584974159654893,
+      "grad_norm": 0.3594360649585724,
+      "learning_rate": 2e-05,
+      "loss": 0.6158,
+      "step": 2010
+    },
+    {
+      "epoch": 0.08627685473882031,
+      "grad_norm": 0.388683557510376,
+      "learning_rate": 2e-05,
+      "loss": 0.5829,
+      "step": 2020
+    },
+    {
+      "epoch": 0.0867039678810917,
+      "grad_norm": 0.33351218700408936,
+      "learning_rate": 2e-05,
+      "loss": 0.5698,
+      "step": 2030
+    }
+  ],
+  "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 sha256:50bce28aa60b5e52e815b7feb16c8a64a1dbca440f3f650b1debb1f3844ff3e1
+size 7953