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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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": 262144,
+  "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": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51eb07636f9811c00ab15a7c739262f60f04e5876a4e4f2de496c83cc896541
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5121ecfc9cdeac3e813082d7a5c5759ed80e9c2b0fce5fd0125027200b5046
+size 3855679144

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8822848512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1762 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020833333333333332,
+      "grad_norm": 5.9375,
+      "learning_rate": 0.0,
+      "loss": 1.457,
+      "memory/device_reserved (GiB)": 68.17,
+      "memory/max_active (GiB)": 62.24,
+      "memory/max_allocated (GiB)": 62.24,
+      "step": 1,
+      "tokens_per_second_per_gpu": 4754.85,
+      "total_tokens": 193735
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 6.40625,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.5117,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 2,
+      "tokens_per_second_per_gpu": 8987.92,
+      "total_tokens": 377645
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 6.34375,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.5352,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 3,
+      "tokens_per_second_per_gpu": 10584.88,
+      "total_tokens": 572231
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 5.75,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.4023,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 4,
+      "tokens_per_second_per_gpu": 10641.72,
+      "total_tokens": 771980
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": 5.8125,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.5234,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 5,
+      "tokens_per_second_per_gpu": 10136.19,
+      "total_tokens": 960629
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 5.5,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.4961,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 6,
+      "tokens_per_second_per_gpu": 10066.87,
+      "total_tokens": 1145765
+    },
+    {
+      "epoch": 0.14583333333333334,
+      "grad_norm": 4.59375,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.3828,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 7,
+      "tokens_per_second_per_gpu": 10793.17,
+      "total_tokens": 1339007
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.53125,
+      "learning_rate": 1e-05,
+      "loss": 1.3359,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 8,
+      "tokens_per_second_per_gpu": 10042.61,
+      "total_tokens": 1533294
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 2.625,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.3203,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 9,
+      "tokens_per_second_per_gpu": 9880.69,
+      "total_tokens": 1715421
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 1.2695,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 10,
+      "tokens_per_second_per_gpu": 10012.45,
+      "total_tokens": 1899665
+    },
+    {
+      "epoch": 0.22916666666666666,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.2539,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 11,
+      "tokens_per_second_per_gpu": 10498.2,
+      "total_tokens": 2090232
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 1.2383,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 12,
+      "tokens_per_second_per_gpu": 10504.24,
+      "total_tokens": 2277678
+    },
+    {
+      "epoch": 0.2708333333333333,
+      "grad_norm": 1.3828125,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.2031,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 13,
+      "tokens_per_second_per_gpu": 11150.71,
+      "total_tokens": 2475912
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 1.1172,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 14,
+      "tokens_per_second_per_gpu": 10549.83,
+      "total_tokens": 2677381
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 1.3671875,
+      "learning_rate": 2e-05,
+      "loss": 1.1602,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 15,
+      "tokens_per_second_per_gpu": 10901.98,
+      "total_tokens": 2876565
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.9997080140801932e-05,
+      "loss": 1.1445,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 16,
+      "tokens_per_second_per_gpu": 10121.73,
+      "total_tokens": 3065392
+    },
+    {
+      "epoch": 0.3541666666666667,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.998832226832327e-05,
+      "loss": 1.1016,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 17,
+      "tokens_per_second_per_gpu": 10594.37,
+      "total_tokens": 3260102
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.9973731496914914e-05,
+      "loss": 1.168,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 18,
+      "tokens_per_second_per_gpu": 9736.14,
+      "total_tokens": 3442701
+    },
+    {
+      "epoch": 0.3958333333333333,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.995331634717649e-05,
+      "loss": 1.082,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 19,
+      "tokens_per_second_per_gpu": 10128.02,
+      "total_tokens": 3638349
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.75,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 1.1055,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 20,
+      "tokens_per_second_per_gpu": 10243.56,
+      "total_tokens": 3826742
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.9895063994510512e-05,
+      "loss": 1.1016,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 21,
+      "tokens_per_second_per_gpu": 9967.12,
+      "total_tokens": 4014944
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.985726080931651e-05,
+      "loss": 1.1211,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 22,
+      "tokens_per_second_per_gpu": 10518.66,
+      "total_tokens": 4208308
+    },
+    {
+      "epoch": 0.4791666666666667,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.9813701261394136e-05,
+      "loss": 1.1523,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 23,
+      "tokens_per_second_per_gpu": 10033.96,
+      "total_tokens": 4394123
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.9764410788292724e-05,
+      "loss": 1.0898,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 24,
+      "tokens_per_second_per_gpu": 10669.49,
+      "total_tokens": 4588895
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 1.1172,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 25,
+      "tokens_per_second_per_gpu": 10276.83,
+      "total_tokens": 4781600
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.6328125,
+      "learning_rate": 1.9648755533435517e-05,
+      "loss": 1.1094,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 26,
+      "tokens_per_second_per_gpu": 9934.02,
+      "total_tokens": 4962927
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.9582458291091664e-05,
+      "loss": 1.0898,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 27,
+      "tokens_per_second_per_gpu": 10213.04,
+      "total_tokens": 5154156
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.5390625,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.0625,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 28,
+      "tokens_per_second_per_gpu": 10650.84,
+      "total_tokens": 5346313
+    },
+    {
+      "epoch": 0.6041666666666666,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.9433118132577432e-05,
+      "loss": 1.0859,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 29,
+      "tokens_per_second_per_gpu": 10206.96,
+      "total_tokens": 5537564
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 1.0859,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 30,
+      "tokens_per_second_per_gpu": 9831.26,
+      "total_tokens": 5720388
+    },
+    {
+      "epoch": 0.6458333333333334,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.9261746489577767e-05,
+      "loss": 1.0781,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 31,
+      "tokens_per_second_per_gpu": 10701.1,
+      "total_tokens": 5906962
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.9167921953165827e-05,
+      "loss": 1.0938,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 32,
+      "tokens_per_second_per_gpu": 10732.53,
+      "total_tokens": 6104218
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.9068743608505454e-05,
+      "loss": 1.1133,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 33,
+      "tokens_per_second_per_gpu": 10156.96,
+      "total_tokens": 6291571
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.5,
+      "learning_rate": 1.896426937295704e-05,
+      "loss": 1.0781,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 34,
+      "tokens_per_second_per_gpu": 10651.58,
+      "total_tokens": 6476350
+    },
+    {
+      "epoch": 0.7291666666666666,
+      "grad_norm": 0.5390625,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 1.0859,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 35,
+      "tokens_per_second_per_gpu": 10027.99,
+      "total_tokens": 6660433
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.49609375,
+      "learning_rate": 1.873968032626518e-05,
+      "loss": 1.0625,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 36,
+      "tokens_per_second_per_gpu": 10538.25,
+      "total_tokens": 6853661
+    },
+    {
+      "epoch": 0.7708333333333334,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.8619696668800494e-05,
+      "loss": 1.1055,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 37,
+      "tokens_per_second_per_gpu": 10499.61,
+      "total_tokens": 7041887
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.8494679351215212e-05,
+      "loss": 1.0117,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 38,
+      "tokens_per_second_per_gpu": 10892.76,
+      "total_tokens": 7242129
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.8364701380102267e-05,
+      "loss": 1.0391,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 39,
+      "tokens_per_second_per_gpu": 10826.51,
+      "total_tokens": 7442101
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.998,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 40,
+      "tokens_per_second_per_gpu": 9529.96,
+      "total_tokens": 7637450
+    },
+    {
+      "epoch": 0.8541666666666666,
+      "grad_norm": 0.458984375,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.0859,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 41,
+      "tokens_per_second_per_gpu": 10530.91,
+      "total_tokens": 7830567
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.7945776797137544e-05,
+      "loss": 1.0859,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 42,
+      "tokens_per_second_per_gpu": 10621.21,
+      "total_tokens": 8025656
+    },
+    {
+      "epoch": 0.8958333333333334,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.7796743540632226e-05,
+      "loss": 1.0254,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 43,
+      "tokens_per_second_per_gpu": 10096.46,
+      "total_tokens": 8212765
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.447265625,
+      "learning_rate": 1.7643157205458483e-05,
+      "loss": 1.0332,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 44,
+      "tokens_per_second_per_gpu": 10109.75,
+      "total_tokens": 8408896
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 1.002,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 45,
+      "tokens_per_second_per_gpu": 10350.81,
+      "total_tokens": 8608276
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.53125,
+      "learning_rate": 1.7322686665977738e-05,
+      "loss": 1.1094,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 46,
+      "tokens_per_second_per_gpu": 10131.42,
+      "total_tokens": 8799852
+    },
+    {
+      "epoch": 0.9791666666666666,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.715598960744121e-05,
+      "loss": 0.9707,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 47,
+      "tokens_per_second_per_gpu": 9848.57,
+      "total_tokens": 8991281
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.6985113652489374e-05,
+      "loss": 1.0391,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 48,
+      "tokens_per_second_per_gpu": 10189.26,
+      "total_tokens": 9182092
+    },
+    {
+      "epoch": 1.0208333333333333,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.6810158587867973e-05,
+      "loss": 1.0117,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 49,
+      "tokens_per_second_per_gpu": 10109.46,
+      "total_tokens": 9375827
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 1.0312,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 50,
+      "tokens_per_second_per_gpu": 9167.36,
+      "total_tokens": 9559737
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 0.458984375,
+      "learning_rate": 1.6448422127361707e-05,
+      "loss": 1.0703,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 51,
+      "tokens_per_second_per_gpu": 10531.34,
+      "total_tokens": 9754323
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.626185197538314e-05,
+      "loss": 0.9688,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 52,
+      "tokens_per_second_per_gpu": 10570.62,
+      "total_tokens": 9954072
+    },
+    {
+      "epoch": 1.1041666666666667,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.6071625078187113e-05,
+      "loss": 1.0859,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 53,
+      "tokens_per_second_per_gpu": 10132.93,
+      "total_tokens": 10142721
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 1.0703,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 54,
+      "tokens_per_second_per_gpu": 10263.22,
+      "total_tokens": 10327857
+    },
+    {
+      "epoch": 1.1458333333333333,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 1.0176,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 55,
+      "tokens_per_second_per_gpu": 10786.39,
+      "total_tokens": 10521099
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.5480125073546705e-05,
+      "loss": 1.0352,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 56,
+      "tokens_per_second_per_gpu": 10023.87,
+      "total_tokens": 10715386
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.527640244106133e-05,
+      "loss": 1.043,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 57,
+      "tokens_per_second_per_gpu": 9848.52,
+      "total_tokens": 10897513
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.482421875,
+      "learning_rate": 1.5069598538135905e-05,
+      "loss": 1.0352,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 58,
+      "tokens_per_second_per_gpu": 10004.24,
+      "total_tokens": 11081757
+    },
+    {
+      "epoch": 1.2291666666666667,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.485983413242606e-05,
+      "loss": 1.0195,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 59,
+      "tokens_per_second_per_gpu": 10483.32,
+      "total_tokens": 11272324
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 1.0293,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 60,
+      "tokens_per_second_per_gpu": 10478.12,
+      "total_tokens": 11459770
+    },
+    {
+      "epoch": 1.2708333333333333,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.4431915455992416e-05,
+      "loss": 1.0039,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 61,
+      "tokens_per_second_per_gpu": 11157.45,
+      "total_tokens": 11658004
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.4214011077725293e-05,
+      "loss": 0.9414,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 62,
+      "tokens_per_second_per_gpu": 10464.97,
+      "total_tokens": 11859473
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.3993645835656955e-05,
+      "loss": 0.9844,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 63,
+      "tokens_per_second_per_gpu": 10802.11,
+      "total_tokens": 12058657
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.3770948416883205e-05,
+      "loss": 0.9746,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 64,
+      "tokens_per_second_per_gpu": 10169.34,
+      "total_tokens": 12247484
+    },
+    {
+      "epoch": 1.3541666666666667,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.9434,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 65,
+      "tokens_per_second_per_gpu": 10566.69,
+      "total_tokens": 12442194
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.3319078531285286e-05,
+      "loss": 1.002,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 66,
+      "tokens_per_second_per_gpu": 9699.95,
+      "total_tokens": 12624793
+    },
+    {
+      "epoch": 1.3958333333333333,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.9336,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 67,
+      "tokens_per_second_per_gpu": 10187.26,
+      "total_tokens": 12820441
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.458984375,
+      "learning_rate": 1.2859456783986892e-05,
+      "loss": 0.9629,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 68,
+      "tokens_per_second_per_gpu": 10254.48,
+      "total_tokens": 13008834
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 0.447265625,
+      "learning_rate": 1.262707378198587e-05,
+      "loss": 0.9648,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 69,
+      "tokens_per_second_per_gpu": 9940.27,
+      "total_tokens": 13197036
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.2393156642875579e-05,
+      "loss": 0.9902,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 70,
+      "tokens_per_second_per_gpu": 10499.3,
+      "total_tokens": 13390400
+    },
+    {
+      "epoch": 1.4791666666666667,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.2157841967678064e-05,
+      "loss": 1.0215,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 71,
+      "tokens_per_second_per_gpu": 10092.49,
+      "total_tokens": 13576215
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.1921267173537085e-05,
+      "loss": 0.9707,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 72,
+      "tokens_per_second_per_gpu": 10734.78,
+      "total_tokens": 13770987
+    },
+    {
+      "epoch": 1.5208333333333335,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.1683570413470384e-05,
+      "loss": 1.0039,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 73,
+      "tokens_per_second_per_gpu": 10374.13,
+      "total_tokens": 13963692
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.1444890495692214e-05,
+      "loss": 0.9863,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 74,
+      "tokens_per_second_per_gpu": 9925.41,
+      "total_tokens": 14145019
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 0.9844,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 75,
+      "tokens_per_second_per_gpu": 10193.32,
+      "total_tokens": 14336248
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.0965139209145153e-05,
+      "loss": 0.957,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 76,
+      "tokens_per_second_per_gpu": 10648.45,
+      "total_tokens": 14528405
+    },
+    {
+      "epoch": 1.6041666666666665,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.0724348001617626e-05,
+      "loss": 0.9902,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 77,
+      "tokens_per_second_per_gpu": 10212.71,
+      "total_tokens": 14719656
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.0483133795255072e-05,
+      "loss": 0.9941,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 78,
+      "tokens_per_second_per_gpu": 9784.17,
+      "total_tokens": 14902480
+    },
+    {
+      "epoch": 1.6458333333333335,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.0241637452361323e-05,
+      "loss": 0.9883,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 79,
+      "tokens_per_second_per_gpu": 10663.55,
+      "total_tokens": 15089054
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.4375,
+      "learning_rate": 1e-05,
+      "loss": 1.0078,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 80,
+      "tokens_per_second_per_gpu": 10776.49,
+      "total_tokens": 15286310
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 0.4453125,
+      "learning_rate": 9.75836254763868e-06,
+      "loss": 1.0234,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 81,
+      "tokens_per_second_per_gpu": 10157.52,
+      "total_tokens": 15473663
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.470703125,
+      "learning_rate": 9.516866204744932e-06,
+      "loss": 1.0,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 82,
+      "tokens_per_second_per_gpu": 10701.67,
+      "total_tokens": 15658442
+    },
+    {
+      "epoch": 1.7291666666666665,
+      "grad_norm": 0.466796875,
+      "learning_rate": 9.275651998382377e-06,
+      "loss": 1.0039,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 83,
+      "tokens_per_second_per_gpu": 9974.39,
+      "total_tokens": 15842525
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.455078125,
+      "learning_rate": 9.034860790854848e-06,
+      "loss": 0.9863,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 84,
+      "tokens_per_second_per_gpu": 10560.42,
+      "total_tokens": 16035753
+    },
+    {
+      "epoch": 1.7708333333333335,
+      "grad_norm": 0.455078125,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 1.0312,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 85,
+      "tokens_per_second_per_gpu": 10498.04,
+      "total_tokens": 16223979
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.42578125,
+      "learning_rate": 8.55510950430779e-06,
+      "loss": 0.9492,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 86,
+      "tokens_per_second_per_gpu": 10922.51,
+      "total_tokens": 16424221
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 0.431640625,
+      "learning_rate": 8.316429586529616e-06,
+      "loss": 0.9746,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 87,
+      "tokens_per_second_per_gpu": 10848.98,
+      "total_tokens": 16624193
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.4296875,
+      "learning_rate": 8.078732826462917e-06,
+      "loss": 0.9355,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 88,
+      "tokens_per_second_per_gpu": 9565.65,
+      "total_tokens": 16819542
+    },
+    {
+      "epoch": 1.8541666666666665,
+      "grad_norm": 0.43359375,
+      "learning_rate": 7.84215803232194e-06,
+      "loss": 1.0234,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 89,
+      "tokens_per_second_per_gpu": 10503.54,
+      "total_tokens": 17012659
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.4296875,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 1.0215,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 90,
+      "tokens_per_second_per_gpu": 10559.42,
+      "total_tokens": 17207748
+    },
+    {
+      "epoch": 1.8958333333333335,
+      "grad_norm": 0.4375,
+      "learning_rate": 7.372926218014131e-06,
+      "loss": 0.9668,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 91,
+      "tokens_per_second_per_gpu": 10102.48,
+      "total_tokens": 17394857
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.4453125,
+      "learning_rate": 7.140543216013109e-06,
+      "loss": 0.9785,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 92,
+      "tokens_per_second_per_gpu": 10165.22,
+      "total_tokens": 17590988
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 0.423828125,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.9492,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 93,
+      "tokens_per_second_per_gpu": 10355.66,
+      "total_tokens": 17790368
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.431640625,
+      "learning_rate": 6.680921468714718e-06,
+      "loss": 1.0508,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 94,
+      "tokens_per_second_per_gpu": 10134.55,
+      "total_tokens": 17981944
+    },
+    {
+      "epoch": 1.9791666666666665,
+      "grad_norm": 0.40625,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.9199,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 95,
+      "tokens_per_second_per_gpu": 9778.3,
+      "total_tokens": 18173373
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.43359375,
+      "learning_rate": 6.229051583116796e-06,
+      "loss": 0.9863,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 96,
+      "tokens_per_second_per_gpu": 10231.38,
+      "total_tokens": 18364184
+    },
+    {
+      "epoch": 2.0208333333333335,
+      "grad_norm": 0.546875,
+      "learning_rate": 6.006354164343047e-06,
+      "loss": 0.959,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 97,
+      "tokens_per_second_per_gpu": 10122.23,
+      "total_tokens": 18557919
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.4296875,
+      "learning_rate": 5.785988922274711e-06,
+      "loss": 0.9824,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 98,
+      "tokens_per_second_per_gpu": 9172.58,
+      "total_tokens": 18741829
+    },
+    {
+      "epoch": 2.0625,
+      "grad_norm": 0.42578125,
+      "learning_rate": 5.5680845440075885e-06,
+      "loss": 1.0273,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 99,
+      "tokens_per_second_per_gpu": 10557.98,
+      "total_tokens": 18936415
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.40234375,
+      "learning_rate": 5.352768279562315e-06,
+      "loss": 0.9277,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 100,
+      "tokens_per_second_per_gpu": 10657.64,
+      "total_tokens": 19136164
+    },
+    {
+      "epoch": 2.1041666666666665,
+      "grad_norm": 0.435546875,
+      "learning_rate": 5.14016586757394e-06,
+      "loss": 1.0391,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 101,
+      "tokens_per_second_per_gpu": 9843.32,
+      "total_tokens": 19324813
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.4453125,
+      "learning_rate": 4.930401461864099e-06,
+      "loss": 1.0273,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 102,
+      "tokens_per_second_per_gpu": 10233.37,
+      "total_tokens": 19509949
+    },
+    {
+      "epoch": 2.1458333333333335,
+      "grad_norm": 0.431640625,
+      "learning_rate": 4.7235975589386715e-06,
+      "loss": 0.9805,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 103,
+      "tokens_per_second_per_gpu": 10815.24,
+      "total_tokens": 19703191
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.447265625,
+      "learning_rate": 4.519874926453303e-06,
+      "loss": 1.0,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 104,
+      "tokens_per_second_per_gpu": 10097.8,
+      "total_tokens": 19897478
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 0.4375,
+      "learning_rate": 4.319352532688444e-06,
+      "loss": 1.0059,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 105,
+      "tokens_per_second_per_gpu": 9860.18,
+      "total_tokens": 20079605
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.439453125,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 1.0039,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 106,
+      "tokens_per_second_per_gpu": 9991.56,
+      "total_tokens": 20263849
+    },
+    {
+      "epoch": 2.2291666666666665,
+      "grad_norm": 0.43359375,
+      "learning_rate": 3.9283749218128885e-06,
+      "loss": 0.9863,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 107,
+      "tokens_per_second_per_gpu": 10478.45,
+      "total_tokens": 20454416
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.45703125,
+      "learning_rate": 3.738148024616863e-06,
+      "loss": 0.998,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 108,
+      "tokens_per_second_per_gpu": 10475.15,
+      "total_tokens": 20641862
+    },
+    {
+      "epoch": 2.2708333333333335,
+      "grad_norm": 0.443359375,
+      "learning_rate": 3.5515778726382967e-06,
+      "loss": 0.9727,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 109,
+      "tokens_per_second_per_gpu": 11180.87,
+      "total_tokens": 20840096
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.41796875,
+      "learning_rate": 3.3687734175920505e-06,
+      "loss": 0.916,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 110,
+      "tokens_per_second_per_gpu": 10457.13,
+      "total_tokens": 21041565
+    },
+    {
+      "epoch": 2.3125,
+      "grad_norm": 0.42578125,
+      "learning_rate": 3.1898414121320277e-06,
+      "loss": 0.959,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 111,
+      "tokens_per_second_per_gpu": 10793.07,
+      "total_tokens": 21240749
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.439453125,
+      "learning_rate": 3.0148863475106315e-06,
+      "loss": 0.9453,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 112,
+      "tokens_per_second_per_gpu": 10139.81,
+      "total_tokens": 21429576
+    },
+    {
+      "epoch": 2.3541666666666665,
+      "grad_norm": 0.42578125,
+      "learning_rate": 2.8440103925587904e-06,
+      "loss": 0.9199,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 113,
+      "tokens_per_second_per_gpu": 10567.3,
+      "total_tokens": 21624286
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.4375,
+      "learning_rate": 2.6773133340222677e-06,
+      "loss": 0.9746,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 114,
+      "tokens_per_second_per_gpu": 9746.37,
+      "total_tokens": 21806885
+    },
+    {
+      "epoch": 2.3958333333333335,
+      "grad_norm": 0.4453125,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.9121,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 115,
+      "tokens_per_second_per_gpu": 10113.82,
+      "total_tokens": 22002533
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.56640625,
+      "learning_rate": 2.3568427945415163e-06,
+      "loss": 0.9434,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 116,
+      "tokens_per_second_per_gpu": 10289.14,
+      "total_tokens": 22190926
+    },
+    {
+      "epoch": 2.4375,
+      "grad_norm": 0.5703125,
+      "learning_rate": 2.2032564593677773e-06,
+      "loss": 0.9434,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 117,
+      "tokens_per_second_per_gpu": 10024.32,
+      "total_tokens": 22379128
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.4375,
+      "learning_rate": 2.0542232028624585e-06,
+      "loss": 0.9707,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 118,
+      "tokens_per_second_per_gpu": 10599.9,
+      "total_tokens": 22572492
+    },
+    {
+      "epoch": 2.4791666666666665,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.0039,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 119,
+      "tokens_per_second_per_gpu": 10064.53,
+      "total_tokens": 22758307
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.7701613410634367e-06,
+      "loss": 0.9551,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 120,
+      "tokens_per_second_per_gpu": 10637.75,
+      "total_tokens": 22953079
+    },
+    {
+      "epoch": 2.5208333333333335,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.6352986198977327e-06,
+      "loss": 0.9844,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 121,
+      "tokens_per_second_per_gpu": 10333.95,
+      "total_tokens": 23145784
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.5053206487847916e-06,
+      "loss": 0.9707,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 122,
+      "tokens_per_second_per_gpu": 9911.59,
+      "total_tokens": 23327111
+    },
+    {
+      "epoch": 2.5625,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.3803033311995072e-06,
+      "loss": 0.9688,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 123,
+      "tokens_per_second_per_gpu": 10171.63,
+      "total_tokens": 23518340
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.41796875,
+      "learning_rate": 1.2603196737348211e-06,
+      "loss": 0.9434,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 124,
+      "tokens_per_second_per_gpu": 10639.7,
+      "total_tokens": 23710497
+    },
+    {
+      "epoch": 2.6041666666666665,
+      "grad_norm": 0.41796875,
+      "learning_rate": 1.1454397434679022e-06,
+      "loss": 0.9805,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 125,
+      "tokens_per_second_per_gpu": 10197.71,
+      "total_tokens": 23901748
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.0357306270429623e-06,
+      "loss": 0.9785,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 126,
+      "tokens_per_second_per_gpu": 9804.54,
+      "total_tokens": 24084572
+    },
+    {
+      "epoch": 2.6458333333333335,
+      "grad_norm": 0.4296875,
+      "learning_rate": 9.312563914945461e-07,
+      "loss": 0.9766,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 127,
+      "tokens_per_second_per_gpu": 10687.65,
+      "total_tokens": 24271146
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.41796875,
+      "learning_rate": 8.320780468341761e-07,
+      "loss": 0.9961,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 128,
+      "tokens_per_second_per_gpu": 10789.28,
+      "total_tokens": 24468402
+    },
+    {
+      "epoch": 2.6875,
+      "grad_norm": 0.4296875,
+      "learning_rate": 7.382535104222366e-07,
+      "loss": 1.0117,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 129,
+      "tokens_per_second_per_gpu": 10137.94,
+      "total_tokens": 24655755
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.4296875,
+      "learning_rate": 6.498375731458529e-07,
+      "loss": 0.9883,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 130,
+      "tokens_per_second_per_gpu": 10640.27,
+      "total_tokens": 24840534
+    },
+    {
+      "epoch": 2.7291666666666665,
+      "grad_norm": 0.439453125,
+      "learning_rate": 5.668818674225684e-07,
+      "loss": 0.9941,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 131,
+      "tokens_per_second_per_gpu": 10018.08,
+      "total_tokens": 25024617
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.427734375,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.9746,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 132,
+      "tokens_per_second_per_gpu": 10544.96,
+      "total_tokens": 25217845
+    },
+    {
+      "epoch": 2.7708333333333335,
+      "grad_norm": 0.455078125,
+      "learning_rate": 4.1754170890833777e-07,
+      "loss": 1.0234,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 133,
+      "tokens_per_second_per_gpu": 10490.58,
+      "total_tokens": 25406071
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.419921875,
+      "learning_rate": 3.5124446656448654e-07,
+      "loss": 0.9414,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 134,
+      "tokens_per_second_per_gpu": 10903.67,
+      "total_tokens": 25606313
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 0.416015625,
+      "learning_rate": 2.905818257394799e-07,
+      "loss": 0.9688,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 135,
+      "tokens_per_second_per_gpu": 10824.22,
+      "total_tokens": 25806285
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.421875,
+      "learning_rate": 2.355892117072789e-07,
+      "loss": 0.9277,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 136,
+      "tokens_per_second_per_gpu": 9550.25,
+      "total_tokens": 26001634
+    },
+    {
+      "epoch": 2.8541666666666665,
+      "grad_norm": 0.56640625,
+      "learning_rate": 1.8629873860586567e-07,
+      "loss": 1.0156,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 137,
+      "tokens_per_second_per_gpu": 10503.94,
+      "total_tokens": 26194751
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.4273919068349184e-07,
+      "loss": 1.0176,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 138,
+      "tokens_per_second_per_gpu": 10613.72,
+      "total_tokens": 26389840
+    },
+    {
+      "epoch": 2.8958333333333335,
+      "grad_norm": 0.55078125,
+      "learning_rate": 1.0493600548948879e-07,
+      "loss": 0.959,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 139,
+      "tokens_per_second_per_gpu": 10081.76,
+      "total_tokens": 26576949
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.421875,
+      "learning_rate": 7.291125901946027e-08,
+      "loss": 0.9727,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 140,
+      "tokens_per_second_per_gpu": 10169.04,
+      "total_tokens": 26773080
+    },
+    {
+      "epoch": 2.9375,
+      "grad_norm": 0.40625,
+      "learning_rate": 4.6683652823513725e-08,
+      "loss": 0.9434,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 141,
+      "tokens_per_second_per_gpu": 10390.82,
+      "total_tokens": 26972460
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.423828125,
+      "learning_rate": 2.6268503085089547e-08,
+      "loss": 1.0469,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 142,
+      "tokens_per_second_per_gpu": 10107.1,
+      "total_tokens": 27164036
+    },
+    {
+      "epoch": 2.9791666666666665,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.1677731676733584e-08,
+      "loss": 0.916,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 143,
+      "tokens_per_second_per_gpu": 9845.86,
+      "total_tokens": 27355465
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.421875,
+      "learning_rate": 2.9198591980705847e-09,
+      "loss": 0.9844,
+      "memory/device_reserved (GiB)": 77.12,
+      "memory/max_active (GiB)": 69.81,
+      "memory/max_allocated (GiB)": 69.81,
+      "step": 144,
+      "tokens_per_second_per_gpu": 10249.72,
+      "total_tokens": 27546276
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 48,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.229628582947717e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}