Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1500/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

checkpoint-1500/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1500/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

checkpoint-1500/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70b9215420e53c5e032c8be35fb7d10a0de7bcee0f1807962f2ff169348080a
+size 4976687216

checkpoint-1500/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958dd8a6ea9789ed1af2e3e5795bc9b946ab1bfd1a070afb06348ffe1035fb25
+size 4778622352

checkpoint-1500/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc152d768a0234dd7abcf8ec6bd181605966148a6e3c740bdb9971562eecf22a
+size 4932743960

checkpoint-1500/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59d825f4f68db7f1e227346b7e8eb767351d1802a4bc4693b235345aa978072
+size 4932743992

checkpoint-1500/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0bcb9972c87e1d7e0613df79f13e68def1a75f29b6d591119b9fe49dc268c1
+size 4998852296

checkpoint-1500/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca3b745f2465fd0e12f9c799c7d5f60e2f2d6d7633b9dc17e727dd43a962644
+size 3662865184

checkpoint-1500/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54baf1da6ff4ae7214012e8d8710cfd2d9aaf1fdc39f36b40bb00bd15f9d3118
+size 2179989632

checkpoint-1500/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 3807808256,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-1500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619b193a2803d6d1c43616228b0a60d9c8c2875c4e145a0d69af1a4f0bc15eb9
+size 60925254788

checkpoint-1500/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6434a913a6b860fcc9806817f2652615161e11fe386de28fdbaba7b10c044d
+size 30462624740

checkpoint-1500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce66cbbb4d80808680a9a9eb511769ba2db3909d7f62993fb4e0ac84eefa9ad
+size 14917

checkpoint-1500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56584a2ce2b67b560dbdca2a56519ad7e6aba8e34b3c8ae11350541319cdc5f6
+size 14917

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ee3116c8fb7b2527484e5c0b5b94d378c1714b90938f1908765e947bc295cc
+size 1465

checkpoint-1500/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
+  }
+}

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.05,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 5.616273880004883,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.9513,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.260721206665039,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.7789,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 5.373858451843262,
+      "learning_rate": 5.8e-06,
+      "loss": 1.6535,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.073526859283447,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4488,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 4.743659973144531,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.4239,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.532003879547119,
+      "learning_rate": 1.18e-05,
+      "loss": 1.4531,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.564126491546631,
+      "learning_rate": 1.38e-05,
+      "loss": 1.4279,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.471712112426758,
+      "learning_rate": 1.58e-05,
+      "loss": 1.3619,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 5.032183647155762,
+      "learning_rate": 1.7800000000000002e-05,
+      "loss": 1.3614,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.518551349639893,
+      "learning_rate": 1.98e-05,
+      "loss": 1.3551,
+      "step": 100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 6.518773555755615,
+      "learning_rate": 1.990526315789474e-05,
+      "loss": 0.8287,
+      "step": 110
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 3.6112170219421387,
+      "learning_rate": 1.98e-05,
+      "loss": 0.7035,
+      "step": 120
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 5.7912726402282715,
+      "learning_rate": 1.9694736842105263e-05,
+      "loss": 0.8074,
+      "step": 130
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 3.595136880874634,
+      "learning_rate": 1.9589473684210527e-05,
+      "loss": 0.7915,
+      "step": 140
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 4.417491912841797,
+      "learning_rate": 1.9484210526315793e-05,
+      "loss": 0.8106,
+      "step": 150
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.246488094329834,
+      "learning_rate": 1.9378947368421053e-05,
+      "loss": 0.8249,
+      "step": 160
+    },
+    {
+      "epoch": 1.035,
+      "grad_norm": 5.055039882659912,
+      "learning_rate": 1.9273684210526317e-05,
+      "loss": 0.8426,
+      "step": 170
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 4.677482604980469,
+      "learning_rate": 1.916842105263158e-05,
+      "loss": 0.8494,
+      "step": 180
+    },
+    {
+      "epoch": 1.045,
+      "grad_norm": 4.659126281738281,
+      "learning_rate": 1.9063157894736843e-05,
+      "loss": 0.8388,
+      "step": 190
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 4.688161849975586,
+      "learning_rate": 1.8957894736842106e-05,
+      "loss": 0.8079,
+      "step": 200
+    },
+    {
+      "epoch": 2.005,
+      "grad_norm": 5.431162357330322,
+      "learning_rate": 1.885263157894737e-05,
+      "loss": 0.3679,
+      "step": 210
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 3.8187713623046875,
+      "learning_rate": 1.8747368421052633e-05,
+      "loss": 0.358,
+      "step": 220
+    },
+    {
+      "epoch": 2.015,
+      "grad_norm": 3.1807172298431396,
+      "learning_rate": 1.8642105263157896e-05,
+      "loss": 0.3387,
+      "step": 230
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 4.693820953369141,
+      "learning_rate": 1.853684210526316e-05,
+      "loss": 0.3047,
+      "step": 240
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 4.142691135406494,
+      "learning_rate": 1.8431578947368423e-05,
+      "loss": 0.3039,
+      "step": 250
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 3.9841394424438477,
+      "learning_rate": 1.8326315789473686e-05,
+      "loss": 0.3011,
+      "step": 260
+    },
+    {
+      "epoch": 2.035,
+      "grad_norm": 4.5235676765441895,
+      "learning_rate": 1.822105263157895e-05,
+      "loss": 0.3537,
+      "step": 270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 4.285941123962402,
+      "learning_rate": 1.8115789473684213e-05,
+      "loss": 0.3105,
+      "step": 280
+    },
+    {
+      "epoch": 2.045,
+      "grad_norm": 3.71958327293396,
+      "learning_rate": 1.8010526315789476e-05,
+      "loss": 0.3346,
+      "step": 290
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 3.477006196975708,
+      "learning_rate": 1.790526315789474e-05,
+      "loss": 0.3125,
+      "step": 300
+    },
+    {
+      "epoch": 3.005,
+      "grad_norm": 2.9285550117492676,
+      "learning_rate": 1.7800000000000002e-05,
+      "loss": 0.1397,
+      "step": 310
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 2.792161703109741,
+      "learning_rate": 1.7694736842105266e-05,
+      "loss": 0.1566,
+      "step": 320
+    },
+    {
+      "epoch": 3.015,
+      "grad_norm": 2.6446938514709473,
+      "learning_rate": 1.758947368421053e-05,
+      "loss": 0.1583,
+      "step": 330
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 3.135241985321045,
+      "learning_rate": 1.748421052631579e-05,
+      "loss": 0.1536,
+      "step": 340
+    },
+    {
+      "epoch": 3.025,
+      "grad_norm": 2.987708568572998,
+      "learning_rate": 1.7378947368421052e-05,
+      "loss": 0.1542,
+      "step": 350
+    },
+    {
+      "epoch": 3.03,
+      "grad_norm": 2.5585477352142334,
+      "learning_rate": 1.727368421052632e-05,
+      "loss": 0.1742,
+      "step": 360
+    },
+    {
+      "epoch": 3.035,
+      "grad_norm": 2.899765729904175,
+      "learning_rate": 1.7168421052631582e-05,
+      "loss": 0.1611,
+      "step": 370
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.752307176589966,
+      "learning_rate": 1.7063157894736845e-05,
+      "loss": 0.2076,
+      "step": 380
+    },
+    {
+      "epoch": 3.045,
+      "grad_norm": 2.4184489250183105,
+      "learning_rate": 1.6957894736842105e-05,
+      "loss": 0.1744,
+      "step": 390
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 2.342548131942749,
+      "learning_rate": 1.685263157894737e-05,
+      "loss": 0.1657,
+      "step": 400
+    },
+    {
+      "epoch": 4.005,
+      "grad_norm": 3.1114871501922607,
+      "learning_rate": 1.6747368421052632e-05,
+      "loss": 0.0931,
+      "step": 410
+    },
+    {
+      "epoch": 4.01,
+      "grad_norm": 2.3490405082702637,
+      "learning_rate": 1.66421052631579e-05,
+      "loss": 0.097,
+      "step": 420
+    },
+    {
+      "epoch": 4.015,
+      "grad_norm": 2.8796679973602295,
+      "learning_rate": 1.653684210526316e-05,
+      "loss": 0.1063,
+      "step": 430
+    },
+    {
+      "epoch": 4.02,
+      "grad_norm": 2.324800491333008,
+      "learning_rate": 1.643157894736842e-05,
+      "loss": 0.1073,
+      "step": 440
+    },
+    {
+      "epoch": 4.025,
+      "grad_norm": 2.4009687900543213,
+      "learning_rate": 1.6326315789473685e-05,
+      "loss": 0.0968,
+      "step": 450
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 2.9474356174468994,
+      "learning_rate": 1.6221052631578948e-05,
+      "loss": 0.0925,
+      "step": 460
+    },
+    {
+      "epoch": 4.035,
+      "grad_norm": 2.1847965717315674,
+      "learning_rate": 1.611578947368421e-05,
+      "loss": 0.114,
+      "step": 470
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 1.7918593883514404,
+      "learning_rate": 1.6010526315789475e-05,
+      "loss": 0.1036,
+      "step": 480
+    },
+    {
+      "epoch": 4.045,
+      "grad_norm": 2.242753505706787,
+      "learning_rate": 1.5905263157894738e-05,
+      "loss": 0.0939,
+      "step": 490
+    },
+    {
+      "epoch": 4.05,
+      "grad_norm": 4.071936130523682,
+      "learning_rate": 1.58e-05,
+      "loss": 0.1138,
+      "step": 500
+    },
+    {
+      "epoch": 5.005,
+      "grad_norm": 1.5614343881607056,
+      "learning_rate": 1.5694736842105264e-05,
+      "loss": 0.0469,
+      "step": 510
+    },
+    {
+      "epoch": 5.01,
+      "grad_norm": 2.1511878967285156,
+      "learning_rate": 1.5589473684210528e-05,
+      "loss": 0.0544,
+      "step": 520
+    },
+    {
+      "epoch": 5.015,
+      "grad_norm": 1.4617661237716675,
+      "learning_rate": 1.548421052631579e-05,
+      "loss": 0.0565,
+      "step": 530
+    },
+    {
+      "epoch": 5.02,
+      "grad_norm": 2.533205270767212,
+      "learning_rate": 1.5378947368421054e-05,
+      "loss": 0.0582,
+      "step": 540
+    },
+    {
+      "epoch": 5.025,
+      "grad_norm": 2.398082733154297,
+      "learning_rate": 1.5273684210526318e-05,
+      "loss": 0.065,
+      "step": 550
+    },
+    {
+      "epoch": 5.03,
+      "grad_norm": 1.9306875467300415,
+      "learning_rate": 1.516842105263158e-05,
+      "loss": 0.0631,
+      "step": 560
+    },
+    {
+      "epoch": 5.035,
+      "grad_norm": 2.3642289638519287,
+      "learning_rate": 1.5063157894736844e-05,
+      "loss": 0.0641,
+      "step": 570
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 1.4011757373809814,
+      "learning_rate": 1.4957894736842107e-05,
+      "loss": 0.0773,
+      "step": 580
+    },
+    {
+      "epoch": 5.045,
+      "grad_norm": 2.026855945587158,
+      "learning_rate": 1.4852631578947369e-05,
+      "loss": 0.0664,
+      "step": 590
+    },
+    {
+      "epoch": 5.05,
+      "grad_norm": 2.1766583919525146,
+      "learning_rate": 1.4747368421052632e-05,
+      "loss": 0.0545,
+      "step": 600
+    },
+    {
+      "epoch": 6.005,
+      "grad_norm": 1.652336835861206,
+      "learning_rate": 1.4642105263157896e-05,
+      "loss": 0.0482,
+      "step": 610
+    },
+    {
+      "epoch": 6.01,
+      "grad_norm": 1.5396881103515625,
+      "learning_rate": 1.4536842105263159e-05,
+      "loss": 0.0349,
+      "step": 620
+    },
+    {
+      "epoch": 6.015,
+      "grad_norm": 2.64931321144104,
+      "learning_rate": 1.4431578947368424e-05,
+      "loss": 0.0491,
+      "step": 630
+    },
+    {
+      "epoch": 6.02,
+      "grad_norm": 1.5272787809371948,
+      "learning_rate": 1.4326315789473685e-05,
+      "loss": 0.0471,
+      "step": 640
+    },
+    {
+      "epoch": 6.025,
+      "grad_norm": 1.5077707767486572,
+      "learning_rate": 1.4221052631578949e-05,
+      "loss": 0.0413,
+      "step": 650
+    },
+    {
+      "epoch": 6.03,
+      "grad_norm": 1.2149569988250732,
+      "learning_rate": 1.4115789473684212e-05,
+      "loss": 0.0442,
+      "step": 660
+    },
+    {
+      "epoch": 6.035,
+      "grad_norm": 1.6021332740783691,
+      "learning_rate": 1.4010526315789475e-05,
+      "loss": 0.0386,
+      "step": 670
+    },
+    {
+      "epoch": 6.04,
+      "grad_norm": 1.8967393636703491,
+      "learning_rate": 1.3905263157894737e-05,
+      "loss": 0.047,
+      "step": 680
+    },
+    {
+      "epoch": 6.045,
+      "grad_norm": 1.5336661338806152,
+      "learning_rate": 1.38e-05,
+      "loss": 0.0381,
+      "step": 690
+    },
+    {
+      "epoch": 6.05,
+      "grad_norm": 2.3286962509155273,
+      "learning_rate": 1.3694736842105265e-05,
+      "loss": 0.0479,
+      "step": 700
+    },
+    {
+      "epoch": 7.005,
+      "grad_norm": 1.4702962636947632,
+      "learning_rate": 1.3589473684210528e-05,
+      "loss": 0.0231,
+      "step": 710
+    },
+    {
+      "epoch": 7.01,
+      "grad_norm": 1.7746834754943848,
+      "learning_rate": 1.3484210526315792e-05,
+      "loss": 0.0291,
+      "step": 720
+    },
+    {
+      "epoch": 7.015,
+      "grad_norm": 1.37478768825531,
+      "learning_rate": 1.3378947368421053e-05,
+      "loss": 0.0368,
+      "step": 730
+    },
+    {
+      "epoch": 7.02,
+      "grad_norm": 1.2662794589996338,
+      "learning_rate": 1.3273684210526316e-05,
+      "loss": 0.034,
+      "step": 740
+    },
+    {
+      "epoch": 7.025,
+      "grad_norm": 0.6514212489128113,
+      "learning_rate": 1.316842105263158e-05,
+      "loss": 0.0295,
+      "step": 750
+    },
+    {
+      "epoch": 7.03,
+      "grad_norm": 0.9872649908065796,
+      "learning_rate": 1.3063157894736845e-05,
+      "loss": 0.0248,
+      "step": 760
+    },
+    {
+      "epoch": 7.035,
+      "grad_norm": 0.9525852203369141,
+      "learning_rate": 1.2957894736842108e-05,
+      "loss": 0.0254,
+      "step": 770
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 1.5137120485305786,
+      "learning_rate": 1.285263157894737e-05,
+      "loss": 0.0238,
+      "step": 780
+    },
+    {
+      "epoch": 7.045,
+      "grad_norm": 3.0998730659484863,
+      "learning_rate": 1.2747368421052633e-05,
+      "loss": 0.0337,
+      "step": 790
+    },
+    {
+      "epoch": 7.05,
+      "grad_norm": 1.361088752746582,
+      "learning_rate": 1.2642105263157896e-05,
+      "loss": 0.0399,
+      "step": 800
+    },
+    {
+      "epoch": 8.005,
+      "grad_norm": 0.9619424343109131,
+      "learning_rate": 1.2536842105263158e-05,
+      "loss": 0.0215,
+      "step": 810
+    },
+    {
+      "epoch": 8.01,
+      "grad_norm": 1.0369452238082886,
+      "learning_rate": 1.2431578947368421e-05,
+      "loss": 0.0247,
+      "step": 820
+    },
+    {
+      "epoch": 8.015,
+      "grad_norm": 1.344269871711731,
+      "learning_rate": 1.2326315789473686e-05,
+      "loss": 0.025,
+      "step": 830
+    },
+    {
+      "epoch": 8.02,
+      "grad_norm": 1.2112865447998047,
+      "learning_rate": 1.2221052631578949e-05,
+      "loss": 0.0216,
+      "step": 840
+    },
+    {
+      "epoch": 8.025,
+      "grad_norm": 1.7333956956863403,
+      "learning_rate": 1.2115789473684212e-05,
+      "loss": 0.0183,
+      "step": 850
+    },
+    {
+      "epoch": 8.03,
+      "grad_norm": 2.0652589797973633,
+      "learning_rate": 1.2010526315789474e-05,
+      "loss": 0.0241,
+      "step": 860
+    },
+    {
+      "epoch": 8.035,
+      "grad_norm": 0.624588131904602,
+      "learning_rate": 1.1905263157894737e-05,
+      "loss": 0.0202,
+      "step": 870
+    },
+    {
+      "epoch": 8.04,
+      "grad_norm": 1.0641587972640991,
+      "learning_rate": 1.18e-05,
+      "loss": 0.019,
+      "step": 880
+    },
+    {
+      "epoch": 8.045,
+      "grad_norm": 1.1550590991973877,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 0.0214,
+      "step": 890
+    },
+    {
+      "epoch": 8.05,
+      "grad_norm": 1.3287566900253296,
+      "learning_rate": 1.1589473684210529e-05,
+      "loss": 0.0292,
+      "step": 900
+    },
+    {
+      "epoch": 9.005,
+      "grad_norm": 1.3364150524139404,
+      "learning_rate": 1.148421052631579e-05,
+      "loss": 0.0213,
+      "step": 910
+    },
+    {
+      "epoch": 9.01,
+      "grad_norm": 0.7193664908409119,
+      "learning_rate": 1.1378947368421054e-05,
+      "loss": 0.0082,
+      "step": 920
+    },
+    {
+      "epoch": 9.015,
+      "grad_norm": 1.0872008800506592,
+      "learning_rate": 1.1273684210526317e-05,
+      "loss": 0.0151,
+      "step": 930
+    },
+    {
+      "epoch": 9.02,
+      "grad_norm": 0.22245873510837555,
+      "learning_rate": 1.116842105263158e-05,
+      "loss": 0.0128,
+      "step": 940
+    },
+    {
+      "epoch": 9.025,
+      "grad_norm": 0.9914424419403076,
+      "learning_rate": 1.1063157894736842e-05,
+      "loss": 0.0174,
+      "step": 950
+    },
+    {
+      "epoch": 9.03,
+      "grad_norm": 0.9509072303771973,
+      "learning_rate": 1.0957894736842105e-05,
+      "loss": 0.0181,
+      "step": 960
+    },
+    {
+      "epoch": 9.035,
+      "grad_norm": 0.40795469284057617,
+      "learning_rate": 1.085263157894737e-05,
+      "loss": 0.0202,
+      "step": 970
+    },
+    {
+      "epoch": 9.04,
+      "grad_norm": 1.3863106966018677,
+      "learning_rate": 1.0747368421052633e-05,
+      "loss": 0.0172,
+      "step": 980
+    },
+    {
+      "epoch": 9.045,
+      "grad_norm": 0.6388317942619324,
+      "learning_rate": 1.0642105263157897e-05,
+      "loss": 0.0185,
+      "step": 990
+    },
+    {
+      "epoch": 9.05,
+      "grad_norm": 1.0237617492675781,
+      "learning_rate": 1.0536842105263158e-05,
+      "loss": 0.0193,
+      "step": 1000
+    },
+    {
+      "epoch": 10.005,
+      "grad_norm": 0.2478121817111969,
+      "learning_rate": 1.0431578947368421e-05,
+      "loss": 0.0111,
+      "step": 1010
+    },
+    {
+      "epoch": 10.01,
+      "grad_norm": 1.0051342248916626,
+      "learning_rate": 1.0326315789473685e-05,
+      "loss": 0.0102,
+      "step": 1020
+    },
+    {
+      "epoch": 10.015,
+      "grad_norm": 0.9585472345352173,
+      "learning_rate": 1.0221052631578948e-05,
+      "loss": 0.0141,
+      "step": 1030
+    },
+    {
+      "epoch": 10.02,
+      "grad_norm": 1.248799204826355,
+      "learning_rate": 1.0115789473684213e-05,
+      "loss": 0.0088,
+      "step": 1040
+    },
+    {
+      "epoch": 10.025,
+      "grad_norm": 1.050134301185608,
+      "learning_rate": 1.0010526315789474e-05,
+      "loss": 0.0097,
+      "step": 1050
+    },
+    {
+      "epoch": 10.03,
+      "grad_norm": 0.2019995152950287,
+      "learning_rate": 9.905263157894738e-06,
+      "loss": 0.011,
+      "step": 1060
+    },
+    {
+      "epoch": 10.035,
+      "grad_norm": 0.9100256562232971,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.0149,
+      "step": 1070
+    },
+    {
+      "epoch": 10.04,
+      "grad_norm": 0.8645588159561157,
+      "learning_rate": 9.694736842105263e-06,
+      "loss": 0.011,
+      "step": 1080
+    },
+    {
+      "epoch": 10.045,
+      "grad_norm": 0.9465664029121399,
+      "learning_rate": 9.589473684210528e-06,
+      "loss": 0.0116,
+      "step": 1090
+    },
+    {
+      "epoch": 10.05,
+      "grad_norm": 0.7357518076896667,
+      "learning_rate": 9.484210526315791e-06,
+      "loss": 0.0132,
+      "step": 1100
+    },
+    {
+      "epoch": 11.005,
+      "grad_norm": 0.0960564911365509,
+      "learning_rate": 9.378947368421052e-06,
+      "loss": 0.0079,
+      "step": 1110
+    },
+    {
+      "epoch": 11.01,
+      "grad_norm": 0.07488369941711426,
+      "learning_rate": 9.273684210526317e-06,
+      "loss": 0.0079,
+      "step": 1120
+    },
+    {
+      "epoch": 11.015,
+      "grad_norm": 0.4596630334854126,
+      "learning_rate": 9.168421052631579e-06,
+      "loss": 0.0073,
+      "step": 1130
+    },
+    {
+      "epoch": 11.02,
+      "grad_norm": 0.915014386177063,
+      "learning_rate": 9.063157894736842e-06,
+      "loss": 0.0058,
+      "step": 1140
+    },
+    {
+      "epoch": 11.025,
+      "grad_norm": 0.4357207119464874,
+      "learning_rate": 8.957894736842107e-06,
+      "loss": 0.0082,
+      "step": 1150
+    },
+    {
+      "epoch": 11.03,
+      "grad_norm": 0.6345843076705933,
+      "learning_rate": 8.852631578947369e-06,
+      "loss": 0.009,
+      "step": 1160
+    },
+    {
+      "epoch": 11.035,
+      "grad_norm": 0.2351154237985611,
+      "learning_rate": 8.747368421052632e-06,
+      "loss": 0.0071,
+      "step": 1170
+    },
+    {
+      "epoch": 11.04,
+      "grad_norm": 0.5750226378440857,
+      "learning_rate": 8.642105263157895e-06,
+      "loss": 0.0065,
+      "step": 1180
+    },
+    {
+      "epoch": 11.045,
+      "grad_norm": 0.49880605936050415,
+      "learning_rate": 8.536842105263159e-06,
+      "loss": 0.0061,
+      "step": 1190
+    },
+    {
+      "epoch": 11.05,
+      "grad_norm": 0.6473588347434998,
+      "learning_rate": 8.431578947368422e-06,
+      "loss": 0.0091,
+      "step": 1200
+    },
+    {
+      "epoch": 12.005,
+      "grad_norm": 0.02745138294994831,
+      "learning_rate": 8.326315789473685e-06,
+      "loss": 0.0027,
+      "step": 1210
+    },
+    {
+      "epoch": 12.01,
+      "grad_norm": 0.6922830939292908,
+      "learning_rate": 8.221052631578948e-06,
+      "loss": 0.0058,
+      "step": 1220
+    },
+    {
+      "epoch": 12.015,
+      "grad_norm": 0.6273651719093323,
+      "learning_rate": 8.115789473684212e-06,
+      "loss": 0.0034,
+      "step": 1230
+    },
+    {
+      "epoch": 12.02,
+      "grad_norm": 1.0830379724502563,
+      "learning_rate": 8.010526315789473e-06,
+      "loss": 0.0063,
+      "step": 1240
+    },
+    {
+      "epoch": 12.025,
+      "grad_norm": 0.824835479259491,
+      "learning_rate": 7.905263157894737e-06,
+      "loss": 0.0064,
+      "step": 1250
+    },
+    {
+      "epoch": 12.03,
+      "grad_norm": 0.5051027536392212,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 0.0029,
+      "step": 1260
+    },
+    {
+      "epoch": 12.035,
+      "grad_norm": 0.6191169619560242,
+      "learning_rate": 7.694736842105263e-06,
+      "loss": 0.0036,
+      "step": 1270
+    },
+    {
+      "epoch": 12.04,
+      "grad_norm": 0.03212520107626915,
+      "learning_rate": 7.589473684210526e-06,
+      "loss": 0.001,
+      "step": 1280
+    },
+    {
+      "epoch": 12.045,
+      "grad_norm": 0.027301745489239693,
+      "learning_rate": 7.4842105263157905e-06,
+      "loss": 0.0024,
+      "step": 1290
+    },
+    {
+      "epoch": 12.05,
+      "grad_norm": 0.6917107701301575,
+      "learning_rate": 7.378947368421053e-06,
+      "loss": 0.002,
+      "step": 1300
+    },
+    {
+      "epoch": 13.005,
+      "grad_norm": 0.009404812939465046,
+      "learning_rate": 7.273684210526316e-06,
+      "loss": 0.0023,
+      "step": 1310
+    },
+    {
+      "epoch": 13.01,
+      "grad_norm": 0.5634567737579346,
+      "learning_rate": 7.16842105263158e-06,
+      "loss": 0.001,
+      "step": 1320
+    },
+    {
+      "epoch": 13.015,
+      "grad_norm": 0.02036663331091404,
+      "learning_rate": 7.063157894736843e-06,
+      "loss": 0.0025,
+      "step": 1330
+    },
+    {
+      "epoch": 13.02,
+      "grad_norm": 0.05707384645938873,
+      "learning_rate": 6.957894736842106e-06,
+      "loss": 0.0012,
+      "step": 1340
+    },
+    {
+      "epoch": 13.025,
+      "grad_norm": 0.022448807954788208,
+      "learning_rate": 6.8526315789473685e-06,
+      "loss": 0.0008,
+      "step": 1350
+    },
+    {
+      "epoch": 13.03,
+      "grad_norm": 0.012089096009731293,
+      "learning_rate": 6.747368421052633e-06,
+      "loss": 0.0039,
+      "step": 1360
+    },
+    {
+      "epoch": 13.035,
+      "grad_norm": 0.14159785211086273,
+      "learning_rate": 6.642105263157895e-06,
+      "loss": 0.0005,
+      "step": 1370
+    },
+    {
+      "epoch": 13.04,
+      "grad_norm": 0.05650542676448822,
+      "learning_rate": 6.536842105263158e-06,
+      "loss": 0.0011,
+      "step": 1380
+    },
+    {
+      "epoch": 13.045,
+      "grad_norm": 0.030941806733608246,
+      "learning_rate": 6.431578947368422e-06,
+      "loss": 0.0024,
+      "step": 1390
+    },
+    {
+      "epoch": 13.05,
+      "grad_norm": 0.022141387686133385,
+      "learning_rate": 6.326315789473685e-06,
+      "loss": 0.0035,
+      "step": 1400
+    },
+    {
+      "epoch": 14.005,
+      "grad_norm": 0.010789740830659866,
+      "learning_rate": 6.221052631578947e-06,
+      "loss": 0.0002,
+      "step": 1410
+    },
+    {
+      "epoch": 14.01,
+      "grad_norm": 0.008089865557849407,
+      "learning_rate": 6.1157894736842106e-06,
+      "loss": 0.0002,
+      "step": 1420
+    },
+    {
+      "epoch": 14.015,
+      "grad_norm": 0.009247499518096447,
+      "learning_rate": 6.010526315789475e-06,
+      "loss": 0.0004,
+      "step": 1430
+    },
+    {
+      "epoch": 14.02,
+      "grad_norm": 0.005500028375536203,
+      "learning_rate": 5.905263157894737e-06,
+      "loss": 0.0019,
+      "step": 1440
+    },
+    {
+      "epoch": 14.025,
+      "grad_norm": 0.04416996240615845,
+      "learning_rate": 5.8e-06,
+      "loss": 0.0013,
+      "step": 1450
+    },
+    {
+      "epoch": 14.03,
+      "grad_norm": 0.10680264979600906,
+      "learning_rate": 5.694736842105264e-06,
+      "loss": 0.0012,
+      "step": 1460
+    },
+    {
+      "epoch": 14.035,
+      "grad_norm": 0.008884921669960022,
+      "learning_rate": 5.589473684210527e-06,
+      "loss": 0.0002,
+      "step": 1470
+    },
+    {
+      "epoch": 14.04,
+      "grad_norm": 0.179422989487648,
+      "learning_rate": 5.484210526315789e-06,
+      "loss": 0.0009,
+      "step": 1480
+    },
+    {
+      "epoch": 14.045,
+      "grad_norm": 0.7773061990737915,
+      "learning_rate": 5.3789473684210535e-06,
+      "loss": 0.0003,
+      "step": 1490
+    },
+    {
+      "epoch": 14.05,
+      "grad_norm": 0.04718916490674019,
+      "learning_rate": 5.273684210526317e-06,
+      "loss": 0.0009,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.758292910191411e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b144045336f4f3606add1e223999e524680be7894eda34a4b0257439b230feff
+size 5969

checkpoint-2000/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-2000/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

checkpoint-2000/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77649a1b219e4bc187cae3cc5aca916fbec8a25eea88c772ce69dfe88b416e4
+size 4976687216

checkpoint-2000/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c97225bc3921512ca195d4e96b14d8022e8ea4e055043bc34d33b3d4c591fcc
+size 4778622352

checkpoint-2000/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b346dfe4fb8f0528cc704e68230a6adfea3ce9493354a4e46f405708b3c3afa
+size 4932743960

checkpoint-2000/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7158efa6583ae4698013f44b48490c0ef93c7919f82a1a5e22fa6ff34b5643
+size 4932743992

checkpoint-2000/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5350aed90c3b9ab92f08ac1ab20f0d8c8a3ac913e6f43f56be4d8fe6fa5b844
+size 4998852296

checkpoint-2000/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960785c135ce1a11268775a775e30033d166b7468ac6f72ad19129f09f54c58e
+size 3662865184

checkpoint-2000/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8777f4a42f4e464199c2997433c43dec13c2f75b1f43d4774a8b16866a9e07e
+size 2179989632

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 3807808256,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-2000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5e29f6706afef708674d61e37584e08c3c40c2b21a97db5dc82a48ad89919e
+size 60925254788

checkpoint-2000/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75249282b4dba1d5fc860a19ba5f7cc0ea49922cfa4fc6f345bab2b9b202eac
+size 30462624740

checkpoint-2000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40bf20f197bd17ec1bdfd489331bcafb0e17bda96efa01f1b3e1e76e3ed3951a
+size 14917

checkpoint-2000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7965805c42203518e2434e22dd33231635b46e7a22514777eeaf57b35226977d
+size 14917

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197cfcfbf9a36f4f36efb39330b481554a65e22895ce4f427a55d7698d737749
+size 1465

checkpoint-2000/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
+  }
+}

checkpoint-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.05,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 5.616273880004883,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.9513,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.260721206665039,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.7789,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 5.373858451843262,
+      "learning_rate": 5.8e-06,
+      "loss": 1.6535,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.073526859283447,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.4488,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 4.743659973144531,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.4239,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.532003879547119,
+      "learning_rate": 1.18e-05,
+      "loss": 1.4531,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.564126491546631,
+      "learning_rate": 1.38e-05,
+      "loss": 1.4279,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.471712112426758,
+      "learning_rate": 1.58e-05,
+      "loss": 1.3619,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 5.032183647155762,
+      "learning_rate": 1.7800000000000002e-05,
+      "loss": 1.3614,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.518551349639893,
+      "learning_rate": 1.98e-05,
+      "loss": 1.3551,
+      "step": 100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 6.518773555755615,
+      "learning_rate": 1.990526315789474e-05,
+      "loss": 0.8287,
+      "step": 110
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 3.6112170219421387,
+      "learning_rate": 1.98e-05,
+      "loss": 0.7035,
+      "step": 120
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 5.7912726402282715,
+      "learning_rate": 1.9694736842105263e-05,
+      "loss": 0.8074,
+      "step": 130
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 3.595136880874634,
+      "learning_rate": 1.9589473684210527e-05,
+      "loss": 0.7915,
+      "step": 140
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 4.417491912841797,
+      "learning_rate": 1.9484210526315793e-05,
+      "loss": 0.8106,
+      "step": 150
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.246488094329834,
+      "learning_rate": 1.9378947368421053e-05,
+      "loss": 0.8249,
+      "step": 160
+    },
+    {
+      "epoch": 1.035,
+      "grad_norm": 5.055039882659912,
+      "learning_rate": 1.9273684210526317e-05,
+      "loss": 0.8426,
+      "step": 170
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 4.677482604980469,
+      "learning_rate": 1.916842105263158e-05,
+      "loss": 0.8494,
+      "step": 180
+    },
+    {
+      "epoch": 1.045,
+      "grad_norm": 4.659126281738281,
+      "learning_rate": 1.9063157894736843e-05,
+      "loss": 0.8388,
+      "step": 190
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 4.688161849975586,
+      "learning_rate": 1.8957894736842106e-05,
+      "loss": 0.8079,
+      "step": 200
+    },
+    {
+      "epoch": 2.005,
+      "grad_norm": 5.431162357330322,
+      "learning_rate": 1.885263157894737e-05,
+      "loss": 0.3679,
+      "step": 210
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 3.8187713623046875,
+      "learning_rate": 1.8747368421052633e-05,
+      "loss": 0.358,
+      "step": 220
+    },
+    {
+      "epoch": 2.015,
+      "grad_norm": 3.1807172298431396,
+      "learning_rate": 1.8642105263157896e-05,
+      "loss": 0.3387,
+      "step": 230
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 4.693820953369141,
+      "learning_rate": 1.853684210526316e-05,
+      "loss": 0.3047,
+      "step": 240
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 4.142691135406494,
+      "learning_rate": 1.8431578947368423e-05,
+      "loss": 0.3039,
+      "step": 250
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 3.9841394424438477,
+      "learning_rate": 1.8326315789473686e-05,
+      "loss": 0.3011,
+      "step": 260
+    },
+    {
+      "epoch": 2.035,
+      "grad_norm": 4.5235676765441895,
+      "learning_rate": 1.822105263157895e-05,
+      "loss": 0.3537,
+      "step": 270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 4.285941123962402,
+      "learning_rate": 1.8115789473684213e-05,
+      "loss": 0.3105,
+      "step": 280
+    },
+    {
+      "epoch": 2.045,
+      "grad_norm": 3.71958327293396,
+      "learning_rate": 1.8010526315789476e-05,
+      "loss": 0.3346,
+      "step": 290
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 3.477006196975708,
+      "learning_rate": 1.790526315789474e-05,
+      "loss": 0.3125,
+      "step": 300
+    },
+    {
+      "epoch": 3.005,
+      "grad_norm": 2.9285550117492676,
+      "learning_rate": 1.7800000000000002e-05,
+      "loss": 0.1397,
+      "step": 310
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 2.792161703109741,
+      "learning_rate": 1.7694736842105266e-05,
+      "loss": 0.1566,
+      "step": 320
+    },
+    {
+      "epoch": 3.015,
+      "grad_norm": 2.6446938514709473,
+      "learning_rate": 1.758947368421053e-05,
+      "loss": 0.1583,
+      "step": 330
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 3.135241985321045,
+      "learning_rate": 1.748421052631579e-05,
+      "loss": 0.1536,
+      "step": 340
+    },
+    {
+      "epoch": 3.025,
+      "grad_norm": 2.987708568572998,
+      "learning_rate": 1.7378947368421052e-05,
+      "loss": 0.1542,
+      "step": 350
+    },
+    {
+      "epoch": 3.03,
+      "grad_norm": 2.5585477352142334,
+      "learning_rate": 1.727368421052632e-05,
+      "loss": 0.1742,
+      "step": 360
+    },
+    {
+      "epoch": 3.035,
+      "grad_norm": 2.899765729904175,
+      "learning_rate": 1.7168421052631582e-05,
+      "loss": 0.1611,
+      "step": 370
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.752307176589966,
+      "learning_rate": 1.7063157894736845e-05,
+      "loss": 0.2076,
+      "step": 380
+    },
+    {
+      "epoch": 3.045,
+      "grad_norm": 2.4184489250183105,
+      "learning_rate": 1.6957894736842105e-05,
+      "loss": 0.1744,
+      "step": 390
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 2.342548131942749,
+      "learning_rate": 1.685263157894737e-05,
+      "loss": 0.1657,
+      "step": 400
+    },
+    {
+      "epoch": 4.005,
+      "grad_norm": 3.1114871501922607,
+      "learning_rate": 1.6747368421052632e-05,
+      "loss": 0.0931,
+      "step": 410
+    },
+    {
+      "epoch": 4.01,
+      "grad_norm": 2.3490405082702637,
+      "learning_rate": 1.66421052631579e-05,
+      "loss": 0.097,
+      "step": 420
+    },
+    {
+      "epoch": 4.015,
+      "grad_norm": 2.8796679973602295,
+      "learning_rate": 1.653684210526316e-05,
+      "loss": 0.1063,
+      "step": 430
+    },
+    {
+      "epoch": 4.02,
+      "grad_norm": 2.324800491333008,
+      "learning_rate": 1.643157894736842e-05,
+      "loss": 0.1073,
+      "step": 440
+    },
+    {
+      "epoch": 4.025,
+      "grad_norm": 2.4009687900543213,
+      "learning_rate": 1.6326315789473685e-05,
+      "loss": 0.0968,
+      "step": 450
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 2.9474356174468994,
+      "learning_rate": 1.6221052631578948e-05,
+      "loss": 0.0925,
+      "step": 460
+    },
+    {
+      "epoch": 4.035,
+      "grad_norm": 2.1847965717315674,
+      "learning_rate": 1.611578947368421e-05,
+      "loss": 0.114,
+      "step": 470
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 1.7918593883514404,
+      "learning_rate": 1.6010526315789475e-05,
+      "loss": 0.1036,
+      "step": 480
+    },
+    {
+      "epoch": 4.045,
+      "grad_norm": 2.242753505706787,
+      "learning_rate": 1.5905263157894738e-05,
+      "loss": 0.0939,
+      "step": 490
+    },
+    {
+      "epoch": 4.05,
+      "grad_norm": 4.071936130523682,
+      "learning_rate": 1.58e-05,
+      "loss": 0.1138,
+      "step": 500
+    },
+    {
+      "epoch": 5.005,
+      "grad_norm": 1.5614343881607056,
+      "learning_rate": 1.5694736842105264e-05,
+      "loss": 0.0469,
+      "step": 510
+    },
+    {
+      "epoch": 5.01,
+      "grad_norm": 2.1511878967285156,
+      "learning_rate": 1.5589473684210528e-05,
+      "loss": 0.0544,
+      "step": 520
+    },
+    {
+      "epoch": 5.015,
+      "grad_norm": 1.4617661237716675,
+      "learning_rate": 1.548421052631579e-05,
+      "loss": 0.0565,
+      "step": 530
+    },
+    {
+      "epoch": 5.02,
+      "grad_norm": 2.533205270767212,
+      "learning_rate": 1.5378947368421054e-05,
+      "loss": 0.0582,
+      "step": 540
+    },
+    {
+      "epoch": 5.025,
+      "grad_norm": 2.398082733154297,
+      "learning_rate": 1.5273684210526318e-05,
+      "loss": 0.065,
+      "step": 550
+    },
+    {
+      "epoch": 5.03,
+      "grad_norm": 1.9306875467300415,
+      "learning_rate": 1.516842105263158e-05,
+      "loss": 0.0631,
+      "step": 560
+    },
+    {
+      "epoch": 5.035,
+      "grad_norm": 2.3642289638519287,
+      "learning_rate": 1.5063157894736844e-05,
+      "loss": 0.0641,
+      "step": 570
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 1.4011757373809814,
+      "learning_rate": 1.4957894736842107e-05,
+      "loss": 0.0773,
+      "step": 580
+    },
+    {
+      "epoch": 5.045,
+      "grad_norm": 2.026855945587158,
+      "learning_rate": 1.4852631578947369e-05,
+      "loss": 0.0664,
+      "step": 590
+    },
+    {
+      "epoch": 5.05,
+      "grad_norm": 2.1766583919525146,
+      "learning_rate": 1.4747368421052632e-05,
+      "loss": 0.0545,
+      "step": 600
+    },
+    {
+      "epoch": 6.005,
+      "grad_norm": 1.652336835861206,
+      "learning_rate": 1.4642105263157896e-05,
+      "loss": 0.0482,
+      "step": 610
+    },
+    {
+      "epoch": 6.01,
+      "grad_norm": 1.5396881103515625,
+      "learning_rate": 1.4536842105263159e-05,
+      "loss": 0.0349,
+      "step": 620
+    },
+    {
+      "epoch": 6.015,
+      "grad_norm": 2.64931321144104,
+      "learning_rate": 1.4431578947368424e-05,
+      "loss": 0.0491,
+      "step": 630
+    },
+    {
+      "epoch": 6.02,
+      "grad_norm": 1.5272787809371948,
+      "learning_rate": 1.4326315789473685e-05,
+      "loss": 0.0471,
+      "step": 640
+    },
+    {
+      "epoch": 6.025,
+      "grad_norm": 1.5077707767486572,
+      "learning_rate": 1.4221052631578949e-05,
+      "loss": 0.0413,
+      "step": 650
+    },
+    {
+      "epoch": 6.03,
+      "grad_norm": 1.2149569988250732,
+      "learning_rate": 1.4115789473684212e-05,
+      "loss": 0.0442,
+      "step": 660
+    },
+    {
+      "epoch": 6.035,
+      "grad_norm": 1.6021332740783691,
+      "learning_rate": 1.4010526315789475e-05,
+      "loss": 0.0386,
+      "step": 670
+    },
+    {
+      "epoch": 6.04,
+      "grad_norm": 1.8967393636703491,
+      "learning_rate": 1.3905263157894737e-05,
+      "loss": 0.047,
+      "step": 680
+    },
+    {
+      "epoch": 6.045,
+      "grad_norm": 1.5336661338806152,
+      "learning_rate": 1.38e-05,
+      "loss": 0.0381,
+      "step": 690
+    },
+    {
+      "epoch": 6.05,
+      "grad_norm": 2.3286962509155273,
+      "learning_rate": 1.3694736842105265e-05,
+      "loss": 0.0479,
+      "step": 700
+    },
+    {
+      "epoch": 7.005,
+      "grad_norm": 1.4702962636947632,
+      "learning_rate": 1.3589473684210528e-05,
+      "loss": 0.0231,
+      "step": 710
+    },
+    {
+      "epoch": 7.01,
+      "grad_norm": 1.7746834754943848,
+      "learning_rate": 1.3484210526315792e-05,
+      "loss": 0.0291,
+      "step": 720
+    },
+    {
+      "epoch": 7.015,
+      "grad_norm": 1.37478768825531,
+      "learning_rate": 1.3378947368421053e-05,
+      "loss": 0.0368,
+      "step": 730
+    },
+    {
+      "epoch": 7.02,
+      "grad_norm": 1.2662794589996338,
+      "learning_rate": 1.3273684210526316e-05,
+      "loss": 0.034,
+      "step": 740
+    },
+    {
+      "epoch": 7.025,
+      "grad_norm": 0.6514212489128113,
+      "learning_rate": 1.316842105263158e-05,
+      "loss": 0.0295,
+      "step": 750
+    },
+    {
+      "epoch": 7.03,
+      "grad_norm": 0.9872649908065796,
+      "learning_rate": 1.3063157894736845e-05,
+      "loss": 0.0248,
+      "step": 760
+    },
+    {
+      "epoch": 7.035,
+      "grad_norm": 0.9525852203369141,
+      "learning_rate": 1.2957894736842108e-05,
+      "loss": 0.0254,
+      "step": 770
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 1.5137120485305786,
+      "learning_rate": 1.285263157894737e-05,
+      "loss": 0.0238,
+      "step": 780
+    },
+    {
+      "epoch": 7.045,
+      "grad_norm": 3.0998730659484863,
+      "learning_rate": 1.2747368421052633e-05,
+      "loss": 0.0337,
+      "step": 790
+    },
+    {
+      "epoch": 7.05,
+      "grad_norm": 1.361088752746582,
+      "learning_rate": 1.2642105263157896e-05,
+      "loss": 0.0399,
+      "step": 800
+    },
+    {
+      "epoch": 8.005,
+      "grad_norm": 0.9619424343109131,
+      "learning_rate": 1.2536842105263158e-05,
+      "loss": 0.0215,
+      "step": 810
+    },
+    {
+      "epoch": 8.01,
+      "grad_norm": 1.0369452238082886,
+      "learning_rate": 1.2431578947368421e-05,
+      "loss": 0.0247,
+      "step": 820
+    },
+    {
+      "epoch": 8.015,
+      "grad_norm": 1.344269871711731,
+      "learning_rate": 1.2326315789473686e-05,
+      "loss": 0.025,
+      "step": 830
+    },
+    {
+      "epoch": 8.02,
+      "grad_norm": 1.2112865447998047,
+      "learning_rate": 1.2221052631578949e-05,
+      "loss": 0.0216,
+      "step": 840
+    },
+    {
+      "epoch": 8.025,
+      "grad_norm": 1.7333956956863403,
+      "learning_rate": 1.2115789473684212e-05,
+      "loss": 0.0183,
+      "step": 850
+    },
+    {
+      "epoch": 8.03,
+      "grad_norm": 2.0652589797973633,
+      "learning_rate": 1.2010526315789474e-05,
+      "loss": 0.0241,
+      "step": 860
+    },
+    {
+      "epoch": 8.035,
+      "grad_norm": 0.624588131904602,
+      "learning_rate": 1.1905263157894737e-05,
+      "loss": 0.0202,
+      "step": 870
+    },
+    {
+      "epoch": 8.04,
+      "grad_norm": 1.0641587972640991,
+      "learning_rate": 1.18e-05,
+      "loss": 0.019,
+      "step": 880
+    },
+    {
+      "epoch": 8.045,
+      "grad_norm": 1.1550590991973877,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 0.0214,
+      "step": 890
+    },
+    {
+      "epoch": 8.05,
+      "grad_norm": 1.3287566900253296,
+      "learning_rate": 1.1589473684210529e-05,
+      "loss": 0.0292,
+      "step": 900
+    },
+    {
+      "epoch": 9.005,
+      "grad_norm": 1.3364150524139404,
+      "learning_rate": 1.148421052631579e-05,
+      "loss": 0.0213,
+      "step": 910
+    },
+    {
+      "epoch": 9.01,
+      "grad_norm": 0.7193664908409119,
+      "learning_rate": 1.1378947368421054e-05,
+      "loss": 0.0082,
+      "step": 920
+    },
+    {
+      "epoch": 9.015,
+      "grad_norm": 1.0872008800506592,
+      "learning_rate": 1.1273684210526317e-05,
+      "loss": 0.0151,
+      "step": 930
+    },
+    {
+      "epoch": 9.02,
+      "grad_norm": 0.22245873510837555,
+      "learning_rate": 1.116842105263158e-05,
+      "loss": 0.0128,
+      "step": 940
+    },
+    {
+      "epoch": 9.025,
+      "grad_norm": 0.9914424419403076,
+      "learning_rate": 1.1063157894736842e-05,
+      "loss": 0.0174,
+      "step": 950
+    },
+    {
+      "epoch": 9.03,
+      "grad_norm": 0.9509072303771973,
+      "learning_rate": 1.0957894736842105e-05,
+      "loss": 0.0181,
+      "step": 960
+    },
+    {
+      "epoch": 9.035,
+      "grad_norm": 0.40795469284057617,
+      "learning_rate": 1.085263157894737e-05,
+      "loss": 0.0202,
+      "step": 970
+    },
+    {
+      "epoch": 9.04,
+      "grad_norm": 1.3863106966018677,
+      "learning_rate": 1.0747368421052633e-05,
+      "loss": 0.0172,
+      "step": 980
+    },
+    {
+      "epoch": 9.045,
+      "grad_norm": 0.6388317942619324,
+      "learning_rate": 1.0642105263157897e-05,
+      "loss": 0.0185,
+      "step": 990
+    },
+    {
+      "epoch": 9.05,
+      "grad_norm": 1.0237617492675781,
+      "learning_rate": 1.0536842105263158e-05,
+      "loss": 0.0193,
+      "step": 1000
+    },
+    {
+      "epoch": 10.005,
+      "grad_norm": 0.2478121817111969,
+      "learning_rate": 1.0431578947368421e-05,
+      "loss": 0.0111,
+      "step": 1010
+    },
+    {
+      "epoch": 10.01,
+      "grad_norm": 1.0051342248916626,
+      "learning_rate": 1.0326315789473685e-05,
+      "loss": 0.0102,
+      "step": 1020
+    },
+    {
+      "epoch": 10.015,
+      "grad_norm": 0.9585472345352173,
+      "learning_rate": 1.0221052631578948e-05,
+      "loss": 0.0141,
+      "step": 1030
+    },
+    {
+      "epoch": 10.02,
+      "grad_norm": 1.248799204826355,
+      "learning_rate": 1.0115789473684213e-05,
+      "loss": 0.0088,
+      "step": 1040
+    },
+    {
+      "epoch": 10.025,
+      "grad_norm": 1.050134301185608,
+      "learning_rate": 1.0010526315789474e-05,
+      "loss": 0.0097,
+      "step": 1050
+    },
+    {
+      "epoch": 10.03,
+      "grad_norm": 0.2019995152950287,
+      "learning_rate": 9.905263157894738e-06,
+      "loss": 0.011,
+      "step": 1060
+    },
+    {
+      "epoch": 10.035,
+      "grad_norm": 0.9100256562232971,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.0149,
+      "step": 1070
+    },
+    {
+      "epoch": 10.04,
+      "grad_norm": 0.8645588159561157,
+      "learning_rate": 9.694736842105263e-06,
+      "loss": 0.011,
+      "step": 1080
+    },
+    {
+      "epoch": 10.045,
+      "grad_norm": 0.9465664029121399,
+      "learning_rate": 9.589473684210528e-06,
+      "loss": 0.0116,
+      "step": 1090
+    },
+    {
+      "epoch": 10.05,
+      "grad_norm": 0.7357518076896667,
+      "learning_rate": 9.484210526315791e-06,
+      "loss": 0.0132,
+      "step": 1100
+    },
+    {
+      "epoch": 11.005,
+      "grad_norm": 0.0960564911365509,
+      "learning_rate": 9.378947368421052e-06,
+      "loss": 0.0079,
+      "step": 1110
+    },
+    {
+      "epoch": 11.01,
+      "grad_norm": 0.07488369941711426,
+      "learning_rate": 9.273684210526317e-06,
+      "loss": 0.0079,
+      "step": 1120
+    },
+    {
+      "epoch": 11.015,
+      "grad_norm": 0.4596630334854126,
+      "learning_rate": 9.168421052631579e-06,
+      "loss": 0.0073,
+      "step": 1130
+    },
+    {
+      "epoch": 11.02,
+      "grad_norm": 0.915014386177063,
+      "learning_rate": 9.063157894736842e-06,
+      "loss": 0.0058,
+      "step": 1140
+    },
+    {
+      "epoch": 11.025,
+      "grad_norm": 0.4357207119464874,
+      "learning_rate": 8.957894736842107e-06,
+      "loss": 0.0082,
+      "step": 1150
+    },
+    {
+      "epoch": 11.03,
+      "grad_norm": 0.6345843076705933,
+      "learning_rate": 8.852631578947369e-06,
+      "loss": 0.009,
+      "step": 1160
+    },
+    {
+      "epoch": 11.035,
+      "grad_norm": 0.2351154237985611,
+      "learning_rate": 8.747368421052632e-06,
+      "loss": 0.0071,
+      "step": 1170
+    },
+    {
+      "epoch": 11.04,
+      "grad_norm": 0.5750226378440857,
+      "learning_rate": 8.642105263157895e-06,
+      "loss": 0.0065,
+      "step": 1180
+    },
+    {
+      "epoch": 11.045,
+      "grad_norm": 0.49880605936050415,
+      "learning_rate": 8.536842105263159e-06,
+      "loss": 0.0061,
+      "step": 1190
+    },
+    {
+      "epoch": 11.05,
+      "grad_norm": 0.6473588347434998,
+      "learning_rate": 8.431578947368422e-06,
+      "loss": 0.0091,
+      "step": 1200
+    },
+    {
+      "epoch": 12.005,
+      "grad_norm": 0.02745138294994831,
+      "learning_rate": 8.326315789473685e-06,
+      "loss": 0.0027,
+      "step": 1210
+    },
+    {
+      "epoch": 12.01,
+      "grad_norm": 0.6922830939292908,
+      "learning_rate": 8.221052631578948e-06,
+      "loss": 0.0058,
+      "step": 1220
+    },
+    {
+      "epoch": 12.015,
+      "grad_norm": 0.6273651719093323,
+      "learning_rate": 8.115789473684212e-06,
+      "loss": 0.0034,
+      "step": 1230
+    },
+    {
+      "epoch": 12.02,
+      "grad_norm": 1.0830379724502563,
+      "learning_rate": 8.010526315789473e-06,
+      "loss": 0.0063,
+      "step": 1240
+    },
+    {
+      "epoch": 12.025,
+      "grad_norm": 0.824835479259491,
+      "learning_rate": 7.905263157894737e-06,
+      "loss": 0.0064,
+      "step": 1250
+    },
+    {
+      "epoch": 12.03,
+      "grad_norm": 0.5051027536392212,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 0.0029,
+      "step": 1260
+    },
+    {
+      "epoch": 12.035,
+      "grad_norm": 0.6191169619560242,
+      "learning_rate": 7.694736842105263e-06,
+      "loss": 0.0036,
+      "step": 1270
+    },
+    {
+      "epoch": 12.04,
+      "grad_norm": 0.03212520107626915,
+      "learning_rate": 7.589473684210526e-06,
+      "loss": 0.001,
+      "step": 1280
+    },
+    {
+      "epoch": 12.045,
+      "grad_norm": 0.027301745489239693,
+      "learning_rate": 7.4842105263157905e-06,
+      "loss": 0.0024,
+      "step": 1290
+    },
+    {
+      "epoch": 12.05,
+      "grad_norm": 0.6917107701301575,
+      "learning_rate": 7.378947368421053e-06,
+      "loss": 0.002,
+      "step": 1300
+    },
+    {
+      "epoch": 13.005,
+      "grad_norm": 0.009404812939465046,
+      "learning_rate": 7.273684210526316e-06,
+      "loss": 0.0023,
+      "step": 1310
+    },
+    {
+      "epoch": 13.01,
+      "grad_norm": 0.5634567737579346,
+      "learning_rate": 7.16842105263158e-06,
+      "loss": 0.001,
+      "step": 1320
+    },
+    {
+      "epoch": 13.015,
+      "grad_norm": 0.02036663331091404,
+      "learning_rate": 7.063157894736843e-06,
+      "loss": 0.0025,
+      "step": 1330
+    },
+    {
+      "epoch": 13.02,
+      "grad_norm": 0.05707384645938873,
+      "learning_rate": 6.957894736842106e-06,
+      "loss": 0.0012,
+      "step": 1340
+    },
+    {
+      "epoch": 13.025,
+      "grad_norm": 0.022448807954788208,
+      "learning_rate": 6.8526315789473685e-06,
+      "loss": 0.0008,
+      "step": 1350
+    },
+    {
+      "epoch": 13.03,
+      "grad_norm": 0.012089096009731293,
+      "learning_rate": 6.747368421052633e-06,
+      "loss": 0.0039,
+      "step": 1360
+    },
+    {
+      "epoch": 13.035,
+      "grad_norm": 0.14159785211086273,
+      "learning_rate": 6.642105263157895e-06,
+      "loss": 0.0005,
+      "step": 1370
+    },
+    {
+      "epoch": 13.04,
+      "grad_norm": 0.05650542676448822,
+      "learning_rate": 6.536842105263158e-06,
+      "loss": 0.0011,
+      "step": 1380
+    },
+    {
+      "epoch": 13.045,
+      "grad_norm": 0.030941806733608246,
+      "learning_rate": 6.431578947368422e-06,
+      "loss": 0.0024,
+      "step": 1390
+    },
+    {
+      "epoch": 13.05,
+      "grad_norm": 0.022141387686133385,
+      "learning_rate": 6.326315789473685e-06,
+      "loss": 0.0035,
+      "step": 1400
+    },
+    {
+      "epoch": 14.005,
+      "grad_norm": 0.010789740830659866,
+      "learning_rate": 6.221052631578947e-06,
+      "loss": 0.0002,
+      "step": 1410
+    },
+    {
+      "epoch": 14.01,
+      "grad_norm": 0.008089865557849407,
+      "learning_rate": 6.1157894736842106e-06,
+      "loss": 0.0002,
+      "step": 1420
+    },
+    {
+      "epoch": 14.015,
+      "grad_norm": 0.009247499518096447,
+      "learning_rate": 6.010526315789475e-06,
+      "loss": 0.0004,
+      "step": 1430
+    },
+    {
+      "epoch": 14.02,
+      "grad_norm": 0.005500028375536203,
+      "learning_rate": 5.905263157894737e-06,
+      "loss": 0.0019,
+      "step": 1440
+    },
+    {
+      "epoch": 14.025,
+      "grad_norm": 0.04416996240615845,
+      "learning_rate": 5.8e-06,
+      "loss": 0.0013,
+      "step": 1450
+    },
+    {
+      "epoch": 14.03,
+      "grad_norm": 0.10680264979600906,
+      "learning_rate": 5.694736842105264e-06,
+      "loss": 0.0012,
+      "step": 1460
+    },
+    {
+      "epoch": 14.035,
+      "grad_norm": 0.008884921669960022,
+      "learning_rate": 5.589473684210527e-06,
+      "loss": 0.0002,
+      "step": 1470
+    },
+    {
+      "epoch": 14.04,
+      "grad_norm": 0.179422989487648,
+      "learning_rate": 5.484210526315789e-06,
+      "loss": 0.0009,
+      "step": 1480
+    },
+    {
+      "epoch": 14.045,
+      "grad_norm": 0.7773061990737915,
+      "learning_rate": 5.3789473684210535e-06,
+      "loss": 0.0003,
+      "step": 1490
+    },
+    {
+      "epoch": 14.05,
+      "grad_norm": 0.04718916490674019,
+      "learning_rate": 5.273684210526317e-06,
+      "loss": 0.0009,
+      "step": 1500
+    },
+    {
+      "epoch": 15.005,
+      "grad_norm": 0.0084745017811656,
+      "learning_rate": 5.168421052631579e-06,
+      "loss": 0.0014,
+      "step": 1510
+    },
+    {
+      "epoch": 15.01,
+      "grad_norm": 0.006006155628710985,
+      "learning_rate": 5.0631578947368424e-06,
+      "loss": 0.0008,
+      "step": 1520
+    },
+    {
+      "epoch": 15.015,
+      "grad_norm": 0.007198017556220293,
+      "learning_rate": 4.957894736842106e-06,
+      "loss": 0.0002,
+      "step": 1530
+    },
+    {
+      "epoch": 15.02,
+      "grad_norm": 0.004182496573776007,
+      "learning_rate": 4.852631578947369e-06,
+      "loss": 0.0003,
+      "step": 1540
+    },
+    {
+      "epoch": 15.025,
+      "grad_norm": 0.00469869002699852,
+      "learning_rate": 4.747368421052632e-06,
+      "loss": 0.0001,
+      "step": 1550
+    },
+    {
+      "epoch": 15.03,
+      "grad_norm": 0.005362135358154774,
+      "learning_rate": 4.642105263157895e-06,
+      "loss": 0.0002,
+      "step": 1560
+    },
+    {
+      "epoch": 15.035,
+      "grad_norm": 0.005833903793245554,
+      "learning_rate": 4.536842105263158e-06,
+      "loss": 0.0003,
+      "step": 1570
+    },
+    {
+      "epoch": 15.04,
+      "grad_norm": 0.006048844661563635,
+      "learning_rate": 4.431578947368421e-06,
+      "loss": 0.0002,
+      "step": 1580
+    },
+    {
+      "epoch": 15.045,
+      "grad_norm": 0.005061362404376268,
+      "learning_rate": 4.3263157894736845e-06,
+      "loss": 0.0001,
+      "step": 1590
+    },
+    {
+      "epoch": 15.05,
+      "grad_norm": 0.007132957689464092,
+      "learning_rate": 4.221052631578948e-06,
+      "loss": 0.0004,
+      "step": 1600
+    },
+    {
+      "epoch": 16.005,
+      "grad_norm": 0.004316328559070826,
+      "learning_rate": 4.115789473684211e-06,
+      "loss": 0.0001,
+      "step": 1610
+    },
+    {
+      "epoch": 16.01,
+      "grad_norm": 0.0065157352946698666,
+      "learning_rate": 4.010526315789474e-06,
+      "loss": 0.0001,
+      "step": 1620
+    },
+    {
+      "epoch": 16.015,
+      "grad_norm": 0.004985947627574205,
+      "learning_rate": 3.905263157894737e-06,
+      "loss": 0.0001,
+      "step": 1630
+    },
+    {
+      "epoch": 16.02,
+      "grad_norm": 0.0039834328927099705,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0003,
+      "step": 1640
+    },
+    {
+      "epoch": 16.025,
+      "grad_norm": 0.15245139598846436,
+      "learning_rate": 3.6947368421052637e-06,
+      "loss": 0.0001,
+      "step": 1650
+    },
+    {
+      "epoch": 16.03,
+      "grad_norm": 0.13511842489242554,
+      "learning_rate": 3.5894736842105266e-06,
+      "loss": 0.0003,
+      "step": 1660
+    },
+    {
+      "epoch": 16.035,
+      "grad_norm": 0.0028432030230760574,
+      "learning_rate": 3.48421052631579e-06,
+      "loss": 0.0001,
+      "step": 1670
+    },
+    {
+      "epoch": 16.04,
+      "grad_norm": 0.003842442063614726,
+      "learning_rate": 3.3789473684210527e-06,
+      "loss": 0.0003,
+      "step": 1680
+    },
+    {
+      "epoch": 16.045,
+      "grad_norm": 0.005007196217775345,
+      "learning_rate": 3.273684210526316e-06,
+      "loss": 0.0002,
+      "step": 1690
+    },
+    {
+      "epoch": 16.05,
+      "grad_norm": 0.003745683468878269,
+      "learning_rate": 3.168421052631579e-06,
+      "loss": 0.0003,
+      "step": 1700
+    },
+    {
+      "epoch": 17.005,
+      "grad_norm": 0.0036488028708845377,
+      "learning_rate": 3.0631578947368425e-06,
+      "loss": 0.0002,
+      "step": 1710
+    },
+    {
+      "epoch": 17.01,
+      "grad_norm": 0.0031844789627939463,
+      "learning_rate": 2.957894736842106e-06,
+      "loss": 0.0001,
+      "step": 1720
+    },
+    {
+      "epoch": 17.015,
+      "grad_norm": 0.008146918378770351,
+      "learning_rate": 2.8526315789473687e-06,
+      "loss": 0.0002,
+      "step": 1730
+    },
+    {
+      "epoch": 17.02,
+      "grad_norm": 0.0034727228339761496,
+      "learning_rate": 2.747368421052632e-06,
+      "loss": 0.0001,
+      "step": 1740
+    },
+    {
+      "epoch": 17.025,
+      "grad_norm": 0.00454725231975317,
+      "learning_rate": 2.6421052631578948e-06,
+      "loss": 0.0001,
+      "step": 1750
+    },
+    {
+      "epoch": 17.03,
+      "grad_norm": 0.005313561297953129,
+      "learning_rate": 2.536842105263158e-06,
+      "loss": 0.0002,
+      "step": 1760
+    },
+    {
+      "epoch": 17.035,
+      "grad_norm": 0.1343342512845993,
+      "learning_rate": 2.4315789473684213e-06,
+      "loss": 0.0002,
+      "step": 1770
+    },
+    {
+      "epoch": 17.04,
+      "grad_norm": 0.004856111016124487,
+      "learning_rate": 2.326315789473684e-06,
+      "loss": 0.0001,
+      "step": 1780
+    },
+    {
+      "epoch": 17.045,
+      "grad_norm": 0.10679910331964493,
+      "learning_rate": 2.221052631578948e-06,
+      "loss": 0.0002,
+      "step": 1790
+    },
+    {
+      "epoch": 17.05,
+      "grad_norm": 0.003918065223842859,
+      "learning_rate": 2.1157894736842107e-06,
+      "loss": 0.0001,
+      "step": 1800
+    },
+    {
+      "epoch": 18.005,
+      "grad_norm": 0.0038473308086395264,
+      "learning_rate": 2.010526315789474e-06,
+      "loss": 0.0001,
+      "step": 1810
+    },
+    {
+      "epoch": 18.01,
+      "grad_norm": 0.0027081076987087727,
+      "learning_rate": 1.905263157894737e-06,
+      "loss": 0.0002,
+      "step": 1820
+    },
+    {
+      "epoch": 18.015,
+      "grad_norm": 0.003243462648242712,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.0002,
+      "step": 1830
+    },
+    {
+      "epoch": 18.02,
+      "grad_norm": 0.004891443997621536,
+      "learning_rate": 1.6947368421052632e-06,
+      "loss": 0.0001,
+      "step": 1840
+    },
+    {
+      "epoch": 18.025,
+      "grad_norm": 0.00323393102735281,
+      "learning_rate": 1.5894736842105265e-06,
+      "loss": 0.0001,
+      "step": 1850
+    },
+    {
+      "epoch": 18.03,
+      "grad_norm": 0.00286379037424922,
+      "learning_rate": 1.4842105263157897e-06,
+      "loss": 0.0001,
+      "step": 1860
+    },
+    {
+      "epoch": 18.035,
+      "grad_norm": 0.0032987131271511316,
+      "learning_rate": 1.3789473684210528e-06,
+      "loss": 0.0001,
+      "step": 1870
+    },
+    {
+      "epoch": 18.04,
+      "grad_norm": 0.003127966308966279,
+      "learning_rate": 1.2736842105263159e-06,
+      "loss": 0.0001,
+      "step": 1880
+    },
+    {
+      "epoch": 18.045,
+      "grad_norm": 0.0026523026172071695,
+      "learning_rate": 1.1684210526315791e-06,
+      "loss": 0.0002,
+      "step": 1890
+    },
+    {
+      "epoch": 18.05,
+      "grad_norm": 0.0035338886082172394,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 0.0002,
+      "step": 1900
+    },
+    {
+      "epoch": 19.005,
+      "grad_norm": 0.0032154133077710867,
+      "learning_rate": 9.578947368421053e-07,
+      "loss": 0.0001,
+      "step": 1910
+    },
+    {
+      "epoch": 19.01,
+      "grad_norm": 0.0040828268975019455,
+      "learning_rate": 8.526315789473685e-07,
+      "loss": 0.0001,
+      "step": 1920
+    },
+    {
+      "epoch": 19.015,
+      "grad_norm": 0.002462048316374421,
+      "learning_rate": 7.473684210526316e-07,
+      "loss": 0.0001,
+      "step": 1930
+    },
+    {
+      "epoch": 19.02,
+      "grad_norm": 0.00201555248349905,
+      "learning_rate": 6.421052631578948e-07,
+      "loss": 0.0003,
+      "step": 1940
+    },
+    {
+      "epoch": 19.025,
+      "grad_norm": 0.0026351658161729574,
+      "learning_rate": 5.368421052631579e-07,
+      "loss": 0.0001,
+      "step": 1950
+    },
+    {
+      "epoch": 19.03,
+      "grad_norm": 0.002890300936996937,
+      "learning_rate": 4.3157894736842105e-07,
+      "loss": 0.0001,
+      "step": 1960
+    },
+    {
+      "epoch": 19.035,
+      "grad_norm": 0.002067763591185212,
+      "learning_rate": 3.263157894736842e-07,
+      "loss": 0.0001,
+      "step": 1970
+    },
+    {
+      "epoch": 19.04,
+      "grad_norm": 0.1408688873052597,
+      "learning_rate": 2.2105263157894736e-07,
+      "loss": 0.0003,
+      "step": 1980
+    },
+    {
+      "epoch": 19.045,
+      "grad_norm": 0.002841346897184849,
+      "learning_rate": 1.1578947368421054e-07,
+      "loss": 0.0001,
+      "step": 1990
+    },
+    {
+      "epoch": 19.05,
+      "grad_norm": 0.0034785745665431023,
+      "learning_rate": 1.0526315789473684e-08,
+      "loss": 0.0001,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.010451846896026e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b144045336f4f3606add1e223999e524680be7894eda34a4b0257439b230feff
+size 5969