初始化项目，由ModelHub XC社区提供模型

Model: JunHowie/Qwen3-0.6B-Instruct-2512 Source: Original Platform
2026-05-19 20:03:56 +08:00
commit 30b62f6d26
15 changed files with 1371 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,53 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+vocab.json filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,48 @@
+---
+license: Apache License 2.0
+tags: []
+
+#model-type:
+##如 gpt、phi、llama、chatglm、baichuan 等
+#- gpt
+
+#domain:
+##如 nlp、cv、audio、multi-modal
+#- nlp
+
+#language:
+##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+#- cn 
+
+#metrics:
+##如 CIDEr、Blue、ROUGE 等
+#- CIDEr
+
+#tags:
+##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+#- pretrained
+
+#tools:
+##如 vllm、fastchat、llamacpp、AdaSeq 等
+#- vllm
+---
+### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
+#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+
+SDK下载
+```bash
+#安装ModelScope
+pip install modelscope
+```
+```python
+#SDK模型下载
+from modelscope import snapshot_download
+model_dir = snapshot_download('JunHowie/Qwen3-0.6B-Instruct-2512')
+```
+Git下载
+```
+#Git模型下载
+git clone https://www.modelscope.cn/JunHowie/Qwen3-0.6B-Instruct-2512.git
+```
+
+<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
--- a/args.json
+++ b/args.json
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510cff474ac939e45694d7e4bb2f354d928b3e5b36d9e3729aa9f3bc7169e7b7
+size 1192135096
--- a/special_tokens_map.json
+++ b/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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,409 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 1.32418597,
+  "best_model_checkpoint": "/mnt/workspace/output/Qwen3-0.6B-full-SFT-A10/v2-20251216-110947/checkpoint-1000",
+  "epoch": 0.20108586366378445,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00020108586366378444,
+      "grad_norm": 1.3245757996916807,
+      "learning_rate": 3.333333333333334e-08,
+      "loss": 1.9319875240325928,
+      "step": 1
+    },
+    {
+      "epoch": 0.004021717273275689,
+      "grad_norm": 1.1977762194852222,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.5824153297825863,
+      "step": 20
+    },
+    {
+      "epoch": 0.008043434546551377,
+      "grad_norm": 0.7774889250642103,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.5533018112182617,
+      "step": 40
+    },
+    {
+      "epoch": 0.012065151819827067,
+      "grad_norm": 0.48132649181807075,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.520798397064209,
+      "step": 60
+    },
+    {
+      "epoch": 0.016086869093102755,
+      "grad_norm": 0.5581916898540064,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.4769352912902831,
+      "step": 80
+    },
+    {
+      "epoch": 0.020108586366378443,
+      "grad_norm": 0.5203862639160307,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.4677474975585938,
+      "step": 100
+    },
+    {
+      "epoch": 0.024130303639654134,
+      "grad_norm": 0.5367365180854085,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3774413108825683,
+      "step": 120
+    },
+    {
+      "epoch": 0.028152020912929822,
+      "grad_norm": 0.5128695714566152,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 1.3422178268432616,
+      "step": 140
+    },
+    {
+      "epoch": 0.03217373818620551,
+      "grad_norm": 0.5206425075578179,
+      "learning_rate": 4.999946963641327e-06,
+      "loss": 1.3980652809143066,
+      "step": 160
+    },
+    {
+      "epoch": 0.0361954554594812,
+      "grad_norm": 0.5090299565342754,
+      "learning_rate": 4.9995226862735515e-06,
+      "loss": 1.406095600128174,
+      "step": 180
+    },
+    {
+      "epoch": 0.040217172732756885,
+      "grad_norm": 0.5379423514470855,
+      "learning_rate": 4.998674203544041e-06,
+      "loss": 1.3799993515014648,
+      "step": 200
+    },
+    {
+      "epoch": 0.04423889000603257,
+      "grad_norm": 0.4993307790129066,
+      "learning_rate": 4.997401659452658e-06,
+      "loss": 1.3666109085083007,
+      "step": 220
+    },
+    {
+      "epoch": 0.04826060727930827,
+      "grad_norm": 0.5213511221501015,
+      "learning_rate": 4.995705269968647e-06,
+      "loss": 1.3320393562316895,
+      "step": 240
+    },
+    {
+      "epoch": 0.052282324552583956,
+      "grad_norm": 0.500734977087879,
+      "learning_rate": 4.993585322993984e-06,
+      "loss": 1.3647167205810546,
+      "step": 260
+    },
+    {
+      "epoch": 0.056304041825859644,
+      "grad_norm": 0.5348054923133945,
+      "learning_rate": 4.991042178314507e-06,
+      "loss": 1.3998963356018066,
+      "step": 280
+    },
+    {
+      "epoch": 0.06032575909913533,
+      "grad_norm": 0.5375043268859722,
+      "learning_rate": 4.988076267538868e-06,
+      "loss": 1.3735774040222168,
+      "step": 300
+    },
+    {
+      "epoch": 0.06434747637241102,
+      "grad_norm": 0.5472187756248204,
+      "learning_rate": 4.98468809402527e-06,
+      "loss": 1.3957695007324218,
+      "step": 320
+    },
+    {
+      "epoch": 0.06836919364568671,
+      "grad_norm": 0.5401600886886373,
+      "learning_rate": 4.980878232796049e-06,
+      "loss": 1.3429646492004395,
+      "step": 340
+    },
+    {
+      "epoch": 0.0723909109189624,
+      "grad_norm": 0.5053769482990914,
+      "learning_rate": 4.976647330440079e-06,
+      "loss": 1.4069278717041016,
+      "step": 360
+    },
+    {
+      "epoch": 0.07641262819223808,
+      "grad_norm": 0.46054241564759896,
+      "learning_rate": 4.971996105003039e-06,
+      "loss": 1.3300314903259278,
+      "step": 380
+    },
+    {
+      "epoch": 0.08043434546551377,
+      "grad_norm": 0.5822740132757419,
+      "learning_rate": 4.96692534586555e-06,
+      "loss": 1.33113374710083,
+      "step": 400
+    },
+    {
+      "epoch": 0.08445606273878946,
+      "grad_norm": 0.4900433357652362,
+      "learning_rate": 4.961435913609204e-06,
+      "loss": 1.3425264358520508,
+      "step": 420
+    },
+    {
+      "epoch": 0.08847778001206515,
+      "grad_norm": 0.5066732407209128,
+      "learning_rate": 4.955528739870512e-06,
+      "loss": 1.384002113342285,
+      "step": 440
+    },
+    {
+      "epoch": 0.09249949728534083,
+      "grad_norm": 0.4788481857754503,
+      "learning_rate": 4.949204827182795e-06,
+      "loss": 1.439993667602539,
+      "step": 460
+    },
+    {
+      "epoch": 0.09652121455861654,
+      "grad_norm": 0.5353628309273895,
+      "learning_rate": 4.9424652488060305e-06,
+      "loss": 1.3668890953063966,
+      "step": 480
+    },
+    {
+      "epoch": 0.10054293183189222,
+      "grad_norm": 0.4934064878902107,
+      "learning_rate": 4.935311148544714e-06,
+      "loss": 1.3029553413391113,
+      "step": 500
+    },
+    {
+      "epoch": 0.10054293183189222,
+      "eval_loss": 1.3484046459197998,
+      "eval_runtime": 102.7994,
+      "eval_samples_per_second": 7.889,
+      "eval_steps_per_second": 7.889,
+      "eval_token_acc": 0.6690674926114705,
+      "step": 500
+    },
+    {
+      "epoch": 0.10456464910516791,
+      "grad_norm": 0.5120477751801278,
+      "learning_rate": 4.927743740553735e-06,
+      "loss": 1.4136478424072265,
+      "step": 520
+    },
+    {
+      "epoch": 0.1085863663784436,
+      "grad_norm": 0.5396355455455603,
+      "learning_rate": 4.919764309132317e-06,
+      "loss": 1.3338500022888184,
+      "step": 540
+    },
+    {
+      "epoch": 0.11260808365171929,
+      "grad_norm": 0.5183609857485824,
+      "learning_rate": 4.911374208506051e-06,
+      "loss": 1.368019962310791,
+      "step": 560
+    },
+    {
+      "epoch": 0.11662980092499498,
+      "grad_norm": 0.5367378807414639,
+      "learning_rate": 4.90257486259707e-06,
+      "loss": 1.3670174598693847,
+      "step": 580
+    },
+    {
+      "epoch": 0.12065151819827066,
+      "grad_norm": 0.5439177927602133,
+      "learning_rate": 4.893367764782384e-06,
+      "loss": 1.3594793319702148,
+      "step": 600
+    },
+    {
+      "epoch": 0.12467323547154635,
+      "grad_norm": 0.531786110904097,
+      "learning_rate": 4.883754477640432e-06,
+      "loss": 1.3755881309509277,
+      "step": 620
+    },
+    {
+      "epoch": 0.12869495274482204,
+      "grad_norm": 0.5686138829284232,
+      "learning_rate": 4.873736632685891e-06,
+      "loss": 1.338373851776123,
+      "step": 640
+    },
+    {
+      "epoch": 0.13271667001809773,
+      "grad_norm": 0.5291643495623265,
+      "learning_rate": 4.863315930092785e-06,
+      "loss": 1.3327385902404785,
+      "step": 660
+    },
+    {
+      "epoch": 0.13673838729137341,
+      "grad_norm": 0.5130002311117202,
+      "learning_rate": 4.852494138405942e-06,
+      "loss": 1.3230693817138672,
+      "step": 680
+    },
+    {
+      "epoch": 0.1407601045646491,
+      "grad_norm": 0.5329034424877147,
+      "learning_rate": 4.841273094240837e-06,
+      "loss": 1.3934517860412599,
+      "step": 700
+    },
+    {
+      "epoch": 0.1447818218379248,
+      "grad_norm": 0.5221456215851134,
+      "learning_rate": 4.829654701971906e-06,
+      "loss": 1.2989065170288085,
+      "step": 720
+    },
+    {
+      "epoch": 0.14880353911120048,
+      "grad_norm": 0.49579046263633203,
+      "learning_rate": 4.817640933409337e-06,
+      "loss": 1.3047898292541504,
+      "step": 740
+    },
+    {
+      "epoch": 0.15282525638447617,
+      "grad_norm": 0.46687423703913566,
+      "learning_rate": 4.805233827464422e-06,
+      "loss": 1.3056100845336913,
+      "step": 760
+    },
+    {
+      "epoch": 0.15684697365775185,
+      "grad_norm": 0.5358233951172744,
+      "learning_rate": 4.792435489803536e-06,
+      "loss": 1.3041315078735352,
+      "step": 780
+    },
+    {
+      "epoch": 0.16086869093102754,
+      "grad_norm": 0.5012904638141517,
+      "learning_rate": 4.779248092490763e-06,
+      "loss": 1.3688041687011718,
+      "step": 800
+    },
+    {
+      "epoch": 0.16489040820430323,
+      "grad_norm": 0.5109005357497123,
+      "learning_rate": 4.7656738736192695e-06,
+      "loss": 1.321615982055664,
+      "step": 820
+    },
+    {
+      "epoch": 0.16891212547757892,
+      "grad_norm": 0.5317466980441882,
+      "learning_rate": 4.751715136931473e-06,
+      "loss": 1.3299549102783204,
+      "step": 840
+    },
+    {
+      "epoch": 0.1729338427508546,
+      "grad_norm": 0.5122100757056366,
+      "learning_rate": 4.737374251428051e-06,
+      "loss": 1.346351718902588,
+      "step": 860
+    },
+    {
+      "epoch": 0.1769555600241303,
+      "grad_norm": 0.5032167561577816,
+      "learning_rate": 4.722653650965899e-06,
+      "loss": 1.3551355361938477,
+      "step": 880
+    },
+    {
+      "epoch": 0.18097727729740598,
+      "grad_norm": 0.49968462554008924,
+      "learning_rate": 4.707555833845064e-06,
+      "loss": 1.3179678916931152,
+      "step": 900
+    },
+    {
+      "epoch": 0.18499899457068167,
+      "grad_norm": 0.5114844340219878,
+      "learning_rate": 4.692083362384747e-06,
+      "loss": 1.3317890167236328,
+      "step": 920
+    },
+    {
+      "epoch": 0.18902071184395736,
+      "grad_norm": 0.4981790467057629,
+      "learning_rate": 4.6762388624884415e-06,
+      "loss": 1.3447076797485351,
+      "step": 940
+    },
+    {
+      "epoch": 0.19304242911723307,
+      "grad_norm": 0.5119106503439425,
+      "learning_rate": 4.660025023198278e-06,
+      "loss": 1.4079626083374024,
+      "step": 960
+    },
+    {
+      "epoch": 0.19706414639050876,
+      "grad_norm": 0.5124577628196203,
+      "learning_rate": 4.643444596238656e-06,
+      "loss": 1.3586789131164552,
+      "step": 980
+    },
+    {
+      "epoch": 0.20108586366378445,
+      "grad_norm": 0.545904256919923,
+      "learning_rate": 4.626500395549233e-06,
+      "loss": 1.2963348388671876,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20108586366378445,
+      "eval_loss": 1.3241859674453735,
+      "eval_runtime": 102.6391,
+      "eval_samples_per_second": 7.901,
+      "eval_steps_per_second": 7.901,
+      "eval_token_acc": 0.6739275924101598,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 4973,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3194047954944.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb81b9a3a9c56356b974f157450d5de3cb62ed5bea1d07895aa397cb13765c1f
+size 9489
--- a/vocab.json
+++ b/vocab.json