commit 277bab5a50ff36b5441a45a7891b04b30e7f36d5
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Jul 18 20:49:10 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: miiikiik/Qwen3-8B-music-coa-sft
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..26e2a24
--- /dev/null
+++ b/README.md
@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen3-8B-music-coa-sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen3-8B-music-coa-sft
+
+This model is a fine-tuned version of [/mnt/tidal-alsh01/usr/zhongmeizhi/meiwangyi/models/Qwen3-8B-onto-fixed-traj](https://huggingface.co//mnt/tidal-alsh01/usr/zhongmeizhi/meiwangyi/models/Qwen3-8B-onto-fixed-traj) on the music_coa_sft dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.7.1+cu126
+- Datasets 3.4.1
+- Tokenizers 0.22.1
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..4130956
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 76776714797056.0,
+    "train_loss": 0.08690919660139775,
+    "train_runtime": 2313.134,
+    "train_samples_per_second": 9.525,
+    "train_steps_per_second": 0.149
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..699ff8d
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..746f56e
--- /dev/null
+++ b/config.json
@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..cf5bf49
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..bd5153f
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49085b381db57f95f5024195e46a62b6d94e7f61078ac10211fc017ba42f446f
+size 16381517208
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..c8c14f0
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
\ No newline at end of file
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..4130956
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 76776714797056.0,
+    "train_loss": 0.08690919660139775,
+    "train_runtime": 2313.134,
+    "train_samples_per_second": 9.525,
+    "train_steps_per_second": 0.149
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..8d8eead
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,35 @@
+{"current_steps": 10, "total_steps": 345, "loss": 0.6153196334838867, "lr": 2.571428571428571e-06, "epoch": 0.08714596949891068, "percentage": 2.9, "elapsed_time": "0:01:09", "remaining_time": "0:38:47"}
+{"current_steps": 20, "total_steps": 345, "loss": 0.28919568061828616, "lr": 5.428571428571429e-06, "epoch": 0.17429193899782136, "percentage": 5.8, "elapsed_time": "0:02:16", "remaining_time": "0:36:57"}
+{"current_steps": 30, "total_steps": 345, "loss": 0.17522474527359008, "lr": 8.285714285714287e-06, "epoch": 0.26143790849673204, "percentage": 8.7, "elapsed_time": "0:03:29", "remaining_time": "0:36:36"}
+{"current_steps": 40, "total_steps": 345, "loss": 0.14669673442840575, "lr": 9.995892506564461e-06, "epoch": 0.3485838779956427, "percentage": 11.59, "elapsed_time": "0:04:34", "remaining_time": "0:34:52"}
+{"current_steps": 50, "total_steps": 345, "loss": 0.12744725942611695, "lr": 9.949760673863846e-06, "epoch": 0.4357298474945534, "percentage": 14.49, "elapsed_time": "0:05:41", "remaining_time": "0:33:37"}
+{"current_steps": 60, "total_steps": 345, "loss": 0.11766195297241211, "lr": 9.85283759855301e-06, "epoch": 0.5228758169934641, "percentage": 17.39, "elapsed_time": "0:06:44", "remaining_time": "0:32:02"}
+{"current_steps": 70, "total_steps": 345, "loss": 0.10788841247558593, "lr": 9.706117842542517e-06, "epoch": 0.6100217864923747, "percentage": 20.29, "elapsed_time": "0:07:49", "remaining_time": "0:30:42"}
+{"current_steps": 80, "total_steps": 345, "loss": 0.09764145016670227, "lr": 9.511106949072588e-06, "epoch": 0.6971677559912854, "percentage": 23.19, "elapsed_time": "0:09:00", "remaining_time": "0:29:50"}
+{"current_steps": 90, "total_steps": 345, "loss": 0.10603783130645753, "lr": 9.26980599380213e-06, "epoch": 0.7843137254901961, "percentage": 26.09, "elapsed_time": "0:10:04", "remaining_time": "0:28:31"}
+{"current_steps": 100, "total_steps": 345, "loss": 0.09546730518341065, "lr": 8.984691051064576e-06, "epoch": 0.8714596949891068, "percentage": 28.99, "elapsed_time": "0:11:13", "remaining_time": "0:27:29"}
+{"current_steps": 110, "total_steps": 345, "loss": 0.092532217502594, "lr": 8.658687785994579e-06, "epoch": 0.9586056644880174, "percentage": 31.88, "elapsed_time": "0:12:12", "remaining_time": "0:26:05"}
+{"current_steps": 120, "total_steps": 345, "loss": 0.08056190013885497, "lr": 8.29514143324466e-06, "epoch": 1.0435729847494553, "percentage": 34.78, "elapsed_time": "0:13:14", "remaining_time": "0:24:49"}
+{"current_steps": 130, "total_steps": 345, "loss": 0.07299971580505371, "lr": 7.89778247035085e-06, "epoch": 1.130718954248366, "percentage": 37.68, "elapsed_time": "0:14:16", "remaining_time": "0:23:37"}
+{"current_steps": 140, "total_steps": 345, "loss": 0.07079986333847046, "lr": 7.470688337985029e-06, "epoch": 1.2178649237472767, "percentage": 40.58, "elapsed_time": "0:15:20", "remaining_time": "0:22:27"}
+{"current_steps": 150, "total_steps": 345, "loss": 0.06660881042480468, "lr": 7.018241599895974e-06, "epoch": 1.3050108932461875, "percentage": 43.48, "elapsed_time": "0:16:26", "remaining_time": "0:21:22"}
+{"current_steps": 160, "total_steps": 345, "loss": 0.0653923749923706, "lr": 6.545084971874738e-06, "epoch": 1.392156862745098, "percentage": 46.38, "elapsed_time": "0:17:31", "remaining_time": "0:20:16"}
+{"current_steps": 170, "total_steps": 345, "loss": 0.06376279592514038, "lr": 6.056073681208038e-06, "epoch": 1.4793028322440087, "percentage": 49.28, "elapsed_time": "0:18:36", "remaining_time": "0:19:09"}
+{"current_steps": 180, "total_steps": 345, "loss": 0.06115278005599976, "lr": 5.556225645476119e-06, "epoch": 1.5664488017429194, "percentage": 52.17, "elapsed_time": "0:19:45", "remaining_time": "0:18:07"}
+{"current_steps": 190, "total_steps": 345, "loss": 0.05721602439880371, "lr": 5.050669981928056e-06, "epoch": 1.65359477124183, "percentage": 55.07, "elapsed_time": "0:20:57", "remaining_time": "0:17:05"}
+{"current_steps": 200, "total_steps": 345, "loss": 0.05891573429107666, "lr": 4.544594375797969e-06, "epoch": 1.7407407407407407, "percentage": 57.97, "elapsed_time": "0:22:06", "remaining_time": "0:16:01"}
+{"current_steps": 210, "total_steps": 345, "loss": 0.053774547576904294, "lr": 4.043191847634469e-06, "epoch": 1.8278867102396514, "percentage": 60.87, "elapsed_time": "0:23:14", "remaining_time": "0:14:56"}
+{"current_steps": 220, "total_steps": 345, "loss": 0.05282905101776123, "lr": 3.55160746588254e-06, "epoch": 1.915032679738562, "percentage": 63.77, "elapsed_time": "0:24:16", "remaining_time": "0:13:47"}
+{"current_steps": 230, "total_steps": 345, "loss": 0.04842503666877747, "lr": 3.0748855515189104e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:25:21", "remaining_time": "0:12:40"}
+{"current_steps": 240, "total_steps": 345, "loss": 0.030383211374282838, "lr": 2.617917916492776e-06, "epoch": 2.0871459694989105, "percentage": 69.57, "elapsed_time": "0:26:29", "remaining_time": "0:11:35"}
+{"current_steps": 250, "total_steps": 345, "loss": 0.027488625049591063, "lr": 2.185393667115513e-06, "epoch": 2.1742919389978215, "percentage": 72.46, "elapsed_time": "0:27:37", "remaining_time": "0:10:30"}
+{"current_steps": 260, "total_steps": 345, "loss": 0.02891799509525299, "lr": 1.7817510874845585e-06, "epoch": 2.261437908496732, "percentage": 75.36, "elapsed_time": "0:28:38", "remaining_time": "0:09:21"}
+{"current_steps": 270, "total_steps": 345, "loss": 0.025755631923675536, "lr": 1.411132096682606e-06, "epoch": 2.348583877995643, "percentage": 78.26, "elapsed_time": "0:29:39", "remaining_time": "0:08:14"}
+{"current_steps": 280, "total_steps": 345, "loss": 0.02339869737625122, "lr": 1.0773397470829145e-06, "epoch": 2.4357298474945535, "percentage": 81.16, "elapsed_time": "0:30:50", "remaining_time": "0:07:09"}
+{"current_steps": 290, "total_steps": 345, "loss": 0.02193155437707901, "lr": 7.837991998855899e-07, "epoch": 2.522875816993464, "percentage": 84.06, "elapsed_time": "0:31:55", "remaining_time": "0:06:03"}
+{"current_steps": 300, "total_steps": 345, "loss": 0.022859147191047667, "lr": 5.335225783287051e-07, "epoch": 2.610021786492375, "percentage": 86.96, "elapsed_time": "0:32:56", "remaining_time": "0:04:56"}
+{"current_steps": 310, "total_steps": 345, "loss": 0.022240425646305084, "lr": 3.290780592278148e-07, "epoch": 2.6971677559912854, "percentage": 89.86, "elapsed_time": "0:34:06", "remaining_time": "0:03:51"}
+{"current_steps": 320, "total_steps": 345, "loss": 0.021587590873241424, "lr": 1.725635200065323e-07, "epoch": 2.784313725490196, "percentage": 92.75, "elapsed_time": "0:35:07", "remaining_time": "0:02:44"}
+{"current_steps": 330, "total_steps": 345, "loss": 0.020273779332637788, "lr": 6.558501163527964e-08, "epoch": 2.871459694989107, "percentage": 95.65, "elapsed_time": "0:36:20", "remaining_time": "0:01:39"}
+{"current_steps": 340, "total_steps": 345, "loss": 0.019534435868263245, "lr": 9.240278374995637e-09, "epoch": 2.9586056644880174, "percentage": 98.55, "elapsed_time": "0:37:25", "remaining_time": "0:00:33"}
+{"current_steps": 345, "total_steps": 345, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:38:33", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..481a35d
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,281 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08714596949891068,
+      "grad_norm": 5.177986166517991,
+      "learning_rate": 2.571428571428571e-06,
+      "loss": 0.6153196334838867,
+      "step": 10
+    },
+    {
+      "epoch": 0.17429193899782136,
+      "grad_norm": 1.44175757217302,
+      "learning_rate": 5.428571428571429e-06,
+      "loss": 0.28919568061828616,
+      "step": 20
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.9165793261415883,
+      "learning_rate": 8.285714285714287e-06,
+      "loss": 0.17522474527359008,
+      "step": 30
+    },
+    {
+      "epoch": 0.3485838779956427,
+      "grad_norm": 0.6521905966085462,
+      "learning_rate": 9.995892506564461e-06,
+      "loss": 0.14669673442840575,
+      "step": 40
+    },
+    {
+      "epoch": 0.4357298474945534,
+      "grad_norm": 0.607127669832236,
+      "learning_rate": 9.949760673863846e-06,
+      "loss": 0.12744725942611695,
+      "step": 50
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.5498782876340255,
+      "learning_rate": 9.85283759855301e-06,
+      "loss": 0.11766195297241211,
+      "step": 60
+    },
+    {
+      "epoch": 0.6100217864923747,
+      "grad_norm": 0.5918131618600547,
+      "learning_rate": 9.706117842542517e-06,
+      "loss": 0.10788841247558593,
+      "step": 70
+    },
+    {
+      "epoch": 0.6971677559912854,
+      "grad_norm": 0.4439997345152047,
+      "learning_rate": 9.511106949072588e-06,
+      "loss": 0.09764145016670227,
+      "step": 80
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.5075520825167553,
+      "learning_rate": 9.26980599380213e-06,
+      "loss": 0.10603783130645753,
+      "step": 90
+    },
+    {
+      "epoch": 0.8714596949891068,
+      "grad_norm": 0.5140097183992045,
+      "learning_rate": 8.984691051064576e-06,
+      "loss": 0.09546730518341065,
+      "step": 100
+    },
+    {
+      "epoch": 0.9586056644880174,
+      "grad_norm": 0.5703007918047962,
+      "learning_rate": 8.658687785994579e-06,
+      "loss": 0.092532217502594,
+      "step": 110
+    },
+    {
+      "epoch": 1.0435729847494553,
+      "grad_norm": 0.5044506688179623,
+      "learning_rate": 8.29514143324466e-06,
+      "loss": 0.08056190013885497,
+      "step": 120
+    },
+    {
+      "epoch": 1.130718954248366,
+      "grad_norm": 0.45897327652678604,
+      "learning_rate": 7.89778247035085e-06,
+      "loss": 0.07299971580505371,
+      "step": 130
+    },
+    {
+      "epoch": 1.2178649237472767,
+      "grad_norm": 0.512980363314234,
+      "learning_rate": 7.470688337985029e-06,
+      "loss": 0.07079986333847046,
+      "step": 140
+    },
+    {
+      "epoch": 1.3050108932461875,
+      "grad_norm": 0.47351565581785493,
+      "learning_rate": 7.018241599895974e-06,
+      "loss": 0.06660881042480468,
+      "step": 150
+    },
+    {
+      "epoch": 1.392156862745098,
+      "grad_norm": 0.5370628072208776,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.0653923749923706,
+      "step": 160
+    },
+    {
+      "epoch": 1.4793028322440087,
+      "grad_norm": 0.48059037186135045,
+      "learning_rate": 6.056073681208038e-06,
+      "loss": 0.06376279592514038,
+      "step": 170
+    },
+    {
+      "epoch": 1.5664488017429194,
+      "grad_norm": 0.5064023315317826,
+      "learning_rate": 5.556225645476119e-06,
+      "loss": 0.06115278005599976,
+      "step": 180
+    },
+    {
+      "epoch": 1.65359477124183,
+      "grad_norm": 0.42527473207127103,
+      "learning_rate": 5.050669981928056e-06,
+      "loss": 0.05721602439880371,
+      "step": 190
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.6697126311013827,
+      "learning_rate": 4.544594375797969e-06,
+      "loss": 0.05891573429107666,
+      "step": 200
+    },
+    {
+      "epoch": 1.8278867102396514,
+      "grad_norm": 0.5279032397256536,
+      "learning_rate": 4.043191847634469e-06,
+      "loss": 0.053774547576904294,
+      "step": 210
+    },
+    {
+      "epoch": 1.915032679738562,
+      "grad_norm": 0.5503203177829016,
+      "learning_rate": 3.55160746588254e-06,
+      "loss": 0.05282905101776123,
+      "step": 220
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5834909575577394,
+      "learning_rate": 3.0748855515189104e-06,
+      "loss": 0.04842503666877747,
+      "step": 230
+    },
+    {
+      "epoch": 2.0871459694989105,
+      "grad_norm": 0.45637637277474224,
+      "learning_rate": 2.617917916492776e-06,
+      "loss": 0.030383211374282838,
+      "step": 240
+    },
+    {
+      "epoch": 2.1742919389978215,
+      "grad_norm": 0.5460303567191565,
+      "learning_rate": 2.185393667115513e-06,
+      "loss": 0.027488625049591063,
+      "step": 250
+    },
+    {
+      "epoch": 2.261437908496732,
+      "grad_norm": 0.5299369784489509,
+      "learning_rate": 1.7817510874845585e-06,
+      "loss": 0.02891799509525299,
+      "step": 260
+    },
+    {
+      "epoch": 2.348583877995643,
+      "grad_norm": 0.47946594564717776,
+      "learning_rate": 1.411132096682606e-06,
+      "loss": 0.025755631923675536,
+      "step": 270
+    },
+    {
+      "epoch": 2.4357298474945535,
+      "grad_norm": 0.5587855844190783,
+      "learning_rate": 1.0773397470829145e-06,
+      "loss": 0.02339869737625122,
+      "step": 280
+    },
+    {
+      "epoch": 2.522875816993464,
+      "grad_norm": 0.5415169503522139,
+      "learning_rate": 7.837991998855899e-07,
+      "loss": 0.02193155437707901,
+      "step": 290
+    },
+    {
+      "epoch": 2.610021786492375,
+      "grad_norm": 0.5047370934641092,
+      "learning_rate": 5.335225783287051e-07,
+      "loss": 0.022859147191047667,
+      "step": 300
+    },
+    {
+      "epoch": 2.6971677559912854,
+      "grad_norm": 0.5339811061748208,
+      "learning_rate": 3.290780592278148e-07,
+      "loss": 0.022240425646305084,
+      "step": 310
+    },
+    {
+      "epoch": 2.784313725490196,
+      "grad_norm": 0.5269387231320517,
+      "learning_rate": 1.725635200065323e-07,
+      "loss": 0.021587590873241424,
+      "step": 320
+    },
+    {
+      "epoch": 2.871459694989107,
+      "grad_norm": 0.4475061358613248,
+      "learning_rate": 6.558501163527964e-08,
+      "loss": 0.020273779332637788,
+      "step": 330
+    },
+    {
+      "epoch": 2.9586056644880174,
+      "grad_norm": 0.38102973450948285,
+      "learning_rate": 9.240278374995637e-09,
+      "loss": 0.019534435868263245,
+      "step": 340
+    },
+    {
+      "epoch": 3.0,
+      "step": 345,
+      "total_flos": 76776714797056.0,
+      "train_loss": 0.08690919660139775,
+      "train_runtime": 2313.134,
+      "train_samples_per_second": 9.525,
+      "train_steps_per_second": 0.149
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 76776714797056.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..95ce810
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d769ee4536f0f8d9ef008b0a55032c2f50341f48b3ac9af78bde5aabaf1ce5
+size 7761
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..a613aae
Binary files /dev/null and b/training_loss.png differ