commit 3e3401c6eb92cb6975a7e9a28beb45ef1a986ffc
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Tue Apr 28 09:50:39 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: aasim-m/daft-qwen2.5-coder-3b-instruct-full
    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..d42d3ad
--- /dev/null
+++ b/README.md
@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 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. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the daft_functions_dedup_sharegpt 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 5.2.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..20e603a
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3081875480379392.0,
+    "train_loss": 0.06056562058377327,
+    "train_runtime": 29609.547,
+    "train_samples_per_second": 6.685,
+    "train_steps_per_second": 0.013
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..bdf7919
--- /dev/null
+++ b/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 %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..63534fe
--- /dev/null
+++ b/config.json
@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..47205fb
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.2.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..3252dad
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3a0782298f3bc5526de50d9ee1bba89a44248fe431ffc888ea86d6ed217618
+size 6171927112
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..34510ff
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..dc55654
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "<|im_start|>": "<|im_start|>",
+    "<|im_end|>": "<|im_end|>",
+    "<|object_ref_start|>": "<|object_ref_start|>",
+    "<|object_ref_end|>": "<|object_ref_end|>",
+    "<|box_start|>": "<|box_start|>",
+    "<|box_end|>": "<|box_end|>",
+    "<|quad_start|>": "<|quad_start|>",
+    "<|quad_end|>": "<|quad_end|>",
+    "<|vision_start|>": "<|vision_start|>",
+    "<|vision_end|>": "<|vision_end|>",
+    "<|vision_pad|>": "<|vision_pad|>",
+    "<|image_pad|>": "<|image_pad|>",
+    "<|video_pad|>": "<|video_pad|>"
+  },
+  "is_local": false,
+  "model_max_length": 32768,
+  "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..20e603a
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3081875480379392.0,
+    "train_loss": 0.06056562058377327,
+    "train_runtime": 29609.547,
+    "train_samples_per_second": 6.685,
+    "train_steps_per_second": 0.013
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..a1601f9
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,27 @@
+{"current_steps": 130, "total_steps": 387, "loss": 0.11126101016998291, "lr": 8.438497294267117e-06, "epoch": 1.0077594568380213, "percentage": 33.59, "elapsed_time": "0:18:26", "remaining_time": "0:36:26"}
+{"current_steps": 140, "total_steps": 387, "loss": 0.10776399374008179, "lr": 8.097241806078616e-06, "epoch": 1.0853540252182348, "percentage": 36.18, "elapsed_time": "0:36:50", "remaining_time": "1:04:59"}
+{"current_steps": 150, "total_steps": 387, "loss": 0.10431833267211914, "lr": 7.730761885468486e-06, "epoch": 1.162948593598448, "percentage": 38.76, "elapsed_time": "0:55:23", "remaining_time": "1:27:31"}
+{"current_steps": 160, "total_steps": 387, "loss": 0.10304663181304932, "lr": 7.342042203498952e-06, "epoch": 1.2405431619786615, "percentage": 41.34, "elapsed_time": "1:14:02", "remaining_time": "1:45:03"}
+{"current_steps": 170, "total_steps": 387, "loss": 0.09784629344940185, "lr": 6.934248555404197e-06, "epoch": 1.3181377303588748, "percentage": 43.93, "elapsed_time": "1:32:53", "remaining_time": "1:58:33"}
+{"current_steps": 180, "total_steps": 387, "loss": 0.09537227749824524, "lr": 6.510702077847864e-06, "epoch": 1.3957322987390883, "percentage": 46.51, "elapsed_time": "1:51:08", "remaining_time": "2:07:48"}
+{"current_steps": 190, "total_steps": 387, "loss": 0.09520423412322998, "lr": 6.074852201055121e-06, "epoch": 1.4733268671193016, "percentage": 49.1, "elapsed_time": "2:09:17", "remaining_time": "2:14:03"}
+{"current_steps": 200, "total_steps": 387, "loss": 0.09088362455368042, "lr": 5.630248556101448e-06, "epoch": 1.5509214354995149, "percentage": 51.68, "elapsed_time": "2:27:46", "remaining_time": "2:18:10"}
+{"current_steps": 210, "total_steps": 387, "loss": 0.0899280071258545, "lr": 5.180512066149682e-06, "epoch": 1.6285160038797284, "percentage": 54.26, "elapsed_time": "2:46:36", "remaining_time": "2:20:25"}
+{"current_steps": 220, "total_steps": 387, "loss": 0.0881616234779358, "lr": 4.729305457072913e-06, "epoch": 1.706110572259942, "percentage": 56.85, "elapsed_time": "3:04:52", "remaining_time": "2:20:20"}
+{"current_steps": 230, "total_steps": 387, "loss": 0.08638249635696411, "lr": 4.280303427629404e-06, "epoch": 1.7837051406401552, "percentage": 59.43, "elapsed_time": "3:23:30", "remaining_time": "2:18:54"}
+{"current_steps": 240, "total_steps": 387, "loss": 0.08716154098510742, "lr": 3.8371627221284495e-06, "epoch": 1.8612997090203685, "percentage": 62.02, "elapsed_time": "3:41:53", "remaining_time": "2:15:54"}
+{"current_steps": 250, "total_steps": 387, "loss": 0.08580605983734131, "lr": 3.403492349320101e-06, "epoch": 1.938894277400582, "percentage": 64.6, "elapsed_time": "4:00:25", "remaining_time": "2:11:44"}
+{"current_steps": 260, "total_steps": 387, "loss": 0.08316840529441834, "lr": 2.982824190050958e-06, "epoch": 2.0155189136760425, "percentage": 67.18, "elapsed_time": "4:18:27", "remaining_time": "2:06:14"}
+{"current_steps": 270, "total_steps": 387, "loss": 0.08091338872909545, "lr": 2.5785842330619038e-06, "epoch": 2.093113482056256, "percentage": 69.77, "elapsed_time": "4:37:00", "remaining_time": "2:00:02"}
+{"current_steps": 280, "total_steps": 387, "loss": 0.08085420131683349, "lr": 2.1940646731880887e-06, "epoch": 2.1707080504364695, "percentage": 72.35, "elapsed_time": "4:55:04", "remaining_time": "1:52:45"}
+{"current_steps": 290, "total_steps": 387, "loss": 0.08156624436378479, "lr": 1.8323970991978823e-06, "epoch": 2.248302618816683, "percentage": 74.94, "elapsed_time": "5:14:09", "remaining_time": "1:45:04"}
+{"current_steps": 300, "total_steps": 387, "loss": 0.0808843195438385, "lr": 1.4965269896332884e-06, "epoch": 2.325897187196896, "percentage": 77.52, "elapsed_time": "5:32:45", "remaining_time": "1:36:30"}
+{"current_steps": 310, "total_steps": 387, "loss": 0.07979943156242371, "lr": 1.1891897243618184e-06, "epoch": 2.4034917555771096, "percentage": 80.1, "elapsed_time": "5:50:50", "remaining_time": "1:27:08"}
+{"current_steps": 320, "total_steps": 387, "loss": 0.08049517869949341, "lr": 9.128883072055411e-07, "epoch": 2.481086323957323, "percentage": 82.69, "elapsed_time": "6:09:14", "remaining_time": "1:17:18"}
+{"current_steps": 330, "total_steps": 387, "loss": 0.08011389374732972, "lr": 6.698729810778065e-07, "epoch": 2.558680892337536, "percentage": 85.27, "elapsed_time": "6:27:50", "remaining_time": "1:06:59"}
+{"current_steps": 340, "total_steps": 387, "loss": 0.08163015246391296, "lr": 4.6212290164521554e-07, "epoch": 2.6362754607177497, "percentage": 87.86, "elapsed_time": "6:46:09", "remaining_time": "0:56:08"}
+{"current_steps": 350, "total_steps": 387, "loss": 0.08051948547363282, "lr": 2.9133001876746004e-07, "epoch": 2.713870029097963, "percentage": 90.44, "elapsed_time": "7:04:35", "remaining_time": "0:44:53"}
+{"current_steps": 360, "total_steps": 387, "loss": 0.07719261646270752, "lr": 1.5888529698718347e-07, "epoch": 2.7914645974781767, "percentage": 93.02, "elapsed_time": "7:23:07", "remaining_time": "0:33:14"}
+{"current_steps": 370, "total_steps": 387, "loss": 0.08128957152366638, "lr": 6.58673872923693e-08, "epoch": 2.86905916585839, "percentage": 95.61, "elapsed_time": "7:42:08", "remaining_time": "0:21:14"}
+{"current_steps": 380, "total_steps": 387, "loss": 0.07743191719055176, "lr": 1.3033842410251074e-08, "epoch": 2.946653734238603, "percentage": 98.19, "elapsed_time": "8:00:28", "remaining_time": "0:08:51"}
+{"current_steps": 387, "total_steps": 387, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "8:13:28", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..80c17ff
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,309 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 387,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07759456838021339,
+      "grad_norm": 1.9683642394428182,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 0.7343237400054932,
+      "step": 10
+    },
+    {
+      "epoch": 0.15518913676042678,
+      "grad_norm": 1.4175428237350762,
+      "learning_rate": 4.871794871794872e-06,
+      "loss": 0.5461452007293701,
+      "step": 20
+    },
+    {
+      "epoch": 0.23278370514064015,
+      "grad_norm": 0.5442834252561063,
+      "learning_rate": 7.435897435897437e-06,
+      "loss": 0.3490773677825928,
+      "step": 30
+    },
+    {
+      "epoch": 0.31037827352085356,
+      "grad_norm": 0.32322946422972365,
+      "learning_rate": 1e-05,
+      "loss": 0.2592954635620117,
+      "step": 40
+    },
+    {
+      "epoch": 0.3879728419010669,
+      "grad_norm": 0.24901563193155196,
+      "learning_rate": 9.979639600327522e-06,
+      "loss": 0.2136533737182617,
+      "step": 50
+    },
+    {
+      "epoch": 0.4655674102812803,
+      "grad_norm": 0.2047675084448879,
+      "learning_rate": 9.918724219660013e-06,
+      "loss": 0.18301695585250854,
+      "step": 60
+    },
+    {
+      "epoch": 0.5431619786614937,
+      "grad_norm": 0.1694310997257767,
+      "learning_rate": 9.817749962596115e-06,
+      "loss": 0.16246029138565063,
+      "step": 70
+    },
+    {
+      "epoch": 0.6207565470417071,
+      "grad_norm": 0.22587456656054467,
+      "learning_rate": 9.677539179628005e-06,
+      "loss": 0.14934264421463012,
+      "step": 80
+    },
+    {
+      "epoch": 0.6983511154219205,
+      "grad_norm": 0.22154973989105028,
+      "learning_rate": 9.499233769787534e-06,
+      "loss": 0.134801185131073,
+      "step": 90
+    },
+    {
+      "epoch": 0.7759456838021338,
+      "grad_norm": 0.2099862635469814,
+      "learning_rate": 9.284285880837947e-06,
+      "loss": 0.13017673492431642,
+      "step": 100
+    },
+    {
+      "epoch": 0.8535402521823472,
+      "grad_norm": 0.32230657820182124,
+      "learning_rate": 9.034446082750352e-06,
+      "loss": 0.12214579582214355,
+      "step": 110
+    },
+    {
+      "epoch": 0.9311348205625606,
+      "grad_norm": 0.324253054340729,
+      "learning_rate": 8.751749110782013e-06,
+      "loss": 0.12026152610778809,
+      "step": 120
+    },
+    {
+      "epoch": 1.0077594568380213,
+      "grad_norm": 0.20488241588612174,
+      "learning_rate": 8.438497294267117e-06,
+      "loss": 0.11126101016998291,
+      "step": 130
+    },
+    {
+      "epoch": 1.0853540252182348,
+      "grad_norm": 0.20661218086124847,
+      "learning_rate": 8.097241806078616e-06,
+      "loss": 0.10776399374008179,
+      "step": 140
+    },
+    {
+      "epoch": 1.162948593598448,
+      "grad_norm": 0.25468202960165104,
+      "learning_rate": 7.730761885468486e-06,
+      "loss": 0.10431833267211914,
+      "step": 150
+    },
+    {
+      "epoch": 1.2405431619786615,
+      "grad_norm": 0.17930064486716413,
+      "learning_rate": 7.342042203498952e-06,
+      "loss": 0.10304663181304932,
+      "step": 160
+    },
+    {
+      "epoch": 1.3181377303588748,
+      "grad_norm": 0.20225538073749422,
+      "learning_rate": 6.934248555404197e-06,
+      "loss": 0.09784629344940185,
+      "step": 170
+    },
+    {
+      "epoch": 1.3957322987390883,
+      "grad_norm": 0.2256721972453044,
+      "learning_rate": 6.510702077847864e-06,
+      "loss": 0.09537227749824524,
+      "step": 180
+    },
+    {
+      "epoch": 1.4733268671193016,
+      "grad_norm": 0.21487787771920072,
+      "learning_rate": 6.074852201055121e-06,
+      "loss": 0.09520423412322998,
+      "step": 190
+    },
+    {
+      "epoch": 1.5509214354995149,
+      "grad_norm": 0.17540761321861204,
+      "learning_rate": 5.630248556101448e-06,
+      "loss": 0.09088362455368042,
+      "step": 200
+    },
+    {
+      "epoch": 1.6285160038797284,
+      "grad_norm": 0.21743503130668765,
+      "learning_rate": 5.180512066149682e-06,
+      "loss": 0.0899280071258545,
+      "step": 210
+    },
+    {
+      "epoch": 1.706110572259942,
+      "grad_norm": 0.20331687416060285,
+      "learning_rate": 4.729305457072913e-06,
+      "loss": 0.0881616234779358,
+      "step": 220
+    },
+    {
+      "epoch": 1.7837051406401552,
+      "grad_norm": 0.15781467110120098,
+      "learning_rate": 4.280303427629404e-06,
+      "loss": 0.08638249635696411,
+      "step": 230
+    },
+    {
+      "epoch": 1.8612997090203685,
+      "grad_norm": 0.1623620489054104,
+      "learning_rate": 3.8371627221284495e-06,
+      "loss": 0.08716154098510742,
+      "step": 240
+    },
+    {
+      "epoch": 1.938894277400582,
+      "grad_norm": 0.15611783173066054,
+      "learning_rate": 3.403492349320101e-06,
+      "loss": 0.08580605983734131,
+      "step": 250
+    },
+    {
+      "epoch": 2.0155189136760425,
+      "grad_norm": 0.15287072067575233,
+      "learning_rate": 2.982824190050958e-06,
+      "loss": 0.08316840529441834,
+      "step": 260
+    },
+    {
+      "epoch": 2.093113482056256,
+      "grad_norm": 0.1853136112632167,
+      "learning_rate": 2.5785842330619038e-06,
+      "loss": 0.08091338872909545,
+      "step": 270
+    },
+    {
+      "epoch": 2.1707080504364695,
+      "grad_norm": 0.14114872525549504,
+      "learning_rate": 2.1940646731880887e-06,
+      "loss": 0.08085420131683349,
+      "step": 280
+    },
+    {
+      "epoch": 2.248302618816683,
+      "grad_norm": 0.13643528182686213,
+      "learning_rate": 1.8323970991978823e-06,
+      "loss": 0.08156624436378479,
+      "step": 290
+    },
+    {
+      "epoch": 2.325897187196896,
+      "grad_norm": 0.14573681730374075,
+      "learning_rate": 1.4965269896332884e-06,
+      "loss": 0.0808843195438385,
+      "step": 300
+    },
+    {
+      "epoch": 2.4034917555771096,
+      "grad_norm": 0.1466398992341211,
+      "learning_rate": 1.1891897243618184e-06,
+      "loss": 0.07979943156242371,
+      "step": 310
+    },
+    {
+      "epoch": 2.481086323957323,
+      "grad_norm": 0.12798260710398743,
+      "learning_rate": 9.128883072055411e-07,
+      "loss": 0.08049517869949341,
+      "step": 320
+    },
+    {
+      "epoch": 2.558680892337536,
+      "grad_norm": 0.13826353734235647,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.08011389374732972,
+      "step": 330
+    },
+    {
+      "epoch": 2.6362754607177497,
+      "grad_norm": 0.1305401343538733,
+      "learning_rate": 4.6212290164521554e-07,
+      "loss": 0.08163015246391296,
+      "step": 340
+    },
+    {
+      "epoch": 2.713870029097963,
+      "grad_norm": 0.12804004522045906,
+      "learning_rate": 2.9133001876746004e-07,
+      "loss": 0.08051948547363282,
+      "step": 350
+    },
+    {
+      "epoch": 2.7914645974781767,
+      "grad_norm": 0.12808224007612634,
+      "learning_rate": 1.5888529698718347e-07,
+      "loss": 0.07719261646270752,
+      "step": 360
+    },
+    {
+      "epoch": 2.86905916585839,
+      "grad_norm": 0.12117673381149041,
+      "learning_rate": 6.58673872923693e-08,
+      "loss": 0.08128957152366638,
+      "step": 370
+    },
+    {
+      "epoch": 2.946653734238603,
+      "grad_norm": 0.124324493318766,
+      "learning_rate": 1.3033842410251074e-08,
+      "loss": 0.07743191719055176,
+      "step": 380
+    },
+    {
+      "epoch": 3.0,
+      "step": 387,
+      "total_flos": 3081875480379392.0,
+      "train_loss": 0.06056562058377327,
+      "train_runtime": 29609.547,
+      "train_samples_per_second": 6.685,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 387,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3081875480379392.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..5be1217
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183e7b3bdde253f2571677062e7c65704a64af443b29948fe6b9d366ccf011e3
+size 7377
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..490158f
Binary files /dev/null and b/training_loss.png differ