初始化项目，由ModelHub XC社区提供模型

Model: tengfeima-ai/Qwen2.5-0.5B-Math-SFT-1024 Source: Original Platform
2026-05-26 15:23:02 +08:00
commit 9a5698d47e
20 changed files with 152124 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft_1024_qwen25_0.5b
+  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_1024_qwen25_0.5b
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the deepmath_sft_1024 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6684
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- 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_ratio: 0.05
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4883        | 2.9481 | 200  | 0.6684          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.4.1+cu124
+- Datasets 4.0.0
+- Tokenizers 0.22.2
--- a/added_tokens.json
+++ b/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
+}
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6683521866798401,
+    "eval_runtime": 0.3349,
+    "eval_samples_per_second": 131.393,
+    "eval_steps_per_second": 17.917,
+    "total_flos": 5.359421722984448e+16,
+    "train_loss": 0.5856129340097016,
+    "train_runtime": 310.1981,
+    "train_samples_per_second": 41.751,
+    "train_steps_per_second": 0.658
+}
--- a/chat_template.jinja
+++ 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 %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/eval_results.json
+++ b/eval_results.json
@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6683521866798401,
+    "eval_runtime": 0.3349,
+    "eval_samples_per_second": 131.393,
+    "eval_steps_per_second": 17.917
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "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": "4.57.1"
+}
--- 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 sha256:4690b764ee0fab13600dae0d1f655ce806fb033c73b617f2412f7776829d3e67
+size 1260367448
--- 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
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,208 @@
+{
+  "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 5.359421722984448e+16,
+    "train_loss": 0.5856129340097016,
+    "train_runtime": 310.1981,
+    "train_samples_per_second": 41.751,
+    "train_steps_per_second": 0.658
+}
--- a/trainer_log.jsonl
+++ b/trainer_log.jsonl
@@ -0,0 +1,22 @@
+{"current_steps": 10, "total_steps": 204, "loss": 0.8932, "lr": 1.6363636363636366e-05, "epoch": 0.14814814814814814, "percentage": 4.9, "elapsed_time": "0:00:14", "remaining_time": "0:04:50"}
+{"current_steps": 20, "total_steps": 204, "loss": 0.7355, "lr": 1.991533160993366e-05, "epoch": 0.2962962962962963, "percentage": 9.8, "elapsed_time": "0:00:29", "remaining_time": "0:04:30"}
+{"current_steps": 30, "total_steps": 204, "loss": 0.6846, "lr": 1.9573822052208013e-05, "epoch": 0.4444444444444444, "percentage": 14.71, "elapsed_time": "0:00:43", "remaining_time": "0:04:14"}
+{"current_steps": 40, "total_steps": 204, "loss": 0.6672, "lr": 1.8979201311434434e-05, "epoch": 0.5925925925925926, "percentage": 19.61, "elapsed_time": "0:00:58", "remaining_time": "0:03:59"}
+{"current_steps": 50, "total_steps": 204, "loss": 0.6607, "lr": 1.8147189876080463e-05, "epoch": 0.7407407407407407, "percentage": 24.51, "elapsed_time": "0:01:12", "remaining_time": "0:03:44"}
+{"current_steps": 60, "total_steps": 204, "loss": 0.6538, "lr": 1.709978433199901e-05, "epoch": 0.8888888888888888, "percentage": 29.41, "elapsed_time": "0:01:27", "remaining_time": "0:03:29"}
+{"current_steps": 70, "total_steps": 204, "loss": 0.6235, "lr": 1.586467582019392e-05, "epoch": 1.0296296296296297, "percentage": 34.31, "elapsed_time": "0:01:40", "remaining_time": "0:03:13"}
+{"current_steps": 80, "total_steps": 204, "loss": 0.5681, "lr": 1.4474517942843173e-05, "epoch": 1.1777777777777778, "percentage": 39.22, "elapsed_time": "0:01:55", "remaining_time": "0:02:58"}
+{"current_steps": 90, "total_steps": 204, "loss": 0.5632, "lr": 1.2966063472563686e-05, "epoch": 1.325925925925926, "percentage": 44.12, "elapsed_time": "0:02:09", "remaining_time": "0:02:44"}
+{"current_steps": 100, "total_steps": 204, "loss": 0.5595, "lr": 1.137919268846074e-05, "epoch": 1.474074074074074, "percentage": 49.02, "elapsed_time": "0:02:24", "remaining_time": "0:02:30"}
+{"current_steps": 110, "total_steps": 204, "loss": 0.5516, "lr": 9.755859027658848e-06, "epoch": 1.6222222222222222, "percentage": 53.92, "elapsed_time": "0:02:38", "remaining_time": "0:02:15"}
+{"current_steps": 120, "total_steps": 204, "loss": 0.552, "lr": 8.138979927010964e-06, "epoch": 1.7703703703703704, "percentage": 58.82, "elapsed_time": "0:02:53", "remaining_time": "0:02:01"}
+{"current_steps": 130, "total_steps": 204, "loss": 0.5492, "lr": 6.571302178736404e-06, "epoch": 1.9185185185185185, "percentage": 63.73, "elapsed_time": "0:03:07", "remaining_time": "0:01:46"}
+{"current_steps": 140, "total_steps": 204, "loss": 0.5272, "lr": 5.094271797534404e-06, "epoch": 2.0592592592592593, "percentage": 68.63, "elapsed_time": "0:03:21", "remaining_time": "0:01:31"}
+{"current_steps": 150, "total_steps": 204, "loss": 0.492, "lr": 3.74693827744665e-06, "epoch": 2.2074074074074073, "percentage": 73.53, "elapsed_time": "0:03:35", "remaining_time": "0:01:17"}
+{"current_steps": 160, "total_steps": 204, "loss": 0.4981, "lr": 2.564922207551337e-06, "epoch": 2.3555555555555556, "percentage": 78.43, "elapsed_time": "0:03:49", "remaining_time": "0:01:03"}
+{"current_steps": 170, "total_steps": 204, "loss": 0.4926, "lr": 1.579473540500751e-06, "epoch": 2.5037037037037035, "percentage": 83.33, "elapsed_time": "0:04:04", "remaining_time": "0:00:48"}
+{"current_steps": 180, "total_steps": 204, "loss": 0.4956, "lr": 8.166454112487287e-07, "epoch": 2.651851851851852, "percentage": 88.24, "elapsed_time": "0:04:18", "remaining_time": "0:00:34"}
+{"current_steps": 190, "total_steps": 204, "loss": 0.4903, "lr": 2.9660534841699175e-07, "epoch": 2.8, "percentage": 93.14, "elapsed_time": "0:04:32", "remaining_time": "0:00:20"}
+{"current_steps": 200, "total_steps": 204, "loss": 0.4883, "lr": 3.310208838458562e-08, "epoch": 2.948148148148148, "percentage": 98.04, "elapsed_time": "0:04:47", "remaining_time": "0:00:05"}
+{"current_steps": 200, "total_steps": 204, "eval_loss": 0.6684299111366272, "epoch": 2.948148148148148, "percentage": 98.04, "elapsed_time": "0:04:47", "remaining_time": "0:00:05"}
+{"current_steps": 204, "total_steps": 204, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:08", "remaining_time": "0:00:00"}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,191 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 2.5787038803100586,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.8932,
+      "step": 10
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 1.3832252025604248,
+      "learning_rate": 1.991533160993366e-05,
+      "loss": 0.7355,
+      "step": 20
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.1969517469406128,
+      "learning_rate": 1.9573822052208013e-05,
+      "loss": 0.6846,
+      "step": 30
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 1.1520695686340332,
+      "learning_rate": 1.8979201311434434e-05,
+      "loss": 0.6672,
+      "step": 40
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.3113605976104736,
+      "learning_rate": 1.8147189876080463e-05,
+      "loss": 0.6607,
+      "step": 50
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.1071128845214844,
+      "learning_rate": 1.709978433199901e-05,
+      "loss": 0.6538,
+      "step": 60
+    },
+    {
+      "epoch": 1.0296296296296297,
+      "grad_norm": 1.3430020809173584,
+      "learning_rate": 1.586467582019392e-05,
+      "loss": 0.6235,
+      "step": 70
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 1.1768577098846436,
+      "learning_rate": 1.4474517942843173e-05,
+      "loss": 0.5681,
+      "step": 80
+    },
+    {
+      "epoch": 1.325925925925926,
+      "grad_norm": 1.1502654552459717,
+      "learning_rate": 1.2966063472563686e-05,
+      "loss": 0.5632,
+      "step": 90
+    },
+    {
+      "epoch": 1.474074074074074,
+      "grad_norm": 1.2426036596298218,
+      "learning_rate": 1.137919268846074e-05,
+      "loss": 0.5595,
+      "step": 100
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 1.1577049493789673,
+      "learning_rate": 9.755859027658848e-06,
+      "loss": 0.5516,
+      "step": 110
+    },
+    {
+      "epoch": 1.7703703703703704,
+      "grad_norm": 1.0877997875213623,
+      "learning_rate": 8.138979927010964e-06,
+      "loss": 0.552,
+      "step": 120
+    },
+    {
+      "epoch": 1.9185185185185185,
+      "grad_norm": 1.0529100894927979,
+      "learning_rate": 6.571302178736404e-06,
+      "loss": 0.5492,
+      "step": 130
+    },
+    {
+      "epoch": 2.0592592592592593,
+      "grad_norm": 1.0376404523849487,
+      "learning_rate": 5.094271797534404e-06,
+      "loss": 0.5272,
+      "step": 140
+    },
+    {
+      "epoch": 2.2074074074074073,
+      "grad_norm": 1.0315033197402954,
+      "learning_rate": 3.74693827744665e-06,
+      "loss": 0.492,
+      "step": 150
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.9723921418190002,
+      "learning_rate": 2.564922207551337e-06,
+      "loss": 0.4981,
+      "step": 160
+    },
+    {
+      "epoch": 2.5037037037037035,
+      "grad_norm": 0.9567559957504272,
+      "learning_rate": 1.579473540500751e-06,
+      "loss": 0.4926,
+      "step": 170
+    },
+    {
+      "epoch": 2.651851851851852,
+      "grad_norm": 0.994361937046051,
+      "learning_rate": 8.166454112487287e-07,
+      "loss": 0.4956,
+      "step": 180
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.9385385513305664,
+      "learning_rate": 2.9660534841699175e-07,
+      "loss": 0.4903,
+      "step": 190
+    },
+    {
+      "epoch": 2.948148148148148,
+      "grad_norm": 0.9814600944519043,
+      "learning_rate": 3.310208838458562e-08,
+      "loss": 0.4883,
+      "step": 200
+    },
+    {
+      "epoch": 2.948148148148148,
+      "eval_loss": 0.6684299111366272,
+      "eval_runtime": 0.3376,
+      "eval_samples_per_second": 130.315,
+      "eval_steps_per_second": 17.77,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "step": 204,
+      "total_flos": 5.359421722984448e+16,
+      "train_loss": 0.5856129340097016,
+      "train_runtime": 310.1981,
+      "train_samples_per_second": 41.751,
+      "train_steps_per_second": 0.658
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 204,
+  "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": 5.359421722984448e+16,
+  "train_batch_size": 4,
+  "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 sha256:8097a2b9bf6b47f4a673225e14950ee92f8c6c4ac860da926362695c34356b81
+size 7352
--- a/training_eval_loss.png
+++ b/training_eval_loss.png
--- a/training_loss.png
+++ b/training_loss.png
--- a/vocab.json
+++ b/vocab.json