commit 592a9453a17a2d4ba56aaf7a264ba2d996c8388f
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat May 9 00:00:03 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: varshak1/openrubric-rubric-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..3dede04
--- /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: 8b_openrubric-rubric-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. -->
+
+# 8b_openrubric-rubric-sft
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the openrubric-rubric-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: 8e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- 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: 0.05
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.22.2
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..a9f89e6
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.329238633864495e+18,
+    "train_loss": 0.37422844500524594,
+    "train_runtime": 1723.7802,
+    "train_samples_per_second": 20.659,
+    "train_steps_per_second": 0.162
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..01be9b3
--- /dev/null
+++ 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 %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..a8e7a96
--- /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": "5.2.0",
+  "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..1701c94
--- /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": "5.2.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..fc49317
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393b850635e1f49697cd110964d5cec60f6eef04cdc49d03dc000764b2e2f054
+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..ea4d101
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..a9f89e6
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.329238633864495e+18,
+    "train_loss": 0.37422844500524594,
+    "train_runtime": 1723.7802,
+    "train_samples_per_second": 20.659,
+    "train_steps_per_second": 0.162
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..be49685
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,28 @@
+{"current_steps": 10, "total_steps": 279, "loss": 0.9999963760375976, "lr": 5.142857142857143e-06, "epoch": 0.03593890386343217, "percentage": 3.58, "elapsed_time": "0:01:03", "remaining_time": "0:28:32"}
+{"current_steps": 20, "total_steps": 279, "loss": 0.5433789730072022, "lr": 7.992974927057286e-06, "epoch": 0.07187780772686433, "percentage": 7.17, "elapsed_time": "0:02:03", "remaining_time": "0:26:35"}
+{"current_steps": 30, "total_steps": 279, "loss": 0.4406783103942871, "lr": 7.936922311790387e-06, "epoch": 0.1078167115902965, "percentage": 10.75, "elapsed_time": "0:03:02", "remaining_time": "0:25:10"}
+{"current_steps": 40, "total_steps": 279, "loss": 0.4059865951538086, "lr": 7.825603937106089e-06, "epoch": 0.14375561545372867, "percentage": 14.34, "elapsed_time": "0:04:01", "remaining_time": "0:24:00"}
+{"current_steps": 50, "total_steps": 279, "loss": 0.38223881721496583, "lr": 7.660582468972073e-06, "epoch": 0.17969451931716082, "percentage": 17.92, "elapsed_time": "0:04:59", "remaining_time": "0:22:53"}
+{"current_steps": 60, "total_steps": 279, "loss": 0.37668166160583494, "lr": 7.444174447069421e-06, "epoch": 0.215633423180593, "percentage": 21.51, "elapsed_time": "0:05:59", "remaining_time": "0:21:50"}
+{"current_steps": 70, "total_steps": 279, "loss": 0.359727144241333, "lr": 7.179417765653413e-06, "epoch": 0.25157232704402516, "percentage": 25.09, "elapsed_time": "0:06:58", "remaining_time": "0:20:49"}
+{"current_steps": 80, "total_steps": 279, "loss": 0.35879950523376464, "lr": 6.870029028177324e-06, "epoch": 0.28751123090745734, "percentage": 28.67, "elapsed_time": "0:07:58", "remaining_time": "0:19:49"}
+{"current_steps": 90, "total_steps": 279, "loss": 0.350269079208374, "lr": 6.520351374326845e-06, "epoch": 0.32345013477088946, "percentage": 32.26, "elapsed_time": "0:08:58", "remaining_time": "0:18:50"}
+{"current_steps": 100, "total_steps": 279, "loss": 0.35556807518005373, "lr": 6.1352935118591635e-06, "epoch": 0.35938903863432164, "percentage": 35.84, "elapsed_time": "0:09:58", "remaining_time": "0:17:50"}
+{"current_steps": 110, "total_steps": 279, "loss": 0.3427577495574951, "lr": 5.720260809106082e-06, "epoch": 0.3953279424977538, "percentage": 39.43, "elapsed_time": "0:10:55", "remaining_time": "0:16:47"}
+{"current_steps": 120, "total_steps": 279, "loss": 0.3359182596206665, "lr": 5.28107941545135e-06, "epoch": 0.431266846361186, "percentage": 43.01, "elapsed_time": "0:11:55", "remaining_time": "0:15:47"}
+{"current_steps": 130, "total_steps": 279, "loss": 0.3400346040725708, "lr": 4.823914474964393e-06, "epoch": 0.46720575022461813, "percentage": 46.59, "elapsed_time": "0:12:53", "remaining_time": "0:14:47"}
+{"current_steps": 140, "total_steps": 279, "loss": 0.3393260478973389, "lr": 4.355183581291739e-06, "epoch": 0.5031446540880503, "percentage": 50.18, "elapsed_time": "0:13:52", "remaining_time": "0:13:46"}
+{"current_steps": 150, "total_steps": 279, "loss": 0.33171849250793456, "lr": 3.8814666887097606e-06, "epoch": 0.5390835579514824, "percentage": 53.76, "elapsed_time": "0:14:51", "remaining_time": "0:12:46"}
+{"current_steps": 160, "total_steps": 279, "loss": 0.33351149559021, "lr": 3.4094137439900755e-06, "epoch": 0.5750224618149147, "percentage": 57.35, "elapsed_time": "0:15:51", "remaining_time": "0:11:47"}
+{"current_steps": 170, "total_steps": 279, "loss": 0.32773785591125487, "lr": 2.94565133572373e-06, "epoch": 0.6109613656783468, "percentage": 60.93, "elapsed_time": "0:16:51", "remaining_time": "0:10:48"}
+{"current_steps": 180, "total_steps": 279, "loss": 0.32363770008087156, "lr": 2.496689671543048e-06, "epoch": 0.6469002695417789, "percentage": 64.52, "elapsed_time": "0:17:50", "remaining_time": "0:09:48"}
+{"current_steps": 190, "total_steps": 279, "loss": 0.33127546310424805, "lr": 2.068831189077021e-06, "epoch": 0.6828391734052112, "percentage": 68.1, "elapsed_time": "0:18:50", "remaining_time": "0:08:49"}
+{"current_steps": 200, "total_steps": 279, "loss": 0.3253414392471313, "lr": 1.6680820835421124e-06, "epoch": 0.7187780772686433, "percentage": 71.68, "elapsed_time": "0:19:50", "remaining_time": "0:07:50"}
+{"current_steps": 210, "total_steps": 279, "loss": 0.32832999229431153, "lr": 1.3000679939271586e-06, "epoch": 0.7547169811320755, "percentage": 75.27, "elapsed_time": "0:20:48", "remaining_time": "0:06:50"}
+{"current_steps": 220, "total_steps": 279, "loss": 0.33035430908203123, "lr": 9.699550313535194e-07, "epoch": 0.7906558849955077, "percentage": 78.85, "elapsed_time": "0:21:48", "remaining_time": "0:05:50"}
+{"current_steps": 230, "total_steps": 279, "loss": 0.31977477073669436, "lr": 6.823772581991929e-07, "epoch": 0.8265947888589398, "percentage": 82.44, "elapsed_time": "0:22:48", "remaining_time": "0:04:51"}
+{"current_steps": 240, "total_steps": 279, "loss": 0.32599825859069825, "lr": 4.413716360210111e-07, "epoch": 0.862533692722372, "percentage": 86.02, "elapsed_time": "0:23:47", "remaining_time": "0:03:52"}
+{"current_steps": 250, "total_steps": 279, "loss": 0.3147287845611572, "lr": 2.503213554635164e-07, "epoch": 0.8984725965858041, "percentage": 89.61, "elapsed_time": "0:24:47", "remaining_time": "0:02:52"}
+{"current_steps": 260, "total_steps": 279, "loss": 0.32068469524383547, "lr": 1.11908343678357e-07, "epoch": 0.9344115004492363, "percentage": 93.19, "elapsed_time": "0:25:47", "remaining_time": "0:01:53"}
+{"current_steps": 270, "total_steps": 279, "loss": 0.3222502708435059, "lr": 2.8075615945932328e-08, "epoch": 0.9703504043126685, "percentage": 96.77, "elapsed_time": "0:26:47", "remaining_time": "0:00:53"}
+{"current_steps": 279, "total_steps": 279, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:28:42", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..82f19d7
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,232 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 279,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03593890386343217,
+      "grad_norm": 3.182513952255249,
+      "learning_rate": 5.142857142857143e-06,
+      "loss": 0.9999963760375976,
+      "step": 10
+    },
+    {
+      "epoch": 0.07187780772686433,
+      "grad_norm": 1.173149585723877,
+      "learning_rate": 7.992974927057286e-06,
+      "loss": 0.5433789730072022,
+      "step": 20
+    },
+    {
+      "epoch": 0.1078167115902965,
+      "grad_norm": 0.8281139731407166,
+      "learning_rate": 7.936922311790387e-06,
+      "loss": 0.4406783103942871,
+      "step": 30
+    },
+    {
+      "epoch": 0.14375561545372867,
+      "grad_norm": 0.8478610515594482,
+      "learning_rate": 7.825603937106089e-06,
+      "loss": 0.4059865951538086,
+      "step": 40
+    },
+    {
+      "epoch": 0.17969451931716082,
+      "grad_norm": 0.8095178604125977,
+      "learning_rate": 7.660582468972073e-06,
+      "loss": 0.38223881721496583,
+      "step": 50
+    },
+    {
+      "epoch": 0.215633423180593,
+      "grad_norm": 0.7364096641540527,
+      "learning_rate": 7.444174447069421e-06,
+      "loss": 0.37668166160583494,
+      "step": 60
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 0.7268216609954834,
+      "learning_rate": 7.179417765653413e-06,
+      "loss": 0.359727144241333,
+      "step": 70
+    },
+    {
+      "epoch": 0.28751123090745734,
+      "grad_norm": 0.7387126684188843,
+      "learning_rate": 6.870029028177324e-06,
+      "loss": 0.35879950523376464,
+      "step": 80
+    },
+    {
+      "epoch": 0.32345013477088946,
+      "grad_norm": 0.8118855953216553,
+      "learning_rate": 6.520351374326845e-06,
+      "loss": 0.350269079208374,
+      "step": 90
+    },
+    {
+      "epoch": 0.35938903863432164,
+      "grad_norm": 0.7069733738899231,
+      "learning_rate": 6.1352935118591635e-06,
+      "loss": 0.35556807518005373,
+      "step": 100
+    },
+    {
+      "epoch": 0.3953279424977538,
+      "grad_norm": 0.7542175650596619,
+      "learning_rate": 5.720260809106082e-06,
+      "loss": 0.3427577495574951,
+      "step": 110
+    },
+    {
+      "epoch": 0.431266846361186,
+      "grad_norm": 0.8069055080413818,
+      "learning_rate": 5.28107941545135e-06,
+      "loss": 0.3359182596206665,
+      "step": 120
+    },
+    {
+      "epoch": 0.46720575022461813,
+      "grad_norm": 0.8552827835083008,
+      "learning_rate": 4.823914474964393e-06,
+      "loss": 0.3400346040725708,
+      "step": 130
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 0.7165119647979736,
+      "learning_rate": 4.355183581291739e-06,
+      "loss": 0.3393260478973389,
+      "step": 140
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "grad_norm": 0.7520389556884766,
+      "learning_rate": 3.8814666887097606e-06,
+      "loss": 0.33171849250793456,
+      "step": 150
+    },
+    {
+      "epoch": 0.5750224618149147,
+      "grad_norm": 0.6773005723953247,
+      "learning_rate": 3.4094137439900755e-06,
+      "loss": 0.33351149559021,
+      "step": 160
+    },
+    {
+      "epoch": 0.6109613656783468,
+      "grad_norm": 0.7068390846252441,
+      "learning_rate": 2.94565133572373e-06,
+      "loss": 0.32773785591125487,
+      "step": 170
+    },
+    {
+      "epoch": 0.6469002695417789,
+      "grad_norm": 0.8255635499954224,
+      "learning_rate": 2.496689671543048e-06,
+      "loss": 0.32363770008087156,
+      "step": 180
+    },
+    {
+      "epoch": 0.6828391734052112,
+      "grad_norm": 0.6686235070228577,
+      "learning_rate": 2.068831189077021e-06,
+      "loss": 0.33127546310424805,
+      "step": 190
+    },
+    {
+      "epoch": 0.7187780772686433,
+      "grad_norm": 0.7526047229766846,
+      "learning_rate": 1.6680820835421124e-06,
+      "loss": 0.3253414392471313,
+      "step": 200
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.6801684498786926,
+      "learning_rate": 1.3000679939271586e-06,
+      "loss": 0.32832999229431153,
+      "step": 210
+    },
+    {
+      "epoch": 0.7906558849955077,
+      "grad_norm": 0.6622071266174316,
+      "learning_rate": 9.699550313535194e-07,
+      "loss": 0.33035430908203123,
+      "step": 220
+    },
+    {
+      "epoch": 0.8265947888589398,
+      "grad_norm": 0.6161302924156189,
+      "learning_rate": 6.823772581991929e-07,
+      "loss": 0.31977477073669436,
+      "step": 230
+    },
+    {
+      "epoch": 0.862533692722372,
+      "grad_norm": 0.6483022570610046,
+      "learning_rate": 4.413716360210111e-07,
+      "loss": 0.32599825859069825,
+      "step": 240
+    },
+    {
+      "epoch": 0.8984725965858041,
+      "grad_norm": 0.6623414158821106,
+      "learning_rate": 2.503213554635164e-07,
+      "loss": 0.3147287845611572,
+      "step": 250
+    },
+    {
+      "epoch": 0.9344115004492363,
+      "grad_norm": 0.6427763104438782,
+      "learning_rate": 1.11908343678357e-07,
+      "loss": 0.32068469524383547,
+      "step": 260
+    },
+    {
+      "epoch": 0.9703504043126685,
+      "grad_norm": 0.6542255878448486,
+      "learning_rate": 2.8075615945932328e-08,
+      "loss": 0.3222502708435059,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "step": 279,
+      "total_flos": 3.329238633864495e+18,
+      "train_loss": 0.37422844500524594,
+      "train_runtime": 1723.7802,
+      "train_samples_per_second": 20.659,
+      "train_steps_per_second": 0.162
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 279,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3.329238633864495e+18,
+  "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..6f9145a
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15790e8a7fa7712c1cbb8951995a11388e47338b6637b38d72415ff3f909e07
+size 6776
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..564c392
Binary files /dev/null and b/training_loss.png differ