commit 78b48a9c88cca24b3ededf9a8eb8701f0171d6c7
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Fri May 8 03:23:02 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: varshak1/reproducing-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..f3ed9f6
--- /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: reproducing-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. -->
+
+# reproducing-openrubric-rubric-sft
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the reproducing-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..9a067dd
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.3482902468228547e+18,
+    "train_loss": 0.6133034630915597,
+    "train_runtime": 1004.8538,
+    "train_samples_per_second": 35.45,
+    "train_steps_per_second": 0.278
+}
\ 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..fb5e02b
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f9ec07bb4dbd816e33eaaf9fbb09c4b13241a891e97bc7025a27d1f35fdb0f
+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..9a067dd
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.3482902468228547e+18,
+    "train_loss": 0.6133034630915597,
+    "train_runtime": 1004.8538,
+    "train_samples_per_second": 35.45,
+    "train_steps_per_second": 0.278
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..fabd4bc
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,28 @@
+{"current_steps": 10, "total_steps": 279, "loss": 1.4155162811279296, "lr": 5.142857142857143e-06, "epoch": 0.03590664272890485, "percentage": 3.58, "elapsed_time": "0:00:37", "remaining_time": "0:16:45"}
+{"current_steps": 20, "total_steps": 279, "loss": 0.805302906036377, "lr": 7.992974927057286e-06, "epoch": 0.0718132854578097, "percentage": 7.17, "elapsed_time": "0:01:10", "remaining_time": "0:15:18"}
+{"current_steps": 30, "total_steps": 279, "loss": 0.6863783836364746, "lr": 7.936922311790387e-06, "epoch": 0.10771992818671454, "percentage": 10.75, "elapsed_time": "0:01:43", "remaining_time": "0:14:19"}
+{"current_steps": 40, "total_steps": 279, "loss": 0.6478697299957276, "lr": 7.825603937106089e-06, "epoch": 0.1436265709156194, "percentage": 14.34, "elapsed_time": "0:02:16", "remaining_time": "0:13:35"}
+{"current_steps": 50, "total_steps": 279, "loss": 0.630420446395874, "lr": 7.660582468972073e-06, "epoch": 0.17953321364452424, "percentage": 17.92, "elapsed_time": "0:02:49", "remaining_time": "0:12:57"}
+{"current_steps": 60, "total_steps": 279, "loss": 0.6120198726654053, "lr": 7.444174447069421e-06, "epoch": 0.21543985637342908, "percentage": 21.51, "elapsed_time": "0:03:22", "remaining_time": "0:12:20"}
+{"current_steps": 70, "total_steps": 279, "loss": 0.6067015647888183, "lr": 7.179417765653413e-06, "epoch": 0.2513464991023339, "percentage": 25.09, "elapsed_time": "0:03:56", "remaining_time": "0:11:46"}
+{"current_steps": 80, "total_steps": 279, "loss": 0.5879001617431641, "lr": 6.870029028177324e-06, "epoch": 0.2872531418312388, "percentage": 28.67, "elapsed_time": "0:04:31", "remaining_time": "0:11:14"}
+{"current_steps": 90, "total_steps": 279, "loss": 0.5899921417236328, "lr": 6.520351374326845e-06, "epoch": 0.3231597845601436, "percentage": 32.26, "elapsed_time": "0:05:02", "remaining_time": "0:10:34"}
+{"current_steps": 100, "total_steps": 279, "loss": 0.5808853149414063, "lr": 6.1352935118591635e-06, "epoch": 0.3590664272890485, "percentage": 35.84, "elapsed_time": "0:05:35", "remaining_time": "0:09:59"}
+{"current_steps": 110, "total_steps": 279, "loss": 0.5790524482727051, "lr": 5.720260809106082e-06, "epoch": 0.39497307001795334, "percentage": 39.43, "elapsed_time": "0:06:08", "remaining_time": "0:09:25"}
+{"current_steps": 120, "total_steps": 279, "loss": 0.5731555938720703, "lr": 5.28107941545135e-06, "epoch": 0.43087971274685816, "percentage": 43.01, "elapsed_time": "0:06:42", "remaining_time": "0:08:52"}
+{"current_steps": 130, "total_steps": 279, "loss": 0.5686985969543457, "lr": 4.823914474964393e-06, "epoch": 0.466786355475763, "percentage": 46.59, "elapsed_time": "0:07:16", "remaining_time": "0:08:20"}
+{"current_steps": 140, "total_steps": 279, "loss": 0.5693955898284913, "lr": 4.355183581291739e-06, "epoch": 0.5026929982046678, "percentage": 50.18, "elapsed_time": "0:07:51", "remaining_time": "0:07:48"}
+{"current_steps": 150, "total_steps": 279, "loss": 0.5598339080810547, "lr": 3.8814666887097606e-06, "epoch": 0.5385996409335727, "percentage": 53.76, "elapsed_time": "0:08:26", "remaining_time": "0:07:15"}
+{"current_steps": 160, "total_steps": 279, "loss": 0.5563373565673828, "lr": 3.4094137439900755e-06, "epoch": 0.5745062836624776, "percentage": 57.35, "elapsed_time": "0:09:00", "remaining_time": "0:06:42"}
+{"current_steps": 170, "total_steps": 279, "loss": 0.5573836326599121, "lr": 2.94565133572373e-06, "epoch": 0.6104129263913824, "percentage": 60.93, "elapsed_time": "0:09:34", "remaining_time": "0:06:08"}
+{"current_steps": 180, "total_steps": 279, "loss": 0.5560619354248046, "lr": 2.496689671543048e-06, "epoch": 0.6463195691202872, "percentage": 64.52, "elapsed_time": "0:10:07", "remaining_time": "0:05:34"}
+{"current_steps": 190, "total_steps": 279, "loss": 0.5496598720550537, "lr": 2.068831189077021e-06, "epoch": 0.6822262118491921, "percentage": 68.1, "elapsed_time": "0:10:41", "remaining_time": "0:05:00"}
+{"current_steps": 200, "total_steps": 279, "loss": 0.5505017757415771, "lr": 1.6680820835421124e-06, "epoch": 0.718132854578097, "percentage": 71.68, "elapsed_time": "0:11:14", "remaining_time": "0:04:26"}
+{"current_steps": 210, "total_steps": 279, "loss": 0.5497483253479004, "lr": 1.3000679939271586e-06, "epoch": 0.7540394973070018, "percentage": 75.27, "elapsed_time": "0:11:47", "remaining_time": "0:03:52"}
+{"current_steps": 220, "total_steps": 279, "loss": 0.5485612392425537, "lr": 9.699550313535194e-07, "epoch": 0.7899461400359067, "percentage": 78.85, "elapsed_time": "0:12:20", "remaining_time": "0:03:18"}
+{"current_steps": 230, "total_steps": 279, "loss": 0.5506965160369873, "lr": 6.823772581991929e-07, "epoch": 0.8258527827648114, "percentage": 82.44, "elapsed_time": "0:12:53", "remaining_time": "0:02:44"}
+{"current_steps": 240, "total_steps": 279, "loss": 0.5589346885681152, "lr": 4.413716360210111e-07, "epoch": 0.8617594254937163, "percentage": 86.02, "elapsed_time": "0:13:27", "remaining_time": "0:02:11"}
+{"current_steps": 250, "total_steps": 279, "loss": 0.5451088905334472, "lr": 2.503213554635164e-07, "epoch": 0.8976660682226212, "percentage": 89.61, "elapsed_time": "0:14:01", "remaining_time": "0:01:37"}
+{"current_steps": 260, "total_steps": 279, "loss": 0.5363705635070801, "lr": 1.11908343678357e-07, "epoch": 0.933572710951526, "percentage": 93.19, "elapsed_time": "0:14:34", "remaining_time": "0:01:03"}
+{"current_steps": 270, "total_steps": 279, "loss": 0.5481849670410156, "lr": 2.8075615945932328e-08, "epoch": 0.9694793536804309, "percentage": 96.77, "elapsed_time": "0:15:08", "remaining_time": "0:00:30"}
+{"current_steps": 279, "total_steps": 279, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:16:43", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..683901a
--- /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": 0.03590664272890485,
+      "grad_norm": 4.158227443695068,
+      "learning_rate": 5.142857142857143e-06,
+      "loss": 1.4155162811279296,
+      "step": 10
+    },
+    {
+      "epoch": 0.0718132854578097,
+      "grad_norm": 1.651964545249939,
+      "learning_rate": 7.992974927057286e-06,
+      "loss": 0.805302906036377,
+      "step": 20
+    },
+    {
+      "epoch": 0.10771992818671454,
+      "grad_norm": 1.1457046270370483,
+      "learning_rate": 7.936922311790387e-06,
+      "loss": 0.6863783836364746,
+      "step": 30
+    },
+    {
+      "epoch": 0.1436265709156194,
+      "grad_norm": 1.0957046747207642,
+      "learning_rate": 7.825603937106089e-06,
+      "loss": 0.6478697299957276,
+      "step": 40
+    },
+    {
+      "epoch": 0.17953321364452424,
+      "grad_norm": 1.0592354536056519,
+      "learning_rate": 7.660582468972073e-06,
+      "loss": 0.630420446395874,
+      "step": 50
+    },
+    {
+      "epoch": 0.21543985637342908,
+      "grad_norm": 1.193621277809143,
+      "learning_rate": 7.444174447069421e-06,
+      "loss": 0.6120198726654053,
+      "step": 60
+    },
+    {
+      "epoch": 0.2513464991023339,
+      "grad_norm": 1.2658783197402954,
+      "learning_rate": 7.179417765653413e-06,
+      "loss": 0.6067015647888183,
+      "step": 70
+    },
+    {
+      "epoch": 0.2872531418312388,
+      "grad_norm": 1.2949614524841309,
+      "learning_rate": 6.870029028177324e-06,
+      "loss": 0.5879001617431641,
+      "step": 80
+    },
+    {
+      "epoch": 0.3231597845601436,
+      "grad_norm": 1.060629963874817,
+      "learning_rate": 6.520351374326845e-06,
+      "loss": 0.5899921417236328,
+      "step": 90
+    },
+    {
+      "epoch": 0.3590664272890485,
+      "grad_norm": 1.0478813648223877,
+      "learning_rate": 6.1352935118591635e-06,
+      "loss": 0.5808853149414063,
+      "step": 100
+    },
+    {
+      "epoch": 0.39497307001795334,
+      "grad_norm": 1.261673092842102,
+      "learning_rate": 5.720260809106082e-06,
+      "loss": 0.5790524482727051,
+      "step": 110
+    },
+    {
+      "epoch": 0.43087971274685816,
+      "grad_norm": 0.9995132088661194,
+      "learning_rate": 5.28107941545135e-06,
+      "loss": 0.5731555938720703,
+      "step": 120
+    },
+    {
+      "epoch": 0.466786355475763,
+      "grad_norm": 1.0616153478622437,
+      "learning_rate": 4.823914474964393e-06,
+      "loss": 0.5686985969543457,
+      "step": 130
+    },
+    {
+      "epoch": 0.5026929982046678,
+      "grad_norm": 1.0009936094284058,
+      "learning_rate": 4.355183581291739e-06,
+      "loss": 0.5693955898284913,
+      "step": 140
+    },
+    {
+      "epoch": 0.5385996409335727,
+      "grad_norm": 0.9809271097183228,
+      "learning_rate": 3.8814666887097606e-06,
+      "loss": 0.5598339080810547,
+      "step": 150
+    },
+    {
+      "epoch": 0.5745062836624776,
+      "grad_norm": 0.9185540080070496,
+      "learning_rate": 3.4094137439900755e-06,
+      "loss": 0.5563373565673828,
+      "step": 160
+    },
+    {
+      "epoch": 0.6104129263913824,
+      "grad_norm": 0.9326531887054443,
+      "learning_rate": 2.94565133572373e-06,
+      "loss": 0.5573836326599121,
+      "step": 170
+    },
+    {
+      "epoch": 0.6463195691202872,
+      "grad_norm": 0.9872980117797852,
+      "learning_rate": 2.496689671543048e-06,
+      "loss": 0.5560619354248046,
+      "step": 180
+    },
+    {
+      "epoch": 0.6822262118491921,
+      "grad_norm": 0.8914107084274292,
+      "learning_rate": 2.068831189077021e-06,
+      "loss": 0.5496598720550537,
+      "step": 190
+    },
+    {
+      "epoch": 0.718132854578097,
+      "grad_norm": 0.9620088338851929,
+      "learning_rate": 1.6680820835421124e-06,
+      "loss": 0.5505017757415771,
+      "step": 200
+    },
+    {
+      "epoch": 0.7540394973070018,
+      "grad_norm": 0.8976511359214783,
+      "learning_rate": 1.3000679939271586e-06,
+      "loss": 0.5497483253479004,
+      "step": 210
+    },
+    {
+      "epoch": 0.7899461400359067,
+      "grad_norm": 0.8932470679283142,
+      "learning_rate": 9.699550313535194e-07,
+      "loss": 0.5485612392425537,
+      "step": 220
+    },
+    {
+      "epoch": 0.8258527827648114,
+      "grad_norm": 0.9887930154800415,
+      "learning_rate": 6.823772581991929e-07,
+      "loss": 0.5506965160369873,
+      "step": 230
+    },
+    {
+      "epoch": 0.8617594254937163,
+      "grad_norm": 0.9191465973854065,
+      "learning_rate": 4.413716360210111e-07,
+      "loss": 0.5589346885681152,
+      "step": 240
+    },
+    {
+      "epoch": 0.8976660682226212,
+      "grad_norm": 0.8461963534355164,
+      "learning_rate": 2.503213554635164e-07,
+      "loss": 0.5451088905334472,
+      "step": 250
+    },
+    {
+      "epoch": 0.933572710951526,
+      "grad_norm": 0.8567756414413452,
+      "learning_rate": 1.11908343678357e-07,
+      "loss": 0.5363705635070801,
+      "step": 260
+    },
+    {
+      "epoch": 0.9694793536804309,
+      "grad_norm": 0.8579103946685791,
+      "learning_rate": 2.8075615945932328e-08,
+      "loss": 0.5481849670410156,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "step": 279,
+      "total_flos": 1.3482902468228547e+18,
+      "train_loss": 0.6133034630915597,
+      "train_runtime": 1004.8538,
+      "train_samples_per_second": 35.45,
+      "train_steps_per_second": 0.278
+    }
+  ],
+  "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": 1.3482902468228547e+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..0e8f4c7
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4554311b13ffd44fe3155e5942637cc6743804271e77066eed04f8ef8b404a43
+size 6840
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..d61dbe1
Binary files /dev/null and b/training_loss.png differ