Instructions to use RyanFan/RLVR-pmdata-stress with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RyanFan/RLVR-pmdata-stress with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RyanFan/RLVR-pmdata-stress")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RyanFan/RLVR-pmdata-stress")
model = AutoModelForCausalLM.from_pretrained("RyanFan/RLVR-pmdata-stress", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RyanFan/RLVR-pmdata-stress with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RyanFan/RLVR-pmdata-stress"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RyanFan/RLVR-pmdata-stress",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RyanFan/RLVR-pmdata-stress

SGLang

How to use RyanFan/RLVR-pmdata-stress with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RyanFan/RLVR-pmdata-stress" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RyanFan/RLVR-pmdata-stress",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RyanFan/RLVR-pmdata-stress" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RyanFan/RLVR-pmdata-stress",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RyanFan/RLVR-pmdata-stress with Docker Model Runner:
```
docker model run hf.co/RyanFan/RLVR-pmdata-stress
```

RyanFan commited on Jan 27

Commit

8b2b153

verified ·

1 Parent(s): a1ce794

Model save

Browse files

Files changed (14) hide show

.gitattributes +1 -0
README.md +68 -0
added_tokens.json +24 -0
chat_template.jinja +54 -0
config.json +58 -0
generation_config.json +13 -0
merges.txt +0 -0
model.safetensors +3 -0
special_tokens_map.json +31 -0
tokenizer.json +3 -0
tokenizer_config.json +208 -0
trainer_state.json +437 -0
training_args.bin +3 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* 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

 *.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

README.md ADDED Viewed

	@@ -0,0 +1,68 @@

+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: RLVR-pmdata-stress
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+# Model Card for RLVR-pmdata-stress
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+## Quick start
+```python
+from transformers import pipeline
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="RyanFan/RLVR-pmdata-stress", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ryanzhang123-the-university-of-auckland/RLCR/runs/uyivg3er)
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+### Framework versions
+- TRL: 0.16.0.dev0
+- Transformers: 4.57.6
+- Pytorch: 2.5.1
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+## Citations
+Cite GRPO as:
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+```
+Cite TRL as:
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json ADDED Viewed

	@@ -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
+}

chat_template.jinja ADDED Viewed

	@@ -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 %}

config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json ADDED Viewed

	@@ -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": "4.57.6"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b88eb08b1e57a43ce9431d2568b8769d44e86bb1f1089031e1f5c51d4e884f7c
+size 3554214752

special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json ADDED Viewed

	@@ -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": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,437 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 40,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.01875,
+      "completions/max_length": 1430.6,
+      "completions/max_terminated_length": 1348.6,
+      "completions/mean_length": 335.071875,
+      "completions/mean_terminated_length": 312.637841796875,
+      "completions/min_length": 38.4,
+      "completions/min_terminated_length": 38.4,
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.28337302803993225,
+      "learning_rate": 1e-06,
+      "loss": 0.0087,
+      "num_tokens": 353715.0,
+      "reward": 0.49375,
+      "reward_std": 0.14153526425361634,
+      "rewards/accuracy_reward": 0.078125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.909375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.028125,
+      "completions/max_length": 1459.6,
+      "completions/max_terminated_length": 1266.4,
+      "completions/mean_length": 364.325,
+      "completions/mean_terminated_length": 330.822705078125,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.2535293400287628,
+      "learning_rate": 1e-06,
+      "loss": 0.0203,
+      "num_tokens": 721175.0,
+      "reward": 0.5078125,
+      "reward_std": 0.1156127318739891,
+      "rewards/accuracy_reward": 0.075,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.940625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1304.0,
+      "completions/mean_length": 369.721875,
+      "completions/mean_terminated_length": 332.17138671875,
+      "completions/min_length": 43.8,
+      "completions/min_terminated_length": 43.8,
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.2700359523296356,
+      "learning_rate": 1e-06,
+      "loss": 0.0239,
+      "num_tokens": 1100826.0,
+      "reward": 0.509375,
+      "reward_std": 0.11002618819475174,
+      "rewards/accuracy_reward": 0.06875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.95,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.01875,
+      "completions/max_length": 1535.4,
+      "completions/max_terminated_length": 1345.6,
+      "completions/mean_length": 308.225,
+      "completions/mean_terminated_length": 284.83876953125,
+      "completions/min_length": 52.8,
+      "completions/min_terminated_length": 52.8,
+      "epoch": 0.2898550724637681,
+      "grad_norm": 79.66336059570312,
+      "learning_rate": 1e-06,
+      "loss": 0.006,
+      "num_tokens": 1455930.0,
+      "reward": 0.5375,
+      "reward_std": 0.14514370113611222,
+      "rewards/accuracy_reward": 0.125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.95,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.009375,
+      "completions/max_length": 1318.6,
+      "completions/max_terminated_length": 1085.4,
+      "completions/mean_length": 294.978125,
+      "completions/mean_terminated_length": 283.2386779785156,
+      "completions/min_length": 50.4,
+      "completions/min_terminated_length": 50.4,
+      "epoch": 0.36231884057971014,
+      "grad_norm": 0.3315078914165497,
+      "learning_rate": 1e-06,
+      "loss": 0.0131,
+      "num_tokens": 1802399.0,
+      "reward": 0.546875,
+      "reward_std": 0.10421528071165084,
+      "rewards/accuracy_reward": 0.109375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.984375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 1316.8,
+      "completions/max_terminated_length": 1147.8,
+      "completions/mean_length": 302.25625,
+      "completions/mean_terminated_length": 285.8982391357422,
+      "completions/min_length": 38.2,
+      "completions/min_terminated_length": 38.2,
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.28265270590782166,
+      "learning_rate": 1e-06,
+      "loss": 0.0216,
+      "num_tokens": 2145009.0,
+      "reward": 0.5640625,
+      "reward_std": 0.14281345307826995,
+      "rewards/accuracy_reward": 0.15,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.978125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.009375,
+      "completions/max_length": 1283.4,
+      "completions/max_terminated_length": 1149.0,
+      "completions/mean_length": 203.6375,
+      "completions/mean_terminated_length": 191.23175659179688,
+      "completions/min_length": 33.4,
+      "completions/min_terminated_length": 33.4,
+      "epoch": 0.5072463768115942,
+      "grad_norm": 0.521085798740387,
+      "learning_rate": 1e-06,
+      "loss": 0.0275,
+      "num_tokens": 2468121.0,
+      "reward": 0.5921875,
+      "reward_std": 0.17295827567577363,
+      "rewards/accuracy_reward": 0.203125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.98125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 882.6,
+      "completions/max_terminated_length": 882.6,
+      "completions/mean_length": 147.784375,
+      "completions/mean_terminated_length": 147.784375,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.8032597899436951,
+      "learning_rate": 1e-06,
+      "loss": 0.0051,
+      "num_tokens": 2770984.0,
+      "reward": 0.640625,
+      "reward_std": 0.21402235925197602,
+      "rewards/accuracy_reward": 0.290625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.990625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 476.0,
+      "eval_completions/max_terminated_length": 476.0,
+      "eval_completions/mean_length": 158.0253623188406,
+      "eval_completions/mean_terminated_length": 158.0253623188406,
+      "eval_completions/min_length": 52.710144927536234,
+      "eval_completions/min_terminated_length": 52.710144927536234,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 2770984.0,
+      "eval_reward": 0.6630434782608695,
+      "eval_reward_std": 0.182892012855281,
+      "eval_rewards/accuracy_reward": 0.3278985507246377,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9981884057971014,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 344.0574,
+      "eval_samples_per_second": 0.802,
+      "eval_steps_per_second": 0.102,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.003125,
+      "completions/max_length": 936.2,
+      "completions/max_terminated_length": 822.2,
+      "completions/mean_length": 140.45625,
+      "completions/mean_terminated_length": 136.07177734375,
+      "completions/min_length": 38.8,
+      "completions/min_terminated_length": 38.8,
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.6651497483253479,
+      "learning_rate": 1e-06,
+      "loss": 0.0099,
+      "num_tokens": 3060702.0,
+      "reward": 0.6875,
+      "reward_std": 0.20059720277786255,
+      "rewards/accuracy_reward": 0.378125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.996875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 727.0,
+      "completions/max_terminated_length": 727.0,
+      "completions/mean_length": 102.665625,
+      "completions/mean_terminated_length": 102.665625,
+      "completions/min_length": 33.0,
+      "completions/min_terminated_length": 33.0,
+      "epoch": 0.7246376811594203,
+      "grad_norm": 0.5408816933631897,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 3339431.0,
+      "reward": 0.75,
+      "reward_std": 0.1764850214123726,
+      "rewards/accuracy_reward": 0.5,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 334.6,
+      "completions/max_terminated_length": 334.6,
+      "completions/mean_length": 80.190625,
+      "completions/mean_terminated_length": 80.190625,
+      "completions/min_length": 30.6,
+      "completions/min_terminated_length": 30.6,
+      "epoch": 0.7971014492753623,
+      "grad_norm": 0.3914719820022583,
+      "learning_rate": 1e-06,
+      "loss": 0.0084,
+      "num_tokens": 3607440.0,
+      "reward": 0.775,
+      "reward_std": 0.10122594833374024,
+      "rewards/accuracy_reward": 0.55,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 448.4,
+      "completions/max_terminated_length": 448.4,
+      "completions/mean_length": 79.365625,
+      "completions/mean_terminated_length": 79.365625,
+      "completions/min_length": 31.8,
+      "completions/min_terminated_length": 31.8,
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.31264522671699524,
+      "learning_rate": 1e-06,
+      "loss": 0.0008,
+      "num_tokens": 3882353.0,
+      "reward": 0.7984375,
+      "reward_std": 0.07020031586289406,
+      "rewards/accuracy_reward": 0.596875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 315.0,
+      "completions/max_terminated_length": 315.0,
+      "completions/mean_length": 71.5,
+      "completions/mean_terminated_length": 71.5,
+      "completions/min_length": 32.8,
+      "completions/min_terminated_length": 32.8,
+      "epoch": 0.9420289855072463,
+      "grad_norm": 0.23081329464912415,
+      "learning_rate": 1e-06,
+      "loss": 0.0006,
+      "num_tokens": 4160501.0,
+      "reward": 0.7890625,
+      "reward_std": 0.04423343911767006,
+      "rewards/accuracy_reward": 0.578125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 231.0,
+      "completions/max_terminated_length": 231.0,
+      "completions/mean_length": 68.57421875,
+      "completions/mean_terminated_length": 68.57421875,
+      "completions/min_length": 35.5,
+      "completions/min_terminated_length": 35.5,
+      "epoch": 1.0,
+      "num_tokens": 4377256.0,
+      "reward": 0.787109375,
+      "reward_std": 0.0655214935541153,
+      "rewards/accuracy_reward": 0.57421875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 69,
+      "total_flos": 0.0,
+      "train_loss": 0.010691649024037348,
+      "train_runtime": 1641.1771,
+      "train_samples_per_second": 0.673,
+      "train_steps_per_second": 0.042
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 69,
+  "num_input_tokens_seen": 4377256,
+  "num_train_epochs": 1,
+  "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": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb61c261bf13bf5183c2c6f70305d8134e1c7ab2dc594b8f48f51fdb8be6a05a
+size 8120

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff