Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Instructions to use HaichuanWang/Qwen2.5-32B-Open-R1-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HaichuanWang/Qwen2.5-32B-Open-R1-Distill with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HaichuanWang/Qwen2.5-32B-Open-R1-Distill") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HaichuanWang/Qwen2.5-32B-Open-R1-Distill") model = AutoModelForCausalLM.from_pretrained("HaichuanWang/Qwen2.5-32B-Open-R1-Distill") 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HaichuanWang/Qwen2.5-32B-Open-R1-Distill with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HaichuanWang/Qwen2.5-32B-Open-R1-Distill" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HaichuanWang/Qwen2.5-32B-Open-R1-Distill", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/HaichuanWang/Qwen2.5-32B-Open-R1-Distill
- SGLang
How to use HaichuanWang/Qwen2.5-32B-Open-R1-Distill 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 "HaichuanWang/Qwen2.5-32B-Open-R1-Distill" \ --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": "HaichuanWang/Qwen2.5-32B-Open-R1-Distill", "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 "HaichuanWang/Qwen2.5-32B-Open-R1-Distill" \ --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": "HaichuanWang/Qwen2.5-32B-Open-R1-Distill", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use HaichuanWang/Qwen2.5-32B-Open-R1-Distill with Docker Model Runner:
docker model run hf.co/HaichuanWang/Qwen2.5-32B-Open-R1-Distill
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994447529150472, | |
| "eval_steps": 100, | |
| "global_step": 675, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007403294466037387, | |
| "grad_norm": 6.054015357976966, | |
| "learning_rate": 1.4705882352941177e-06, | |
| "loss": 1.0223, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014806588932074774, | |
| "grad_norm": 3.00178071483638, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 0.9735, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02220988339811216, | |
| "grad_norm": 3.3110378377541045, | |
| "learning_rate": 4.411764705882353e-06, | |
| "loss": 0.9131, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029613177864149548, | |
| "grad_norm": 1.7167593624815825, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.838, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.037016472330186935, | |
| "grad_norm": 1.3355609975763119, | |
| "learning_rate": 7.352941176470589e-06, | |
| "loss": 0.7854, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04441976679622432, | |
| "grad_norm": 1.1944056299426455, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.7426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05182306126226171, | |
| "grad_norm": 1.0979891003870184, | |
| "learning_rate": 1.0294117647058823e-05, | |
| "loss": 0.7111, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.059226355728299096, | |
| "grad_norm": 1.03030412384513, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.6921, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06662965019433648, | |
| "grad_norm": 1.0511707964694386, | |
| "learning_rate": 1.323529411764706e-05, | |
| "loss": 0.6809, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07403294466037387, | |
| "grad_norm": 1.3831226662358083, | |
| "learning_rate": 1.4705882352941179e-05, | |
| "loss": 0.6892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08143623912641125, | |
| "grad_norm": 1.0200254363547938, | |
| "learning_rate": 1.6176470588235296e-05, | |
| "loss": 0.6888, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08883953359244864, | |
| "grad_norm": 1.1148922545078945, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.6664, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09624282805848602, | |
| "grad_norm": 0.9161248428501321, | |
| "learning_rate": 1.911764705882353e-05, | |
| "loss": 0.6656, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10364612252452342, | |
| "grad_norm": 1.0394239702550545, | |
| "learning_rate": 1.9999464266898485e-05, | |
| "loss": 0.6623, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1110494169905608, | |
| "grad_norm": 1.3621230342460557, | |
| "learning_rate": 1.9993437928712977e-05, | |
| "loss": 0.6595, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11845271145659819, | |
| "grad_norm": 1.0557714099921336, | |
| "learning_rate": 1.998071963486563e-05, | |
| "loss": 0.6493, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12585600592263557, | |
| "grad_norm": 0.9819086436530112, | |
| "learning_rate": 1.9961317901970953e-05, | |
| "loss": 0.6422, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.13325930038867295, | |
| "grad_norm": 1.0991025777736856, | |
| "learning_rate": 1.993524572210807e-05, | |
| "loss": 0.6417, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14066259485471036, | |
| "grad_norm": 0.9146519268371706, | |
| "learning_rate": 1.990252055412077e-05, | |
| "loss": 0.6393, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.14806588932074774, | |
| "grad_norm": 0.9083117689325773, | |
| "learning_rate": 1.9863164311926433e-05, | |
| "loss": 0.6634, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14806588932074774, | |
| "eval_loss": 0.6650124192237854, | |
| "eval_runtime": 5.451, | |
| "eval_samples_per_second": 23.482, | |
| "eval_steps_per_second": 5.87, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15546918378678512, | |
| "grad_norm": 0.8311871350343286, | |
| "learning_rate": 1.981720334984174e-05, | |
| "loss": 0.6404, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.1628724782528225, | |
| "grad_norm": 0.8554441640252184, | |
| "learning_rate": 1.9764668444934853e-05, | |
| "loss": 0.6366, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17027577271885988, | |
| "grad_norm": 0.8768031438584897, | |
| "learning_rate": 1.970559477641606e-05, | |
| "loss": 0.6177, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1776790671848973, | |
| "grad_norm": 0.8129255159587778, | |
| "learning_rate": 1.9640021902080523e-05, | |
| "loss": 0.6455, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18508236165093467, | |
| "grad_norm": 0.7615880874721697, | |
| "learning_rate": 1.9567993731818988e-05, | |
| "loss": 0.642, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19248565611697205, | |
| "grad_norm": 0.939937392812517, | |
| "learning_rate": 1.9489558498214197e-05, | |
| "loss": 0.6374, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19988895058300943, | |
| "grad_norm": 0.779781527968629, | |
| "learning_rate": 1.9404768724242667e-05, | |
| "loss": 0.6249, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.20729224504904684, | |
| "grad_norm": 0.8178726952811586, | |
| "learning_rate": 1.931368118810346e-05, | |
| "loss": 0.6462, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.21469553951508422, | |
| "grad_norm": 0.813537931225484, | |
| "learning_rate": 1.92163568851975e-05, | |
| "loss": 0.6266, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2220988339811216, | |
| "grad_norm": 0.8669240193026168, | |
| "learning_rate": 1.911286098728296e-05, | |
| "loss": 0.6284, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22950212844715898, | |
| "grad_norm": 0.8459528275224641, | |
| "learning_rate": 1.900326279883392e-05, | |
| "loss": 0.6502, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.23690542291319638, | |
| "grad_norm": 0.7547723658789413, | |
| "learning_rate": 1.8887635710631716e-05, | |
| "loss": 0.6555, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.24430871737923376, | |
| "grad_norm": 0.7988067765230787, | |
| "learning_rate": 1.8766057150619865e-05, | |
| "loss": 0.633, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.25171201184527114, | |
| "grad_norm": 0.8435217927099935, | |
| "learning_rate": 1.8638608532055635e-05, | |
| "loss": 0.6486, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2591153063113085, | |
| "grad_norm": 0.7570773505946161, | |
| "learning_rate": 1.8505375198992856e-05, | |
| "loss": 0.6369, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2665186007773459, | |
| "grad_norm": 0.6908791003663142, | |
| "learning_rate": 1.836644636913258e-05, | |
| "loss": 0.6142, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2739218952433833, | |
| "grad_norm": 0.9038360663088197, | |
| "learning_rate": 1.8221915074079764e-05, | |
| "loss": 0.6315, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2813251897094207, | |
| "grad_norm": 0.761598119680851, | |
| "learning_rate": 1.8071878097046064e-05, | |
| "loss": 0.6147, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2887284841754581, | |
| "grad_norm": 0.8338375619723758, | |
| "learning_rate": 1.7916435908040413e-05, | |
| "loss": 0.6286, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2961317786414955, | |
| "grad_norm": 0.8217875765251234, | |
| "learning_rate": 1.7755692596590778e-05, | |
| "loss": 0.6296, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2961317786414955, | |
| "eval_loss": 0.6434462070465088, | |
| "eval_runtime": 5.3536, | |
| "eval_samples_per_second": 23.909, | |
| "eval_steps_per_second": 5.977, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.30353507310753286, | |
| "grad_norm": 0.7531256929909127, | |
| "learning_rate": 1.7589755802042188e-05, | |
| "loss": 0.6278, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.31093836757357024, | |
| "grad_norm": 0.985208375246224, | |
| "learning_rate": 1.7418736641477636e-05, | |
| "loss": 0.6141, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3183416620396076, | |
| "grad_norm": 0.7150890431535333, | |
| "learning_rate": 1.7242749635310222e-05, | |
| "loss": 0.6141, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.325744956505645, | |
| "grad_norm": 0.7385393462012849, | |
| "learning_rate": 1.7061912630596252e-05, | |
| "loss": 0.6146, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3331482509716824, | |
| "grad_norm": 0.8380261285347705, | |
| "learning_rate": 1.6876346722120747e-05, | |
| "loss": 0.6293, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.34055154543771976, | |
| "grad_norm": 0.9432686338096382, | |
| "learning_rate": 1.6686176171308125e-05, | |
| "loss": 0.6469, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3479548399037572, | |
| "grad_norm": 0.7391761909531978, | |
| "learning_rate": 1.6491528323012412e-05, | |
| "loss": 0.6163, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.3553581343697946, | |
| "grad_norm": 0.7229880563274125, | |
| "learning_rate": 1.6292533520242663e-05, | |
| "loss": 0.6184, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.36276142883583196, | |
| "grad_norm": 0.7177721205878652, | |
| "learning_rate": 1.6089325016880737e-05, | |
| "loss": 0.6071, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.37016472330186934, | |
| "grad_norm": 0.7400280432263608, | |
| "learning_rate": 1.588203888844982e-05, | |
| "loss": 0.6218, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3775680177679067, | |
| "grad_norm": 0.7130487254827719, | |
| "learning_rate": 1.5670813940993504e-05, | |
| "loss": 0.5997, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.3849713122339441, | |
| "grad_norm": 0.6384986808575821, | |
| "learning_rate": 1.5455791618126407e-05, | |
| "loss": 0.5909, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3923746066999815, | |
| "grad_norm": 0.7429225442557332, | |
| "learning_rate": 1.5237115906318565e-05, | |
| "loss": 0.6131, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.39977790116601886, | |
| "grad_norm": 0.7773016849508944, | |
| "learning_rate": 1.5014933238477069e-05, | |
| "loss": 0.5977, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.4071811956320563, | |
| "grad_norm": 0.7650662881600563, | |
| "learning_rate": 1.4789392395889468e-05, | |
| "loss": 0.6194, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.41458449009809367, | |
| "grad_norm": 0.6953161119063832, | |
| "learning_rate": 1.4560644408594602e-05, | |
| "loss": 0.6043, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.42198778456413105, | |
| "grad_norm": 0.7262425334896014, | |
| "learning_rate": 1.432884245424761e-05, | |
| "loss": 0.6106, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.42939107903016843, | |
| "grad_norm": 0.7699388146969168, | |
| "learning_rate": 1.4094141755546816e-05, | |
| "loss": 0.6336, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4367943734962058, | |
| "grad_norm": 0.7564571816635713, | |
| "learning_rate": 1.3856699476291176e-05, | |
| "loss": 0.6002, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.4441976679622432, | |
| "grad_norm": 0.8146760886684846, | |
| "learning_rate": 1.3616674616137902e-05, | |
| "loss": 0.6205, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4441976679622432, | |
| "eval_loss": 0.6286216974258423, | |
| "eval_runtime": 5.3343, | |
| "eval_samples_per_second": 23.996, | |
| "eval_steps_per_second": 5.999, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4516009624282806, | |
| "grad_norm": 0.8782027157116415, | |
| "learning_rate": 1.3374227904130724e-05, | |
| "loss": 0.6086, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.45900425689431795, | |
| "grad_norm": 0.7256976422349936, | |
| "learning_rate": 1.3129521691070108e-05, | |
| "loss": 0.5901, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.46640755136035533, | |
| "grad_norm": 0.8220017881024869, | |
| "learning_rate": 1.2882719840797473e-05, | |
| "loss": 0.609, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.47381084582639277, | |
| "grad_norm": 0.7245365715191799, | |
| "learning_rate": 1.2633987620466229e-05, | |
| "loss": 0.5915, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.48121414029243015, | |
| "grad_norm": 0.6781553517961295, | |
| "learning_rate": 1.2383491589873122e-05, | |
| "loss": 0.5986, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.48861743475846753, | |
| "grad_norm": 0.6587446870275878, | |
| "learning_rate": 1.213139948992394e-05, | |
| "loss": 0.6061, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4960207292245049, | |
| "grad_norm": 0.657348449028724, | |
| "learning_rate": 1.187788013030837e-05, | |
| "loss": 0.601, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.5034240236905423, | |
| "grad_norm": 0.7312864930554595, | |
| "learning_rate": 1.1623103276459086e-05, | |
| "loss": 0.609, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5108273181565797, | |
| "grad_norm": 0.6998503014455123, | |
| "learning_rate": 1.1367239535870913e-05, | |
| "loss": 0.5996, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.518230612622617, | |
| "grad_norm": 0.7195665500605787, | |
| "learning_rate": 1.1110460243856051e-05, | |
| "loss": 0.5878, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5256339070886544, | |
| "grad_norm": 0.7353713724425344, | |
| "learning_rate": 1.085293734881197e-05, | |
| "loss": 0.601, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.5330372015546918, | |
| "grad_norm": 0.7043285272462022, | |
| "learning_rate": 1.0594843297078736e-05, | |
| "loss": 0.6155, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5404404960207292, | |
| "grad_norm": 0.7499907024463522, | |
| "learning_rate": 1.0336350917462925e-05, | |
| "loss": 0.6077, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.5478437904867666, | |
| "grad_norm": 0.7647587567267611, | |
| "learning_rate": 1.0077633305505402e-05, | |
| "loss": 0.5977, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.555247084952804, | |
| "grad_norm": 0.7364351326908367, | |
| "learning_rate": 9.818863707570476e-06, | |
| "loss": 0.6139, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5626503794188414, | |
| "grad_norm": 0.6737008789562675, | |
| "learning_rate": 9.560215404834094e-06, | |
| "loss": 0.6054, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5700536738848788, | |
| "grad_norm": 0.6710478117331311, | |
| "learning_rate": 9.30186159724869e-06, | |
| "loss": 0.5745, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.5774569683509162, | |
| "grad_norm": 0.7365682389903926, | |
| "learning_rate": 9.043975287562443e-06, | |
| "loss": 0.5996, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5848602628169536, | |
| "grad_norm": 0.7108000943046539, | |
| "learning_rate": 8.786729165470584e-06, | |
| "loss": 0.5814, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.592263557282991, | |
| "grad_norm": 0.726649744341547, | |
| "learning_rate": 8.530295491976338e-06, | |
| "loss": 0.5883, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.592263557282991, | |
| "eval_loss": 0.6156524419784546, | |
| "eval_runtime": 5.3162, | |
| "eval_samples_per_second": 24.078, | |
| "eval_steps_per_second": 6.019, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5996668517490283, | |
| "grad_norm": 0.6285431309190148, | |
| "learning_rate": 8.274845984038916e-06, | |
| "loss": 0.5735, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.6070701462150657, | |
| "grad_norm": 0.7208707564961211, | |
| "learning_rate": 8.020551699585843e-06, | |
| "loss": 0.5981, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6144734406811031, | |
| "grad_norm": 0.6348365120026416, | |
| "learning_rate": 7.76758292296659e-06, | |
| "loss": 0.5844, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.6218767351471405, | |
| "grad_norm": 0.6813003995268427, | |
| "learning_rate": 7.5161090509242005e-06, | |
| "loss": 0.5949, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6292800296131779, | |
| "grad_norm": 0.6630486660871571, | |
| "learning_rate": 7.2662984791613186e-06, | |
| "loss": 0.5884, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.6366833240792152, | |
| "grad_norm": 0.6944735724630203, | |
| "learning_rate": 7.01831848957653e-06, | |
| "loss": 0.6016, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6440866185452526, | |
| "grad_norm": 0.6930000305045221, | |
| "learning_rate": 6.772335138246548e-06, | |
| "loss": 0.5984, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.65148991301129, | |
| "grad_norm": 0.6915055176325112, | |
| "learning_rate": 6.528513144229256e-06, | |
| "loss": 0.5973, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6588932074773274, | |
| "grad_norm": 0.6436856302826529, | |
| "learning_rate": 6.287015779262064e-06, | |
| "loss": 0.5994, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.6662965019433648, | |
| "grad_norm": 0.6398985771780272, | |
| "learning_rate": 6.048004758429451e-06, | |
| "loss": 0.5806, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6736997964094021, | |
| "grad_norm": 0.6406669893911426, | |
| "learning_rate": 5.811640131872867e-06, | |
| "loss": 0.5987, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.6811030908754395, | |
| "grad_norm": 0.689174459076953, | |
| "learning_rate": 5.578080177615575e-06, | |
| "loss": 0.5748, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.688506385341477, | |
| "grad_norm": 0.67870415344058, | |
| "learning_rate": 5.347481295574141e-06, | |
| "loss": 0.574, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.6959096798075144, | |
| "grad_norm": 0.6243577511474816, | |
| "learning_rate": 5.119997902827584e-06, | |
| "loss": 0.5815, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7033129742735518, | |
| "grad_norm": 0.6717650293833948, | |
| "learning_rate": 4.8957823302142916e-06, | |
| "loss": 0.5863, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7107162687395892, | |
| "grad_norm": 0.5794169400811537, | |
| "learning_rate": 4.674984720325961e-06, | |
| "loss": 0.5782, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7181195632056265, | |
| "grad_norm": 0.6397551889388262, | |
| "learning_rate": 4.457752926966888e-06, | |
| "loss": 0.5694, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.7255228576716639, | |
| "grad_norm": 0.5964917560176475, | |
| "learning_rate": 4.244232416145839e-06, | |
| "loss": 0.5864, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7329261521377013, | |
| "grad_norm": 0.6170967107219237, | |
| "learning_rate": 4.0345661686669745e-06, | |
| "loss": 0.5804, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.7403294466037387, | |
| "grad_norm": 0.648181489337827, | |
| "learning_rate": 3.828894584384867e-06, | |
| "loss": 0.5856, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7403294466037387, | |
| "eval_loss": 0.6065641045570374, | |
| "eval_runtime": 5.32, | |
| "eval_samples_per_second": 24.06, | |
| "eval_steps_per_second": 6.015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.747732741069776, | |
| "grad_norm": 0.584272251554233, | |
| "learning_rate": 3.62735538818787e-06, | |
| "loss": 0.5722, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.7551360355358134, | |
| "grad_norm": 0.6048521839290723, | |
| "learning_rate": 3.4300835377726904e-06, | |
| "loss": 0.576, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7625393300018508, | |
| "grad_norm": 0.630230887353358, | |
| "learning_rate": 3.2372111332720045e-06, | |
| "loss": 0.6038, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.7699426244678882, | |
| "grad_norm": 0.6743439331706056, | |
| "learning_rate": 3.048867328795588e-06, | |
| "loss": 0.5698, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7773459189339256, | |
| "grad_norm": 0.6133783881575644, | |
| "learning_rate": 2.865178245944218e-06, | |
| "loss": 0.5674, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.784749213399963, | |
| "grad_norm": 0.587498815361936, | |
| "learning_rate": 2.686266889354211e-06, | |
| "loss": 0.5891, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.7921525078660003, | |
| "grad_norm": 0.6028941643634989, | |
| "learning_rate": 2.5122530643292274e-06, | |
| "loss": 0.5944, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.7995558023320377, | |
| "grad_norm": 0.591978984767699, | |
| "learning_rate": 2.3432532966144526e-06, | |
| "loss": 0.5817, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8069590967980751, | |
| "grad_norm": 0.5847122315340881, | |
| "learning_rate": 2.1793807543668857e-06, | |
| "loss": 0.5851, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.8143623912641126, | |
| "grad_norm": 0.5775163753554184, | |
| "learning_rate": 2.0207451723739633e-06, | |
| "loss": 0.5773, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.82176568573015, | |
| "grad_norm": 0.5737766519888903, | |
| "learning_rate": 1.8674527785713247e-06, | |
| "loss": 0.5842, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.8291689801961873, | |
| "grad_norm": 0.625674241986595, | |
| "learning_rate": 1.7196062229088606e-06, | |
| "loss": 0.5543, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8365722746622247, | |
| "grad_norm": 0.6869281902630824, | |
| "learning_rate": 1.577304508612717e-06, | |
| "loss": 0.5812, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.8439755691282621, | |
| "grad_norm": 0.5569467854145252, | |
| "learning_rate": 1.4406429258892762e-06, | |
| "loss": 0.5997, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.8513788635942995, | |
| "grad_norm": 0.6285080967939072, | |
| "learning_rate": 1.3097129881154936e-06, | |
| "loss": 0.5716, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.8587821580603369, | |
| "grad_norm": 0.6275198643982588, | |
| "learning_rate": 1.1846023705583442e-06, | |
| "loss": 0.5704, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.8661854525263742, | |
| "grad_norm": 0.6283404886717425, | |
| "learning_rate": 1.065394851664394e-06, | |
| "loss": 0.5851, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.8735887469924116, | |
| "grad_norm": 0.5792463960702049, | |
| "learning_rate": 9.521702569588199e-07, | |
| "loss": 0.6029, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.880992041458449, | |
| "grad_norm": 0.5763115972641945, | |
| "learning_rate": 8.450044055914497e-07, | |
| "loss": 0.5733, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.8883953359244864, | |
| "grad_norm": 0.5995202047279281, | |
| "learning_rate": 7.439690595656013e-07, | |
| "loss": 0.5941, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8883953359244864, | |
| "eval_loss": 0.6024371385574341, | |
| "eval_runtime": 5.314, | |
| "eval_samples_per_second": 24.087, | |
| "eval_steps_per_second": 6.022, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8957986303905238, | |
| "grad_norm": 0.6269709647548051, | |
| "learning_rate": 6.491318756837417e-07, | |
| "loss": 0.581, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.9032019248565611, | |
| "grad_norm": 0.5333931949440825, | |
| "learning_rate": 5.605563602421149e-07, | |
| "loss": 0.5621, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9106052193225985, | |
| "grad_norm": 0.5981201173913836, | |
| "learning_rate": 4.783018265047179e-07, | |
| "loss": 0.6018, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.9180085137886359, | |
| "grad_norm": 0.6222694811889932, | |
| "learning_rate": 4.024233549850509e-07, | |
| "loss": 0.593, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9254118082546733, | |
| "grad_norm": 0.5685925372104171, | |
| "learning_rate": 3.329717565622825e-07, | |
| "loss": 0.5888, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.9328151027207107, | |
| "grad_norm": 0.5818847562857973, | |
| "learning_rate": 2.6999353845651113e-07, | |
| "loss": 0.5783, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9402183971867482, | |
| "grad_norm": 0.6074418996538741, | |
| "learning_rate": 2.1353087308590314e-07, | |
| "loss": 0.5909, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.9476216916527855, | |
| "grad_norm": 0.584617964311902, | |
| "learning_rate": 1.6362156982656085e-07, | |
| "loss": 0.5798, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9550249861188229, | |
| "grad_norm": 0.5687926808356795, | |
| "learning_rate": 1.2029904969404482e-07, | |
| "loss": 0.5681, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.9624282805848603, | |
| "grad_norm": 0.6080717140090887, | |
| "learning_rate": 8.359232296349163e-08, | |
| "loss": 0.5677, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9698315750508977, | |
| "grad_norm": 0.5827162035016727, | |
| "learning_rate": 5.3525969743324356e-08, | |
| "loss": 0.5835, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.9772348695169351, | |
| "grad_norm": 0.607590392614964, | |
| "learning_rate": 3.012012351554017e-08, | |
| "loss": 0.5625, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9846381639829724, | |
| "grad_norm": 0.5844855309654554, | |
| "learning_rate": 1.3390457653639221e-08, | |
| "loss": 0.585, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.9920414584490098, | |
| "grad_norm": 0.5889754681628832, | |
| "learning_rate": 3.3481749271768726e-09, | |
| "loss": 0.596, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.9994447529150472, | |
| "grad_norm": 0.600571388380399, | |
| "learning_rate": 0.0, | |
| "loss": 0.5688, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.9994447529150472, | |
| "step": 675, | |
| "total_flos": 176903109476352.0, | |
| "train_loss": 0.61981393955372, | |
| "train_runtime": 3766.2204, | |
| "train_samples_per_second": 5.738, | |
| "train_steps_per_second": 0.179 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 675, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 176903109476352.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |