Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use varshak1/openrubric-judgment-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use varshak1/openrubric-judgment-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="varshak1/openrubric-judgment-sft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("varshak1/openrubric-judgment-sft") model = AutoModelForCausalLM.from_pretrained("varshak1/openrubric-judgment-sft", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use varshak1/openrubric-judgment-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "varshak1/openrubric-judgment-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "varshak1/openrubric-judgment-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/varshak1/openrubric-judgment-sft
- SGLang
How to use varshak1/openrubric-judgment-sft 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 "varshak1/openrubric-judgment-sft" \ --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": "varshak1/openrubric-judgment-sft", "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 "varshak1/openrubric-judgment-sft" \ --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": "varshak1/openrubric-judgment-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use varshak1/openrubric-judgment-sft with Docker Model Runner:
docker model run hf.co/varshak1/openrubric-judgment-sft
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1114, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017969451931716084, | |
| "grad_norm": 1.0288746356964111, | |
| "learning_rate": 4.959605026929982e-06, | |
| "loss": 0.5949527740478515, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03593890386343217, | |
| "grad_norm": 0.6101402044296265, | |
| "learning_rate": 4.9147217235188516e-06, | |
| "loss": 0.41325950622558594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05390835579514825, | |
| "grad_norm": 0.5305581092834473, | |
| "learning_rate": 4.86983842010772e-06, | |
| "loss": 0.3709533929824829, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07187780772686433, | |
| "grad_norm": 0.5169686675071716, | |
| "learning_rate": 4.8249551166965895e-06, | |
| "loss": 0.3509422540664673, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08984725965858041, | |
| "grad_norm": 0.5222465991973877, | |
| "learning_rate": 4.780071813285458e-06, | |
| "loss": 0.3454415321350098, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1078167115902965, | |
| "grad_norm": 0.4856426417827606, | |
| "learning_rate": 4.7351885098743274e-06, | |
| "loss": 0.33249969482421876, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12578616352201258, | |
| "grad_norm": 0.5357626676559448, | |
| "learning_rate": 4.690305206463196e-06, | |
| "loss": 0.3292850971221924, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14375561545372867, | |
| "grad_norm": 0.46837398409843445, | |
| "learning_rate": 4.6454219030520645e-06, | |
| "loss": 0.3244313716888428, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16172506738544473, | |
| "grad_norm": 0.48174625635147095, | |
| "learning_rate": 4.600538599640934e-06, | |
| "loss": 0.3236015558242798, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17969451931716082, | |
| "grad_norm": 0.5259532332420349, | |
| "learning_rate": 4.5556552962298025e-06, | |
| "loss": 0.3194127559661865, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1976639712488769, | |
| "grad_norm": 0.5332797765731812, | |
| "learning_rate": 4.510771992818672e-06, | |
| "loss": 0.31786675453186036, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.215633423180593, | |
| "grad_norm": 0.4909115433692932, | |
| "learning_rate": 4.465888689407541e-06, | |
| "loss": 0.3128951072692871, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23360287511230907, | |
| "grad_norm": 0.4780581295490265, | |
| "learning_rate": 4.42100538599641e-06, | |
| "loss": 0.31437077522277834, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25157232704402516, | |
| "grad_norm": 0.5149464011192322, | |
| "learning_rate": 4.376122082585278e-06, | |
| "loss": 0.30969116687774656, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2695417789757412, | |
| "grad_norm": 0.4815337657928467, | |
| "learning_rate": 4.331238779174148e-06, | |
| "loss": 0.31036303043365476, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28751123090745734, | |
| "grad_norm": 0.4882141053676605, | |
| "learning_rate": 4.286355475763016e-06, | |
| "loss": 0.30779433250427246, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3054806828391734, | |
| "grad_norm": 0.47035127878189087, | |
| "learning_rate": 4.241472172351886e-06, | |
| "loss": 0.3062736511230469, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32345013477088946, | |
| "grad_norm": 0.47444701194763184, | |
| "learning_rate": 4.196588868940754e-06, | |
| "loss": 0.30041847229003904, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3414195867026056, | |
| "grad_norm": 0.4834694564342499, | |
| "learning_rate": 4.151705565529624e-06, | |
| "loss": 0.29730544090270994, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.35938903863432164, | |
| "grad_norm": 0.508245587348938, | |
| "learning_rate": 4.106822262118492e-06, | |
| "loss": 0.30029687881469724, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 0.48643767833709717, | |
| "learning_rate": 4.061938958707361e-06, | |
| "loss": 0.29685449600219727, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3953279424977538, | |
| "grad_norm": 0.4577917456626892, | |
| "learning_rate": 4.01705565529623e-06, | |
| "loss": 0.2990954160690308, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4132973944294699, | |
| "grad_norm": 0.5375077724456787, | |
| "learning_rate": 3.9721723518850995e-06, | |
| "loss": 0.30233011245727537, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.431266846361186, | |
| "grad_norm": 0.4925467371940613, | |
| "learning_rate": 3.927289048473968e-06, | |
| "loss": 0.2941945314407349, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.44923629829290207, | |
| "grad_norm": 0.5110061168670654, | |
| "learning_rate": 3.882405745062837e-06, | |
| "loss": 0.3003401279449463, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.46720575022461813, | |
| "grad_norm": 0.44966429471969604, | |
| "learning_rate": 3.837522441651706e-06, | |
| "loss": 0.2935019016265869, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48517520215633425, | |
| "grad_norm": 0.49473223090171814, | |
| "learning_rate": 3.792639138240575e-06, | |
| "loss": 0.2941242218017578, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5031446540880503, | |
| "grad_norm": 0.4826172888278961, | |
| "learning_rate": 3.7477558348294435e-06, | |
| "loss": 0.2936396598815918, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5211141060197664, | |
| "grad_norm": 0.5087786316871643, | |
| "learning_rate": 3.702872531418313e-06, | |
| "loss": 0.28728442192077636, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5390835579514824, | |
| "grad_norm": 0.45754265785217285, | |
| "learning_rate": 3.6579892280071814e-06, | |
| "loss": 0.29381372928619387, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5570530098831986, | |
| "grad_norm": 0.47864410281181335, | |
| "learning_rate": 3.6131059245960504e-06, | |
| "loss": 0.28871979713439944, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5750224618149147, | |
| "grad_norm": 0.446613073348999, | |
| "learning_rate": 3.5682226211849198e-06, | |
| "loss": 0.2919660806655884, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5929919137466307, | |
| "grad_norm": 0.5203211903572083, | |
| "learning_rate": 3.5233393177737883e-06, | |
| "loss": 0.2949108600616455, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6109613656783468, | |
| "grad_norm": 0.5251737236976624, | |
| "learning_rate": 3.4784560143626573e-06, | |
| "loss": 0.28940815925598146, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6289308176100629, | |
| "grad_norm": 0.4626797139644623, | |
| "learning_rate": 3.4335727109515267e-06, | |
| "loss": 0.2877013683319092, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6469002695417789, | |
| "grad_norm": 0.5425576567649841, | |
| "learning_rate": 3.3886894075403952e-06, | |
| "loss": 0.28816981315612794, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6648697214734951, | |
| "grad_norm": 0.5507893562316895, | |
| "learning_rate": 3.343806104129264e-06, | |
| "loss": 0.28344998359680174, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6828391734052112, | |
| "grad_norm": 0.45895373821258545, | |
| "learning_rate": 3.2989228007181327e-06, | |
| "loss": 0.28453927040100097, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7008086253369272, | |
| "grad_norm": 0.47491055727005005, | |
| "learning_rate": 3.254039497307002e-06, | |
| "loss": 0.27885701656341555, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7187780772686433, | |
| "grad_norm": 0.4567403793334961, | |
| "learning_rate": 3.209156193895871e-06, | |
| "loss": 0.2846828937530518, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7367475292003594, | |
| "grad_norm": 0.506420910358429, | |
| "learning_rate": 3.1642728904847396e-06, | |
| "loss": 0.2884047269821167, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 0.4960302710533142, | |
| "learning_rate": 3.119389587073609e-06, | |
| "loss": 0.28609886169433596, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7726864330637916, | |
| "grad_norm": 0.44618239998817444, | |
| "learning_rate": 3.074506283662478e-06, | |
| "loss": 0.2808084487915039, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7906558849955077, | |
| "grad_norm": 0.45904698967933655, | |
| "learning_rate": 3.0296229802513465e-06, | |
| "loss": 0.28656601905822754, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8086253369272237, | |
| "grad_norm": 0.5420985817909241, | |
| "learning_rate": 2.984739676840216e-06, | |
| "loss": 0.2885767936706543, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8265947888589398, | |
| "grad_norm": 0.49061647057533264, | |
| "learning_rate": 2.939856373429085e-06, | |
| "loss": 0.28384861946105955, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.8445642407906558, | |
| "grad_norm": 0.5167312026023865, | |
| "learning_rate": 2.8949730700179535e-06, | |
| "loss": 0.28023710250854494, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.862533692722372, | |
| "grad_norm": 0.46029844880104065, | |
| "learning_rate": 2.8500897666068224e-06, | |
| "loss": 0.280789852142334, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8805031446540881, | |
| "grad_norm": 0.44982901215553284, | |
| "learning_rate": 2.8052064631956914e-06, | |
| "loss": 0.27998642921447753, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8984725965858041, | |
| "grad_norm": 0.4832385182380676, | |
| "learning_rate": 2.7603231597845604e-06, | |
| "loss": 0.2860716819763184, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9164420485175202, | |
| "grad_norm": 0.5139860510826111, | |
| "learning_rate": 2.715439856373429e-06, | |
| "loss": 0.2779590845108032, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9344115004492363, | |
| "grad_norm": 0.4550414979457855, | |
| "learning_rate": 2.6705565529622983e-06, | |
| "loss": 0.2789080381393433, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.4613369107246399, | |
| "learning_rate": 2.6256732495511673e-06, | |
| "loss": 0.28540740013122556, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9703504043126685, | |
| "grad_norm": 0.45095086097717285, | |
| "learning_rate": 2.580789946140036e-06, | |
| "loss": 0.276381254196167, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9883198562443846, | |
| "grad_norm": 0.48203322291374207, | |
| "learning_rate": 2.535906642728905e-06, | |
| "loss": 0.2832359790802002, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.005390835579515, | |
| "grad_norm": 0.4708728492259979, | |
| "learning_rate": 2.491023339317774e-06, | |
| "loss": 0.2769860029220581, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.0233602875112309, | |
| "grad_norm": 0.4912715554237366, | |
| "learning_rate": 2.4461400359066427e-06, | |
| "loss": 0.2540097713470459, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.041329739442947, | |
| "grad_norm": 0.48824694752693176, | |
| "learning_rate": 2.4012567324955117e-06, | |
| "loss": 0.2609401226043701, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.059299191374663, | |
| "grad_norm": 0.4870210289955139, | |
| "learning_rate": 2.356373429084381e-06, | |
| "loss": 0.25025138854980467, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.0772686433063792, | |
| "grad_norm": 0.5163658261299133, | |
| "learning_rate": 2.3114901256732496e-06, | |
| "loss": 0.25263664722442625, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0952380952380953, | |
| "grad_norm": 0.5006254315376282, | |
| "learning_rate": 2.2666068222621186e-06, | |
| "loss": 0.25940570831298826, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.1132075471698113, | |
| "grad_norm": 0.511043131351471, | |
| "learning_rate": 2.2217235188509876e-06, | |
| "loss": 0.2521126508712769, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.1311769991015275, | |
| "grad_norm": 0.49282217025756836, | |
| "learning_rate": 2.1768402154398565e-06, | |
| "loss": 0.25096635818481444, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.1491464510332434, | |
| "grad_norm": 0.5031591653823853, | |
| "learning_rate": 2.1319569120287255e-06, | |
| "loss": 0.2539719581604004, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.1671159029649596, | |
| "grad_norm": 0.5004000067710876, | |
| "learning_rate": 2.0870736086175945e-06, | |
| "loss": 0.2542546510696411, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1850853548966755, | |
| "grad_norm": 0.47906896471977234, | |
| "learning_rate": 2.0421903052064634e-06, | |
| "loss": 0.2506051778793335, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.2030548068283917, | |
| "grad_norm": 0.5111077427864075, | |
| "learning_rate": 1.9973070017953324e-06, | |
| "loss": 0.2501336336135864, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.221024258760108, | |
| "grad_norm": 0.46470290422439575, | |
| "learning_rate": 1.9524236983842014e-06, | |
| "loss": 0.2527280330657959, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.2389937106918238, | |
| "grad_norm": 0.49279844760894775, | |
| "learning_rate": 1.9075403949730703e-06, | |
| "loss": 0.25149285793304443, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.25696316262354, | |
| "grad_norm": 0.48192131519317627, | |
| "learning_rate": 1.862657091561939e-06, | |
| "loss": 0.2485593795776367, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2749326145552562, | |
| "grad_norm": 0.49026069045066833, | |
| "learning_rate": 1.817773788150808e-06, | |
| "loss": 0.24832606315612793, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.2929020664869721, | |
| "grad_norm": 0.46640709042549133, | |
| "learning_rate": 1.7728904847396768e-06, | |
| "loss": 0.2521926164627075, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.310871518418688, | |
| "grad_norm": 0.5054717063903809, | |
| "learning_rate": 1.728007181328546e-06, | |
| "loss": 0.25048768520355225, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.3288409703504043, | |
| "grad_norm": 0.4634091258049011, | |
| "learning_rate": 1.683123877917415e-06, | |
| "loss": 0.24852404594421387, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.3468104222821204, | |
| "grad_norm": 0.4614594578742981, | |
| "learning_rate": 1.6382405745062837e-06, | |
| "loss": 0.2514226198196411, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.3647798742138364, | |
| "grad_norm": 0.5008041262626648, | |
| "learning_rate": 1.593357271095153e-06, | |
| "loss": 0.2507458686828613, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.3827493261455526, | |
| "grad_norm": 0.47305938601493835, | |
| "learning_rate": 1.5484739676840217e-06, | |
| "loss": 0.2497103691101074, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.4007187780772687, | |
| "grad_norm": 0.5139908194541931, | |
| "learning_rate": 1.5035906642728906e-06, | |
| "loss": 0.24853968620300293, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.4186882300089847, | |
| "grad_norm": 0.4631156027317047, | |
| "learning_rate": 1.4587073608617596e-06, | |
| "loss": 0.248740816116333, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.4366576819407009, | |
| "grad_norm": 0.47681012749671936, | |
| "learning_rate": 1.4138240574506283e-06, | |
| "loss": 0.2534752368927002, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4546271338724168, | |
| "grad_norm": 0.4538913667201996, | |
| "learning_rate": 1.3689407540394975e-06, | |
| "loss": 0.24337444305419922, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.472596585804133, | |
| "grad_norm": 0.48104986548423767, | |
| "learning_rate": 1.3240574506283663e-06, | |
| "loss": 0.2502609729766846, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.490566037735849, | |
| "grad_norm": 0.4610423147678375, | |
| "learning_rate": 1.2791741472172353e-06, | |
| "loss": 0.24652738571166993, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.5085354896675651, | |
| "grad_norm": 0.4587244689464569, | |
| "learning_rate": 1.2342908438061042e-06, | |
| "loss": 0.25362207889556887, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.5265049415992813, | |
| "grad_norm": 0.4708814322948456, | |
| "learning_rate": 1.1894075403949732e-06, | |
| "loss": 0.24814538955688475, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.5444743935309972, | |
| "grad_norm": 0.4898167550563812, | |
| "learning_rate": 1.144524236983842e-06, | |
| "loss": 0.2517171621322632, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.5624438454627134, | |
| "grad_norm": 0.5054773688316345, | |
| "learning_rate": 1.0996409335727111e-06, | |
| "loss": 0.25095720291137696, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.5804132973944296, | |
| "grad_norm": 0.5150067806243896, | |
| "learning_rate": 1.05475763016158e-06, | |
| "loss": 0.25122294425964353, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.5983827493261455, | |
| "grad_norm": 0.44859108328819275, | |
| "learning_rate": 1.0098743267504488e-06, | |
| "loss": 0.24518187046051027, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.6163522012578615, | |
| "grad_norm": 0.4460717737674713, | |
| "learning_rate": 9.649910233393178e-07, | |
| "loss": 0.25164237022399905, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6343216531895777, | |
| "grad_norm": 0.4884060323238373, | |
| "learning_rate": 9.201077199281867e-07, | |
| "loss": 0.2497255325317383, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.6522911051212938, | |
| "grad_norm": 0.4527634084224701, | |
| "learning_rate": 8.752244165170558e-07, | |
| "loss": 0.2494762897491455, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.6702605570530098, | |
| "grad_norm": 0.47182497382164, | |
| "learning_rate": 8.303411131059247e-07, | |
| "loss": 0.24840357303619384, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.688230008984726, | |
| "grad_norm": 0.4759376347064972, | |
| "learning_rate": 7.854578096947936e-07, | |
| "loss": 0.25184221267700196, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.7061994609164421, | |
| "grad_norm": 0.495343416929245, | |
| "learning_rate": 7.405745062836626e-07, | |
| "loss": 0.25055861473083496, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.724168912848158, | |
| "grad_norm": 0.5005154609680176, | |
| "learning_rate": 6.956912028725314e-07, | |
| "loss": 0.25119876861572266, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.742138364779874, | |
| "grad_norm": 0.47676777839660645, | |
| "learning_rate": 6.508078994614005e-07, | |
| "loss": 0.2516517162322998, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.7601078167115904, | |
| "grad_norm": 0.4394581913948059, | |
| "learning_rate": 6.059245960502694e-07, | |
| "loss": 0.250733470916748, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.7780772686433064, | |
| "grad_norm": 0.4702657163143158, | |
| "learning_rate": 5.610412926391383e-07, | |
| "loss": 0.2478208065032959, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.7960467205750223, | |
| "grad_norm": 0.4843612611293793, | |
| "learning_rate": 5.161579892280072e-07, | |
| "loss": 0.24935145378112794, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.8140161725067385, | |
| "grad_norm": 0.4673105776309967, | |
| "learning_rate": 4.7127468581687615e-07, | |
| "loss": 0.24984090328216552, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.8319856244384547, | |
| "grad_norm": 0.4820215404033661, | |
| "learning_rate": 4.2639138240574507e-07, | |
| "loss": 0.24917204380035402, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.8499550763701706, | |
| "grad_norm": 0.45277148485183716, | |
| "learning_rate": 3.815080789946141e-07, | |
| "loss": 0.24739840030670165, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.8679245283018868, | |
| "grad_norm": 0.48467275500297546, | |
| "learning_rate": 3.3662477558348295e-07, | |
| "loss": 0.24694859981536865, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.885893980233603, | |
| "grad_norm": 0.46758314967155457, | |
| "learning_rate": 2.917414721723519e-07, | |
| "loss": 0.24703009128570558, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.903863432165319, | |
| "grad_norm": 0.4634384512901306, | |
| "learning_rate": 2.4685816876122083e-07, | |
| "loss": 0.2495879650115967, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.921832884097035, | |
| "grad_norm": 0.4621906578540802, | |
| "learning_rate": 2.0197486535008978e-07, | |
| "loss": 0.25526316165924073, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.939802336028751, | |
| "grad_norm": 0.46646031737327576, | |
| "learning_rate": 1.5709156193895872e-07, | |
| "loss": 0.24767594337463378, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.9577717879604672, | |
| "grad_norm": 0.4569203555583954, | |
| "learning_rate": 1.1220825852782766e-07, | |
| "loss": 0.24955098628997802, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.9757412398921832, | |
| "grad_norm": 0.47747698426246643, | |
| "learning_rate": 6.732495511669659e-08, | |
| "loss": 0.2489546775817871, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 0.47046294808387756, | |
| "learning_rate": 2.2441651705565532e-08, | |
| "loss": 0.24430301189422607, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1114, | |
| "total_flos": 1.4534558685629252e+19, | |
| "train_loss": 0.27833450065266935, | |
| "train_runtime": 6971.6374, | |
| "train_samples_per_second": 20.435, | |
| "train_steps_per_second": 0.16 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1114, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.4534558685629252e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |