Text Generation
Transformers
TensorBoard
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lldois/v16_rec_cot_pattern_clean_lr15e6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lldois/v16_rec_cot_pattern_clean_lr15e6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lldois/v16_rec_cot_pattern_clean_lr15e6") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lldois/v16_rec_cot_pattern_clean_lr15e6") model = AutoModelForCausalLM.from_pretrained("lldois/v16_rec_cot_pattern_clean_lr15e6", 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 lldois/v16_rec_cot_pattern_clean_lr15e6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lldois/v16_rec_cot_pattern_clean_lr15e6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lldois/v16_rec_cot_pattern_clean_lr15e6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lldois/v16_rec_cot_pattern_clean_lr15e6
- SGLang
How to use lldois/v16_rec_cot_pattern_clean_lr15e6 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 "lldois/v16_rec_cot_pattern_clean_lr15e6" \ --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": "lldois/v16_rec_cot_pattern_clean_lr15e6", "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 "lldois/v16_rec_cot_pattern_clean_lr15e6" \ --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": "lldois/v16_rec_cot_pattern_clean_lr15e6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lldois/v16_rec_cot_pattern_clean_lr15e6 with Docker Model Runner:
docker model run hf.co/lldois/v16_rec_cot_pattern_clean_lr15e6
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 664, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007535795026375283, | |
| "grad_norm": 58.0, | |
| "learning_rate": 3e-06, | |
| "loss": 3.0889440536499024, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015071590052750565, | |
| "grad_norm": 18.25, | |
| "learning_rate": 6.750000000000001e-06, | |
| "loss": 2.845233154296875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02260738507912585, | |
| "grad_norm": 6.625, | |
| "learning_rate": 1.05e-05, | |
| "loss": 2.5583972930908203, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03014318010550113, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.4249999999999999e-05, | |
| "loss": 2.399222183227539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.037678975131876416, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 1.4998572206235544e-05, | |
| "loss": 2.1797840118408205, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0452147701582517, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.4992772725756523e-05, | |
| "loss": 1.9999149322509766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05275056518462698, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 1.4982515768929044e-05, | |
| "loss": 1.922983741760254, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06028636021100226, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.4967807437652124e-05, | |
| "loss": 1.8583049774169922, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06782215523737754, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 1.4948656481962783e-05, | |
| "loss": 1.7922269821166992, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07535795026375283, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.4925074294830649e-05, | |
| "loss": 1.7535554885864257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0828937452901281, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.4897074905380211e-05, | |
| "loss": 1.7319807052612304, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0904295403165034, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.486467497054487e-05, | |
| "loss": 1.6926809310913087, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09796533534287867, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.4827893765157653e-05, | |
| "loss": 1.6913116455078125, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10550113036925396, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 1.4786753170484561e-05, | |
| "loss": 1.648867416381836, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11303692539562923, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.474127766120732e-05, | |
| "loss": 1.6269556045532227, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.12057272042200452, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 1.4691494290863313e-05, | |
| "loss": 1.6556577682495117, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1281085154483798, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.4637432675751334e-05, | |
| "loss": 1.6556646347045898, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1356443104747551, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.4579124977312757e-05, | |
| "loss": 1.595597267150879, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14318010550113036, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.4516605882998572e-05, | |
| "loss": 1.6290622711181642, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.15071590052750566, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.4449912585633709e-05, | |
| "loss": 1.6448266983032227, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15825169555388094, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.4379084761290898e-05, | |
| "loss": 1.5661279678344726, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.1657874905802562, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.4304164545687233e-05, | |
| "loss": 1.5793392181396484, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1733232856066315, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.4225196509117487e-05, | |
| "loss": 1.5613231658935547, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1808590806330068, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 1.4142227629939096e-05, | |
| "loss": 1.6571407318115234, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18839487565938207, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.4055307266624572e-05, | |
| "loss": 1.5722612380981444, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19593067068575734, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.3964487128397966e-05, | |
| "loss": 1.5921846389770509, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20346646571213264, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.386982124447289e-05, | |
| "loss": 1.555877113342285, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.21100226073850792, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.3771365931910332e-05, | |
| "loss": 1.5413886070251466, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2185380557648832, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.3669179762115459e-05, | |
| "loss": 1.542860507965088, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.22607385079125847, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.3563323525993275e-05, | |
| "loss": 1.5646774291992187, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23360964581763377, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.345386019778391e-05, | |
| "loss": 1.5369146347045899, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.24114544084400905, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 1.3340854897599017e-05, | |
| "loss": 1.5391293525695802, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.24868123587038432, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.3224374852681604e-05, | |
| "loss": 1.5518495559692382, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.2562170308967596, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 1.3104489357412308e-05, | |
| "loss": 1.5065268516540526, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.26375282592313487, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 1.2981269732085932e-05, | |
| "loss": 1.5436999320983886, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2712886209495102, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.2854789280482752e-05, | |
| "loss": 1.5034493446350097, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2788244159758855, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.272512324625985e-05, | |
| "loss": 1.5417941093444825, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2863602110022607, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 1.2592348768188394e-05, | |
| "loss": 1.5073047637939454, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.293896006028636, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.2456544834263536e-05, | |
| "loss": 1.501516342163086, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.30143180105501133, | |
| "grad_norm": 2.71875, | |
| "learning_rate": 1.231779223471416e-05, | |
| "loss": 1.51112642288208, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3089675960813866, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.2176173513940502e-05, | |
| "loss": 1.4900212287902832, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.3165033911077619, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.2031772921408209e-05, | |
| "loss": 1.5136810302734376, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3240391861341371, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.1884676361528035e-05, | |
| "loss": 1.5209362030029296, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.3315749811605124, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 1.173497134255101e-05, | |
| "loss": 1.5429197311401368, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.33911077618688773, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.1582746924509483e-05, | |
| "loss": 1.4890120506286622, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.346646571213263, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 1.1428093666235e-05, | |
| "loss": 1.5285821914672852, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3541823662396383, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 1.1271103571484538e-05, | |
| "loss": 1.526703453063965, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.3617181612660136, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 1.1111870034207164e-05, | |
| "loss": 1.548676109313965, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.36925395629238883, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 1.0950487782983642e-05, | |
| "loss": 1.5409740447998046, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.37678975131876413, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.0787052824672073e-05, | |
| "loss": 1.4851038932800293, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.38432554634513943, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.062166238729309e-05, | |
| "loss": 1.4853837013244628, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.3918613413715147, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 1.0454414862188575e-05, | |
| "loss": 1.4933822631835938, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.39939713639789, | |
| "grad_norm": 2.0, | |
| "learning_rate": 1.0285409745488301e-05, | |
| "loss": 1.498341941833496, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.4069329314242653, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 1.0114747578919347e-05, | |
| "loss": 1.4747099876403809, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.41446872645064053, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 9.942529889993475e-06, | |
| "loss": 1.4785110473632812, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.42200452147701584, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 9.76885913160807e-06, | |
| "loss": 1.480055046081543, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4295403165033911, | |
| "grad_norm": 2.125, | |
| "learning_rate": 9.593838621096545e-06, | |
| "loss": 1.5196352005004883, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.4370761115297664, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 9.417572478764514e-06, | |
| "loss": 1.4994166374206543, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4446119065561417, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 9.24016556594826e-06, | |
| "loss": 1.4789586067199707, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.45214770158251694, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 9.061723422632362e-06, | |
| "loss": 1.4982659339904785, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.45968349660889224, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 8.882352204663596e-06, | |
| "loss": 1.476920223236084, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.46721929163526754, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 8.702158620598451e-06, | |
| "loss": 1.4496073722839355, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4747550866616428, | |
| "grad_norm": 1.9140625, | |
| "learning_rate": 8.52124986822185e-06, | |
| "loss": 1.4702765464782714, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.4822908816880181, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 8.33973357077481e-06, | |
| "loss": 1.4745065689086914, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4898266767143934, | |
| "grad_norm": 2.0, | |
| "learning_rate": 8.157717712929003e-06, | |
| "loss": 1.454655933380127, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.49736247174076864, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 7.975310576546317e-06, | |
| "loss": 1.4913531303405763, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5048982667671439, | |
| "grad_norm": 2.125, | |
| "learning_rate": 7.792620676261575e-06, | |
| "loss": 1.5276828765869142, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.5124340617935192, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 7.609756694926835e-06, | |
| "loss": 1.4632510185241698, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5199698568198945, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 7.426827418955565e-06, | |
| "loss": 1.448787307739258, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.5275056518462697, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 7.243941673605241e-06, | |
| "loss": 1.4877211570739746, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5350414468726451, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 7.061208258236822e-06, | |
| "loss": 1.455491542816162, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.5425772418990203, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 6.878735881589636e-06, | |
| "loss": 1.5123778343200684, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5501130369253956, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 6.69663309711017e-06, | |
| "loss": 1.4607969284057618, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.557648831951771, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 6.515008238373259e-06, | |
| "loss": 1.4584217071533203, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5651846269781462, | |
| "grad_norm": 2.0, | |
| "learning_rate": 6.333969354634067e-06, | |
| "loss": 1.4549072265625, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5727204220045214, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 6.153624146549206e-06, | |
| "loss": 1.4819585800170898, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5802562170308968, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 5.974079902105248e-06, | |
| "loss": 1.4508701324462892, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.587792012057272, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 5.795443432792731e-06, | |
| "loss": 1.462479591369629, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5953278070836473, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 5.61782101006364e-06, | |
| "loss": 1.4645420074462892, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.6028636021100227, | |
| "grad_norm": 1.859375, | |
| "learning_rate": 5.441318302110143e-06, | |
| "loss": 1.4418591499328612, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6103993971363979, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 5.266040311002226e-06, | |
| "loss": 1.5144804000854493, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.6179351921627732, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 5.092091310221597e-06, | |
| "loss": 1.5230363845825194, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6254709871891485, | |
| "grad_norm": 1.875, | |
| "learning_rate": 4.919574782629037e-06, | |
| "loss": 1.4765286445617676, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.6330067822155238, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 4.748593358902078e-06, | |
| "loss": 1.5008271217346192, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.640542577241899, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 4.5792487564796675e-06, | |
| "loss": 1.4626501083374024, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.6480783722682742, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 4.411641719050116e-06, | |
| "loss": 1.4993659019470216, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6556141672946496, | |
| "grad_norm": 2.484375, | |
| "learning_rate": 4.245871956618314e-06, | |
| "loss": 1.4285595893859864, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.6631499623210249, | |
| "grad_norm": 2.09375, | |
| "learning_rate": 4.082038086187931e-06, | |
| "loss": 1.4569740295410156, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6706857573474001, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 3.920237573093791e-06, | |
| "loss": 1.4318285942077638, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.6782215523737755, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 3.760566673019431e-06, | |
| "loss": 1.5205245971679688, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6857573474001507, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 3.60312037473425e-06, | |
| "loss": 1.4765802383422852, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.693293142426526, | |
| "grad_norm": 2.796875, | |
| "learning_rate": 3.447992343584366e-06, | |
| "loss": 1.5107611656188964, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7008289374529013, | |
| "grad_norm": 1.8828125, | |
| "learning_rate": 3.2952748657707867e-06, | |
| "loss": 1.4483990669250488, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.7083647324792766, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 3.1450587934480145e-06, | |
| "loss": 1.4701973915100097, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7159005275056518, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 2.997433490675795e-06, | |
| "loss": 1.4567836761474608, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7234363225320272, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 2.852486780256132e-06, | |
| "loss": 1.4270059585571289, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7309721175584024, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 2.7103048914871928e-06, | |
| "loss": 1.4407997131347656, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.7385079125847777, | |
| "grad_norm": 1.8515625, | |
| "learning_rate": 2.5709724088652055e-06, | |
| "loss": 1.4887385368347168, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.746043707611153, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 2.4345722217648545e-06, | |
| "loss": 1.4913487434387207, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.7535795026375283, | |
| "grad_norm": 1.7890625, | |
| "learning_rate": 2.3011854751280943e-06, | |
| "loss": 1.4571470260620116, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7611152976639035, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 2.1708915211907504e-06, | |
| "loss": 1.4817148208618165, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.7686510926902789, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 2.043767872275602e-06, | |
| "loss": 1.5055496215820312, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7761868877166541, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 1.9198901546800303e-06, | |
| "loss": 1.4234349250793457, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.7837226827430294, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 1.799332063685672e-06, | |
| "loss": 1.4568108558654784, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7912584777694047, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 1.6821653197168508e-06, | |
| "loss": 1.4333107948303223, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.79879427279578, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.5684596256738372e-06, | |
| "loss": 1.460732364654541, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8063300678221552, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.4582826254663603e-06, | |
| "loss": 1.4648653984069824, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.8138658628485306, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.3516998637720101e-06, | |
| "loss": 1.4746587753295899, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8214016578749058, | |
| "grad_norm": 1.875, | |
| "learning_rate": 1.2487747470434843e-06, | |
| "loss": 1.4301054000854492, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.8289374529012811, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.1495685057878691e-06, | |
| "loss": 1.4414166450500487, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8364732479276563, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.0541401581403993e-06, | |
| "loss": 1.4925739288330078, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.8440090429540317, | |
| "grad_norm": 1.9140625, | |
| "learning_rate": 9.625464747543647e-07, | |
| "loss": 1.5180048942565918, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8515448379804069, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 8.748419450280614e-07, | |
| "loss": 1.5134897232055664, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.8590806330067822, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 7.910787446888473e-07, | |
| "loss": 1.4737462997436523, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.8666164280331575, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 7.113067047536293e-07, | |
| "loss": 1.4445390701293945, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.8741522230595328, | |
| "grad_norm": 2.203125, | |
| "learning_rate": 6.355732818842191e-07, | |
| "loss": 1.4534795761108399, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.881688018085908, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 5.639235301552015e-07, | |
| "loss": 1.4963753700256348, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.8892238131122834, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 4.964000742511082e-07, | |
| "loss": 1.446830654144287, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8967596081386586, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 4.33043084108847e-07, | |
| "loss": 1.4866412162780762, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.9042954031650339, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 3.73890251020467e-07, | |
| "loss": 1.465456485748291, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9118311981914092, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 3.1897676521048e-07, | |
| "loss": 1.4540048599243165, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.9193669932177845, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 2.683352949010759e-07, | |
| "loss": 1.4424663543701173, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9269027882441597, | |
| "grad_norm": 2.46875, | |
| "learning_rate": 2.2199596687767943e-07, | |
| "loss": 1.4640046119689942, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.9344385832705351, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.7998634856642575e-07, | |
| "loss": 1.4832847595214844, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9419743782969103, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.4233143163420338e-07, | |
| "loss": 1.4776354789733888, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.9495101733232856, | |
| "grad_norm": 1.9609375, | |
| "learning_rate": 1.0905361712102352e-07, | |
| "loss": 1.5160974502563476, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9570459683496609, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 8.01727021135662e-08, | |
| "loss": 1.4372377395629883, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.9645817633760362, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 5.570586796782351e-08, | |
| "loss": 1.4696691513061524, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9721175584024114, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 3.566767008784999e-08, | |
| "loss": 1.505112075805664, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.9796533534287868, | |
| "grad_norm": 2.28125, | |
| "learning_rate": 2.0070029266709145e-08, | |
| "loss": 1.512413787841797, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.987189148455162, | |
| "grad_norm": 2.75, | |
| "learning_rate": 8.922224594743733e-09, | |
| "loss": 1.4716434478759766, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.9947249434815373, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 2.2308879394189464e-09, | |
| "loss": 1.4296034812927245, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 664, | |
| "total_flos": 3.202384716355461e+17, | |
| "train_loss": 1.559677630303854, | |
| "train_runtime": 5251.4031, | |
| "train_samples_per_second": 0.505, | |
| "train_steps_per_second": 0.126 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 664, | |
| "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": 3.202384716355461e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |