Text Generation
PEFT
Safetensors
English
named-entity-recognition
chain-of-thought
lora
conversational
Instructions to use structured-cot-ner/qwen3-8b-structured-cot-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use structured-cot-ner/qwen3-8b-structured-cot-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "structured-cot-ner/qwen3-8b-structured-cot-lora") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from structured-cot-ner/qwen3-8b-structured-cot-lora: direct link, hf CLI and curl.
- Browser
- Download file 19.6 kB
-
https://huggingface.co/structured-cot-ner/qwen3-8b-structured-cot-lora/resolve/main/trainer_state.json
- Command line
-
hf download hf://structured-cot-ner/qwen3-8b-structured-cot-lora/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/structured-cot-ner/qwen3-8b-structured-cot-lora/resolve/main/trainer_state.json
19.6 kB
| { | |
| "best_global_step": 900, | |
| "best_metric": 0.4949971139431, | |
| "best_model_checkpoint": "/outputs/work/qwen3-8b_structured/checkpoints/checkpoint-900", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 908, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02203856749311295, | |
| "grad_norm": 1.1401411294937134, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2701135635375977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0440771349862259, | |
| "grad_norm": 0.3902525007724762, | |
| "learning_rate": 7.037037037037038e-05, | |
| "loss": 0.9818595886230469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 0.38093724846839905, | |
| "learning_rate": 9.999872841297521e-05, | |
| "loss": 0.8187281608581543, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "grad_norm": 0.5122030377388, | |
| "learning_rate": 9.995422965786025e-05, | |
| "loss": 0.7376741409301758, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11019283746556474, | |
| "grad_norm": 0.34034839272499084, | |
| "learning_rate": 9.984621621406273e-05, | |
| "loss": 0.6827547073364257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 0.4963107109069824, | |
| "learning_rate": 9.96748254161048e-05, | |
| "loss": 0.6902705669403076, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15426997245179064, | |
| "grad_norm": 0.3839806020259857, | |
| "learning_rate": 9.944027518013187e-05, | |
| "loss": 0.6199728488922119, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1763085399449036, | |
| "grad_norm": 0.4156777858734131, | |
| "learning_rate": 9.914286372684153e-05, | |
| "loss": 0.5803644180297851, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19834710743801653, | |
| "grad_norm": 0.3978594243526459, | |
| "learning_rate": 9.878296920230869e-05, | |
| "loss": 0.622033166885376, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22038567493112948, | |
| "grad_norm": 0.5015684366226196, | |
| "learning_rate": 9.83610491971886e-05, | |
| "loss": 0.6321930885314941, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22038567493112948, | |
| "eval_loss": 0.6008290648460388, | |
| "eval_runtime": 21.1469, | |
| "eval_samples_per_second": 9.079, | |
| "eval_steps_per_second": 9.079, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.5182624459266663, | |
| "learning_rate": 9.787764016490992e-05, | |
| "loss": 0.6228323459625245, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 0.3285966217517853, | |
| "learning_rate": 9.733335673959671e-05, | |
| "loss": 0.5916787624359131, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2865013774104683, | |
| "grad_norm": 0.5432491302490234, | |
| "learning_rate": 9.672889095458734e-05, | |
| "loss": 0.5869779586791992, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3085399449035813, | |
| "grad_norm": 0.4267979562282562, | |
| "learning_rate": 9.606501136254327e-05, | |
| "loss": 0.5515089511871338, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3305785123966942, | |
| "grad_norm": 0.4595358967781067, | |
| "learning_rate": 9.534256205826684e-05, | |
| "loss": 0.593355369567871, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3526170798898072, | |
| "grad_norm": 0.4213317334651947, | |
| "learning_rate": 9.456246160547057e-05, | |
| "loss": 0.5493035316467285, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3746556473829201, | |
| "grad_norm": 0.4837833344936371, | |
| "learning_rate": 9.372570186886225e-05, | |
| "loss": 0.5423605442047119, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": 0.4311801791191101, | |
| "learning_rate": 9.283334675303084e-05, | |
| "loss": 0.5765563011169433, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.418732782369146, | |
| "grad_norm": 0.5369383096694946, | |
| "learning_rate": 9.188653084973692e-05, | |
| "loss": 0.576381778717041, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.44077134986225897, | |
| "grad_norm": 0.5688263773918152, | |
| "learning_rate": 9.088645799532729e-05, | |
| "loss": 0.5475176811218262, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44077134986225897, | |
| "eval_loss": 0.5566205978393555, | |
| "eval_runtime": 20.9583, | |
| "eval_samples_per_second": 9.161, | |
| "eval_steps_per_second": 9.161, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4628099173553719, | |
| "grad_norm": 0.3890785574913025, | |
| "learning_rate": 8.983439974010794e-05, | |
| "loss": 0.5584116458892823, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.41449877619743347, | |
| "learning_rate": 8.873169373162174e-05, | |
| "loss": 0.5648072242736817, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5068870523415978, | |
| "grad_norm": 0.4085931181907654, | |
| "learning_rate": 8.757974201388605e-05, | |
| "loss": 0.5412596702575684, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 0.508404016494751, | |
| "learning_rate": 8.638000924475336e-05, | |
| "loss": 0.5485456943511963, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5509641873278237, | |
| "grad_norm": 0.4558800160884857, | |
| "learning_rate": 8.513402083366054e-05, | |
| "loss": 0.5300729274749756, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5730027548209367, | |
| "grad_norm": 0.3980095088481903, | |
| "learning_rate": 8.384336100213546e-05, | |
| "loss": 0.5038699150085449, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5950413223140496, | |
| "grad_norm": 0.47308093309402466, | |
| "learning_rate": 8.250967076952635e-05, | |
| "loss": 0.5360618114471436, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6170798898071626, | |
| "grad_norm": 0.5327685475349426, | |
| "learning_rate": 8.113464586651516e-05, | |
| "loss": 0.5388988018035888, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6391184573002755, | |
| "grad_norm": 0.47439834475517273, | |
| "learning_rate": 7.972003457906773e-05, | |
| "loss": 0.5647876262664795, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "grad_norm": 0.5317543745040894, | |
| "learning_rate": 7.826763552556222e-05, | |
| "loss": 0.5195149898529052, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "eval_loss": 0.5337637066841125, | |
| "eval_runtime": 23.5212, | |
| "eval_samples_per_second": 8.163, | |
| "eval_steps_per_second": 8.163, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6831955922865014, | |
| "grad_norm": 0.5223919749259949, | |
| "learning_rate": 7.677929536992194e-05, | |
| "loss": 0.5164742946624756, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7052341597796143, | |
| "grad_norm": 0.5431264638900757, | |
| "learning_rate": 7.525690647366032e-05, | |
| "loss": 0.540907335281372, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.4425135850906372, | |
| "learning_rate": 7.370240448982344e-05, | |
| "loss": 0.5571293354034423, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7493112947658402, | |
| "grad_norm": 0.589937686920166, | |
| "learning_rate": 7.211776590188898e-05, | |
| "loss": 0.5385405540466308, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7713498622589532, | |
| "grad_norm": 0.4778389036655426, | |
| "learning_rate": 7.050500551075121e-05, | |
| "loss": 0.5544189453125, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": 0.4330921471118927, | |
| "learning_rate": 6.886617387298689e-05, | |
| "loss": 0.5346337795257569, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8154269972451791, | |
| "grad_norm": 0.512010395526886, | |
| "learning_rate": 6.720335469365943e-05, | |
| "loss": 0.5182302474975586, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.837465564738292, | |
| "grad_norm": 0.4975775182247162, | |
| "learning_rate": 6.551866217697602e-05, | |
| "loss": 0.5215919017791748, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.859504132231405, | |
| "grad_norm": 0.5255914926528931, | |
| "learning_rate": 6.381423833816653e-05, | |
| "loss": 0.5024703025817872, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8815426997245179, | |
| "grad_norm": 0.49004197120666504, | |
| "learning_rate": 6.209225028000173e-05, | |
| "loss": 0.5324237823486329, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8815426997245179, | |
| "eval_loss": 0.5196252465248108, | |
| "eval_runtime": 21.0828, | |
| "eval_samples_per_second": 9.107, | |
| "eval_steps_per_second": 9.107, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9035812672176309, | |
| "grad_norm": 0.5398105382919312, | |
| "learning_rate": 6.0354887437413965e-05, | |
| "loss": 0.5077178478240967, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9256198347107438, | |
| "grad_norm": 0.4676676392555237, | |
| "learning_rate": 5.860435879372319e-05, | |
| "loss": 0.5333111763000489, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9476584022038568, | |
| "grad_norm": 0.45320942997932434, | |
| "learning_rate": 5.684289007200819e-05, | |
| "loss": 0.5256590843200684, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.38904497027397156, | |
| "learning_rate": 5.5072720905193984e-05, | |
| "loss": 0.5142946243286133, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9917355371900827, | |
| "grad_norm": 0.47056928277015686, | |
| "learning_rate": 5.329610198845322e-05, | |
| "loss": 0.5223372936248779, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0132231404958678, | |
| "grad_norm": 0.5206668376922607, | |
| "learning_rate": 5.151529221754262e-05, | |
| "loss": 0.4722272872924805, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0352617079889808, | |
| "grad_norm": 0.4891754388809204, | |
| "learning_rate": 4.97325558167126e-05, | |
| "loss": 0.4602195262908936, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0573002754820937, | |
| "grad_norm": 0.5338572263717651, | |
| "learning_rate": 4.795015945984198e-05, | |
| "loss": 0.4496175289154053, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0793388429752067, | |
| "grad_norm": 0.5332434773445129, | |
| "learning_rate": 4.617036938845806e-05, | |
| "loss": 0.4558535099029541, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1013774104683196, | |
| "grad_norm": 0.4937024414539337, | |
| "learning_rate": 4.43954485303065e-05, | |
| "loss": 0.4655869483947754, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1013774104683196, | |
| "eval_loss": 0.5089902281761169, | |
| "eval_runtime": 21.272, | |
| "eval_samples_per_second": 9.026, | |
| "eval_steps_per_second": 9.026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1234159779614326, | |
| "grad_norm": 0.5879307389259338, | |
| "learning_rate": 4.2627653622134346e-05, | |
| "loss": 0.46056294441223145, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1454545454545455, | |
| "grad_norm": 0.5306437015533447, | |
| "learning_rate": 4.086923234034493e-05, | |
| "loss": 0.4482734680175781, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1674931129476585, | |
| "grad_norm": 0.5398823618888855, | |
| "learning_rate": 3.912242044317233e-05, | |
| "loss": 0.44658451080322265, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.1895316804407714, | |
| "grad_norm": 0.47986090183258057, | |
| "learning_rate": 3.738943892800951e-05, | |
| "loss": 0.4492937564849854, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2115702479338843, | |
| "grad_norm": 0.5308696031570435, | |
| "learning_rate": 3.5672491207504e-05, | |
| "loss": 0.4509594440460205, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2336088154269973, | |
| "grad_norm": 0.49206674098968506, | |
| "learning_rate": 3.397376030801215e-05, | |
| "loss": 0.48426241874694825, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2556473829201102, | |
| "grad_norm": 0.5836132764816284, | |
| "learning_rate": 3.229540609397334e-05, | |
| "loss": 0.47074213027954104, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.2776859504132232, | |
| "grad_norm": 0.5968069434165955, | |
| "learning_rate": 3.0639562521733935e-05, | |
| "loss": 0.4498295783996582, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.2997245179063361, | |
| "grad_norm": 1.1080132722854614, | |
| "learning_rate": 2.900833492631191e-05, | |
| "loss": 0.44251346588134766, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.321763085399449, | |
| "grad_norm": 0.5732438564300537, | |
| "learning_rate": 2.7403797344552696e-05, | |
| "loss": 0.47441883087158204, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.321763085399449, | |
| "eval_loss": 0.5016403198242188, | |
| "eval_runtime": 20.7631, | |
| "eval_samples_per_second": 9.247, | |
| "eval_steps_per_second": 9.247, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.343801652892562, | |
| "grad_norm": 0.6720594763755798, | |
| "learning_rate": 2.5827989878078972e-05, | |
| "loss": 0.47330598831176757, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.365840220385675, | |
| "grad_norm": 0.5719683170318604, | |
| "learning_rate": 2.428291609938786e-05, | |
| "loss": 0.44268951416015623, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.387878787878788, | |
| "grad_norm": 0.4987220764160156, | |
| "learning_rate": 2.2770540504393224e-05, | |
| "loss": 0.4402753829956055, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4099173553719009, | |
| "grad_norm": 0.6044425368309021, | |
| "learning_rate": 2.1292786014652398e-05, | |
| "loss": 0.4553673267364502, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4319559228650138, | |
| "grad_norm": 0.4916430413722992, | |
| "learning_rate": 1.9851531532452665e-05, | |
| "loss": 0.45170297622680666, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4539944903581268, | |
| "grad_norm": 0.48376408219337463, | |
| "learning_rate": 1.8448609551866647e-05, | |
| "loss": 0.4398249626159668, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.4760330578512397, | |
| "grad_norm": 0.5415279269218445, | |
| "learning_rate": 1.7085803828813546e-05, | |
| "loss": 0.46567907333374026, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.4980716253443527, | |
| "grad_norm": 0.7005756497383118, | |
| "learning_rate": 1.5764847113089094e-05, | |
| "loss": 0.42664399147033694, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.5201101928374654, | |
| "grad_norm": 0.5869502425193787, | |
| "learning_rate": 1.4487418945247438e-05, | |
| "loss": 0.4467651844024658, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5421487603305786, | |
| "grad_norm": 0.5561436414718628, | |
| "learning_rate": 1.3255143521136498e-05, | |
| "loss": 0.46412858963012693, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5421487603305786, | |
| "eval_loss": 0.4981359541416168, | |
| "eval_runtime": 20.9468, | |
| "eval_samples_per_second": 9.166, | |
| "eval_steps_per_second": 9.166, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5641873278236913, | |
| "grad_norm": 0.5624377727508545, | |
| "learning_rate": 1.206958762680157e-05, | |
| "loss": 0.44959306716918945, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.5862258953168045, | |
| "grad_norm": 0.6396487951278687, | |
| "learning_rate": 1.0932258646383336e-05, | |
| "loss": 0.466293478012085, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6082644628099172, | |
| "grad_norm": 0.6718801259994507, | |
| "learning_rate": 9.844602645542584e-06, | |
| "loss": 0.441680908203125, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6303030303030304, | |
| "grad_norm": 0.4969150722026825, | |
| "learning_rate": 8.808002532849047e-06, | |
| "loss": 0.4587891101837158, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.652341597796143, | |
| "grad_norm": 0.5307856798171997, | |
| "learning_rate": 7.823776301471591e-06, | |
| "loss": 0.44096598625183103, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.6743801652892563, | |
| "grad_norm": 0.5885487794876099, | |
| "learning_rate": 6.893175353405756e-06, | |
| "loss": 0.4387216091156006, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.696418732782369, | |
| "grad_norm": 0.5706573128700256, | |
| "learning_rate": 6.017382908369051e-06, | |
| "loss": 0.4459681510925293, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7184573002754822, | |
| "grad_norm": 0.8289659023284912, | |
| "learning_rate": 5.197512499387175e-06, | |
| "loss": 0.4737428665161133, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.7404958677685949, | |
| "grad_norm": 0.739513099193573, | |
| "learning_rate": 4.434606556983878e-06, | |
| "loss": 0.4739110469818115, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.762534435261708, | |
| "grad_norm": 0.5683160424232483, | |
| "learning_rate": 3.729635083774724e-06, | |
| "loss": 0.456526517868042, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.762534435261708, | |
| "eval_loss": 0.4956676959991455, | |
| "eval_runtime": 20.9785, | |
| "eval_samples_per_second": 9.152, | |
| "eval_steps_per_second": 9.152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7845730027548208, | |
| "grad_norm": 0.4664968252182007, | |
| "learning_rate": 3.083494421149752e-06, | |
| "loss": 0.46138567924499513, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.806611570247934, | |
| "grad_norm": 0.5488436222076416, | |
| "learning_rate": 2.49700610961342e-06, | |
| "loss": 0.4630621910095215, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8286501377410467, | |
| "grad_norm": 0.6967591643333435, | |
| "learning_rate": 1.9709158442305365e-06, | |
| "loss": 0.44054317474365234, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.8506887052341598, | |
| "grad_norm": 0.6146882772445679, | |
| "learning_rate": 1.5058925265066194e-06, | |
| "loss": 0.4166208267211914, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.8727272727272726, | |
| "grad_norm": 0.5069621801376343, | |
| "learning_rate": 1.1025274139079057e-06, | |
| "loss": 0.4469327926635742, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.8947658402203857, | |
| "grad_norm": 0.6588456630706787, | |
| "learning_rate": 7.613333681025236e-07, | |
| "loss": 0.4175694465637207, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9168044077134985, | |
| "grad_norm": 0.5935295224189758, | |
| "learning_rate": 4.827442028785655e-07, | |
| "loss": 0.45047478675842284, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9388429752066116, | |
| "grad_norm": 0.5013241171836853, | |
| "learning_rate": 2.67114132568258e-07, | |
| "loss": 0.4644434452056885, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.9608815426997244, | |
| "grad_norm": 0.49648240208625793, | |
| "learning_rate": 1.1471732167938065e-07, | |
| "loss": 0.4408588886260986, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.9829201101928375, | |
| "grad_norm": 0.5255156755447388, | |
| "learning_rate": 2.57475363067472e-08, | |
| "loss": 0.46909260749816895, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.9829201101928375, | |
| "eval_loss": 0.4949971139431, | |
| "eval_runtime": 21.0781, | |
| "eval_samples_per_second": 9.109, | |
| "eval_steps_per_second": 9.109, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.495201975107193, | |
| "eval_runtime": 21.6419, | |
| "eval_samples_per_second": 8.872, | |
| "eval_steps_per_second": 8.872, | |
| "step": 908 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 908, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.294814595608576e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |