Text Generation
PEFT
Safetensors
English
named-entity-recognition
chain-of-thought
lora
conversational
Instructions to use structured-cot-ner/qwen3-4b-thinking-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/qwen3-4b-thinking-structured-cot-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Thinking-2507") model = PeftModel.from_pretrained(base_model, "structured-cot-ner/qwen3-4b-thinking-structured-cot-lora") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from structured-cot-ner/qwen3-4b-thinking-structured-cot-lora: direct link, hf CLI and curl.
- Browser
- Download file 18.3 kB
-
https://huggingface.co/structured-cot-ner/qwen3-4b-thinking-structured-cot-lora/resolve/main/trainer_state.json
- Command line
-
hf download hf://structured-cot-ner/qwen3-4b-thinking-structured-cot-lora/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/structured-cot-ner/qwen3-4b-thinking-structured-cot-lora/resolve/main/trainer_state.json
18.3 kB
| { | |
| "best_global_step": 900, | |
| "best_metric": 0.5007554292678833, | |
| "best_model_checkpoint": "work/qwen3-4b-thinking_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": 1.5118380784988403, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2583, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0440771349862259, | |
| "grad_norm": 0.522850751876831, | |
| "learning_rate": 7.037037037037038e-05, | |
| "loss": 0.9405, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 0.5948781967163086, | |
| "learning_rate": 9.999872841297521e-05, | |
| "loss": 0.7733, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "grad_norm": 0.6703866124153137, | |
| "learning_rate": 9.995422965786025e-05, | |
| "loss": 0.6891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11019283746556474, | |
| "grad_norm": 0.4195103645324707, | |
| "learning_rate": 9.984621621406273e-05, | |
| "loss": 0.6555, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 0.5883722305297852, | |
| "learning_rate": 9.96748254161048e-05, | |
| "loss": 0.6657, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15426997245179064, | |
| "grad_norm": 0.4921148419380188, | |
| "learning_rate": 9.944027518013187e-05, | |
| "loss": 0.6006, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1763085399449036, | |
| "grad_norm": 0.48981523513793945, | |
| "learning_rate": 9.914286372684153e-05, | |
| "loss": 0.567, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19834710743801653, | |
| "grad_norm": 0.5244777202606201, | |
| "learning_rate": 9.878296920230869e-05, | |
| "loss": 0.5976, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22038567493112948, | |
| "grad_norm": 0.5809691548347473, | |
| "learning_rate": 9.83610491971886e-05, | |
| "loss": 0.6201, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22038567493112948, | |
| "eval_loss": 0.5935859680175781, | |
| "eval_runtime": 32.5297, | |
| "eval_samples_per_second": 5.902, | |
| "eval_steps_per_second": 5.902, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.5859531760215759, | |
| "learning_rate": 9.787764016490992e-05, | |
| "loss": 0.607, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 0.3645329773426056, | |
| "learning_rate": 9.733335673959671e-05, | |
| "loss": 0.5835, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2865013774104683, | |
| "grad_norm": 0.6015150547027588, | |
| "learning_rate": 9.672889095458734e-05, | |
| "loss": 0.5817, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3085399449035813, | |
| "grad_norm": 0.4919818639755249, | |
| "learning_rate": 9.606501136254327e-05, | |
| "loss": 0.5362, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3305785123966942, | |
| "grad_norm": 0.5223751068115234, | |
| "learning_rate": 9.534256205826684e-05, | |
| "loss": 0.584, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3526170798898072, | |
| "grad_norm": 0.4703691303730011, | |
| "learning_rate": 9.456246160547057e-05, | |
| "loss": 0.5407, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3746556473829201, | |
| "grad_norm": 0.5494073033332825, | |
| "learning_rate": 9.372570186886225e-05, | |
| "loss": 0.5329, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": 0.5381530523300171, | |
| "learning_rate": 9.283334675303084e-05, | |
| "loss": 0.5692, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.418732782369146, | |
| "grad_norm": 0.6264142990112305, | |
| "learning_rate": 9.188653084973692e-05, | |
| "loss": 0.5662, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.44077134986225897, | |
| "grad_norm": 0.6583027243614197, | |
| "learning_rate": 9.088645799532729e-05, | |
| "loss": 0.5381, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44077134986225897, | |
| "eval_loss": 0.5541233420372009, | |
| "eval_runtime": 32.6224, | |
| "eval_samples_per_second": 5.886, | |
| "eval_steps_per_second": 5.886, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4628099173553719, | |
| "grad_norm": 0.4658336639404297, | |
| "learning_rate": 8.983439974010794e-05, | |
| "loss": 0.5536, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.4708367586135864, | |
| "learning_rate": 8.873169373162174e-05, | |
| "loss": 0.5548, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5068870523415978, | |
| "grad_norm": 0.4323926866054535, | |
| "learning_rate": 8.757974201388605e-05, | |
| "loss": 0.5338, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 0.6082764863967896, | |
| "learning_rate": 8.638000924475336e-05, | |
| "loss": 0.5446, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5509641873278237, | |
| "grad_norm": 0.49819567799568176, | |
| "learning_rate": 8.513402083366054e-05, | |
| "loss": 0.5285, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5730027548209367, | |
| "grad_norm": 0.45436057448387146, | |
| "learning_rate": 8.384336100213546e-05, | |
| "loss": 0.4987, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5950413223140496, | |
| "grad_norm": 0.5505215525627136, | |
| "learning_rate": 8.250967076952635e-05, | |
| "loss": 0.5306, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6170798898071626, | |
| "grad_norm": 0.5948213338851929, | |
| "learning_rate": 8.113464586651516e-05, | |
| "loss": 0.5324, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6391184573002755, | |
| "grad_norm": 0.506367027759552, | |
| "learning_rate": 7.972003457906773e-05, | |
| "loss": 0.5539, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "grad_norm": 0.5841493010520935, | |
| "learning_rate": 7.826763552556222e-05, | |
| "loss": 0.5153, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "eval_loss": 0.5341405272483826, | |
| "eval_runtime": 32.5634, | |
| "eval_samples_per_second": 5.896, | |
| "eval_steps_per_second": 5.896, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6831955922865014, | |
| "grad_norm": 0.591347873210907, | |
| "learning_rate": 7.677929536992194e-05, | |
| "loss": 0.5106, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7052341597796143, | |
| "grad_norm": 0.6303464770317078, | |
| "learning_rate": 7.525690647366032e-05, | |
| "loss": 0.5321, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.46825966238975525, | |
| "learning_rate": 7.370240448982344e-05, | |
| "loss": 0.5494, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7493112947658402, | |
| "grad_norm": 0.601374089717865, | |
| "learning_rate": 7.211776590188898e-05, | |
| "loss": 0.5292, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7713498622589532, | |
| "grad_norm": 0.5138451457023621, | |
| "learning_rate": 7.050500551075121e-05, | |
| "loss": 0.5512, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": 0.49237778782844543, | |
| "learning_rate": 6.886617387298689e-05, | |
| "loss": 0.5316, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8154269972451791, | |
| "grad_norm": 0.5695348978042603, | |
| "learning_rate": 6.720335469365943e-05, | |
| "loss": 0.5133, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.837465564738292, | |
| "grad_norm": 0.5527098178863525, | |
| "learning_rate": 6.551866217697602e-05, | |
| "loss": 0.5189, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.859504132231405, | |
| "grad_norm": 0.6650556325912476, | |
| "learning_rate": 6.381423833816653e-05, | |
| "loss": 0.5107, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8815426997245179, | |
| "grad_norm": 0.5628238916397095, | |
| "learning_rate": 6.209225028000173e-05, | |
| "loss": 0.532, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8815426997245179, | |
| "eval_loss": 0.5212955474853516, | |
| "eval_runtime": 32.7214, | |
| "eval_samples_per_second": 5.868, | |
| "eval_steps_per_second": 5.868, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9035812672176309, | |
| "grad_norm": 0.611126720905304, | |
| "learning_rate": 6.0354887437413965e-05, | |
| "loss": 0.5029, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9256198347107438, | |
| "grad_norm": 0.5568116903305054, | |
| "learning_rate": 5.860435879372319e-05, | |
| "loss": 0.5289, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9476584022038568, | |
| "grad_norm": 0.5040838718414307, | |
| "learning_rate": 5.684289007200819e-05, | |
| "loss": 0.5196, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.47136223316192627, | |
| "learning_rate": 5.5072720905193984e-05, | |
| "loss": 0.5131, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9917355371900827, | |
| "grad_norm": 1.5184211730957031, | |
| "learning_rate": 5.329610198845322e-05, | |
| "loss": 0.5214, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0132231404958678, | |
| "grad_norm": 0.5406650304794312, | |
| "learning_rate": 5.151529221754262e-05, | |
| "loss": 0.4735, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0352617079889808, | |
| "grad_norm": 0.46970129013061523, | |
| "learning_rate": 4.97325558167126e-05, | |
| "loss": 0.4554, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0573002754820937, | |
| "grad_norm": 0.6685709357261658, | |
| "learning_rate": 4.795015945984198e-05, | |
| "loss": 0.4488, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0793388429752067, | |
| "grad_norm": 0.5866950750350952, | |
| "learning_rate": 4.617036938845806e-05, | |
| "loss": 0.4529, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1013774104683196, | |
| "grad_norm": 0.5202255845069885, | |
| "learning_rate": 4.43954485303065e-05, | |
| "loss": 0.4662, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1013774104683196, | |
| "eval_loss": 0.5136515498161316, | |
| "eval_runtime": 32.6706, | |
| "eval_samples_per_second": 5.877, | |
| "eval_steps_per_second": 5.877, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1234159779614326, | |
| "grad_norm": 0.8746190071105957, | |
| "learning_rate": 4.2627653622134346e-05, | |
| "loss": 0.4538, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1454545454545455, | |
| "grad_norm": 0.5891181826591492, | |
| "learning_rate": 4.086923234034493e-05, | |
| "loss": 0.4477, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1674931129476585, | |
| "grad_norm": 0.5674530863761902, | |
| "learning_rate": 3.912242044317233e-05, | |
| "loss": 0.4429, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.1895316804407714, | |
| "grad_norm": 0.5238365530967712, | |
| "learning_rate": 3.738943892800951e-05, | |
| "loss": 0.4466, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2115702479338843, | |
| "grad_norm": 0.6339564919471741, | |
| "learning_rate": 3.5672491207504e-05, | |
| "loss": 0.4503, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2336088154269973, | |
| "grad_norm": 0.5469422340393066, | |
| "learning_rate": 3.397376030801215e-05, | |
| "loss": 0.4814, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2556473829201102, | |
| "grad_norm": 0.6437169313430786, | |
| "learning_rate": 3.229540609397334e-05, | |
| "loss": 0.4685, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.2776859504132232, | |
| "grad_norm": 0.639842689037323, | |
| "learning_rate": 3.0639562521733935e-05, | |
| "loss": 0.4514, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.2997245179063361, | |
| "grad_norm": 0.5976139903068542, | |
| "learning_rate": 2.900833492631191e-05, | |
| "loss": 0.4384, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.321763085399449, | |
| "grad_norm": 0.6333716511726379, | |
| "learning_rate": 2.7403797344552696e-05, | |
| "loss": 0.4681, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.321763085399449, | |
| "eval_loss": 0.5079358220100403, | |
| "eval_runtime": 32.6654, | |
| "eval_samples_per_second": 5.878, | |
| "eval_steps_per_second": 5.878, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.343801652892562, | |
| "grad_norm": 0.7332891821861267, | |
| "learning_rate": 2.5827989878078972e-05, | |
| "loss": 0.4733, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.365840220385675, | |
| "grad_norm": 0.7150602340698242, | |
| "learning_rate": 2.428291609938786e-05, | |
| "loss": 0.4363, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.387878787878788, | |
| "grad_norm": 0.525088369846344, | |
| "learning_rate": 2.2770540504393224e-05, | |
| "loss": 0.4337, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4099173553719009, | |
| "grad_norm": 0.6683711409568787, | |
| "learning_rate": 2.1292786014652398e-05, | |
| "loss": 0.455, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4319559228650138, | |
| "grad_norm": 0.5155622959136963, | |
| "learning_rate": 1.9851531532452665e-05, | |
| "loss": 0.4494, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4539944903581268, | |
| "grad_norm": 0.5524773001670837, | |
| "learning_rate": 1.8448609551866647e-05, | |
| "loss": 0.445, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.4760330578512397, | |
| "grad_norm": 0.5845046639442444, | |
| "learning_rate": 1.7085803828813546e-05, | |
| "loss": 0.4654, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.4980716253443527, | |
| "grad_norm": 0.7400183081626892, | |
| "learning_rate": 1.5764847113089094e-05, | |
| "loss": 0.4232, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.5201101928374654, | |
| "grad_norm": 0.6187362670898438, | |
| "learning_rate": 1.4487418945247438e-05, | |
| "loss": 0.4471, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5421487603305786, | |
| "grad_norm": 0.5757448077201843, | |
| "learning_rate": 1.3255143521136498e-05, | |
| "loss": 0.4641, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5421487603305786, | |
| "eval_loss": 0.504026472568512, | |
| "eval_runtime": 32.353, | |
| "eval_samples_per_second": 5.935, | |
| "eval_steps_per_second": 5.935, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.5641873278236913, | |
| "grad_norm": 0.5613148808479309, | |
| "learning_rate": 1.206958762680157e-05, | |
| "loss": 0.4463, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.5862258953168045, | |
| "grad_norm": 0.6597267389297485, | |
| "learning_rate": 1.0932258646383336e-05, | |
| "loss": 0.4758, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6082644628099172, | |
| "grad_norm": 0.764069139957428, | |
| "learning_rate": 9.844602645542584e-06, | |
| "loss": 0.4401, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6303030303030304, | |
| "grad_norm": 0.5435413718223572, | |
| "learning_rate": 8.808002532849047e-06, | |
| "loss": 0.457, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.652341597796143, | |
| "grad_norm": 0.5651699900627136, | |
| "learning_rate": 7.823776301471591e-06, | |
| "loss": 0.4452, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.6743801652892563, | |
| "grad_norm": 0.6724544763565063, | |
| "learning_rate": 6.893175353405756e-06, | |
| "loss": 0.4439, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.696418732782369, | |
| "grad_norm": 0.6050825715065002, | |
| "learning_rate": 6.017382908369051e-06, | |
| "loss": 0.4464, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7184573002754822, | |
| "grad_norm": 0.8552470207214355, | |
| "learning_rate": 5.197512499387175e-06, | |
| "loss": 0.4753, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.7404958677685949, | |
| "grad_norm": 0.6820724606513977, | |
| "learning_rate": 4.434606556983878e-06, | |
| "loss": 0.4756, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.762534435261708, | |
| "grad_norm": 0.6281607747077942, | |
| "learning_rate": 3.729635083774724e-06, | |
| "loss": 0.4587, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.762534435261708, | |
| "eval_loss": 0.5011577010154724, | |
| "eval_runtime": 32.8882, | |
| "eval_samples_per_second": 5.838, | |
| "eval_steps_per_second": 5.838, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7845730027548208, | |
| "grad_norm": 0.8416563272476196, | |
| "learning_rate": 3.083494421149752e-06, | |
| "loss": 0.4617, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.806611570247934, | |
| "grad_norm": 0.5670965909957886, | |
| "learning_rate": 2.49700610961342e-06, | |
| "loss": 0.4594, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8286501377410467, | |
| "grad_norm": 0.602939248085022, | |
| "learning_rate": 1.9709158442305365e-06, | |
| "loss": 0.442, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.8506887052341598, | |
| "grad_norm": 0.6591982245445251, | |
| "learning_rate": 1.5058925265066194e-06, | |
| "loss": 0.4204, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.8727272727272726, | |
| "grad_norm": 0.5469354391098022, | |
| "learning_rate": 1.1025274139079057e-06, | |
| "loss": 0.4398, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.8947658402203857, | |
| "grad_norm": 0.7477226853370667, | |
| "learning_rate": 7.613333681025236e-07, | |
| "loss": 0.4163, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9168044077134985, | |
| "grad_norm": 0.6220057606697083, | |
| "learning_rate": 4.827442028785655e-07, | |
| "loss": 0.4526, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9388429752066116, | |
| "grad_norm": 0.5309923887252808, | |
| "learning_rate": 2.67114132568258e-07, | |
| "loss": 0.463, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.9608815426997244, | |
| "grad_norm": 0.5211982727050781, | |
| "learning_rate": 1.1471732167938065e-07, | |
| "loss": 0.4395, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.9829201101928375, | |
| "grad_norm": 0.5527125597000122, | |
| "learning_rate": 2.57475363067472e-08, | |
| "loss": 0.4651, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.9829201101928375, | |
| "eval_loss": 0.5007554292678833, | |
| "eval_runtime": 32.8175, | |
| "eval_samples_per_second": 5.851, | |
| "eval_steps_per_second": 5.851, | |
| "step": 900 | |
| } | |
| ], | |
| "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": 1.105356840708096e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |