Instructions to use hchang/reward_modeling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hchang/reward_modeling with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Meta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "hchang/reward_modeling") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-1000/trainer_state.json from hchang/reward_modeling: direct link, hf CLI and curl.
- Browser
- Download file 17.4 kB
-
https://huggingface.co/hchang/reward_modeling/resolve/main/checkpoint-1000/trainer_state.json
- Command line
-
hf download hf://hchang/reward_modeling/checkpoint-1000/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/hchang/reward_modeling/resolve/main/checkpoint-1000/trainer_state.json
17.4 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.33288948069241014, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003328894806924101, | |
| "grad_norm": 37.75, | |
| "learning_rate": 1.9933422103861518e-05, | |
| "loss": 1.4084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006657789613848202, | |
| "grad_norm": 12.125, | |
| "learning_rate": 1.9866844207723038e-05, | |
| "loss": 1.0474, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009986684420772303, | |
| "grad_norm": 45.25, | |
| "learning_rate": 1.9800266311584554e-05, | |
| "loss": 1.2455, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013315579227696404, | |
| "grad_norm": 13.9375, | |
| "learning_rate": 1.9733688415446073e-05, | |
| "loss": 1.1969, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016644474034620507, | |
| "grad_norm": 32.0, | |
| "learning_rate": 1.966711051930759e-05, | |
| "loss": 1.1659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019973368841544607, | |
| "grad_norm": 19.0, | |
| "learning_rate": 1.960053262316911e-05, | |
| "loss": 1.1159, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02330226364846871, | |
| "grad_norm": 27.5, | |
| "learning_rate": 1.953395472703063e-05, | |
| "loss": 1.1861, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02663115845539281, | |
| "grad_norm": 17.5, | |
| "learning_rate": 1.9467376830892145e-05, | |
| "loss": 1.1073, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02996005326231691, | |
| "grad_norm": 33.75, | |
| "learning_rate": 1.9400798934753665e-05, | |
| "loss": 1.1506, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.033288948069241014, | |
| "grad_norm": 9.5, | |
| "learning_rate": 1.933422103861518e-05, | |
| "loss": 1.246, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03661784287616511, | |
| "grad_norm": 11.3125, | |
| "learning_rate": 1.92676431424767e-05, | |
| "loss": 1.1708, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03994673768308921, | |
| "grad_norm": 14.375, | |
| "learning_rate": 1.9201065246338217e-05, | |
| "loss": 1.1302, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.043275632490013316, | |
| "grad_norm": 20.625, | |
| "learning_rate": 1.9134487350199737e-05, | |
| "loss": 1.0537, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04660452729693742, | |
| "grad_norm": 21.75, | |
| "learning_rate": 1.9067909454061253e-05, | |
| "loss": 1.0669, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.049933422103861515, | |
| "grad_norm": 14.125, | |
| "learning_rate": 1.900133155792277e-05, | |
| "loss": 1.0482, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05326231691078562, | |
| "grad_norm": 27.625, | |
| "learning_rate": 1.893475366178429e-05, | |
| "loss": 1.1468, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05659121171770972, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.8868175765645805e-05, | |
| "loss": 1.092, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05992010652463382, | |
| "grad_norm": 32.5, | |
| "learning_rate": 1.8801597869507325e-05, | |
| "loss": 1.2208, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06324900133155792, | |
| "grad_norm": 56.0, | |
| "learning_rate": 1.873501997336884e-05, | |
| "loss": 1.2359, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.06657789613848203, | |
| "grad_norm": 8.375, | |
| "learning_rate": 1.866844207723036e-05, | |
| "loss": 1.0712, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06990679094540612, | |
| "grad_norm": 26.375, | |
| "learning_rate": 1.860186418109188e-05, | |
| "loss": 1.0156, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07323568575233022, | |
| "grad_norm": 12.0, | |
| "learning_rate": 1.8535286284953397e-05, | |
| "loss": 1.0407, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.07656458055925433, | |
| "grad_norm": 13.75, | |
| "learning_rate": 1.8468708388814916e-05, | |
| "loss": 1.0161, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.07989347536617843, | |
| "grad_norm": 27.125, | |
| "learning_rate": 1.8402130492676432e-05, | |
| "loss": 1.1466, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.08322237017310254, | |
| "grad_norm": 26.125, | |
| "learning_rate": 1.8335552596537952e-05, | |
| "loss": 1.3192, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08655126498002663, | |
| "grad_norm": 25.75, | |
| "learning_rate": 1.826897470039947e-05, | |
| "loss": 1.0628, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08988015978695073, | |
| "grad_norm": 29.25, | |
| "learning_rate": 1.8202396804260988e-05, | |
| "loss": 0.967, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.09320905459387484, | |
| "grad_norm": 29.75, | |
| "learning_rate": 1.8135818908122504e-05, | |
| "loss": 1.0356, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.09653794940079893, | |
| "grad_norm": 11.6875, | |
| "learning_rate": 1.806924101198402e-05, | |
| "loss": 0.9853, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.09986684420772303, | |
| "grad_norm": 27.5, | |
| "learning_rate": 1.800266311584554e-05, | |
| "loss": 1.0279, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10319573901464714, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.7936085219707056e-05, | |
| "loss": 1.0115, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.10652463382157124, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 1.7869507323568576e-05, | |
| "loss": 0.942, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.10985352862849534, | |
| "grad_norm": 65.0, | |
| "learning_rate": 1.7802929427430096e-05, | |
| "loss": 1.0208, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.11318242343541944, | |
| "grad_norm": 9.625, | |
| "learning_rate": 1.7736351531291612e-05, | |
| "loss": 1.1729, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.11651131824234354, | |
| "grad_norm": 17.5, | |
| "learning_rate": 1.766977363515313e-05, | |
| "loss": 0.9322, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11984021304926765, | |
| "grad_norm": 28.125, | |
| "learning_rate": 1.7603195739014648e-05, | |
| "loss": 1.0417, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.12316910785619174, | |
| "grad_norm": 18.25, | |
| "learning_rate": 1.7536617842876168e-05, | |
| "loss": 1.2491, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.12649800266311584, | |
| "grad_norm": 27.375, | |
| "learning_rate": 1.7470039946737684e-05, | |
| "loss": 0.9388, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.12982689747003995, | |
| "grad_norm": 22.125, | |
| "learning_rate": 1.7403462050599203e-05, | |
| "loss": 1.0488, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.13315579227696406, | |
| "grad_norm": 21.25, | |
| "learning_rate": 1.733688415446072e-05, | |
| "loss": 0.9951, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13648468708388814, | |
| "grad_norm": 11.75, | |
| "learning_rate": 1.727030625832224e-05, | |
| "loss": 0.9212, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.13981358189081225, | |
| "grad_norm": 16.25, | |
| "learning_rate": 1.7203728362183756e-05, | |
| "loss": 1.0548, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.14314247669773636, | |
| "grad_norm": 19.875, | |
| "learning_rate": 1.7137150466045275e-05, | |
| "loss": 1.0238, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.14647137150466044, | |
| "grad_norm": 18.875, | |
| "learning_rate": 1.707057256990679e-05, | |
| "loss": 1.0327, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.14980026631158455, | |
| "grad_norm": 7.84375, | |
| "learning_rate": 1.7003994673768308e-05, | |
| "loss": 1.1155, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.15312916111850866, | |
| "grad_norm": 14.125, | |
| "learning_rate": 1.693741677762983e-05, | |
| "loss": 0.9627, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.15645805592543274, | |
| "grad_norm": 7.4375, | |
| "learning_rate": 1.6870838881491347e-05, | |
| "loss": 1.0216, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.15978695073235685, | |
| "grad_norm": 9.375, | |
| "learning_rate": 1.6804260985352863e-05, | |
| "loss": 1.0489, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.16311584553928096, | |
| "grad_norm": 19.5, | |
| "learning_rate": 1.6737683089214383e-05, | |
| "loss": 1.1254, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.16644474034620507, | |
| "grad_norm": 26.125, | |
| "learning_rate": 1.66711051930759e-05, | |
| "loss": 1.0134, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16644474034620507, | |
| "eval_accuracy": 0.5015762402521985, | |
| "eval_loss": 0.9942083358764648, | |
| "eval_runtime": 211.8123, | |
| "eval_samples_per_second": 113.818, | |
| "eval_steps_per_second": 28.454, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16977363515312915, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 1.660452729693742e-05, | |
| "loss": 1.0164, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.17310252996005326, | |
| "grad_norm": 38.75, | |
| "learning_rate": 1.6537949400798935e-05, | |
| "loss": 1.0042, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.17643142476697737, | |
| "grad_norm": 20.125, | |
| "learning_rate": 1.6471371504660455e-05, | |
| "loss": 0.9786, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.17976031957390146, | |
| "grad_norm": 11.4375, | |
| "learning_rate": 1.640479360852197e-05, | |
| "loss": 0.9678, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.18308921438082557, | |
| "grad_norm": 19.375, | |
| "learning_rate": 1.633821571238349e-05, | |
| "loss": 1.0477, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.18641810918774968, | |
| "grad_norm": 16.75, | |
| "learning_rate": 1.6271637816245007e-05, | |
| "loss": 1.02, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.18974700399467376, | |
| "grad_norm": 15.5, | |
| "learning_rate": 1.6205059920106527e-05, | |
| "loss": 0.9864, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.19307589880159787, | |
| "grad_norm": 9.75, | |
| "learning_rate": 1.6138482023968043e-05, | |
| "loss": 1.0019, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.19640479360852198, | |
| "grad_norm": 12.125, | |
| "learning_rate": 1.6071904127829563e-05, | |
| "loss": 0.9483, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.19973368841544606, | |
| "grad_norm": 30.875, | |
| "learning_rate": 1.6005326231691082e-05, | |
| "loss": 1.0692, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.20306258322237017, | |
| "grad_norm": 10.125, | |
| "learning_rate": 1.59387483355526e-05, | |
| "loss": 0.9279, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.20639147802929428, | |
| "grad_norm": 11.6875, | |
| "learning_rate": 1.5872170439414115e-05, | |
| "loss": 0.941, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.2097203728362184, | |
| "grad_norm": 3.03125, | |
| "learning_rate": 1.5805592543275634e-05, | |
| "loss": 1.0259, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.21304926764314247, | |
| "grad_norm": 10.4375, | |
| "learning_rate": 1.573901464713715e-05, | |
| "loss": 0.9687, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.21637816245006658, | |
| "grad_norm": 12.8125, | |
| "learning_rate": 1.567243675099867e-05, | |
| "loss": 0.9512, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2197070572569907, | |
| "grad_norm": 9.75, | |
| "learning_rate": 1.5605858854860187e-05, | |
| "loss": 0.9569, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.22303595206391477, | |
| "grad_norm": 17.375, | |
| "learning_rate": 1.5539280958721706e-05, | |
| "loss": 0.9694, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.22636484687083888, | |
| "grad_norm": 9.625, | |
| "learning_rate": 1.5472703062583222e-05, | |
| "loss": 0.97, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.229693741677763, | |
| "grad_norm": 21.0, | |
| "learning_rate": 1.5406125166444742e-05, | |
| "loss": 1.0506, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.23302263648468707, | |
| "grad_norm": 10.3125, | |
| "learning_rate": 1.533954727030626e-05, | |
| "loss": 0.9184, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.23635153129161118, | |
| "grad_norm": 21.5, | |
| "learning_rate": 1.5272969374167778e-05, | |
| "loss": 1.005, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.2396804260985353, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.5206391478029296e-05, | |
| "loss": 0.8624, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.24300932090545938, | |
| "grad_norm": 13.9375, | |
| "learning_rate": 1.5139813581890814e-05, | |
| "loss": 1.0051, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.24633821571238348, | |
| "grad_norm": 16.625, | |
| "learning_rate": 1.5073235685752332e-05, | |
| "loss": 1.0378, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2496671105193076, | |
| "grad_norm": 6.4375, | |
| "learning_rate": 1.500665778961385e-05, | |
| "loss": 0.9191, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2529960053262317, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.4940079893475368e-05, | |
| "loss": 0.9722, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2563249001331558, | |
| "grad_norm": 22.625, | |
| "learning_rate": 1.4873501997336886e-05, | |
| "loss": 1.014, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.2596537949400799, | |
| "grad_norm": 21.0, | |
| "learning_rate": 1.4806924101198404e-05, | |
| "loss": 1.0986, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.262982689747004, | |
| "grad_norm": 10.4375, | |
| "learning_rate": 1.4740346205059922e-05, | |
| "loss": 0.9672, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.2663115845539281, | |
| "grad_norm": 17.0, | |
| "learning_rate": 1.467376830892144e-05, | |
| "loss": 0.9605, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.26964047936085217, | |
| "grad_norm": 31.75, | |
| "learning_rate": 1.4607190412782957e-05, | |
| "loss": 1.0308, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.2729693741677763, | |
| "grad_norm": 12.4375, | |
| "learning_rate": 1.4540612516644474e-05, | |
| "loss": 0.9268, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.2762982689747004, | |
| "grad_norm": 17.125, | |
| "learning_rate": 1.4474034620505992e-05, | |
| "loss": 0.9656, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.2796271637816245, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.440745672436751e-05, | |
| "loss": 0.9865, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.2829560585885486, | |
| "grad_norm": 22.625, | |
| "learning_rate": 1.434087882822903e-05, | |
| "loss": 1.1118, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2862849533954727, | |
| "grad_norm": 13.0, | |
| "learning_rate": 1.4274300932090547e-05, | |
| "loss": 1.0043, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.28961384820239683, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 1.4207723035952065e-05, | |
| "loss": 0.9768, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.2929427430093209, | |
| "grad_norm": 6.75, | |
| "learning_rate": 1.4141145139813583e-05, | |
| "loss": 1.0237, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.296271637816245, | |
| "grad_norm": 10.875, | |
| "learning_rate": 1.4074567243675101e-05, | |
| "loss": 1.1597, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.2996005326231691, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.4007989347536619e-05, | |
| "loss": 0.7993, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3029294274300932, | |
| "grad_norm": 31.5, | |
| "learning_rate": 1.3941411451398137e-05, | |
| "loss": 0.9802, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.3062583222370173, | |
| "grad_norm": 12.25, | |
| "learning_rate": 1.3874833555259655e-05, | |
| "loss": 0.9565, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.30958721704394143, | |
| "grad_norm": 11.8125, | |
| "learning_rate": 1.3808255659121173e-05, | |
| "loss": 1.0024, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.3129161118508655, | |
| "grad_norm": 16.625, | |
| "learning_rate": 1.3741677762982691e-05, | |
| "loss": 1.0209, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.3162450066577896, | |
| "grad_norm": 13.375, | |
| "learning_rate": 1.3675099866844209e-05, | |
| "loss": 0.8767, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3195739014647137, | |
| "grad_norm": 20.875, | |
| "learning_rate": 1.3608521970705725e-05, | |
| "loss": 0.9642, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.3229027962716378, | |
| "grad_norm": 17.25, | |
| "learning_rate": 1.3541944074567243e-05, | |
| "loss": 0.9508, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.3262316910785619, | |
| "grad_norm": 22.25, | |
| "learning_rate": 1.3475366178428764e-05, | |
| "loss": 1.1324, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.32956058588548603, | |
| "grad_norm": 11.5, | |
| "learning_rate": 1.3408788282290282e-05, | |
| "loss": 1.0655, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.33288948069241014, | |
| "grad_norm": 15.625, | |
| "learning_rate": 1.3342210386151799e-05, | |
| "loss": 0.9608, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.33288948069241014, | |
| "eval_accuracy": 0.507300481168077, | |
| "eval_loss": 0.9467151165008545, | |
| "eval_runtime": 211.5004, | |
| "eval_samples_per_second": 113.986, | |
| "eval_steps_per_second": 28.496, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3004, | |
| "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": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |