| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6447368421052633, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01644736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03289473684210526, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5846, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.049342105263157895, | |
| "grad_norm": 56.480621337890625, | |
| "learning_rate": 9.998355263157894e-06, | |
| "loss": 0.8864, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998355263157894e-06, | |
| "loss": 0.4863, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08223684210526316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.4998, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.7638, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11513157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.561, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.5553, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14802631578947367, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.4243, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16447368421052633, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.5658, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18092105263157895, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.6598, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.6398, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2138157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.5054, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23026315789473684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99671052631579e-06, | |
| "loss": 0.5486, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24671052631578946, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99342105263158e-06, | |
| "loss": 0.361, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.6621, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27960526315789475, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29605263157894735, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34539473684210525, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3618421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3782894736842105, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.41118421052631576, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4276315789473684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4440789473684211, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4769736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4934210526315789, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5098684210526315, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5427631578947368, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5592105263157895, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5756578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6085526315789473, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6414473684210527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6743421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6907894736842105, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7072368421052632, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7236842105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.7401315789473685, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.756578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7730263157894737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.805921052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8223684210526315, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8388157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8552631578947368, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8717105263157895, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8881578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9046052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.9539473684210527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9703947368421053, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0032894736842106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.019736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.0361842105263157, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.069078947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0855263157894737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.1019736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.118421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.1348684210526316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.1513157894736843, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1677631578947367, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.200657894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.2171052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.2335526315789473, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.2664473684210527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.2828947368421053, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.299342105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.3322368421052633, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.3486842105263157, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.3651315789473684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.381578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.3980263157894737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.4144736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.430921052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.4638157894736843, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.4802631578947367, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4967105263157894, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.513157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.5296052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.5460526315789473, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.5953947368421053, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.611842105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.6282894736842106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.6447368421052633, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991776315789474e-06, | |
| "loss": 0.0, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6080, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "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 | |
| } | |