| { | |
| "best_metric": 0.8647342995169082, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1620", | |
| "epoch": 5.166666666666667, | |
| "eval_steps": 500, | |
| "global_step": 1620, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.2231, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.7347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1022, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.0396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.5946, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 1.1656, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.494, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.5423, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1873, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.0079, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.1419, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5482, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.5038, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 1.0755, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5767, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.552, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.972565157750343e-05, | |
| "loss": 3.0485, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.6713, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9039780521262005e-05, | |
| "loss": 0.6941, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.86968449931413e-05, | |
| "loss": 0.3063, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.835390946502058e-05, | |
| "loss": 1.4736, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.801097393689987e-05, | |
| "loss": 2.8045, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.766803840877915e-05, | |
| "loss": 1.7318, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.732510288065844e-05, | |
| "loss": 0.1236, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.6982167352537723e-05, | |
| "loss": 1.4885, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.6639231824417016e-05, | |
| "loss": 2.2675, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 2.128, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.7294685990338164, | |
| "eval_loss": 0.753165066242218, | |
| "eval_runtime": 56.9292, | |
| "eval_samples_per_second": 3.636, | |
| "eval_steps_per_second": 3.636, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.5953360768175586e-05, | |
| "loss": 0.5454, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.561042524005487e-05, | |
| "loss": 0.5708, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.5267489711934157e-05, | |
| "loss": 0.5133, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.492455418381344e-05, | |
| "loss": 0.7319, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.4581618655692734e-05, | |
| "loss": 0.7799, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.423868312757202e-05, | |
| "loss": 1.6836, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.3895747599451304e-05, | |
| "loss": 1.4565, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.355281207133059e-05, | |
| "loss": 0.4941, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.6447, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.286694101508916e-05, | |
| "loss": 0.6214, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.252400548696845e-05, | |
| "loss": 1.0549, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.2181069958847744e-05, | |
| "loss": 0.0725, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.183813443072703e-05, | |
| "loss": 1.3638, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.1495198902606315e-05, | |
| "loss": 0.0211, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.11522633744856e-05, | |
| "loss": 2.1372, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.0809327846364885e-05, | |
| "loss": 0.1949, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.046639231824417e-05, | |
| "loss": 1.4151, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.2223, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.978052126200275e-05, | |
| "loss": 2.2408, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.943758573388203e-05, | |
| "loss": 1.888, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.909465020576132e-05, | |
| "loss": 1.4841, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.8751714677640603e-05, | |
| "loss": 1.1911, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.840877914951989e-05, | |
| "loss": 0.5481, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.806584362139918e-05, | |
| "loss": 1.7358, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.7722908093278466e-05, | |
| "loss": 0.0136, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.737997256515775e-05, | |
| "loss": 1.9144, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.004, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.7971014492753623, | |
| "eval_loss": 0.9392079710960388, | |
| "eval_runtime": 56.8677, | |
| "eval_samples_per_second": 3.64, | |
| "eval_steps_per_second": 3.64, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.669410150891632e-05, | |
| "loss": 0.6673, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.635116598079561e-05, | |
| "loss": 0.007, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.60082304526749e-05, | |
| "loss": 1.4758, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.566529492455419e-05, | |
| "loss": 1.3052, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.5322359396433476e-05, | |
| "loss": 1.0021, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.497942386831276e-05, | |
| "loss": 0.8384, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.463648834019205e-05, | |
| "loss": 0.6765, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.429355281207133e-05, | |
| "loss": 0.5246, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.8376, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.360768175582991e-05, | |
| "loss": 0.5031, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.3264746227709195e-05, | |
| "loss": 2.0995, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.292181069958848e-05, | |
| "loss": 0.3882, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.2578875171467765e-05, | |
| "loss": 0.778, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.223593964334705e-05, | |
| "loss": 0.8262, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.1893004115226336e-05, | |
| "loss": 0.307, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.155006858710563e-05, | |
| "loss": 0.0967, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.120713305898491e-05, | |
| "loss": 0.0112, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.6731, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.0521262002743484e-05, | |
| "loss": 0.2789, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.017832647462277e-05, | |
| "loss": 0.0034, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.9835390946502057e-05, | |
| "loss": 0.0045, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.949245541838135e-05, | |
| "loss": 0.4748, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.9149519890260635e-05, | |
| "loss": 0.3657, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.880658436213992e-05, | |
| "loss": 0.4265, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.846364883401921e-05, | |
| "loss": 0.924, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.8120713305898494e-05, | |
| "loss": 0.0073, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.964, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.8357487922705314, | |
| "eval_loss": 0.8219566345214844, | |
| "eval_runtime": 57.0969, | |
| "eval_samples_per_second": 3.625, | |
| "eval_steps_per_second": 3.625, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.7434842249657068e-05, | |
| "loss": 0.7508, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.7091906721536353e-05, | |
| "loss": 0.2073, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2.6748971193415638e-05, | |
| "loss": 0.2977, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2.6406035665294927e-05, | |
| "loss": 0.0036, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.6063100137174212e-05, | |
| "loss": 0.3405, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.5720164609053497e-05, | |
| "loss": 0.4663, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.5377229080932786e-05, | |
| "loss": 0.0016, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.503429355281207e-05, | |
| "loss": 0.3871, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.0032, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 2.434842249657065e-05, | |
| "loss": 0.3635, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 2.4005486968449934e-05, | |
| "loss": 0.1203, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 2.366255144032922e-05, | |
| "loss": 0.2842, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.3319615912208508e-05, | |
| "loss": 0.0011, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.2976680384087793e-05, | |
| "loss": 0.0715, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.2633744855967078e-05, | |
| "loss": 0.347, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.2290809327846367e-05, | |
| "loss": 0.7102, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.1947873799725652e-05, | |
| "loss": 0.904, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.0051, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.1262002743484226e-05, | |
| "loss": 1.2771, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.0919067215363515e-05, | |
| "loss": 1.2444, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2.05761316872428e-05, | |
| "loss": 0.0077, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 2.0233196159122085e-05, | |
| "loss": 0.022, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.9890260631001374e-05, | |
| "loss": 0.3176, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.954732510288066e-05, | |
| "loss": 1.4719, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.9204389574759944e-05, | |
| "loss": 0.4367, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.8861454046639233e-05, | |
| "loss": 0.1277, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0024, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_accuracy": 0.8357487922705314, | |
| "eval_loss": 0.8664024472236633, | |
| "eval_runtime": 56.3506, | |
| "eval_samples_per_second": 3.673, | |
| "eval_steps_per_second": 3.673, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.8175582990397804e-05, | |
| "loss": 0.7364, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.7832647462277096e-05, | |
| "loss": 1.2463, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1.748971193415638e-05, | |
| "loss": 0.7369, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1.7146776406035666e-05, | |
| "loss": 0.0088, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.6803840877914955e-05, | |
| "loss": 0.4225, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.646090534979424e-05, | |
| "loss": 0.0073, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.6117969821673525e-05, | |
| "loss": 0.369, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 1.5775034293552814e-05, | |
| "loss": 0.0054, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 1.426, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.5089163237311384e-05, | |
| "loss": 0.3638, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.4746227709190675e-05, | |
| "loss": 0.0531, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.440329218106996e-05, | |
| "loss": 0.0038, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.4060356652949247e-05, | |
| "loss": 0.0046, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.3717421124828534e-05, | |
| "loss": 0.0037, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.3374485596707819e-05, | |
| "loss": 0.0671, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1.3031550068587106e-05, | |
| "loss": 0.4538, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1.2688614540466393e-05, | |
| "loss": 0.5033, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.0055, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.2002743484224967e-05, | |
| "loss": 0.0027, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.1659807956104254e-05, | |
| "loss": 0.4349, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.1316872427983539e-05, | |
| "loss": 0.0044, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1.0973936899862826e-05, | |
| "loss": 0.0026, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1.0631001371742113e-05, | |
| "loss": 0.5004, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.02880658436214e-05, | |
| "loss": 0.4907, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.945130315500687e-06, | |
| "loss": 0.0008, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.602194787379972e-06, | |
| "loss": 0.4545, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0051, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9912430644035339, | |
| "eval_runtime": 56.763, | |
| "eval_samples_per_second": 3.647, | |
| "eval_steps_per_second": 3.647, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.916323731138548e-06, | |
| "loss": 0.0019, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.573388203017833e-06, | |
| "loss": 0.0845, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 8.23045267489712e-06, | |
| "loss": 0.0052, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 7.887517146776407e-06, | |
| "loss": 0.0027, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.544581618655692e-06, | |
| "loss": 0.0018, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 7.20164609053498e-06, | |
| "loss": 0.0025, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.858710562414267e-06, | |
| "loss": 0.2634, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 6.515775034293553e-06, | |
| "loss": 0.1462, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.4832, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 5.829903978052127e-06, | |
| "loss": 0.6503, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 5.486968449931413e-06, | |
| "loss": 0.6113, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 5.1440329218107e-06, | |
| "loss": 0.0016, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 4.801097393689986e-06, | |
| "loss": 0.1483, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 4.458161865569274e-06, | |
| "loss": 0.48, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 4.11522633744856e-06, | |
| "loss": 1.1156, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.772290809327846e-06, | |
| "loss": 0.0007, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.4293552812071335e-06, | |
| "loss": 0.7245, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.0007, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.7434842249657065e-06, | |
| "loss": 0.0042, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.400548696844993e-06, | |
| "loss": 0.0077, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2.05761316872428e-06, | |
| "loss": 0.026, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 1.7146776406035667e-06, | |
| "loss": 0.0019, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 1.3717421124828533e-06, | |
| "loss": 0.4788, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 1.02880658436214e-06, | |
| "loss": 0.0367, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 6.858710562414266e-07, | |
| "loss": 0.0242, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 3.429355281207133e-07, | |
| "loss": 0.004, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.0, | |
| "loss": 0.3863, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_accuracy": 0.8647342995169082, | |
| "eval_loss": 0.6859284043312073, | |
| "eval_runtime": 55.2825, | |
| "eval_samples_per_second": 3.744, | |
| "eval_steps_per_second": 3.744, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "step": 1620, | |
| "total_flos": 2.0187506515909018e+18, | |
| "train_loss": 0.5581286859681347, | |
| "train_runtime": 1319.7859, | |
| "train_samples_per_second": 1.227, | |
| "train_steps_per_second": 1.227 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_loss": 0.781327486038208, | |
| "eval_runtime": 54.5863, | |
| "eval_samples_per_second": 3.536, | |
| "eval_steps_per_second": 3.536, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_loss": 0.781327486038208, | |
| "eval_runtime": 51.196, | |
| "eval_samples_per_second": 3.77, | |
| "eval_steps_per_second": 3.77, | |
| "step": 1620 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1620, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 2.0187506515909018e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |