| { | |
| "best_metric": 0.2868094742298126, | |
| "best_model_checkpoint": "DrishtiSharma/finetuned-SwinT-Indian-Food-Classification-v1/checkpoint-1400", | |
| "epoch": 5.0, | |
| "global_step": 1665, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001992792792792793, | |
| "loss": 8.5776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019807807807807807, | |
| "loss": 4.601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019687687687687687, | |
| "loss": 2.306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019567567567567567, | |
| "loss": 1.784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019447447447447448, | |
| "loss": 1.8375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001932732732732733, | |
| "loss": 1.2307, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019207207207207208, | |
| "loss": 1.2008, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019087087087087088, | |
| "loss": 1.1303, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00018966966966966968, | |
| "loss": 0.7806, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00018846846846846848, | |
| "loss": 1.2433, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.8193411264612115, | |
| "eval_loss": 0.7067487239837646, | |
| "eval_runtime": 41.0344, | |
| "eval_samples_per_second": 22.932, | |
| "eval_steps_per_second": 2.876, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00018726726726726726, | |
| "loss": 1.2738, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018606606606606606, | |
| "loss": 0.9205, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018486486486486486, | |
| "loss": 1.0657, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00018366366366366366, | |
| "loss": 0.7326, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001824624624624625, | |
| "loss": 0.9267, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018126126126126127, | |
| "loss": 0.6556, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00018006006006006007, | |
| "loss": 0.9394, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00017885885885885887, | |
| "loss": 0.8358, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00017765765765765767, | |
| "loss": 0.8192, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017645645645645647, | |
| "loss": 0.6458, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.8788522848034006, | |
| "eval_loss": 0.4691758453845978, | |
| "eval_runtime": 40.9715, | |
| "eval_samples_per_second": 22.967, | |
| "eval_steps_per_second": 2.88, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00017525525525525525, | |
| "loss": 0.7785, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017405405405405405, | |
| "loss": 0.7238, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00017285285285285285, | |
| "loss": 0.6252, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00017165165165165168, | |
| "loss": 0.5769, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00017045045045045045, | |
| "loss": 0.7919, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00016924924924924926, | |
| "loss": 0.9191, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00016804804804804806, | |
| "loss": 0.7977, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016684684684684686, | |
| "loss": 1.0148, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00016564564564564566, | |
| "loss": 0.6755, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00016444444444444444, | |
| "loss": 0.635, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.8682252922422954, | |
| "eval_loss": 0.48639556765556335, | |
| "eval_runtime": 40.8306, | |
| "eval_samples_per_second": 23.046, | |
| "eval_steps_per_second": 2.89, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00016324324324324324, | |
| "loss": 0.6479, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016204204204204204, | |
| "loss": 0.6987, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00016084084084084087, | |
| "loss": 0.6282, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00015963963963963964, | |
| "loss": 0.6216, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00015843843843843844, | |
| "loss": 0.539, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00015723723723723725, | |
| "loss": 0.2988, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00015603603603603605, | |
| "loss": 0.3224, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00015483483483483485, | |
| "loss": 0.6158, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00015363363363363362, | |
| "loss": 0.484, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00015243243243243243, | |
| "loss": 0.6219, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.8831030818278427, | |
| "eval_loss": 0.4240102171897888, | |
| "eval_runtime": 40.6001, | |
| "eval_samples_per_second": 23.177, | |
| "eval_steps_per_second": 2.906, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00015123123123123123, | |
| "loss": 0.5453, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00015003003003003006, | |
| "loss": 0.56, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014882882882882883, | |
| "loss": 0.3875, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00014762762762762763, | |
| "loss": 0.5187, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00014642642642642643, | |
| "loss": 0.5176, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00014522522522522524, | |
| "loss": 0.8876, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00014402402402402404, | |
| "loss": 0.3874, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0001428228228228228, | |
| "loss": 0.7958, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00014162162162162161, | |
| "loss": 0.5271, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00014042042042042042, | |
| "loss": 0.4889, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.8947927736450585, | |
| "eval_loss": 0.3840125799179077, | |
| "eval_runtime": 41.0356, | |
| "eval_samples_per_second": 22.931, | |
| "eval_steps_per_second": 2.876, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00013921921921921924, | |
| "loss": 0.5692, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00013801801801801802, | |
| "loss": 0.5541, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00013681681681681682, | |
| "loss": 0.6267, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013561561561561562, | |
| "loss": 0.55, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013441441441441442, | |
| "loss": 0.425, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013321321321321323, | |
| "loss": 0.3501, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.000132012012012012, | |
| "loss": 0.5891, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001308108108108108, | |
| "loss": 0.5129, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012960960960960963, | |
| "loss": 0.6074, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012840840840840843, | |
| "loss": 0.2963, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.895855472901169, | |
| "eval_loss": 0.42787039279937744, | |
| "eval_runtime": 40.9188, | |
| "eval_samples_per_second": 22.997, | |
| "eval_steps_per_second": 2.884, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00012720720720720723, | |
| "loss": 0.3153, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.000126006006006006, | |
| "loss": 0.4458, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0001248048048048048, | |
| "loss": 0.5593, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001236036036036036, | |
| "loss": 0.4581, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001224024024024024, | |
| "loss": 0.4293, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001212012012012012, | |
| "loss": 0.3959, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6051, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0001187987987987988, | |
| "loss": 0.4068, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0001175975975975976, | |
| "loss": 0.4732, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00011639639639639641, | |
| "loss": 0.4405, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.9117959617428267, | |
| "eval_loss": 0.35077255964279175, | |
| "eval_runtime": 41.1075, | |
| "eval_samples_per_second": 22.891, | |
| "eval_steps_per_second": 2.871, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0001151951951951952, | |
| "loss": 0.2055, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.000113993993993994, | |
| "loss": 0.3782, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0001127927927927928, | |
| "loss": 0.2767, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001115915915915916, | |
| "loss": 0.275, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00011039039039039039, | |
| "loss": 0.3466, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00010918918918918919, | |
| "loss": 0.5017, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00010798798798798799, | |
| "loss": 0.3676, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0001067867867867868, | |
| "loss": 0.3576, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0001055855855855856, | |
| "loss": 0.4545, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00010438438438438438, | |
| "loss": 0.3803, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.9086078639744952, | |
| "eval_loss": 0.36589011549949646, | |
| "eval_runtime": 40.8562, | |
| "eval_samples_per_second": 23.032, | |
| "eval_steps_per_second": 2.888, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00010318318318318319, | |
| "loss": 0.2818, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00010198198198198199, | |
| "loss": 0.4102, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00010078078078078079, | |
| "loss": 0.3617, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 9.957957957957959e-05, | |
| "loss": 0.4926, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 9.837837837837839e-05, | |
| "loss": 0.2893, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.717717717717718e-05, | |
| "loss": 0.2848, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.597597597597598e-05, | |
| "loss": 0.292, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.477477477477478e-05, | |
| "loss": 0.5481, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.357357357357359e-05, | |
| "loss": 0.2587, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.237237237237237e-05, | |
| "loss": 0.3499, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_accuracy": 0.9213602550478215, | |
| "eval_loss": 0.33470773696899414, | |
| "eval_runtime": 40.8732, | |
| "eval_samples_per_second": 23.022, | |
| "eval_steps_per_second": 2.887, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.117117117117118e-05, | |
| "loss": 0.3355, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 8.996996996996996e-05, | |
| "loss": 0.3938, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 8.876876876876878e-05, | |
| "loss": 0.3229, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.756756756756758e-05, | |
| "loss": 0.2761, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 8.636636636636637e-05, | |
| "loss": 0.362, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.516516516516517e-05, | |
| "loss": 0.3807, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.396396396396397e-05, | |
| "loss": 0.3084, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.276276276276277e-05, | |
| "loss": 0.664, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 8.156156156156156e-05, | |
| "loss": 0.3162, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.036036036036036e-05, | |
| "loss": 0.3131, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9277364505844846, | |
| "eval_loss": 0.290975421667099, | |
| "eval_runtime": 40.7778, | |
| "eval_samples_per_second": 23.076, | |
| "eval_steps_per_second": 2.894, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.915915915915915e-05, | |
| "loss": 0.152, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.795795795795797e-05, | |
| "loss": 0.3068, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.675675675675677e-05, | |
| "loss": 0.1023, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 0.4051, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.435435435435436e-05, | |
| "loss": 0.2915, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.315315315315316e-05, | |
| "loss": 0.1638, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.195195195195196e-05, | |
| "loss": 0.1406, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.075075075075075e-05, | |
| "loss": 0.1844, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 6.954954954954955e-05, | |
| "loss": 0.4238, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 6.834834834834835e-05, | |
| "loss": 0.3036, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.9107332624867163, | |
| "eval_loss": 0.3937636613845825, | |
| "eval_runtime": 40.8699, | |
| "eval_samples_per_second": 23.024, | |
| "eval_steps_per_second": 2.887, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 6.714714714714715e-05, | |
| "loss": 0.366, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 6.594594594594596e-05, | |
| "loss": 0.1498, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.474474474474474e-05, | |
| "loss": 0.241, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 6.354354354354355e-05, | |
| "loss": 0.3446, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.234234234234235e-05, | |
| "loss": 0.1943, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 6.114114114114115e-05, | |
| "loss": 0.2137, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 5.993993993993994e-05, | |
| "loss": 0.1259, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 5.873873873873874e-05, | |
| "loss": 0.1947, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.753753753753755e-05, | |
| "loss": 0.138, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 5.6336336336336336e-05, | |
| "loss": 0.2697, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.9171094580233794, | |
| "eval_loss": 0.35658442974090576, | |
| "eval_runtime": 40.9373, | |
| "eval_samples_per_second": 22.986, | |
| "eval_steps_per_second": 2.882, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 5.5135135135135144e-05, | |
| "loss": 0.1748, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.393393393393393e-05, | |
| "loss": 0.1407, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 5.2732732732732734e-05, | |
| "loss": 0.316, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.153153153153153e-05, | |
| "loss": 0.1369, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 5.033033033033033e-05, | |
| "loss": 0.2623, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 4.912912912912913e-05, | |
| "loss": 0.0935, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 4.792792792792793e-05, | |
| "loss": 0.2738, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.672672672672673e-05, | |
| "loss": 0.35, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.5525525525525524e-05, | |
| "loss": 0.1173, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 4.432432432432433e-05, | |
| "loss": 0.1551, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_accuracy": 0.9341126461211477, | |
| "eval_loss": 0.3369457423686981, | |
| "eval_runtime": 41.1834, | |
| "eval_samples_per_second": 22.849, | |
| "eval_steps_per_second": 2.865, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 4.312312312312313e-05, | |
| "loss": 0.3394, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.192192192192192e-05, | |
| "loss": 0.2533, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.0720720720720724e-05, | |
| "loss": 0.1894, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 3.951951951951952e-05, | |
| "loss": 0.1789, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.831831831831832e-05, | |
| "loss": 0.0723, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 3.7117117117117115e-05, | |
| "loss": 0.1718, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 3.591591591591592e-05, | |
| "loss": 0.1439, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.471471471471472e-05, | |
| "loss": 0.2211, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 3.351351351351352e-05, | |
| "loss": 0.079, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.2312312312312315e-05, | |
| "loss": 0.0752, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9373007438894793, | |
| "eval_loss": 0.2868094742298126, | |
| "eval_runtime": 41.4456, | |
| "eval_samples_per_second": 22.704, | |
| "eval_steps_per_second": 2.847, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.0999, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.990990990990991e-05, | |
| "loss": 0.1528, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 2.870870870870871e-05, | |
| "loss": 0.1456, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 2.7507507507507508e-05, | |
| "loss": 0.1389, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.6306306306306306e-05, | |
| "loss": 0.0957, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.5105105105105108e-05, | |
| "loss": 0.1156, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 2.3903903903903903e-05, | |
| "loss": 0.16, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.2702702702702705e-05, | |
| "loss": 0.1485, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 2.1501501501501503e-05, | |
| "loss": 0.1667, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.03003003003003e-05, | |
| "loss": 0.132, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_accuracy": 0.9373007438894793, | |
| "eval_loss": 0.3023243546485901, | |
| "eval_runtime": 41.2414, | |
| "eval_samples_per_second": 22.817, | |
| "eval_steps_per_second": 2.861, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 1.90990990990991e-05, | |
| "loss": 0.2626, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 1.78978978978979e-05, | |
| "loss": 0.2645, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.66966966966967e-05, | |
| "loss": 0.1691, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.5495495495495498e-05, | |
| "loss": 0.1964, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 1.4294294294294294e-05, | |
| "loss": 0.1062, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.3093093093093094e-05, | |
| "loss": 0.1863, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.1891891891891893e-05, | |
| "loss": 0.1155, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.0690690690690691e-05, | |
| "loss": 0.1222, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 9.489489489489491e-06, | |
| "loss": 0.0238, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.288288288288289e-06, | |
| "loss": 0.1133, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_accuracy": 0.9415515409139213, | |
| "eval_loss": 0.29777178168296814, | |
| "eval_runtime": 41.1597, | |
| "eval_samples_per_second": 22.862, | |
| "eval_steps_per_second": 2.867, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 7.0870870870870866e-06, | |
| "loss": 0.1734, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.8858858858858865e-06, | |
| "loss": 0.086, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 4.684684684684685e-06, | |
| "loss": 0.0928, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.4834834834834835e-06, | |
| "loss": 0.2043, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 2.2822822822822822e-06, | |
| "loss": 0.1768, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 1.0810810810810812e-06, | |
| "loss": 0.0674, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1665, | |
| "total_flos": 2.6257169541360845e+18, | |
| "train_loss": 0.509146851408589, | |
| "train_runtime": 2159.6535, | |
| "train_samples_per_second": 12.335, | |
| "train_steps_per_second": 0.771 | |
| } | |
| ], | |
| "max_steps": 1665, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.6257169541360845e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |