| { | |
| "best_metric": 0.39916983246803284, | |
| "best_model_checkpoint": "Action_all_10_class/checkpoint-1200", | |
| "epoch": 5.0, | |
| "eval_steps": 100, | |
| "global_step": 1245, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019839357429718877, | |
| "loss": 2.2294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019678714859437752, | |
| "loss": 2.1036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019518072289156628, | |
| "loss": 1.9019, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019357429718875504, | |
| "loss": 1.6396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019196787148594377, | |
| "loss": 1.5942, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019036144578313252, | |
| "loss": 1.3722, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018875502008032128, | |
| "loss": 1.2927, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00018714859437751004, | |
| "loss": 1.2947, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001855421686746988, | |
| "loss": 1.2353, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018393574297188755, | |
| "loss": 1.1348, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.698005698005698, | |
| "eval_loss": 1.0964313745498657, | |
| "eval_runtime": 13.3411, | |
| "eval_samples_per_second": 52.619, | |
| "eval_steps_per_second": 6.596, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001823293172690763, | |
| "loss": 1.0305, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018072289156626507, | |
| "loss": 1.0352, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00017911646586345382, | |
| "loss": 1.0957, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00017751004016064258, | |
| "loss": 1.1747, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017590361445783134, | |
| "loss": 1.0863, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001742971887550201, | |
| "loss": 1.0802, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00017269076305220885, | |
| "loss": 1.0912, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001710843373493976, | |
| "loss": 1.0056, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00016947791164658636, | |
| "loss": 0.9641, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016787148594377512, | |
| "loss": 0.9992, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.7948717948717948, | |
| "eval_loss": 0.7362096309661865, | |
| "eval_runtime": 13.2093, | |
| "eval_samples_per_second": 53.145, | |
| "eval_steps_per_second": 6.662, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016626506024096388, | |
| "loss": 0.9851, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016465863453815263, | |
| "loss": 0.886, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001630522088353414, | |
| "loss": 0.9604, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016144578313253015, | |
| "loss": 0.7707, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9153, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00015839357429718874, | |
| "loss": 0.7581, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001567871485943775, | |
| "loss": 0.6622, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00015518072289156626, | |
| "loss": 0.7251, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00015357429718875501, | |
| "loss": 0.7955, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00015196787148594377, | |
| "loss": 0.8314, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.8205128205128205, | |
| "eval_loss": 0.6410418748855591, | |
| "eval_runtime": 12.6655, | |
| "eval_samples_per_second": 55.426, | |
| "eval_steps_per_second": 6.948, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00015036144578313253, | |
| "loss": 0.845, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014875502008032128, | |
| "loss": 0.7132, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00014714859437751004, | |
| "loss": 0.7161, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001455421686746988, | |
| "loss": 0.7773, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00014393574297188756, | |
| "loss": 0.7676, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0001423293172690763, | |
| "loss": 0.8516, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00014072289156626507, | |
| "loss": 0.6597, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00013911646586345383, | |
| "loss": 0.6998, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00013751004016064258, | |
| "loss": 0.8191, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00013590361445783134, | |
| "loss": 0.7359, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.8247863247863247, | |
| "eval_loss": 0.5803518891334534, | |
| "eval_runtime": 12.2034, | |
| "eval_samples_per_second": 57.525, | |
| "eval_steps_per_second": 7.211, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001342971887550201, | |
| "loss": 0.7354, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013269076305220885, | |
| "loss": 0.7507, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0001310843373493976, | |
| "loss": 0.8088, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012947791164658637, | |
| "loss": 0.7279, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012787148594377512, | |
| "loss": 0.7254, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00012626506024096385, | |
| "loss": 0.6707, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0001246586345381526, | |
| "loss": 0.6482, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00012305220883534137, | |
| "loss": 0.7238, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00012144578313253012, | |
| "loss": 0.6626, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00011983935742971888, | |
| "loss": 0.776, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_accuracy": 0.8376068376068376, | |
| "eval_loss": 0.5489934086799622, | |
| "eval_runtime": 12.4349, | |
| "eval_samples_per_second": 56.454, | |
| "eval_steps_per_second": 7.077, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00011823293172690764, | |
| "loss": 0.8069, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0001166265060240964, | |
| "loss": 0.5448, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00011502008032128515, | |
| "loss": 0.7318, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00011341365461847391, | |
| "loss": 0.5083, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00011180722891566267, | |
| "loss": 0.6493, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0001102008032128514, | |
| "loss": 0.4928, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00010859437751004015, | |
| "loss": 0.5395, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00010698795180722891, | |
| "loss": 0.5588, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00010538152610441767, | |
| "loss": 0.5892, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00010377510040160642, | |
| "loss": 0.614, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.8504273504273504, | |
| "eval_loss": 0.5006864070892334, | |
| "eval_runtime": 12.2103, | |
| "eval_samples_per_second": 57.493, | |
| "eval_steps_per_second": 7.207, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.00010216867469879518, | |
| "loss": 0.7658, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00010056224899598394, | |
| "loss": 0.5152, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 9.89558232931727e-05, | |
| "loss": 0.4941, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 9.734939759036145e-05, | |
| "loss": 0.6831, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.574297188755021e-05, | |
| "loss": 0.5971, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 9.413654618473896e-05, | |
| "loss": 0.5842, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 9.253012048192772e-05, | |
| "loss": 0.5976, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.092369477911648e-05, | |
| "loss": 0.5051, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 8.931726907630522e-05, | |
| "loss": 0.4737, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 8.771084337349398e-05, | |
| "loss": 0.5484, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.5322346091270447, | |
| "eval_runtime": 12.3228, | |
| "eval_samples_per_second": 56.968, | |
| "eval_steps_per_second": 7.141, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 8.610441767068274e-05, | |
| "loss": 0.4436, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 8.449799196787149e-05, | |
| "loss": 0.6452, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 8.289156626506025e-05, | |
| "loss": 0.5724, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 8.128514056224899e-05, | |
| "loss": 0.3933, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.967871485943775e-05, | |
| "loss": 0.5753, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.80722891566265e-05, | |
| "loss": 0.4426, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.646586345381526e-05, | |
| "loss": 0.5442, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.485943775100402e-05, | |
| "loss": 0.4839, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.325301204819278e-05, | |
| "loss": 0.3711, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.164658634538153e-05, | |
| "loss": 0.3844, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_accuracy": 0.8518518518518519, | |
| "eval_loss": 0.5012323260307312, | |
| "eval_runtime": 12.9006, | |
| "eval_samples_per_second": 54.416, | |
| "eval_steps_per_second": 6.821, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 7.004016064257029e-05, | |
| "loss": 0.513, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.843373493975905e-05, | |
| "loss": 0.3505, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 6.68273092369478e-05, | |
| "loss": 0.4022, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 6.522088353413655e-05, | |
| "loss": 0.3574, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 6.36144578313253e-05, | |
| "loss": 0.5703, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.200803212851406e-05, | |
| "loss": 0.4585, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 6.040160642570282e-05, | |
| "loss": 0.3114, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 5.8795180722891576e-05, | |
| "loss": 0.3508, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.718875502008032e-05, | |
| "loss": 0.3614, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.5582329317269076e-05, | |
| "loss": 0.5681, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_accuracy": 0.8589743589743589, | |
| "eval_loss": 0.49228861927986145, | |
| "eval_runtime": 13.1999, | |
| "eval_samples_per_second": 53.182, | |
| "eval_steps_per_second": 6.667, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 5.397590361445783e-05, | |
| "loss": 0.5074, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 5.236947791164659e-05, | |
| "loss": 0.3371, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 5.076305220883535e-05, | |
| "loss": 0.5226, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 4.9156626506024104e-05, | |
| "loss": 0.4462, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 4.7550200803212854e-05, | |
| "loss": 0.4781, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 4.594377510040161e-05, | |
| "loss": 0.4001, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 4.433734939759036e-05, | |
| "loss": 0.4788, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 4.273092369477912e-05, | |
| "loss": 0.4561, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 4.1124497991967875e-05, | |
| "loss": 0.2563, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 3.9518072289156625e-05, | |
| "loss": 0.4315, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.8774928774928775, | |
| "eval_loss": 0.42575880885124207, | |
| "eval_runtime": 13.0968, | |
| "eval_samples_per_second": 53.601, | |
| "eval_steps_per_second": 6.719, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.791164658634538e-05, | |
| "loss": 0.2898, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 3.630522088353414e-05, | |
| "loss": 0.3803, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.4698795180722896e-05, | |
| "loss": 0.2827, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 3.309236947791165e-05, | |
| "loss": 0.3382, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 3.14859437751004e-05, | |
| "loss": 0.3808, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.987951807228916e-05, | |
| "loss": 0.2551, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 2.827309236947791e-05, | |
| "loss": 0.3011, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.4091, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.5060240963855423e-05, | |
| "loss": 0.286, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 2.345381526104418e-05, | |
| "loss": 0.3804, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_accuracy": 0.8675213675213675, | |
| "eval_loss": 0.4324430227279663, | |
| "eval_runtime": 12.1257, | |
| "eval_samples_per_second": 57.894, | |
| "eval_steps_per_second": 7.257, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.1847389558232934e-05, | |
| "loss": 0.2672, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.0240963855421687e-05, | |
| "loss": 0.3661, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.863453815261044e-05, | |
| "loss": 0.3126, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.7028112449799198e-05, | |
| "loss": 0.3455, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.5421686746987955e-05, | |
| "loss": 0.3604, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1.3815261044176708e-05, | |
| "loss": 0.4628, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.2208835341365463e-05, | |
| "loss": 0.4074, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.0602409638554217e-05, | |
| "loss": 0.2512, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 8.995983935742972e-06, | |
| "loss": 0.2974, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 7.389558232931727e-06, | |
| "loss": 0.2887, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "eval_accuracy": 0.8803418803418803, | |
| "eval_loss": 0.39916983246803284, | |
| "eval_runtime": 12.2383, | |
| "eval_samples_per_second": 57.361, | |
| "eval_steps_per_second": 7.191, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.783132530120483e-06, | |
| "loss": 0.3073, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 4.176706827309238e-06, | |
| "loss": 0.2825, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.570281124497992e-06, | |
| "loss": 0.288, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 9.638554216867472e-07, | |
| "loss": 0.3198, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1245, | |
| "total_flos": 1.539101261655982e+18, | |
| "train_loss": 0.6643937945844658, | |
| "train_runtime": 748.7697, | |
| "train_samples_per_second": 26.524, | |
| "train_steps_per_second": 1.663 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1245, | |
| "num_train_epochs": 5, | |
| "save_steps": 100, | |
| "total_flos": 1.539101261655982e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |