| { | |
| "best_metric": 0.8636363636363636, | |
| "best_model_checkpoint": "videomae-base-finetuned-2\\checkpoint-555", | |
| "epoch": 2.32972972972973, | |
| "eval_steps": 500, | |
| "global_step": 555, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 9.139641761779785, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 1.3861, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 8.826565742492676, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.2321, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 6.707639217376709, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 1.243, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 11.348919868469238, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.1312, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09009009009009009, | |
| "grad_norm": 14.494072914123535, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 1.3058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 7.667250156402588, | |
| "learning_rate": 4.9599198396793586e-05, | |
| "loss": 1.2019, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12612612612612611, | |
| "grad_norm": 8.06010627746582, | |
| "learning_rate": 4.859719438877756e-05, | |
| "loss": 1.2813, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 10.494473457336426, | |
| "learning_rate": 4.7595190380761524e-05, | |
| "loss": 1.2292, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 11.735258102416992, | |
| "learning_rate": 4.6593186372745496e-05, | |
| "loss": 1.2424, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18018018018018017, | |
| "grad_norm": 7.723865509033203, | |
| "learning_rate": 4.559118236472946e-05, | |
| "loss": 1.2314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1981981981981982, | |
| "grad_norm": 8.27652645111084, | |
| "learning_rate": 4.458917835671343e-05, | |
| "loss": 1.0673, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 7.197485446929932, | |
| "learning_rate": 4.358717434869739e-05, | |
| "loss": 1.337, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23423423423423423, | |
| "grad_norm": 9.621479988098145, | |
| "learning_rate": 4.2585170340681366e-05, | |
| "loss": 1.2103, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.25225225225225223, | |
| "grad_norm": 8.090988159179688, | |
| "learning_rate": 4.158316633266534e-05, | |
| "loss": 1.1458, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 8.642086029052734, | |
| "learning_rate": 4.0581162324649304e-05, | |
| "loss": 1.0949, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 6.245614051818848, | |
| "learning_rate": 3.957915831663327e-05, | |
| "loss": 0.9812, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3063063063063063, | |
| "grad_norm": 10.789504051208496, | |
| "learning_rate": 3.8577154308617235e-05, | |
| "loss": 0.9814, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 17.914480209350586, | |
| "learning_rate": 3.75751503006012e-05, | |
| "loss": 0.8667, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.33513513513513515, | |
| "eval_accuracy": 0.5727272727272728, | |
| "eval_loss": 0.9740895628929138, | |
| "eval_runtime": 280.3552, | |
| "eval_samples_per_second": 0.392, | |
| "eval_steps_per_second": 0.1, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0072072072072071, | |
| "grad_norm": 12.168312072753906, | |
| "learning_rate": 3.657314629258517e-05, | |
| "loss": 0.9448, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0252252252252252, | |
| "grad_norm": 7.322641849517822, | |
| "learning_rate": 3.5571142284569145e-05, | |
| "loss": 1.1193, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0432432432432432, | |
| "grad_norm": 12.514275550842285, | |
| "learning_rate": 3.456913827655311e-05, | |
| "loss": 0.8378, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0612612612612613, | |
| "grad_norm": 7.457886695861816, | |
| "learning_rate": 3.356713426853708e-05, | |
| "loss": 0.7454, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0792792792792794, | |
| "grad_norm": 11.546749114990234, | |
| "learning_rate": 3.256513026052104e-05, | |
| "loss": 0.8304, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0972972972972972, | |
| "grad_norm": 10.54076099395752, | |
| "learning_rate": 3.156312625250501e-05, | |
| "loss": 1.0602, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.1153153153153152, | |
| "grad_norm": 31.803747177124023, | |
| "learning_rate": 3.0561122244488974e-05, | |
| "loss": 0.806, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1333333333333333, | |
| "grad_norm": 28.31694793701172, | |
| "learning_rate": 2.955911823647295e-05, | |
| "loss": 0.8338, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.1513513513513514, | |
| "grad_norm": 9.744572639465332, | |
| "learning_rate": 2.8557114228456915e-05, | |
| "loss": 0.8696, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1693693693693694, | |
| "grad_norm": 12.256711959838867, | |
| "learning_rate": 2.7555110220440884e-05, | |
| "loss": 0.7245, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1873873873873875, | |
| "grad_norm": 7.700608730316162, | |
| "learning_rate": 2.655310621242485e-05, | |
| "loss": 0.6561, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2054054054054055, | |
| "grad_norm": 14.277639389038086, | |
| "learning_rate": 2.5551102204408815e-05, | |
| "loss": 0.7837, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2234234234234234, | |
| "grad_norm": 9.197588920593262, | |
| "learning_rate": 2.4549098196392788e-05, | |
| "loss": 0.5502, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2414414414414414, | |
| "grad_norm": 3.099351167678833, | |
| "learning_rate": 2.3547094188376757e-05, | |
| "loss": 0.5195, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.2594594594594595, | |
| "grad_norm": 9.323990821838379, | |
| "learning_rate": 2.2545090180360722e-05, | |
| "loss": 1.1324, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.2774774774774775, | |
| "grad_norm": 10.672691345214844, | |
| "learning_rate": 2.1543086172344688e-05, | |
| "loss": 0.4475, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.2954954954954956, | |
| "grad_norm": 0.755842924118042, | |
| "learning_rate": 2.054108216432866e-05, | |
| "loss": 0.5673, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3135135135135134, | |
| "grad_norm": 1.0543122291564941, | |
| "learning_rate": 1.9539078156312626e-05, | |
| "loss": 0.7184, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.3315315315315315, | |
| "grad_norm": 12.980474472045898, | |
| "learning_rate": 1.8537074148296592e-05, | |
| "loss": 0.8111, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.3351351351351353, | |
| "eval_accuracy": 0.7363636363636363, | |
| "eval_loss": 0.8580251336097717, | |
| "eval_runtime": 277.5592, | |
| "eval_samples_per_second": 0.396, | |
| "eval_steps_per_second": 0.101, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.0144144144144143, | |
| "grad_norm": 15.273543357849121, | |
| "learning_rate": 1.7535070140280564e-05, | |
| "loss": 0.3997, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0324324324324325, | |
| "grad_norm": 9.675086975097656, | |
| "learning_rate": 1.653306613226453e-05, | |
| "loss": 0.2966, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.0504504504504504, | |
| "grad_norm": 0.6464720368385315, | |
| "learning_rate": 1.5531062124248495e-05, | |
| "loss": 0.3275, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0684684684684687, | |
| "grad_norm": 5.569362163543701, | |
| "learning_rate": 1.4529058116232466e-05, | |
| "loss": 0.1516, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.0864864864864865, | |
| "grad_norm": 20.961273193359375, | |
| "learning_rate": 1.3527054108216433e-05, | |
| "loss": 0.5888, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.1045045045045043, | |
| "grad_norm": 27.309669494628906, | |
| "learning_rate": 1.25250501002004e-05, | |
| "loss": 0.4586, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.1225225225225226, | |
| "grad_norm": 2.0433521270751953, | |
| "learning_rate": 1.152304609218437e-05, | |
| "loss": 0.3667, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.1405405405405404, | |
| "grad_norm": 0.46590688824653625, | |
| "learning_rate": 1.0521042084168337e-05, | |
| "loss": 0.2505, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.1585585585585587, | |
| "grad_norm": 0.8750420808792114, | |
| "learning_rate": 9.519038076152304e-06, | |
| "loss": 0.2555, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.1765765765765765, | |
| "grad_norm": 0.5527063608169556, | |
| "learning_rate": 8.517034068136273e-06, | |
| "loss": 0.2616, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.1945945945945944, | |
| "grad_norm": 2.8728528022766113, | |
| "learning_rate": 7.515030060120242e-06, | |
| "loss": 0.1438, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.2126126126126127, | |
| "grad_norm": 1.5662002563476562, | |
| "learning_rate": 6.513026052104208e-06, | |
| "loss": 0.5138, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.2306306306306305, | |
| "grad_norm": 70.13788604736328, | |
| "learning_rate": 5.511022044088176e-06, | |
| "loss": 0.5573, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.2486486486486488, | |
| "grad_norm": 2.147181510925293, | |
| "learning_rate": 4.5090180360721445e-06, | |
| "loss": 0.2309, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.2666666666666666, | |
| "grad_norm": 73.13829040527344, | |
| "learning_rate": 3.5070140280561122e-06, | |
| "loss": 0.2092, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.2846846846846844, | |
| "grad_norm": 33.50334167480469, | |
| "learning_rate": 2.5050100200400804e-06, | |
| "loss": 0.2009, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.3027027027027027, | |
| "grad_norm": 58.736778259277344, | |
| "learning_rate": 1.5030060120240482e-06, | |
| "loss": 0.2882, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.3207207207207206, | |
| "grad_norm": 7.180970191955566, | |
| "learning_rate": 5.01002004008016e-07, | |
| "loss": 0.4008, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.5939798355102539, | |
| "eval_runtime": 273.4292, | |
| "eval_samples_per_second": 0.402, | |
| "eval_steps_per_second": 0.102, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "step": 555, | |
| "total_flos": 2.758836207590572e+18, | |
| "train_loss": 0.7599288858808912, | |
| "train_runtime": 12937.383, | |
| "train_samples_per_second": 0.172, | |
| "train_steps_per_second": 0.043 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "eval_accuracy": 0.9487179487179487, | |
| "eval_loss": 0.15456415712833405, | |
| "eval_runtime": 1766.8377, | |
| "eval_samples_per_second": 0.419, | |
| "eval_steps_per_second": 0.105, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "eval_accuracy": 0.8530805687203792, | |
| "eval_loss": 0.54169100522995, | |
| "eval_runtime": 505.2243, | |
| "eval_samples_per_second": 0.418, | |
| "eval_steps_per_second": 0.105, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.5939798355102539, | |
| "eval_runtime": 272.8909, | |
| "eval_samples_per_second": 0.403, | |
| "eval_steps_per_second": 0.103, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "eval_accuracy": 0.8636363636363636, | |
| "eval_loss": 0.5939797163009644, | |
| "eval_runtime": 262.8979, | |
| "eval_samples_per_second": 0.418, | |
| "eval_steps_per_second": 0.107, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.32972972972973, | |
| "eval_accuracy": 0.8530805687203792, | |
| "eval_loss": 0.5416910648345947, | |
| "eval_runtime": 510.4742, | |
| "eval_samples_per_second": 0.413, | |
| "eval_steps_per_second": 0.104, | |
| "step": 555 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 555, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 2.758836207590572e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |