yerx's picture
End of training
d1f40fd
{
"best_metric": 1.0,
"best_model_checkpoint": "videomae-base-finetuned-basketball-subset-v2/checkpoint-404",
"epoch": 4.009803921568627,
"global_step": 816,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 6.0975609756097564e-06,
"loss": 0.6571,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.6573,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 1.8292682926829268e-05,
"loss": 0.7806,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.8591,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 3.048780487804878e-05,
"loss": 0.6489,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.7533,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 4.26829268292683e-05,
"loss": 0.576,
"step": 70
},
{
"epoch": 0.1,
"learning_rate": 4.878048780487805e-05,
"loss": 1.0713,
"step": 80
},
{
"epoch": 0.11,
"learning_rate": 4.945504087193461e-05,
"loss": 0.4372,
"step": 90
},
{
"epoch": 0.12,
"learning_rate": 4.877384196185286e-05,
"loss": 0.5813,
"step": 100
},
{
"epoch": 0.13,
"learning_rate": 4.809264305177112e-05,
"loss": 1.1109,
"step": 110
},
{
"epoch": 0.15,
"learning_rate": 4.741144414168938e-05,
"loss": 1.4496,
"step": 120
},
{
"epoch": 0.16,
"learning_rate": 4.673024523160763e-05,
"loss": 0.6032,
"step": 130
},
{
"epoch": 0.17,
"learning_rate": 4.604904632152589e-05,
"loss": 2.0923,
"step": 140
},
{
"epoch": 0.18,
"learning_rate": 4.5367847411444145e-05,
"loss": 1.4158,
"step": 150
},
{
"epoch": 0.2,
"learning_rate": 4.46866485013624e-05,
"loss": 1.5632,
"step": 160
},
{
"epoch": 0.21,
"learning_rate": 4.400544959128066e-05,
"loss": 1.1707,
"step": 170
},
{
"epoch": 0.22,
"learning_rate": 4.332425068119891e-05,
"loss": 0.4736,
"step": 180
},
{
"epoch": 0.23,
"learning_rate": 4.264305177111717e-05,
"loss": 2.0593,
"step": 190
},
{
"epoch": 0.25,
"learning_rate": 4.196185286103542e-05,
"loss": 1.7747,
"step": 200
},
{
"epoch": 0.25,
"eval_accuracy": 0.5,
"eval_loss": 2.5059080123901367,
"eval_runtime": 0.4908,
"eval_samples_per_second": 4.075,
"eval_steps_per_second": 4.075,
"step": 202
},
{
"epoch": 1.01,
"learning_rate": 4.128065395095368e-05,
"loss": 0.706,
"step": 210
},
{
"epoch": 1.02,
"learning_rate": 4.0599455040871935e-05,
"loss": 1.2504,
"step": 220
},
{
"epoch": 1.03,
"learning_rate": 3.9918256130790195e-05,
"loss": 1.8594,
"step": 230
},
{
"epoch": 1.05,
"learning_rate": 3.923705722070845e-05,
"loss": 0.8968,
"step": 240
},
{
"epoch": 1.06,
"learning_rate": 3.85558583106267e-05,
"loss": 0.739,
"step": 250
},
{
"epoch": 1.07,
"learning_rate": 3.787465940054496e-05,
"loss": 1.2789,
"step": 260
},
{
"epoch": 1.08,
"learning_rate": 3.719346049046322e-05,
"loss": 0.8226,
"step": 270
},
{
"epoch": 1.1,
"learning_rate": 3.651226158038147e-05,
"loss": 0.9322,
"step": 280
},
{
"epoch": 1.11,
"learning_rate": 3.583106267029973e-05,
"loss": 0.4803,
"step": 290
},
{
"epoch": 1.12,
"learning_rate": 3.5149863760217985e-05,
"loss": 0.4243,
"step": 300
},
{
"epoch": 1.13,
"learning_rate": 3.446866485013624e-05,
"loss": 0.0077,
"step": 310
},
{
"epoch": 1.14,
"learning_rate": 3.37874659400545e-05,
"loss": 0.5999,
"step": 320
},
{
"epoch": 1.16,
"learning_rate": 3.310626702997276e-05,
"loss": 1.2867,
"step": 330
},
{
"epoch": 1.17,
"learning_rate": 3.242506811989101e-05,
"loss": 2.3124,
"step": 340
},
{
"epoch": 1.18,
"learning_rate": 3.174386920980927e-05,
"loss": 0.9884,
"step": 350
},
{
"epoch": 1.19,
"learning_rate": 3.106267029972752e-05,
"loss": 0.2988,
"step": 360
},
{
"epoch": 1.21,
"learning_rate": 3.038147138964578e-05,
"loss": 0.9146,
"step": 370
},
{
"epoch": 1.22,
"learning_rate": 2.9700272479564035e-05,
"loss": 1.9739,
"step": 380
},
{
"epoch": 1.23,
"learning_rate": 2.901907356948229e-05,
"loss": 0.7482,
"step": 390
},
{
"epoch": 1.24,
"learning_rate": 2.8337874659400547e-05,
"loss": 0.0199,
"step": 400
},
{
"epoch": 1.25,
"eval_accuracy": 1.0,
"eval_loss": 0.008221009746193886,
"eval_runtime": 0.4787,
"eval_samples_per_second": 4.178,
"eval_steps_per_second": 4.178,
"step": 404
},
{
"epoch": 2.01,
"learning_rate": 2.76566757493188e-05,
"loss": 1.4992,
"step": 410
},
{
"epoch": 2.02,
"learning_rate": 2.6975476839237056e-05,
"loss": 0.085,
"step": 420
},
{
"epoch": 2.03,
"learning_rate": 2.6294277929155313e-05,
"loss": 1.2553,
"step": 430
},
{
"epoch": 2.04,
"learning_rate": 2.5613079019073572e-05,
"loss": 0.5826,
"step": 440
},
{
"epoch": 2.06,
"learning_rate": 2.4931880108991825e-05,
"loss": 1.4869,
"step": 450
},
{
"epoch": 2.07,
"learning_rate": 2.425068119891008e-05,
"loss": 0.5711,
"step": 460
},
{
"epoch": 2.08,
"learning_rate": 2.356948228882834e-05,
"loss": 0.0089,
"step": 470
},
{
"epoch": 2.09,
"learning_rate": 2.2888283378746594e-05,
"loss": 0.5027,
"step": 480
},
{
"epoch": 2.11,
"learning_rate": 2.220708446866485e-05,
"loss": 0.4668,
"step": 490
},
{
"epoch": 2.12,
"learning_rate": 2.1525885558583106e-05,
"loss": 0.4391,
"step": 500
},
{
"epoch": 2.13,
"learning_rate": 2.0844686648501363e-05,
"loss": 0.8851,
"step": 510
},
{
"epoch": 2.14,
"learning_rate": 2.016348773841962e-05,
"loss": 0.3284,
"step": 520
},
{
"epoch": 2.15,
"learning_rate": 1.9482288828337875e-05,
"loss": 0.5255,
"step": 530
},
{
"epoch": 2.17,
"learning_rate": 1.880108991825613e-05,
"loss": 1.0862,
"step": 540
},
{
"epoch": 2.18,
"learning_rate": 1.8119891008174387e-05,
"loss": 1.5676,
"step": 550
},
{
"epoch": 2.19,
"learning_rate": 1.7438692098092644e-05,
"loss": 1.2709,
"step": 560
},
{
"epoch": 2.2,
"learning_rate": 1.67574931880109e-05,
"loss": 0.4326,
"step": 570
},
{
"epoch": 2.22,
"learning_rate": 1.6076294277929156e-05,
"loss": 0.0092,
"step": 580
},
{
"epoch": 2.23,
"learning_rate": 1.5395095367847412e-05,
"loss": 0.7223,
"step": 590
},
{
"epoch": 2.24,
"learning_rate": 1.4713896457765669e-05,
"loss": 0.4094,
"step": 600
},
{
"epoch": 2.25,
"eval_accuracy": 1.0,
"eval_loss": 0.03134175017476082,
"eval_runtime": 0.4687,
"eval_samples_per_second": 4.267,
"eval_steps_per_second": 4.267,
"step": 606
},
{
"epoch": 3.0,
"learning_rate": 1.4032697547683923e-05,
"loss": 0.2763,
"step": 610
},
{
"epoch": 3.02,
"learning_rate": 1.3351498637602181e-05,
"loss": 0.8591,
"step": 620
},
{
"epoch": 3.03,
"learning_rate": 1.2670299727520437e-05,
"loss": 0.0039,
"step": 630
},
{
"epoch": 3.04,
"learning_rate": 1.1989100817438692e-05,
"loss": 0.0026,
"step": 640
},
{
"epoch": 3.05,
"learning_rate": 1.130790190735695e-05,
"loss": 0.0036,
"step": 650
},
{
"epoch": 3.07,
"learning_rate": 1.0626702997275204e-05,
"loss": 0.0025,
"step": 660
},
{
"epoch": 3.08,
"learning_rate": 9.94550408719346e-06,
"loss": 1.1266,
"step": 670
},
{
"epoch": 3.09,
"learning_rate": 9.264305177111717e-06,
"loss": 0.497,
"step": 680
},
{
"epoch": 3.1,
"learning_rate": 8.583106267029973e-06,
"loss": 0.0028,
"step": 690
},
{
"epoch": 3.12,
"learning_rate": 7.90190735694823e-06,
"loss": 0.901,
"step": 700
},
{
"epoch": 3.13,
"learning_rate": 7.220708446866485e-06,
"loss": 0.2089,
"step": 710
},
{
"epoch": 3.14,
"learning_rate": 6.539509536784741e-06,
"loss": 1.0508,
"step": 720
},
{
"epoch": 3.15,
"learning_rate": 5.858310626702997e-06,
"loss": 0.004,
"step": 730
},
{
"epoch": 3.16,
"learning_rate": 5.1771117166212534e-06,
"loss": 0.4922,
"step": 740
},
{
"epoch": 3.18,
"learning_rate": 4.49591280653951e-06,
"loss": 0.3897,
"step": 750
},
{
"epoch": 3.19,
"learning_rate": 3.814713896457766e-06,
"loss": 0.003,
"step": 760
},
{
"epoch": 3.2,
"learning_rate": 3.1335149863760217e-06,
"loss": 0.0027,
"step": 770
},
{
"epoch": 3.21,
"learning_rate": 2.452316076294278e-06,
"loss": 0.0159,
"step": 780
},
{
"epoch": 3.23,
"learning_rate": 1.7711171662125342e-06,
"loss": 0.429,
"step": 790
},
{
"epoch": 3.24,
"learning_rate": 1.0899182561307902e-06,
"loss": 0.2331,
"step": 800
},
{
"epoch": 3.25,
"eval_accuracy": 0.5,
"eval_loss": 2.790487051010132,
"eval_runtime": 0.4807,
"eval_samples_per_second": 4.161,
"eval_steps_per_second": 4.161,
"step": 808
},
{
"epoch": 4.0,
"learning_rate": 4.087193460490463e-07,
"loss": 0.0021,
"step": 810
},
{
"epoch": 4.01,
"eval_accuracy": 0.5,
"eval_loss": 2.7916269302368164,
"eval_runtime": 0.9748,
"eval_samples_per_second": 2.052,
"eval_steps_per_second": 2.052,
"step": 816
},
{
"epoch": 4.01,
"step": 816,
"total_flos": 1.0167887050089431e+18,
"train_loss": 0.734293045413306,
"train_runtime": 501.5751,
"train_samples_per_second": 1.627,
"train_steps_per_second": 1.627
},
{
"epoch": 4.01,
"eval_accuracy": 1.0,
"eval_loss": 0.008221009746193886,
"eval_runtime": 0.5089,
"eval_samples_per_second": 3.93,
"eval_steps_per_second": 3.93,
"step": 816
},
{
"epoch": 4.01,
"eval_accuracy": 1.0,
"eval_loss": 0.008221009746193886,
"eval_runtime": 0.5785,
"eval_samples_per_second": 3.457,
"eval_steps_per_second": 3.457,
"step": 816
}
],
"max_steps": 816,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.0167887050089431e+18,
"trial_name": null,
"trial_params": null
}