meetmayaat's picture
Training in progress, epoch 0
0df1958
{
"best_metric": 0.8904109589041096,
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-616",
"epoch": 1.4983766233766234,
"global_step": 616,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 8.064516129032258e-06,
"loss": 2.0959,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 1.6129032258064517e-05,
"loss": 2.3574,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 2.4193548387096777e-05,
"loss": 2.2398,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 3.2258064516129034e-05,
"loss": 2.337,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 4.032258064516129e-05,
"loss": 2.3571,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 4.8387096774193554e-05,
"loss": 2.2421,
"step": 60
},
{
"epoch": 0.11,
"learning_rate": 4.927797833935018e-05,
"loss": 2.2291,
"step": 70
},
{
"epoch": 0.13,
"learning_rate": 4.837545126353791e-05,
"loss": 2.1179,
"step": 80
},
{
"epoch": 0.15,
"learning_rate": 4.747292418772563e-05,
"loss": 2.1622,
"step": 90
},
{
"epoch": 0.16,
"learning_rate": 4.657039711191336e-05,
"loss": 1.7782,
"step": 100
},
{
"epoch": 0.18,
"learning_rate": 4.566787003610109e-05,
"loss": 1.7005,
"step": 110
},
{
"epoch": 0.19,
"learning_rate": 4.4765342960288806e-05,
"loss": 1.466,
"step": 120
},
{
"epoch": 0.21,
"learning_rate": 4.386281588447654e-05,
"loss": 1.591,
"step": 130
},
{
"epoch": 0.23,
"learning_rate": 4.296028880866426e-05,
"loss": 1.6504,
"step": 140
},
{
"epoch": 0.24,
"learning_rate": 4.205776173285199e-05,
"loss": 1.4864,
"step": 150
},
{
"epoch": 0.26,
"learning_rate": 4.115523465703972e-05,
"loss": 1.4457,
"step": 160
},
{
"epoch": 0.28,
"learning_rate": 4.0252707581227436e-05,
"loss": 1.0274,
"step": 170
},
{
"epoch": 0.29,
"learning_rate": 3.935018050541516e-05,
"loss": 1.2666,
"step": 180
},
{
"epoch": 0.31,
"learning_rate": 3.844765342960289e-05,
"loss": 1.0744,
"step": 190
},
{
"epoch": 0.32,
"learning_rate": 3.754512635379062e-05,
"loss": 1.089,
"step": 200
},
{
"epoch": 0.34,
"learning_rate": 3.664259927797834e-05,
"loss": 0.808,
"step": 210
},
{
"epoch": 0.36,
"learning_rate": 3.574007220216607e-05,
"loss": 0.8,
"step": 220
},
{
"epoch": 0.37,
"learning_rate": 3.483754512635379e-05,
"loss": 1.0105,
"step": 230
},
{
"epoch": 0.39,
"learning_rate": 3.3935018050541516e-05,
"loss": 1.1979,
"step": 240
},
{
"epoch": 0.41,
"learning_rate": 3.303249097472924e-05,
"loss": 0.9307,
"step": 250
},
{
"epoch": 0.42,
"learning_rate": 3.212996389891697e-05,
"loss": 0.3521,
"step": 260
},
{
"epoch": 0.44,
"learning_rate": 3.12274368231047e-05,
"loss": 1.4001,
"step": 270
},
{
"epoch": 0.45,
"learning_rate": 3.032490974729242e-05,
"loss": 0.5175,
"step": 280
},
{
"epoch": 0.47,
"learning_rate": 2.9422382671480147e-05,
"loss": 0.1668,
"step": 290
},
{
"epoch": 0.49,
"learning_rate": 2.851985559566787e-05,
"loss": 0.5459,
"step": 300
},
{
"epoch": 0.5,
"eval_accuracy": 0.6894977168949772,
"eval_loss": 0.7228595614433289,
"eval_runtime": 29.1738,
"eval_samples_per_second": 7.507,
"eval_steps_per_second": 3.771,
"step": 309
},
{
"epoch": 1.0,
"learning_rate": 2.7617328519855596e-05,
"loss": 1.5459,
"step": 310
},
{
"epoch": 1.02,
"learning_rate": 2.6714801444043324e-05,
"loss": 0.4643,
"step": 320
},
{
"epoch": 1.03,
"learning_rate": 2.581227436823105e-05,
"loss": 0.8259,
"step": 330
},
{
"epoch": 1.05,
"learning_rate": 2.4909747292418774e-05,
"loss": 0.6214,
"step": 340
},
{
"epoch": 1.07,
"learning_rate": 2.40072202166065e-05,
"loss": 0.8843,
"step": 350
},
{
"epoch": 1.08,
"learning_rate": 2.3104693140794227e-05,
"loss": 0.2658,
"step": 360
},
{
"epoch": 1.1,
"learning_rate": 2.220216606498195e-05,
"loss": 0.3902,
"step": 370
},
{
"epoch": 1.12,
"learning_rate": 2.1299638989169676e-05,
"loss": 0.5593,
"step": 380
},
{
"epoch": 1.13,
"learning_rate": 2.0397111913357404e-05,
"loss": 0.1929,
"step": 390
},
{
"epoch": 1.15,
"learning_rate": 1.9494584837545125e-05,
"loss": 0.3911,
"step": 400
},
{
"epoch": 1.16,
"learning_rate": 1.8592057761732854e-05,
"loss": 0.2596,
"step": 410
},
{
"epoch": 1.18,
"learning_rate": 1.768953068592058e-05,
"loss": 0.2383,
"step": 420
},
{
"epoch": 1.2,
"learning_rate": 1.6787003610108303e-05,
"loss": 0.6246,
"step": 430
},
{
"epoch": 1.21,
"learning_rate": 1.588447653429603e-05,
"loss": 0.6346,
"step": 440
},
{
"epoch": 1.23,
"learning_rate": 1.4981949458483754e-05,
"loss": 0.0803,
"step": 450
},
{
"epoch": 1.25,
"learning_rate": 1.407942238267148e-05,
"loss": 0.5086,
"step": 460
},
{
"epoch": 1.26,
"learning_rate": 1.3176895306859207e-05,
"loss": 0.4873,
"step": 470
},
{
"epoch": 1.28,
"learning_rate": 1.2274368231046932e-05,
"loss": 0.3952,
"step": 480
},
{
"epoch": 1.29,
"learning_rate": 1.1371841155234658e-05,
"loss": 0.3487,
"step": 490
},
{
"epoch": 1.31,
"learning_rate": 1.0469314079422383e-05,
"loss": 0.4474,
"step": 500
},
{
"epoch": 1.33,
"learning_rate": 9.56678700361011e-06,
"loss": 0.1324,
"step": 510
},
{
"epoch": 1.34,
"learning_rate": 8.664259927797834e-06,
"loss": 0.2684,
"step": 520
},
{
"epoch": 1.36,
"learning_rate": 7.76173285198556e-06,
"loss": 0.1551,
"step": 530
},
{
"epoch": 1.38,
"learning_rate": 6.859205776173286e-06,
"loss": 0.253,
"step": 540
},
{
"epoch": 1.39,
"learning_rate": 5.956678700361011e-06,
"loss": 0.3344,
"step": 550
},
{
"epoch": 1.41,
"learning_rate": 5.054151624548736e-06,
"loss": 0.456,
"step": 560
},
{
"epoch": 1.42,
"learning_rate": 4.151624548736462e-06,
"loss": 0.7702,
"step": 570
},
{
"epoch": 1.44,
"learning_rate": 3.2490974729241876e-06,
"loss": 0.5202,
"step": 580
},
{
"epoch": 1.46,
"learning_rate": 2.3465703971119136e-06,
"loss": 0.2023,
"step": 590
},
{
"epoch": 1.47,
"learning_rate": 1.4440433212996392e-06,
"loss": 0.682,
"step": 600
},
{
"epoch": 1.49,
"learning_rate": 5.415162454873646e-07,
"loss": 0.2437,
"step": 610
},
{
"epoch": 1.5,
"eval_accuracy": 0.8904109589041096,
"eval_loss": 0.19235651195049286,
"eval_runtime": 28.627,
"eval_samples_per_second": 7.65,
"eval_steps_per_second": 3.843,
"step": 616
},
{
"epoch": 1.5,
"step": 616,
"total_flos": 1.534014946318418e+18,
"train_loss": 0.9356340753253211,
"train_runtime": 447.2539,
"train_samples_per_second": 2.755,
"train_steps_per_second": 1.377
},
{
"epoch": 1.5,
"eval_accuracy": 0.8683168316831683,
"eval_loss": 0.26337864995002747,
"eval_runtime": 136.0921,
"eval_samples_per_second": 7.421,
"eval_steps_per_second": 3.711,
"step": 616
},
{
"epoch": 1.5,
"eval_accuracy": 0.8683168316831683,
"eval_loss": 0.26337864995002747,
"eval_runtime": 146.5181,
"eval_samples_per_second": 6.893,
"eval_steps_per_second": 3.447,
"step": 616
}
],
"max_steps": 616,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.534014946318418e+18,
"trial_name": null,
"trial_params": null
}