rachidsaid's picture
End of training
15b6d62
{
"best_metric": 0.9142857142857143,
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
"epoch": 3.22972972972973,
"global_step": 148,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.2591,
"step": 10
},
{
"epoch": 0.14,
"learning_rate": 4.81203007518797e-05,
"loss": 2.2132,
"step": 20
},
{
"epoch": 0.2,
"learning_rate": 4.43609022556391e-05,
"loss": 2.1351,
"step": 30
},
{
"epoch": 0.26,
"eval_accuracy": 0.6285714285714286,
"eval_loss": 1.6582270860671997,
"eval_runtime": 48.1772,
"eval_samples_per_second": 1.453,
"eval_steps_per_second": 0.187,
"step": 38
},
{
"epoch": 1.01,
"learning_rate": 4.0601503759398494e-05,
"loss": 1.9093,
"step": 40
},
{
"epoch": 1.08,
"learning_rate": 3.6842105263157895e-05,
"loss": 1.5111,
"step": 50
},
{
"epoch": 1.15,
"learning_rate": 3.3082706766917295e-05,
"loss": 1.1256,
"step": 60
},
{
"epoch": 1.22,
"learning_rate": 2.9323308270676693e-05,
"loss": 0.7409,
"step": 70
},
{
"epoch": 1.26,
"eval_accuracy": 0.7142857142857143,
"eval_loss": 0.8406534194946289,
"eval_runtime": 39.133,
"eval_samples_per_second": 1.789,
"eval_steps_per_second": 0.23,
"step": 76
},
{
"epoch": 2.03,
"learning_rate": 2.556390977443609e-05,
"loss": 0.8077,
"step": 80
},
{
"epoch": 2.09,
"learning_rate": 2.1804511278195487e-05,
"loss": 0.5975,
"step": 90
},
{
"epoch": 2.16,
"learning_rate": 1.8045112781954888e-05,
"loss": 0.6191,
"step": 100
},
{
"epoch": 2.23,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.4333,
"step": 110
},
{
"epoch": 2.26,
"eval_accuracy": 0.8142857142857143,
"eval_loss": 0.5106571316719055,
"eval_runtime": 41.2785,
"eval_samples_per_second": 1.696,
"eval_steps_per_second": 0.218,
"step": 114
},
{
"epoch": 3.04,
"learning_rate": 1.0526315789473684e-05,
"loss": 0.3766,
"step": 120
},
{
"epoch": 3.11,
"learning_rate": 6.766917293233083e-06,
"loss": 0.265,
"step": 130
},
{
"epoch": 3.18,
"learning_rate": 3.007518796992481e-06,
"loss": 0.2766,
"step": 140
},
{
"epoch": 3.23,
"eval_accuracy": 0.9142857142857143,
"eval_loss": 0.3579496741294861,
"eval_runtime": 49.2971,
"eval_samples_per_second": 1.42,
"eval_steps_per_second": 0.183,
"step": 148
},
{
"epoch": 3.23,
"step": 148,
"total_flos": 1.460491890402263e+18,
"train_loss": 1.0465768640105788,
"train_runtime": 3053.3069,
"train_samples_per_second": 0.388,
"train_steps_per_second": 0.048
},
{
"epoch": 3.23,
"eval_accuracy": 0.8516129032258064,
"eval_loss": 0.43549060821533203,
"eval_runtime": 105.4615,
"eval_samples_per_second": 1.47,
"eval_steps_per_second": 0.19,
"step": 148
},
{
"epoch": 3.23,
"eval_accuracy": 0.8516129032258064,
"eval_loss": 0.4354906678199768,
"eval_runtime": 104.5631,
"eval_samples_per_second": 1.482,
"eval_steps_per_second": 0.191,
"step": 148
}
],
"max_steps": 148,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.460491890402263e+18,
"trial_name": null,
"trial_params": null
}