hafidber's picture
End of training
52d1049
raw
history blame
5.26 kB
{
"best_metric": 0.8428571428571429,
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-300",
"epoch": 1.5,
"eval_steps": 500,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 1.6666666666666667e-05,
"loss": 2.3028,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.3514,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 2.3305,
"step": 30
},
{
"epoch": 0.13,
"learning_rate": 4.814814814814815e-05,
"loss": 2.2754,
"step": 40
},
{
"epoch": 0.17,
"learning_rate": 4.62962962962963e-05,
"loss": 2.0044,
"step": 50
},
{
"epoch": 0.2,
"learning_rate": 4.4444444444444447e-05,
"loss": 2.1435,
"step": 60
},
{
"epoch": 0.23,
"learning_rate": 4.259259259259259e-05,
"loss": 2.0639,
"step": 70
},
{
"epoch": 0.27,
"learning_rate": 4.074074074074074e-05,
"loss": 1.6206,
"step": 80
},
{
"epoch": 0.3,
"learning_rate": 3.888888888888889e-05,
"loss": 1.7889,
"step": 90
},
{
"epoch": 0.33,
"learning_rate": 3.7037037037037037e-05,
"loss": 1.6838,
"step": 100
},
{
"epoch": 0.37,
"learning_rate": 3.518518518518519e-05,
"loss": 1.3599,
"step": 110
},
{
"epoch": 0.4,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.4852,
"step": 120
},
{
"epoch": 0.43,
"learning_rate": 3.148148148148148e-05,
"loss": 1.4107,
"step": 130
},
{
"epoch": 0.47,
"learning_rate": 2.962962962962963e-05,
"loss": 1.374,
"step": 140
},
{
"epoch": 0.5,
"learning_rate": 2.777777777777778e-05,
"loss": 1.0549,
"step": 150
},
{
"epoch": 0.5,
"eval_accuracy": 0.7571428571428571,
"eval_loss": 0.9527812600135803,
"eval_runtime": 22.0926,
"eval_samples_per_second": 3.168,
"eval_steps_per_second": 1.584,
"step": 150
},
{
"epoch": 1.03,
"learning_rate": 2.5925925925925925e-05,
"loss": 0.8599,
"step": 160
},
{
"epoch": 1.07,
"learning_rate": 2.4074074074074074e-05,
"loss": 1.287,
"step": 170
},
{
"epoch": 1.1,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.9601,
"step": 180
},
{
"epoch": 1.13,
"learning_rate": 2.037037037037037e-05,
"loss": 0.6645,
"step": 190
},
{
"epoch": 1.17,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.6143,
"step": 200
},
{
"epoch": 1.2,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.4838,
"step": 210
},
{
"epoch": 1.23,
"learning_rate": 1.4814814814814815e-05,
"loss": 0.4428,
"step": 220
},
{
"epoch": 1.27,
"learning_rate": 1.2962962962962962e-05,
"loss": 0.7375,
"step": 230
},
{
"epoch": 1.3,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.6078,
"step": 240
},
{
"epoch": 1.33,
"learning_rate": 9.259259259259259e-06,
"loss": 0.4268,
"step": 250
},
{
"epoch": 1.37,
"learning_rate": 7.4074074074074075e-06,
"loss": 0.2414,
"step": 260
},
{
"epoch": 1.4,
"learning_rate": 5.555555555555556e-06,
"loss": 0.4216,
"step": 270
},
{
"epoch": 1.43,
"learning_rate": 3.7037037037037037e-06,
"loss": 0.1838,
"step": 280
},
{
"epoch": 1.47,
"learning_rate": 1.8518518518518519e-06,
"loss": 0.5178,
"step": 290
},
{
"epoch": 1.5,
"learning_rate": 0.0,
"loss": 0.7251,
"step": 300
},
{
"epoch": 1.5,
"eval_accuracy": 0.8428571428571429,
"eval_loss": 0.4445994794368744,
"eval_runtime": 21.5992,
"eval_samples_per_second": 3.241,
"eval_steps_per_second": 1.62,
"step": 300
},
{
"epoch": 1.5,
"step": 300,
"total_flos": 7.47692094062592e+17,
"train_loss": 1.214137753645579,
"train_runtime": 449.6116,
"train_samples_per_second": 1.334,
"train_steps_per_second": 0.667
},
{
"epoch": 1.5,
"eval_accuracy": 0.864516129032258,
"eval_loss": 0.4195975959300995,
"eval_runtime": 49.2274,
"eval_samples_per_second": 3.149,
"eval_steps_per_second": 1.584,
"step": 300
},
{
"epoch": 1.5,
"eval_accuracy": 0.864516129032258,
"eval_loss": 0.4195975959300995,
"eval_runtime": 48.7546,
"eval_samples_per_second": 3.179,
"eval_steps_per_second": 1.6,
"step": 300
}
],
"logging_steps": 10,
"max_steps": 300,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"total_flos": 7.47692094062592e+17,
"trial_name": null,
"trial_params": null
}