bit-50-IDRiD / trainer_state.json
Fu-chiang's picture
Upload 8 files
24e451c
{
"best_metric": 0.6310679611650486,
"best_model_checkpoint": "bit-50-IDRiD\\checkpoint-37",
"epoch": 24.666666666666668,
"global_step": 37,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.67,
"eval_accuracy": 0.1650485436893204,
"eval_loss": 2.3867640495300293,
"eval_runtime": 9.4798,
"eval_samples_per_second": 10.865,
"eval_steps_per_second": 0.211,
"step": 1
},
{
"epoch": 2.0,
"eval_accuracy": 0.5242718446601942,
"eval_loss": 1.456685185432434,
"eval_runtime": 8.8435,
"eval_samples_per_second": 11.647,
"eval_steps_per_second": 0.226,
"step": 3
},
{
"epoch": 2.67,
"eval_accuracy": 0.3106796116504854,
"eval_loss": 1.688151240348816,
"eval_runtime": 9.0288,
"eval_samples_per_second": 11.408,
"eval_steps_per_second": 0.222,
"step": 4
},
{
"epoch": 4.0,
"eval_accuracy": 0.42718446601941745,
"eval_loss": 1.3363385200500488,
"eval_runtime": 8.6671,
"eval_samples_per_second": 11.884,
"eval_steps_per_second": 0.231,
"step": 6
},
{
"epoch": 4.67,
"eval_accuracy": 0.44660194174757284,
"eval_loss": 1.308953881263733,
"eval_runtime": 8.7719,
"eval_samples_per_second": 11.742,
"eval_steps_per_second": 0.228,
"step": 7
},
{
"epoch": 6.0,
"eval_accuracy": 0.5339805825242718,
"eval_loss": 1.2151198387145996,
"eval_runtime": 8.9493,
"eval_samples_per_second": 11.509,
"eval_steps_per_second": 0.223,
"step": 9
},
{
"epoch": 6.67,
"learning_rate": 4.4444444444444447e-05,
"loss": 1.5527,
"step": 10
},
{
"epoch": 6.67,
"eval_accuracy": 0.49514563106796117,
"eval_loss": 1.2200932502746582,
"eval_runtime": 9.0152,
"eval_samples_per_second": 11.425,
"eval_steps_per_second": 0.222,
"step": 10
},
{
"epoch": 8.0,
"eval_accuracy": 0.5533980582524272,
"eval_loss": 1.131609320640564,
"eval_runtime": 9.0143,
"eval_samples_per_second": 11.426,
"eval_steps_per_second": 0.222,
"step": 12
},
{
"epoch": 8.67,
"eval_accuracy": 0.5728155339805825,
"eval_loss": 1.1541801691055298,
"eval_runtime": 8.744,
"eval_samples_per_second": 11.779,
"eval_steps_per_second": 0.229,
"step": 13
},
{
"epoch": 10.0,
"eval_accuracy": 0.47572815533980584,
"eval_loss": 1.2354609966278076,
"eval_runtime": 8.8063,
"eval_samples_per_second": 11.696,
"eval_steps_per_second": 0.227,
"step": 15
},
{
"epoch": 10.67,
"eval_accuracy": 0.5728155339805825,
"eval_loss": 1.0986073017120361,
"eval_runtime": 8.837,
"eval_samples_per_second": 11.656,
"eval_steps_per_second": 0.226,
"step": 16
},
{
"epoch": 12.0,
"eval_accuracy": 0.5728155339805825,
"eval_loss": 1.1264944076538086,
"eval_runtime": 8.8171,
"eval_samples_per_second": 11.682,
"eval_steps_per_second": 0.227,
"step": 18
},
{
"epoch": 12.67,
"eval_accuracy": 0.5242718446601942,
"eval_loss": 1.1883245706558228,
"eval_runtime": 8.8398,
"eval_samples_per_second": 11.652,
"eval_steps_per_second": 0.226,
"step": 19
},
{
"epoch": 13.33,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.8728,
"step": 20
},
{
"epoch": 14.0,
"eval_accuracy": 0.5922330097087378,
"eval_loss": 1.0414934158325195,
"eval_runtime": 8.8456,
"eval_samples_per_second": 11.644,
"eval_steps_per_second": 0.226,
"step": 21
},
{
"epoch": 14.67,
"eval_accuracy": 0.6213592233009708,
"eval_loss": 1.0244377851486206,
"eval_runtime": 8.8085,
"eval_samples_per_second": 11.693,
"eval_steps_per_second": 0.227,
"step": 22
},
{
"epoch": 16.0,
"eval_accuracy": 0.5728155339805825,
"eval_loss": 1.0664492845535278,
"eval_runtime": 9.0371,
"eval_samples_per_second": 11.397,
"eval_steps_per_second": 0.221,
"step": 24
},
{
"epoch": 16.67,
"eval_accuracy": 0.6019417475728155,
"eval_loss": 1.1014405488967896,
"eval_runtime": 8.9067,
"eval_samples_per_second": 11.564,
"eval_steps_per_second": 0.225,
"step": 25
},
{
"epoch": 18.0,
"eval_accuracy": 0.5533980582524272,
"eval_loss": 1.1310096979141235,
"eval_runtime": 9.404,
"eval_samples_per_second": 10.953,
"eval_steps_per_second": 0.213,
"step": 27
},
{
"epoch": 18.67,
"eval_accuracy": 0.6019417475728155,
"eval_loss": 1.1294002532958984,
"eval_runtime": 8.9554,
"eval_samples_per_second": 11.501,
"eval_steps_per_second": 0.223,
"step": 28
},
{
"epoch": 20.0,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.6827,
"step": 30
},
{
"epoch": 20.0,
"eval_accuracy": 0.5922330097087378,
"eval_loss": 1.1656121015548706,
"eval_runtime": 8.789,
"eval_samples_per_second": 11.719,
"eval_steps_per_second": 0.228,
"step": 30
},
{
"epoch": 20.67,
"eval_accuracy": 0.6116504854368932,
"eval_loss": 1.1699755191802979,
"eval_runtime": 9.0412,
"eval_samples_per_second": 11.392,
"eval_steps_per_second": 0.221,
"step": 31
},
{
"epoch": 22.0,
"eval_accuracy": 0.6116504854368932,
"eval_loss": 1.1977097988128662,
"eval_runtime": 8.8963,
"eval_samples_per_second": 11.578,
"eval_steps_per_second": 0.225,
"step": 33
},
{
"epoch": 22.67,
"eval_accuracy": 0.5825242718446602,
"eval_loss": 1.1683080196380615,
"eval_runtime": 9.0689,
"eval_samples_per_second": 11.358,
"eval_steps_per_second": 0.221,
"step": 34
},
{
"epoch": 24.0,
"eval_accuracy": 0.6116504854368932,
"eval_loss": 1.1035082340240479,
"eval_runtime": 8.6561,
"eval_samples_per_second": 11.899,
"eval_steps_per_second": 0.231,
"step": 36
},
{
"epoch": 24.67,
"eval_accuracy": 0.6310679611650486,
"eval_loss": 1.1037455797195435,
"eval_runtime": 8.9451,
"eval_samples_per_second": 11.515,
"eval_steps_per_second": 0.224,
"step": 37
}
],
"max_steps": 50,
"num_train_epochs": 50,
"total_flos": 6.985992208656384e+17,
"trial_name": null,
"trial_params": null
}