swin-tiny-patch4-window7-224 / trainer_state.json
HorcruxNo13's picture
Training in progress, epoch 1
04ed437
raw
history blame
3.19 kB
{
"best_metric": 0.7583333333333333,
"best_model_checkpoint": "swin-tiny-patch4-window7-224/checkpoint-48",
"epoch": 7.0,
"eval_steps": 500,
"global_step": 56,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.7333333333333333,
"eval_loss": 0.58155757188797,
"eval_runtime": 1.8232,
"eval_samples_per_second": 131.637,
"eval_steps_per_second": 4.388,
"step": 8
},
{
"epoch": 1.25,
"learning_rate": 4.600000000000001e-05,
"loss": 0.6478,
"step": 10
},
{
"epoch": 2.0,
"eval_accuracy": 0.7333333333333333,
"eval_loss": 0.5633648037910461,
"eval_runtime": 1.8405,
"eval_samples_per_second": 130.396,
"eval_steps_per_second": 4.347,
"step": 16
},
{
"epoch": 2.5,
"learning_rate": 3.6e-05,
"loss": 0.5746,
"step": 20
},
{
"epoch": 3.0,
"eval_accuracy": 0.7375,
"eval_loss": 0.5526280999183655,
"eval_runtime": 1.8724,
"eval_samples_per_second": 128.178,
"eval_steps_per_second": 4.273,
"step": 24
},
{
"epoch": 3.75,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.5414,
"step": 30
},
{
"epoch": 4.0,
"eval_accuracy": 0.7333333333333333,
"eval_loss": 0.6044233441352844,
"eval_runtime": 3.3038,
"eval_samples_per_second": 72.644,
"eval_steps_per_second": 2.421,
"step": 32
},
{
"epoch": 5.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.5159,
"step": 40
},
{
"epoch": 5.0,
"eval_accuracy": 0.7541666666666667,
"eval_loss": 0.5310245156288147,
"eval_runtime": 2.8227,
"eval_samples_per_second": 85.024,
"eval_steps_per_second": 2.834,
"step": 40
},
{
"epoch": 6.0,
"eval_accuracy": 0.7583333333333333,
"eval_loss": 0.5481430888175964,
"eval_runtime": 3.9583,
"eval_samples_per_second": 60.632,
"eval_steps_per_second": 2.021,
"step": 48
},
{
"epoch": 6.25,
"learning_rate": 6e-06,
"loss": 0.4901,
"step": 50
},
{
"epoch": 7.0,
"eval_accuracy": 0.7583333333333333,
"eval_loss": 0.5410298109054565,
"eval_runtime": 2.4531,
"eval_samples_per_second": 97.834,
"eval_steps_per_second": 3.261,
"step": 56
},
{
"epoch": 7.0,
"step": 56,
"total_flos": 1.73991922900992e+17,
"train_loss": 0.5463650396892002,
"train_runtime": 159.2288,
"train_samples_per_second": 43.962,
"train_steps_per_second": 0.352
},
{
"epoch": 7.0,
"eval_accuracy": 0.7366666666666667,
"eval_loss": 0.5300371050834656,
"eval_runtime": 4.2651,
"eval_samples_per_second": 70.339,
"eval_steps_per_second": 2.345,
"step": 56
}
],
"logging_steps": 10,
"max_steps": 56,
"num_train_epochs": 7,
"save_steps": 500,
"total_flos": 1.73991922900992e+17,
"trial_name": null,
"trial_params": null
}