roberta-base-neg-tags / trainer_state.json
spoiled's picture
End of training
9b2e957
{
"best_metric": 0.001461439998820424,
"best_model_checkpoint": "./roberta-base-neg-tags/checkpoint-940",
"epoch": 4.0,
"global_step": 940,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.9993098939415952,
"eval_f1": 0.0,
"eval_loss": 0.002094547264277935,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 19.1858,
"eval_samples_per_second": 155.896,
"eval_steps_per_second": 9.747,
"step": 235
},
{
"epoch": 2.0,
"eval_accuracy": 0.9996731076565452,
"eval_f1": 0.0,
"eval_loss": 0.0014849244616925716,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 19.2356,
"eval_samples_per_second": 155.493,
"eval_steps_per_second": 9.722,
"step": 470
},
{
"epoch": 2.13,
"learning_rate": 2.340425531914894e-05,
"loss": 0.0073,
"step": 500
},
{
"epoch": 3.0,
"eval_accuracy": 0.9996731076565452,
"eval_f1": 0.0,
"eval_loss": 0.001533312490209937,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 19.1727,
"eval_samples_per_second": 156.003,
"eval_steps_per_second": 9.753,
"step": 705
},
{
"epoch": 4.0,
"eval_accuracy": 0.9996731076565452,
"eval_f1": 0.0,
"eval_loss": 0.001461439998820424,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 19.1982,
"eval_samples_per_second": 155.796,
"eval_steps_per_second": 9.74,
"step": 940
},
{
"epoch": 4.0,
"step": 940,
"total_flos": 1746409535739648.0,
"train_loss": 0.004449349514981534,
"train_runtime": 510.7148,
"train_samples_per_second": 234.965,
"train_steps_per_second": 1.841
}
],
"max_steps": 940,
"num_train_epochs": 4,
"total_flos": 1746409535739648.0,
"trial_name": null,
"trial_params": null
}