thesis_distilbert / checkpoint-280 /trainer_state.json
therealfent's picture
Caricamento modello v1
08cb0ff verified
{
"best_global_step": 112,
"best_metric": 0.9024482109227872,
"best_model_checkpoint": "./model_3_distilbert/checkpoint-112",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 280,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.9279279279279279,
"eval_f1_macro": 0.8729977116704806,
"eval_f1_negative": 0.7894736842105263,
"eval_f1_positive": 0.9565217391304348,
"eval_f1_weighted": 0.9219081782010845,
"eval_loss": 0.23420116305351257,
"eval_precision_macro": 0.9583333333333333,
"eval_precision_weighted": 0.9339339339339339,
"eval_recall_macro": 0.8260869565217391,
"eval_recall_weighted": 0.9279279279279279,
"eval_runtime": 1.6193,
"eval_samples_per_second": 68.55,
"eval_steps_per_second": 4.323,
"step": 56
},
{
"epoch": 1.7857142857142856,
"grad_norm": 1.320497989654541,
"learning_rate": 3.9347826086956525e-05,
"loss": 0.3207,
"step": 100
},
{
"epoch": 2.0,
"eval_accuracy": 0.9369369369369369,
"eval_f1_macro": 0.9024482109227872,
"eval_f1_negative": 0.8444444444444444,
"eval_f1_positive": 0.96045197740113,
"eval_f1_weighted": 0.9364143804821771,
"eval_loss": 0.3722859025001526,
"eval_precision_macro": 0.9093462717058223,
"eval_precision_weighted": 0.9361133349897395,
"eval_recall_macro": 0.895998023715415,
"eval_recall_weighted": 0.9369369369369369,
"eval_runtime": 2.2494,
"eval_samples_per_second": 49.346,
"eval_steps_per_second": 3.112,
"step": 112
},
{
"epoch": 3.0,
"eval_accuracy": 0.9279279279279279,
"eval_f1_macro": 0.8903162055335969,
"eval_f1_negative": 0.8260869565217391,
"eval_f1_positive": 0.9545454545454546,
"eval_f1_weighted": 0.9279279279279279,
"eval_loss": 0.3547576367855072,
"eval_precision_macro": 0.8903162055335969,
"eval_precision_weighted": 0.9279279279279279,
"eval_recall_macro": 0.8903162055335969,
"eval_recall_weighted": 0.9279279279279279,
"eval_runtime": 2.2351,
"eval_samples_per_second": 49.662,
"eval_steps_per_second": 3.132,
"step": 168
},
{
"epoch": 3.571428571428571,
"grad_norm": 0.029327843338251114,
"learning_rate": 1.7608695652173915e-05,
"loss": 0.0817,
"step": 200
},
{
"epoch": 4.0,
"eval_accuracy": 0.9369369369369369,
"eval_f1_macro": 0.9024482109227872,
"eval_f1_negative": 0.8444444444444444,
"eval_f1_positive": 0.96045197740113,
"eval_f1_weighted": 0.9364143804821771,
"eval_loss": 0.35270601511001587,
"eval_precision_macro": 0.9093462717058223,
"eval_precision_weighted": 0.9361133349897395,
"eval_recall_macro": 0.895998023715415,
"eval_recall_weighted": 0.9369369369369369,
"eval_runtime": 2.2942,
"eval_samples_per_second": 48.383,
"eval_steps_per_second": 3.051,
"step": 224
},
{
"epoch": 5.0,
"eval_accuracy": 0.9369369369369369,
"eval_f1_macro": 0.9024482109227872,
"eval_f1_negative": 0.8444444444444444,
"eval_f1_positive": 0.96045197740113,
"eval_f1_weighted": 0.9364143804821771,
"eval_loss": 0.35882368683815,
"eval_precision_macro": 0.9093462717058223,
"eval_precision_weighted": 0.9361133349897395,
"eval_recall_macro": 0.895998023715415,
"eval_recall_weighted": 0.9369369369369369,
"eval_runtime": 2.1687,
"eval_samples_per_second": 51.183,
"eval_steps_per_second": 3.228,
"step": 280
}
],
"logging_steps": 100,
"max_steps": 280,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 53990813967840.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}