sphobert-spam-binary / trainer_state.json
AnnyNguyen's picture
Upload trainer_state.json with huggingface_hub
4bb1511 verified
{
"best_global_step": 1338,
"best_metric": 0.8786015776943197,
"best_model_checkpoint": "outputs/sphobert-spam-binary/checkpoint-1338",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1338,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.4428337812423706,
"learning_rate": 4.998771926094749e-05,
"loss": 0.3018,
"step": 446
},
{
"epoch": 1.0,
"eval_accuracy": 0.9073724007561437,
"eval_f1": 0.8758155809022719,
"eval_loss": 0.27634894847869873,
"eval_precision": 0.9034638245542119,
"eval_recall": 0.856103394906635,
"eval_runtime": 6.114,
"eval_samples_per_second": 259.568,
"eval_steps_per_second": 8.178,
"step": 446
},
{
"epoch": 2.0,
"grad_norm": 9.62130355834961,
"learning_rate": 4.995077872180951e-05,
"loss": 0.2142,
"step": 892
},
{
"epoch": 2.0,
"eval_accuracy": 0.909892879647133,
"eval_f1": 0.8781504551216691,
"eval_loss": 0.29870447516441345,
"eval_precision": 0.9112078181649159,
"eval_recall": 0.8556400876364294,
"eval_runtime": 6.1075,
"eval_samples_per_second": 259.846,
"eval_steps_per_second": 8.187,
"step": 892
},
{
"epoch": 3.0,
"grad_norm": 8.09521484375,
"learning_rate": 4.988921477641713e-05,
"loss": 0.1644,
"step": 1338
},
{
"epoch": 3.0,
"eval_accuracy": 0.908002520478891,
"eval_f1": 0.8786015776943197,
"eval_loss": 0.3062317669391632,
"eval_precision": 0.8975415956568336,
"eval_recall": 0.8638419328254708,
"eval_runtime": 6.1159,
"eval_samples_per_second": 259.489,
"eval_steps_per_second": 8.175,
"step": 1338
}
],
"logging_steps": 446,
"max_steps": 44600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}