doc-img-classification / trainer_state.json
jnmrr's picture
End of training
0e7ad46 verified
{
"best_metric": 0.3483606557377049,
"best_model_checkpoint": "doc-img-classification/checkpoint-17",
"epoch": 0.9855072463768116,
"eval_steps": 500,
"global_step": 17,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.057971014492753624,
"grad_norm": 7.618393898010254,
"learning_rate": 0.0005,
"loss": 1.2624,
"step": 1
},
{
"epoch": 0.6956521739130435,
"grad_norm": 7.588911056518555,
"learning_rate": 0.0003333333333333333,
"loss": 1.7064,
"step": 12
},
{
"epoch": 0.9855072463768116,
"eval_Macro F1": 0.21733759318423854,
"eval_Macro Precision": 0.37635327635327637,
"eval_Macro Recall": 0.35452414439756214,
"eval_Micro F1": 0.3483606557377049,
"eval_Micro Precision": 0.3483606557377049,
"eval_Micro Recall": 0.3483606557377049,
"eval_Weighted F1": 0.21831561305190383,
"eval_Weighted Precision": 0.4016218299005184,
"eval_Weighted Recall": 0.3483606557377049,
"eval_accuracy": 0.3483606557377049,
"eval_loss": 1.0820339918136597,
"eval_runtime": 13.7157,
"eval_samples_per_second": 17.79,
"eval_steps_per_second": 0.583,
"step": 17
},
{
"epoch": 0.9855072463768116,
"step": 17,
"total_flos": 1.686437022030889e+17,
"train_loss": 1.5057464066673727,
"train_runtime": 321.636,
"train_samples_per_second": 6.824,
"train_steps_per_second": 0.053
}
],
"logging_steps": 12,
"max_steps": 17,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 1.686437022030889e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}