PagesClassificationModel / trainer_state.json
al-css's picture
End of training
25b105d verified
raw
history blame
1.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 51,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 3.0,
"step": 51,
"total_flos": 3.045462487125811e+16,
"train_loss": 0.1802522621902765,
"train_runtime": 46.5838,
"train_samples_per_second": 8.436,
"train_steps_per_second": 1.095
},
{
"epoch": 3.0,
"eval_accuracy": 1.0,
"eval_loss": 0.003107850207015872,
"eval_runtime": 3.2836,
"eval_samples_per_second": 10.05,
"eval_steps_per_second": 1.523,
"step": 51
},
{
"epoch": 3.0,
"eval_accuracy": 1.0,
"eval_loss": 0.003107850207015872,
"eval_runtime": 3.2096,
"eval_samples_per_second": 10.282,
"eval_steps_per_second": 1.558,
"step": 51
}
],
"logging_steps": 500,
"max_steps": 51,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 3.045462487125811e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}