ValA4 / FINAL /trainer_state.json
Egrigor's picture
Training in progress, step 750
b69a252 verified
{
"best_metric": 1.8574875593185425,
"best_model_checkpoint": "C:/WorkingFolder/Models/ValA4\\checkpoint-500",
"epoch": 2.9874055415617127,
"eval_steps": 250,
"global_step": 594,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.256926952141058,
"grad_norm": 1.311490774154663,
"learning_rate": 2.8956228956228958e-05,
"loss": 2.0615,
"step": 250
},
{
"epoch": 1.256926952141058,
"eval_loss": 1.9107320308685303,
"eval_runtime": 19.178,
"eval_samples_per_second": 20.701,
"eval_steps_per_second": 2.607,
"step": 250
},
{
"epoch": 2.513853904282116,
"grad_norm": 1.4435200691223145,
"learning_rate": 7.912457912457913e-06,
"loss": 1.6447,
"step": 500
},
{
"epoch": 2.513853904282116,
"eval_loss": 1.8574875593185425,
"eval_runtime": 19.1861,
"eval_samples_per_second": 20.692,
"eval_steps_per_second": 2.606,
"step": 500
}
],
"logging_steps": 250,
"max_steps": 594,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 250,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"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": true
},
"attributes": {}
}
},
"total_flos": 4583424363724800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}