Mathildeholst's picture
Training in progress, epoch 1
5935cf0 verified
{
"best_global_step": 939,
"best_metric": 1.253981590270996,
"best_model_checkpoint": "classifier-clinc-MBbase-distilled/run-4/checkpoint-939",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 939,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.8706451612903225,
"eval_loss": 2.7779340744018555,
"eval_runtime": 8.631,
"eval_samples_per_second": 359.169,
"eval_steps_per_second": 11.239,
"step": 313
},
{
"epoch": 1.5974440894568689,
"grad_norm": 10.851899147033691,
"learning_rate": 9.3716719914803e-06,
"loss": 5.0159,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9306451612903226,
"eval_loss": 1.468520998954773,
"eval_runtime": 8.7244,
"eval_samples_per_second": 355.326,
"eval_steps_per_second": 11.118,
"step": 626
},
{
"epoch": 3.0,
"eval_accuracy": 0.94,
"eval_loss": 1.253981590270996,
"eval_runtime": 8.7487,
"eval_samples_per_second": 354.337,
"eval_steps_per_second": 11.087,
"step": 939
}
],
"logging_steps": 500,
"max_steps": 939,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"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": 222488892388608.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.4882441225639443,
"num_train_epochs": 3,
"temperature": 4.967098145590025
}
}