File size: 1,385 Bytes
ae15d8f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
{
"best_metric": 0.28564417362213135,
"best_model_checkpoint": "ontonotes_roberta-large/checkpoint-36046",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 36046,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.651404619216919,
"learning_rate": 1.960019974477057e-05,
"loss": 0.4522,
"step": 36046
},
{
"epoch": 1.0,
"eval_loss": 0.28564417362213135,
"eval_runtime": 161.0463,
"eval_samples_per_second": 165.884,
"eval_steps_per_second": 20.739,
"step": 36046
}
],
"logging_steps": 500,
"max_steps": 1802300,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"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": 3.4898747588982e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|