File size: 1,191 Bytes
fd25daf |
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 |
{
"best_metric": 0.7152641878669276,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-52",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 52,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.939810276031494,
"learning_rate": 0.00013471680923458288,
"loss": 0.5033,
"step": 52
},
{
"epoch": 1.0,
"eval_accuracy": 0.7152641878669276,
"eval_f1": 0.712166172106825,
"eval_loss": 0.4479813575744629,
"eval_precision": 0.72,
"eval_recall": 0.7045009784735812,
"eval_runtime": 28.0693,
"eval_samples_per_second": 36.41,
"eval_steps_per_second": 1.14,
"step": 52
}
],
"logging_steps": 500,
"max_steps": 208,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 60,
"trial_name": null,
"trial_params": {
"alpha": 0.7020704368642945,
"learning_rate": 0.00017962241231277718,
"num_train_epochs": 4,
"per_device_train_batch_size": 60,
"temperature": 19
}
}
|