File size: 1,174 Bytes
da692b5 |
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 |
{
"best_metric": 0.7710371819960861,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-766",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 766,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.5445048809051514,
"learning_rate": 0.0001354005618154073,
"loss": 0.4902,
"step": 766
},
{
"epoch": 1.0,
"eval_accuracy": 0.7710371819960861,
"eval_f1": 0.7943760984182776,
"eval_loss": 0.4425993263721466,
"eval_precision": 0.7208931419457735,
"eval_recall": 0.8845401174168297,
"eval_runtime": 133.7206,
"eval_samples_per_second": 7.643,
"eval_steps_per_second": 1.914,
"step": 766
}
],
"logging_steps": 500,
"max_steps": 7660,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"alpha": 0.7711149722361785,
"learning_rate": 0.0001504450686837859,
"num_train_epochs": 10,
"temperature": 20
}
}
|