File size: 1,451 Bytes
6cc00de |
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 59 |
{
"best_metric": 0.5148514851485149,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-75",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.31773510575294495,
"learning_rate": 0.00019498896290528944,
"loss": 0.0964,
"step": 75
},
{
"epoch": 1.0,
"eval_accuracy": 0.5148514851485149,
"eval_loss": 0.077483631670475,
"eval_runtime": 57.3954,
"eval_samples_per_second": 8.799,
"eval_steps_per_second": 0.07,
"step": 75
},
{
"epoch": 2.0,
"grad_norm": 0.29849082231521606,
"learning_rate": 0.00014624172217896707,
"loss": 0.0774,
"step": 150
},
{
"epoch": 2.0,
"eval_accuracy": 0.5069306930693069,
"eval_loss": 0.07408903539180756,
"eval_runtime": 57.3815,
"eval_samples_per_second": 8.801,
"eval_steps_per_second": 0.07,
"step": 150
}
],
"logging_steps": 500,
"max_steps": 375,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 1555686566280.0,
"train_batch_size": 128,
"trial_name": null,
"trial_params": {
"alpha": 0.08009223161090917,
"learning_rate": 0.00024373620363161177,
"num_train_epochs": 5,
"temperature": 24
}
}
|