File size: 1,216 Bytes
60b7616 |
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": 0.5366336633663367,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-297",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 297,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.0489678382873535,
"learning_rate": 0.00030782109688346106,
"loss": 0.6591,
"step": 297
},
{
"epoch": 1.0,
"eval_accuracy": 0.5366336633663367,
"eval_f1": 0.20945945945945946,
"eval_loss": 0.6587525606155396,
"eval_mcc": 0.12699706368366073,
"eval_precision": 0.7045454545454546,
"eval_recall": 0.12301587301587301,
"eval_runtime": 0.9347,
"eval_samples_per_second": 540.253,
"eval_steps_per_second": 17.117,
"step": 297
}
],
"logging_steps": 500,
"max_steps": 1782,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 500,
"total_flos": 730701265980.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9361124407975862,
"learning_rate": 0.0003693853162601533,
"num_train_epochs": 6,
"temperature": 21
}
}
|