File size: 1,326 Bytes
ac08c10 |
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 |
{
"best_metric": 0.8061926605504587,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-527",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 527,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 31.228694915771484,
"learning_rate": 7.086160775881376e-05,
"loss": 2.5988,
"step": 527
},
{
"epoch": 1.0,
"eval_accuracy": 0.8061926605504587,
"eval_loss": 1.924224615097046,
"eval_runtime": 2.5772,
"eval_samples_per_second": 338.351,
"eval_steps_per_second": 2.716,
"step": 527
}
],
"logging_steps": 500,
"max_steps": 3689,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8057768762220.0,
"train_batch_size": 128,
"trial_name": null,
"trial_params": {
"alpha": 0.1351029311037084,
"learning_rate": 8.264573854640023e-05,
"num_train_epochs": 7,
"temperature": 16
}
}
|