File size: 1,364 Bytes
e7398b7 |
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 |
{
"best_metric": 0.8592321755027422,
"best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-12\\checkpoint-240",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 240,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 6.854342606336822e-05,
"loss": 0.499,
"step": 120
},
{
"epoch": 1.0,
"eval_accuracy": 0.8555758683729433,
"eval_loss": 0.48665618896484375,
"eval_runtime": 10.8301,
"eval_samples_per_second": 202.03,
"eval_steps_per_second": 1.662,
"step": 120
},
{
"epoch": 2.0,
"learning_rate": 5.140756954752616e-05,
"loss": 0.4699,
"step": 240
},
{
"epoch": 2.0,
"eval_accuracy": 0.8592321755027422,
"eval_loss": 0.48114827275276184,
"eval_runtime": 10.9276,
"eval_samples_per_second": 200.227,
"eval_steps_per_second": 1.647,
"step": 240
}
],
"logging_steps": 500,
"max_steps": 600,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 4005990775584.0,
"trial_name": null,
"trial_params": {
"learning_rate": 8.567928257921027e-05,
"num_train_epochs": 5,
"per_device_train_batch_size": 64,
"seed": 10
}
}
|