File size: 1,719 Bytes
bb14641 |
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 60 61 62 63 64 65 66 67 68 69 70 71 |
{
"best_metric": 0.6984848484848485,
"best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-0\\checkpoint-165",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 165,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 2.1639231036686423e-05,
"loss": 0.3688,
"step": 55
},
{
"epoch": 1.0,
"eval_accuracy": 0.6378787878787879,
"eval_loss": 0.3670942187309265,
"eval_runtime": 3.2946,
"eval_samples_per_second": 600.98,
"eval_steps_per_second": 4.856,
"step": 55
},
{
"epoch": 2.0,
"learning_rate": 1.6229423277514814e-05,
"loss": 0.3633,
"step": 110
},
{
"epoch": 2.0,
"eval_accuracy": 0.6782828282828283,
"eval_loss": 0.3586779534816742,
"eval_runtime": 3.2782,
"eval_samples_per_second": 603.989,
"eval_steps_per_second": 4.881,
"step": 110
},
{
"epoch": 3.0,
"learning_rate": 1.0819615518343211e-05,
"loss": 0.3544,
"step": 165
},
{
"epoch": 3.0,
"eval_accuracy": 0.6984848484848485,
"eval_loss": 0.3513254225254059,
"eval_runtime": 3.3521,
"eval_samples_per_second": 590.677,
"eval_steps_per_second": 4.773,
"step": 165
}
],
"logging_steps": 500,
"max_steps": 275,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 2524547079600.0,
"trial_name": null,
"trial_params": {
"alpha": 0.5339855376932713,
"learning_rate": 2.7049038795858027e-05,
"num_train_epochs": 5,
"temperature": 24
}
}
|