File size: 1,550 Bytes
8805a44 |
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 |
{
"best_metric": 0.7583549419422403,
"best_model_checkpoint": "outputs/time_lm_nli/checkpoint-422",
"epoch": 3.0,
"global_step": 633,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 9.666666666666666e-07,
"loss": 0.5392,
"step": 211
},
{
"epoch": 1.0,
"eval_accuracy": 0.7,
"eval_f1": 0.6998718119161117,
"eval_loss": 0.4048246741294861,
"eval_runtime": 5.0256,
"eval_samples_per_second": 596.939,
"eval_steps_per_second": 74.617,
"step": 211
},
{
"epoch": 2.0,
"learning_rate": 9.333333333333333e-07,
"loss": 0.3725,
"step": 422
},
{
"epoch": 2.0,
"eval_accuracy": 0.759,
"eval_f1": 0.7583549419422403,
"eval_loss": 0.3489450216293335,
"eval_runtime": 5.103,
"eval_samples_per_second": 587.885,
"eval_steps_per_second": 73.486,
"step": 422
},
{
"epoch": 3.0,
"learning_rate": 9e-07,
"loss": 0.3158,
"step": 633
},
{
"epoch": 3.0,
"eval_accuracy": 0.7613333333333333,
"eval_f1": 0.7569694772671423,
"eval_loss": 0.3286795914173126,
"eval_runtime": 5.4646,
"eval_samples_per_second": 548.991,
"eval_steps_per_second": 68.624,
"step": 633
}
],
"max_steps": 6330,
"num_train_epochs": 30,
"total_flos": 4296378998080512.0,
"trial_name": null,
"trial_params": null
}
|