File size: 1,394 Bytes
e291318 |
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 |
{
"best_metric": 0.8979591836734694,
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-19\\checkpoint-1100",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1100,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.91,
"learning_rate": 4.3587497718473865e-05,
"loss": 1.2013,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.8816326530612245,
"eval_loss": 0.4765537679195404,
"eval_runtime": 1.211,
"eval_samples_per_second": 202.313,
"eval_steps_per_second": 13.212,
"step": 550
},
{
"epoch": 1.82,
"learning_rate": 3.0767645448334495e-05,
"loss": 0.4355,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.8979591836734694,
"eval_loss": 0.3723006844520569,
"eval_runtime": 1.249,
"eval_samples_per_second": 196.157,
"eval_steps_per_second": 12.81,
"step": 1100
}
],
"logging_steps": 500,
"max_steps": 2200,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 1957164674850.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"learning_rate": 5.640734998861324e-05,
"num_train_epochs": 4,
"per_device_train_batch_size": 4,
"seed": 36
}
}
|