File size: 1,553 Bytes
02160f9 |
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 |
{
"best_metric": 0.7326732673267327,
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-3/checkpoint-8",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 16,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.62,
"grad_norm": 0.94398033618927,
"learning_rate": 7.138113611405621e-06,
"loss": 0.6981,
"step": 5
},
{
"epoch": 1.0,
"eval_f1": 0.7326732673267327,
"eval_loss": 0.6864166259765625,
"eval_runtime": 1.3249,
"eval_samples_per_second": 48.305,
"eval_steps_per_second": 6.038,
"step": 8
},
{
"epoch": 1.25,
"grad_norm": 1.5316386222839355,
"learning_rate": 1.1103732284408743e-05,
"loss": 0.683,
"step": 10
},
{
"epoch": 1.88,
"grad_norm": 0.5028849840164185,
"learning_rate": 1.031060854980812e-05,
"loss": 0.6564,
"step": 15
},
{
"epoch": 2.0,
"eval_f1": 0.7326732673267327,
"eval_loss": 0.680694580078125,
"eval_runtime": 1.3565,
"eval_samples_per_second": 47.179,
"eval_steps_per_second": 5.897,
"step": 16
}
],
"logging_steps": 5,
"max_steps": 80,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1863816719524704.0,
"train_batch_size": 24,
"trial_name": null,
"trial_params": {
"learning_rate": 1.1420981778248994e-05,
"per_device_train_batch_size": 24
}
}
|