File size: 1,612 Bytes
46ff548 |
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 |
{
"best_metric": 0.596153624823046,
"best_model_checkpoint": "output/pretraining/vihealthbert-w_unsup-SynPD/lr3e-5_wr0.1_wd0.0/checkpoint-10000",
"epoch": 1.7232465965879717,
"eval_steps": 5000,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017232465965879716,
"grad_norm": 41.827266693115234,
"learning_rate": 5.169739789763915e-09,
"loss": 13.7242,
"step": 1
},
{
"epoch": 0.8616232982939859,
"grad_norm": 5.6151957511901855,
"learning_rate": 2.584869894881958e-05,
"loss": 7.0234,
"step": 5000
},
{
"epoch": 0.8616232982939859,
"eval_accuracy": 0.5576033171446898,
"eval_loss": 2.590928077697754,
"eval_runtime": 37.589,
"eval_samples_per_second": 260.023,
"eval_steps_per_second": 16.255,
"step": 5000
},
{
"epoch": 1.7232465965879717,
"grad_norm": 4.410743713378906,
"learning_rate": 2.758917801137343e-05,
"loss": 5.2736,
"step": 10000
},
{
"epoch": 1.7232465965879717,
"eval_accuracy": 0.596153624823046,
"eval_loss": 2.188957452774048,
"eval_runtime": 37.6297,
"eval_samples_per_second": 259.741,
"eval_steps_per_second": 16.237,
"step": 10000
}
],
"logging_steps": 5000,
"max_steps": 58030,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 5000,
"total_flos": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|