File size: 1,736 Bytes
7771c3e |
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 72 73 74 75 76 77 78 79 80 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.019,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.02,
"learning_rate": 9.960000000000001e-06,
"loss": 0.5615,
"step": 500
},
{
"epoch": 3.02,
"learning_rate": 1e-05,
"loss": 0.3273,
"step": 1000
},
{
"epoch": 3.02,
"eval_loss": 0.4225325584411621,
"eval_runtime": 1489.9228,
"eval_samples_per_second": 3.09,
"eval_steps_per_second": 0.193,
"eval_wer": 20.82533081951615,
"step": 1000
},
{
"epoch": 5.01,
"learning_rate": 1e-05,
"loss": 0.1859,
"step": 1500
},
{
"epoch": 7.0,
"learning_rate": 1e-05,
"loss": 0.0923,
"step": 2000
},
{
"epoch": 7.0,
"eval_loss": 0.46434369683265686,
"eval_runtime": 1504.5618,
"eval_samples_per_second": 3.06,
"eval_steps_per_second": 0.191,
"eval_wer": 21.22002361108664,
"step": 2000
},
{
"epoch": 8.03,
"learning_rate": 1e-05,
"loss": 0.0369,
"step": 2500
},
{
"epoch": 10.02,
"learning_rate": 1e-05,
"loss": 0.0164,
"step": 3000
},
{
"epoch": 10.02,
"eval_loss": 0.5403426885604858,
"eval_runtime": 1504.7378,
"eval_samples_per_second": 3.06,
"eval_steps_per_second": 0.191,
"eval_wer": 22.962662766725987,
"step": 3000
}
],
"max_steps": 10000,
"num_train_epochs": 9223372036854775807,
"total_flos": 6.2122904322048e+18,
"trial_name": null,
"trial_params": null
}
|