File size: 1,430 Bytes
af94d50 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 3500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.43,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.9928,
"step": 500
},
{
"epoch": 2.86,
"learning_rate": 3.571428571428572e-05,
"loss": 0.736,
"step": 1000
},
{
"epoch": 4.29,
"learning_rate": 2.857142857142857e-05,
"loss": 0.6556,
"step": 1500
},
{
"epoch": 5.71,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.6147,
"step": 2000
},
{
"epoch": 7.14,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.5802,
"step": 2500
},
{
"epoch": 8.57,
"learning_rate": 7.142857142857143e-06,
"loss": 0.5609,
"step": 3000
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.5476,
"step": 3500
},
{
"epoch": 10.0,
"step": 3500,
"total_flos": 4.85866580004864e+16,
"train_loss": 0.6696674455915178,
"train_runtime": 2740.83,
"train_samples_per_second": 12.77,
"train_steps_per_second": 1.277
}
],
"max_steps": 3500,
"num_train_epochs": 10,
"total_flos": 4.85866580004864e+16,
"trial_name": null,
"trial_params": null
}
|