File size: 1,335 Bytes
2860767 |
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 |
{
"best_metric": 1.108055830001831,
"best_model_checkpoint": "/kaggle/output/checkpoint-2000",
"epoch": 0.08148631029986962,
"eval_steps": 1000,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.7777777777777777e-11,
"loss": 1.2358,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 2.7750000000000004e-08,
"loss": 1.1519,
"step": 1000
},
{
"epoch": 0.04,
"eval_accuracy": 0.3201596806387226,
"eval_loss": 1.1120171546936035,
"eval_runtime": 29.027,
"eval_samples_per_second": 172.598,
"eval_steps_per_second": 21.601,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 5.5527777777777784e-08,
"loss": 1.128,
"step": 2000
},
{
"epoch": 0.08,
"eval_accuracy": 0.31796407185628744,
"eval_loss": 1.108055830001831,
"eval_runtime": 28.9944,
"eval_samples_per_second": 172.792,
"eval_steps_per_second": 21.625,
"step": 2000
}
],
"logging_steps": 1000,
"max_steps": 10000000,
"num_train_epochs": 408,
"save_steps": 1000,
"total_flos": 2090411753472000.0,
"trial_name": null,
"trial_params": null
}
|