File size: 1,702 Bytes
f80b0e3 |
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 |
{
"best_metric": 1.1045255661010742,
"best_model_checkpoint": "/kaggle/output/checkpoint-2000",
"epoch": 0.12222946544980444,
"eval_steps": 1000,
"global_step": 3000,
"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": 1.1065,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 2.7750000000000004e-08,
"loss": 1.1586,
"step": 1000
},
{
"epoch": 0.04,
"eval_accuracy": 0.32954091816367265,
"eval_loss": 1.1065887212753296,
"eval_runtime": 54.4372,
"eval_samples_per_second": 92.033,
"eval_steps_per_second": 11.518,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 5.5527777777777784e-08,
"loss": 1.1259,
"step": 2000
},
{
"epoch": 0.08,
"eval_accuracy": 0.3435129740518962,
"eval_loss": 1.1045255661010742,
"eval_runtime": 54.458,
"eval_samples_per_second": 91.997,
"eval_steps_per_second": 11.513,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 8.327777777777778e-08,
"loss": 1.1229,
"step": 3000
},
{
"epoch": 0.12,
"eval_accuracy": 0.3441117764471058,
"eval_loss": 1.1050777435302734,
"eval_runtime": 54.349,
"eval_samples_per_second": 92.182,
"eval_steps_per_second": 11.537,
"step": 3000
}
],
"logging_steps": 1000,
"max_steps": 10000000,
"num_train_epochs": 408,
"save_steps": 1000,
"total_flos": 6271065391104000.0,
"trial_name": null,
"trial_params": null
}
|