llama-101 / checkpoint-765 /trainer_state.json
mrichardt's picture
Upload folder using huggingface_hub
11947ee
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 765,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"learning_rate": 0.00013246753246753249,
"loss": 1.6899,
"step": 51
},
{
"epoch": 0.4,
"learning_rate": 0.0001927325581395349,
"loss": 1.4327,
"step": 102
},
{
"epoch": 0.6,
"learning_rate": 0.00017790697674418605,
"loss": 1.3405,
"step": 153
},
{
"epoch": 0.8,
"learning_rate": 0.00016308139534883722,
"loss": 1.3404,
"step": 204
},
{
"epoch": 1.0,
"learning_rate": 0.00014825581395348837,
"loss": 1.3189,
"step": 255
},
{
"epoch": 1.2,
"learning_rate": 0.00013343023255813952,
"loss": 1.27,
"step": 306
},
{
"epoch": 1.4,
"learning_rate": 0.00011860465116279071,
"loss": 1.2726,
"step": 357
},
{
"epoch": 1.6,
"learning_rate": 0.00010377906976744187,
"loss": 1.2476,
"step": 408
},
{
"epoch": 1.8,
"learning_rate": 8.895348837209302e-05,
"loss": 1.2493,
"step": 459
},
{
"epoch": 2.0,
"learning_rate": 7.412790697674419e-05,
"loss": 1.2236,
"step": 510
},
{
"epoch": 2.2,
"learning_rate": 5.9302325581395356e-05,
"loss": 1.1867,
"step": 561
},
{
"epoch": 2.4,
"learning_rate": 4.447674418604651e-05,
"loss": 1.1888,
"step": 612
},
{
"epoch": 2.6,
"learning_rate": 2.9651162790697678e-05,
"loss": 1.1866,
"step": 663
},
{
"epoch": 2.8,
"learning_rate": 1.4825581395348839e-05,
"loss": 1.178,
"step": 714
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 1.1577,
"step": 765
}
],
"max_steps": 765,
"num_train_epochs": 3,
"total_flos": 3.175173851185152e+16,
"trial_name": null,
"trial_params": null
}