cherry-alpaca-pre-experienced-7B / trainer_state.json
Ming Li
Initial commit
e03604b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.896,
"global_step": 7,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13,
"learning_rate": 2e-05,
"loss": 1.5398,
"step": 1
},
{
"epoch": 0.26,
"learning_rate": 1.866025403784439e-05,
"loss": 1.6118,
"step": 2
},
{
"epoch": 0.38,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.3033,
"step": 3
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.1445,
"step": 4
},
{
"epoch": 0.64,
"learning_rate": 5.000000000000003e-06,
"loss": 1.1898,
"step": 5
},
{
"epoch": 0.77,
"learning_rate": 1.339745962155613e-06,
"loss": 1.1864,
"step": 6
},
{
"epoch": 0.9,
"learning_rate": 0.0,
"loss": 1.0916,
"step": 7
},
{
"epoch": 0.9,
"step": 7,
"total_flos": 3035606045163520.0,
"train_loss": 1.2953110592705863,
"train_runtime": 682.8066,
"train_samples_per_second": 1.465,
"train_steps_per_second": 0.01
}
],
"max_steps": 7,
"num_train_epochs": 1,
"total_flos": 3035606045163520.0,
"trial_name": null,
"trial_params": null
}