trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 3.7273695420660276,
 "global_step": 7000,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.27,
 "learning_rate": 4.73482428115016e-05,
 "loss": 3.2886,
 "step": 500
 },
 {
 "epoch": 0.53,
 "learning_rate": 4.468583599574015e-05,
 "loss": 3.0659,
 "step": 1000
 },
 {
 "epoch": 0.8,
 "learning_rate": 4.20234291799787e-05,
 "loss": 2.9652,
 "step": 1500
 },
 {
 "epoch": 1.06,
 "learning_rate": 3.9361022364217254e-05,
 "loss": 2.9062,
 "step": 2000
 },
 {
 "epoch": 1.33,
 "learning_rate": 3.669861554845581e-05,
 "loss": 2.7534,
 "step": 2500
 },
 {
 "epoch": 1.6,
 "learning_rate": 3.4036208732694355e-05,
 "loss": 2.7478,
 "step": 3000
 },
 {
 "epoch": 1.86,
 "learning_rate": 3.137380191693291e-05,
 "loss": 2.6986,
 "step": 3500
 },
 {
 "epoch": 2.13,
 "learning_rate": 2.8711395101171462e-05,
 "loss": 2.6463,
 "step": 4000
 },
 {
 "epoch": 2.4,
 "learning_rate": 2.6054313099041534e-05,
 "loss": 2.606,
 "step": 4500
 },
 {
 "epoch": 2.66,
 "learning_rate": 2.3391906283280085e-05,
 "loss": 2.5894,
 "step": 5000
 },
 {
 "epoch": 2.93,
 "learning_rate": 2.072949946751864e-05,
 "loss": 2.5773,
 "step": 5500
 },
 {
 "epoch": 3.19,
 "learning_rate": 1.806709265175719e-05,
 "loss": 2.5038,
 "step": 6000
 },
 {
 "epoch": 3.46,
 "learning_rate": 1.5404685835995743e-05,
 "loss": 2.523,
 "step": 6500
 },
 {
 "epoch": 3.73,
 "learning_rate": 1.2742279020234293e-05,
 "loss": 2.5071,
 "step": 7000
 }
 ],
 "max_steps": 9390,
 "num_train_epochs": 5,
 "total_flos": 5713925990400000.0,
 "trial_name": null,
 "trial_params": null
}