trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 1.0,
 "eval_steps": 500,
 "global_step": 229,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.4366812227074236,
 "grad_norm": 0.10466119647026062,
 "learning_rate": 6.666666666666667e-06,
 "loss": 2.3802,
 "step": 100
 },
 {
 "epoch": 0.8733624454148472,
 "grad_norm": 0.2237740308046341,
 "learning_rate": 1.3333333333333333e-05,
 "loss": 2.3236,
 "step": 200
 },
 {
 "epoch": 1.0,
 "step": 229,
 "total_flos": 4161668422041600.0,
 "train_loss": 2.3460041029484513,
 "train_runtime": 71.1285,
 "train_samples_per_second": 6.439,
 "train_steps_per_second": 3.22
 }
 ],
 "logging_steps": 100,
 "max_steps": 229,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 1,
 "save_steps": 500,
 "stateful_callbacks": {
 "TrainerControl": {
 "args": {
 "should_epoch_stop": false,
 "should_evaluate": false,
 "should_log": false,
 "should_save": true,
 "should_training_stop": true
 },
 "attributes": {}
 }
 },
 "total_flos": 4161668422041600.0,
 "train_batch_size": 2,
 "trial_name": null,
 "trial_params": null
}