{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.049782202862476664, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009956440572495333, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 38.7621, "step": 1 }, { "epoch": 0.009956440572495333, "eval_loss": NaN, "eval_runtime": 79.7844, "eval_samples_per_second": 2.131, "eval_steps_per_second": 1.065, "step": 1 }, { "epoch": 0.019912881144990666, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 43.4444, "step": 2 }, { "epoch": 0.019912881144990666, "eval_loss": NaN, "eval_runtime": 2.9043, "eval_samples_per_second": 58.534, "eval_steps_per_second": 29.267, "step": 2 }, { "epoch": 0.029869321717486, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 180.3462, "step": 3 }, { "epoch": 0.03982576228998133, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 145.0477, "step": 4 }, { "epoch": 0.03982576228998133, "eval_loss": NaN, "eval_runtime": 2.9202, "eval_samples_per_second": 58.216, "eval_steps_per_second": 29.108, "step": 4 }, { "epoch": 0.049782202862476664, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 6.5303, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1600163005071360.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }