{ "best_metric": null, "best_model_checkpoint": null, "epoch": 8.899535370090886e-05, "eval_steps": 3, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.4832558950151478e-05, "grad_norm": 0.5195764303207397, "learning_rate": 2e-05, "loss": 1.4502, "step": 1 }, { "epoch": 1.4832558950151478e-05, "eval_loss": 1.6685941219329834, "eval_runtime": 4220.9321, "eval_samples_per_second": 6.725, "eval_steps_per_second": 3.363, "step": 1 }, { "epoch": 2.9665117900302956e-05, "grad_norm": 0.3675019443035126, "learning_rate": 4e-05, "loss": 1.5582, "step": 2 }, { "epoch": 4.449767685045443e-05, "grad_norm": 0.33625102043151855, "learning_rate": 6e-05, "loss": 1.5239, "step": 3 }, { "epoch": 4.449767685045443e-05, "eval_loss": 1.6688132286071777, "eval_runtime": 4203.5845, "eval_samples_per_second": 6.753, "eval_steps_per_second": 3.377, "step": 3 }, { "epoch": 5.933023580060591e-05, "grad_norm": 0.5512273907661438, "learning_rate": 8e-05, "loss": 1.607, "step": 4 }, { "epoch": 7.416279475075739e-05, "grad_norm": 0.3602822422981262, "learning_rate": 0.0001, "loss": 1.7489, "step": 5 }, { "epoch": 8.899535370090886e-05, "grad_norm": 0.2666824460029602, "learning_rate": 0.00012, "loss": 1.5206, "step": 6 }, { "epoch": 8.899535370090886e-05, "eval_loss": 1.6630691289901733, "eval_runtime": 4200.132, "eval_samples_per_second": 6.759, "eval_steps_per_second": 3.379, "step": 6 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1235242526441472.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }