{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.736842105263158, "eval_steps": 500, "global_step": 27, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5263157894736842, "grad_norm": 7.114755153656006, "learning_rate": 5e-05, "loss": 0.4079, "step": 5 }, { "epoch": 1.0, "grad_norm": 5.0528388023376465, "learning_rate": 5e-05, "loss": 0.0187, "step": 10 }, { "epoch": 1.526315789473684, "grad_norm": 15.6405029296875, "learning_rate": 5e-05, "loss": -1.4182, "step": 15 }, { "epoch": 2.0, "grad_norm": 4.826280117034912, "learning_rate": 5e-05, "loss": -2.8284, "step": 20 }, { "epoch": 2.526315789473684, "grad_norm": 71.04973602294922, "learning_rate": 5e-05, "loss": -12.8588, "step": 25 }, { "epoch": 2.736842105263158, "step": 27, "total_flos": 0.0, "train_loss": -4.247940336112623, "train_runtime": 89.9131, "train_samples_per_second": 10.01, "train_steps_per_second": 0.3 } ], "logging_steps": 5, "max_steps": 27, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 0.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }