{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0017617264919621229, "eval_steps": 8, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001761726491962123, "eval_loss": 1.258076548576355, "eval_runtime": 351.7517, "eval_samples_per_second": 6.797, "eval_steps_per_second": 3.4, "step": 1 }, { "epoch": 0.0005285179475886368, "grad_norm": 1.8236202001571655, "learning_rate": 6e-05, "loss": 4.8041, "step": 3 }, { "epoch": 0.0010570358951772737, "grad_norm": 2.2088983058929443, "learning_rate": 0.00012, "loss": 5.2211, "step": 6 }, { "epoch": 0.0014093811935696984, "eval_loss": 1.0344609022140503, "eval_runtime": 353.8305, "eval_samples_per_second": 6.757, "eval_steps_per_second": 3.38, "step": 8 }, { "epoch": 0.0015855538427659106, "grad_norm": 1.4011439085006714, "learning_rate": 0.00018, "loss": 4.4971, "step": 9 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 9147531405557760.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }