{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00031127597208892115, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00010375865736297373, "grad_norm": 1.1433764696121216, "learning_rate": 2e-05, "loss": 2.1367, "step": 1 }, { "epoch": 0.00010375865736297373, "eval_loss": 2.0775890350341797, "eval_runtime": 82.1221, "eval_samples_per_second": 49.414, "eval_steps_per_second": 24.707, "step": 1 }, { "epoch": 0.00020751731472594745, "grad_norm": 1.1961828470230103, "learning_rate": 4e-05, "loss": 2.0164, "step": 2 }, { "epoch": 0.00031127597208892115, "grad_norm": 1.2340922355651855, "learning_rate": 6e-05, "loss": 2.1282, "step": 3 }, { "epoch": 0.00031127597208892115, "eval_loss": 2.074273109436035, "eval_runtime": 81.5877, "eval_samples_per_second": 49.738, "eval_steps_per_second": 24.869, "step": 3 } ], "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": 33389311426560.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }