{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 10, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 1.2647441625595093, "learning_rate": 1e-05, "loss": 2.5833, "step": 1 }, { "epoch": 0.2, "grad_norm": 1.2899940013885498, "learning_rate": 9e-06, "loss": 2.6171, "step": 2 }, { "epoch": 0.3, "grad_norm": 1.1980966329574585, "learning_rate": 8.000000000000001e-06, "loss": 2.5623, "step": 3 }, { "epoch": 0.4, "grad_norm": 1.1215522289276123, "learning_rate": 7e-06, "loss": 2.5006, "step": 4 }, { "epoch": 0.5, "grad_norm": 1.1565415859222412, "learning_rate": 6e-06, "loss": 2.5745, "step": 5 }, { "epoch": 0.6, "grad_norm": 1.117405652999878, "learning_rate": 5e-06, "loss": 2.5638, "step": 6 }, { "epoch": 0.7, "grad_norm": 1.0465339422225952, "learning_rate": 4.000000000000001e-06, "loss": 2.4871, "step": 7 }, { "epoch": 0.8, "grad_norm": 1.09225332736969, "learning_rate": 3e-06, "loss": 2.5613, "step": 8 }, { "epoch": 0.9, "grad_norm": 1.069358468055725, "learning_rate": 2.0000000000000003e-06, "loss": 2.5465, "step": 9 }, { "epoch": 1.0, "grad_norm": 1.0126088857650757, "learning_rate": 1.0000000000000002e-06, "loss": 2.467, "step": 10 }, { "epoch": 1.0, "eval_loss": 2.5107979774475098, "eval_runtime": 1.1481, "eval_samples_per_second": 1.742, "eval_steps_per_second": 0.871, "step": 10 } ], "logging_steps": 1.0, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7920165043830784.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }