{ "best_metric": 1.441214680671692, "best_model_checkpoint": "./outputs/checkpoint-200", "epoch": 0.26666666666666666, "eval_steps": 100, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.13, "learning_rate": 0.0002, "loss": 1.3509, "step": 100 }, { "epoch": 0.13, "eval_loss": 1.4751445055007935, "eval_runtime": 155.0414, "eval_samples_per_second": 12.448, "eval_steps_per_second": 1.561, "step": 100 }, { "epoch": 0.27, "learning_rate": 0.0002, "loss": 1.2006, "step": 200 }, { "epoch": 0.27, "eval_loss": 1.441214680671692, "eval_runtime": 151.6424, "eval_samples_per_second": 12.727, "eval_steps_per_second": 1.596, "step": 200 } ], "logging_steps": 100, "max_steps": 2250, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "total_flos": 1.273189776703488e+16, "trial_name": null, "trial_params": null }