{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.1826163301141352, "eval_steps": 13, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.014047410008779631, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.014047410008779631, "eval_loss": NaN, "eval_runtime": 31.5356, "eval_samples_per_second": 15.221, "eval_steps_per_second": 3.805, "step": 1 }, { "epoch": 0.028094820017559263, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.04214223002633889, "grad_norm": NaN, "learning_rate": 9.989294616193017e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.056189640035118525, "grad_norm": NaN, "learning_rate": 9.957224306869053e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.07023705004389816, "grad_norm": NaN, "learning_rate": 9.903926402016153e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.08428446005267778, "grad_norm": NaN, "learning_rate": 9.829629131445342e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.09833187006145742, "grad_norm": NaN, "learning_rate": 9.73465064747553e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.11237928007023705, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.1264266900790167, "grad_norm": NaN, "learning_rate": 9.484363707663442e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.14047410008779632, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.15452151009657594, "grad_norm": NaN, "learning_rate": 9.157348061512727e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.16856892010535557, "grad_norm": NaN, "learning_rate": 8.966766701456177e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.1826163301141352, "grad_norm": NaN, "learning_rate": 8.759199037394887e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.1826163301141352, "eval_loss": NaN, "eval_runtime": 30.8963, "eval_samples_per_second": 15.536, "eval_steps_per_second": 3.884, "step": 13 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.146970028554322e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }