{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.066006600660066, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0033003300330033004, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 370.7898, "step": 1 }, { "epoch": 0.0033003300330033004, "eval_loss": NaN, "eval_runtime": 102.7425, "eval_samples_per_second": 4.974, "eval_steps_per_second": 2.492, "step": 1 }, { "epoch": 0.006600660066006601, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.009900990099009901, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.013201320132013201, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0165016501650165, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0165016501650165, "eval_loss": NaN, "eval_runtime": 7.0293, "eval_samples_per_second": 72.695, "eval_steps_per_second": 36.419, "step": 5 }, { "epoch": 0.019801980198019802, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.0231023102310231, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.026402640264026403, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.0297029702970297, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.033003300330033, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.033003300330033, "eval_loss": NaN, "eval_runtime": 7.0561, "eval_samples_per_second": 72.42, "eval_steps_per_second": 36.281, "step": 10 }, { "epoch": 0.036303630363036306, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.039603960396039604, "grad_norm": NaN, "learning_rate": 9.045084971874738e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.0429042904290429, "grad_norm": NaN, "learning_rate": 7.938926261462366e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.0462046204620462, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.04950495049504951, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.04950495049504951, "eval_loss": NaN, "eval_runtime": 7.0416, "eval_samples_per_second": 72.569, "eval_steps_per_second": 36.355, "step": 15 }, { "epoch": 0.052805280528052806, "grad_norm": NaN, "learning_rate": 3.4549150281252636e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.056105610561056105, "grad_norm": NaN, "learning_rate": 2.061073738537635e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.0594059405940594, "grad_norm": NaN, "learning_rate": 9.549150281252633e-06, "loss": 0.0, "step": 18 }, { "epoch": 0.0627062706270627, "grad_norm": NaN, "learning_rate": 2.4471741852423237e-06, "loss": 0.0, "step": 19 }, { "epoch": 0.066006600660066, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 20 }, { "epoch": 0.066006600660066, "eval_loss": NaN, "eval_runtime": 7.0283, "eval_samples_per_second": 72.706, "eval_steps_per_second": 36.424, "step": 20 } ], "logging_steps": 1, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1254268443033600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }