{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.08787346221441125, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0017574692442882249, "eval_loss": NaN, "eval_runtime": 11.4406, "eval_samples_per_second": 20.978, "eval_steps_per_second": 10.489, "step": 1 }, { "epoch": 0.008787346221441126, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.01757469244288225, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.01757469244288225, "eval_loss": NaN, "eval_runtime": 10.6085, "eval_samples_per_second": 22.623, "eval_steps_per_second": 11.312, "step": 10 }, { "epoch": 0.026362038664323375, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.0351493848857645, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.0351493848857645, "eval_loss": NaN, "eval_runtime": 10.3585, "eval_samples_per_second": 23.169, "eval_steps_per_second": 11.585, "step": 20 }, { "epoch": 0.043936731107205626, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.05272407732864675, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.05272407732864675, "eval_loss": NaN, "eval_runtime": 10.86, "eval_samples_per_second": 22.099, "eval_steps_per_second": 11.05, "step": 30 }, { "epoch": 0.061511423550087874, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.070298769771529, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.070298769771529, "eval_loss": NaN, "eval_runtime": 10.9568, "eval_samples_per_second": 21.904, "eval_steps_per_second": 10.952, "step": 40 }, { "epoch": 0.07908611599297012, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 45 }, { "epoch": 0.08787346221441125, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.08787346221441125, "eval_loss": NaN, "eval_runtime": 10.3299, "eval_samples_per_second": 23.234, "eval_steps_per_second": 11.617, "step": 50 } ], "logging_steps": 5, "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": true }, "attributes": {} } }, "total_flos": 1637706205495296.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }