{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.1949317738791423, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003898635477582846, "eval_loss": NaN, "eval_runtime": 0.7961, "eval_samples_per_second": 136.917, "eval_steps_per_second": 69.087, "step": 1 }, { "epoch": 0.01949317738791423, "grad_norm": 0.36223816871643066, "learning_rate": 5e-05, "loss": 10.3786, "step": 5 }, { "epoch": 0.03898635477582846, "grad_norm": 0.2183828502893448, "learning_rate": 0.0001, "loss": 10.3785, "step": 10 }, { "epoch": 0.03898635477582846, "eval_loss": NaN, "eval_runtime": 0.7946, "eval_samples_per_second": 137.178, "eval_steps_per_second": 69.218, "step": 10 }, { "epoch": 0.05847953216374269, "grad_norm": 0.31415072083473206, "learning_rate": 9.619397662556435e-05, "loss": 10.3825, "step": 15 }, { "epoch": 0.07797270955165692, "grad_norm": 0.18190725147724152, "learning_rate": 8.535533905932738e-05, "loss": 10.3672, "step": 20 }, { "epoch": 0.07797270955165692, "eval_loss": NaN, "eval_runtime": 0.8236, "eval_samples_per_second": 132.351, "eval_steps_per_second": 66.783, "step": 20 }, { "epoch": 0.09746588693957114, "grad_norm": 0.23780079185962677, "learning_rate": 6.91341716182545e-05, "loss": 10.3839, "step": 25 }, { "epoch": 0.11695906432748537, "grad_norm": 0.21464188396930695, "learning_rate": 5e-05, "loss": 10.3772, "step": 30 }, { "epoch": 0.11695906432748537, "eval_loss": NaN, "eval_runtime": 0.7897, "eval_samples_per_second": 138.033, "eval_steps_per_second": 69.65, "step": 30 }, { "epoch": 0.1364522417153996, "grad_norm": 0.3639202415943146, "learning_rate": 3.086582838174551e-05, "loss": 10.3709, "step": 35 }, { "epoch": 0.15594541910331383, "grad_norm": 0.18550260365009308, "learning_rate": 1.4644660940672627e-05, "loss": 10.3873, "step": 40 }, { "epoch": 0.15594541910331383, "eval_loss": NaN, "eval_runtime": 0.7913, "eval_samples_per_second": 137.752, "eval_steps_per_second": 69.508, "step": 40 }, { "epoch": 0.17543859649122806, "grad_norm": 0.26159873604774475, "learning_rate": 3.8060233744356633e-06, "loss": 10.3978, "step": 45 }, { "epoch": 0.1949317738791423, "grad_norm": 0.26113927364349365, "learning_rate": 0.0, "loss": 10.4081, "step": 50 }, { "epoch": 0.1949317738791423, "eval_loss": NaN, "eval_runtime": 0.8116, "eval_samples_per_second": 134.301, "eval_steps_per_second": 67.767, "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": 646545408000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }