{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.8285714285714287, "eval_steps": 500, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.22857142857142856, "grad_norm": 4.018310637001455, "learning_rate": 9.619397662556434e-06, "loss": 0.5721, "step": 1 }, { "epoch": 0.45714285714285713, "grad_norm": 2.1806506112856083, "learning_rate": 8.535533905932739e-06, "loss": 0.4629, "step": 2 }, { "epoch": 0.6857142857142857, "grad_norm": 2.4229847468525425, "learning_rate": 6.913417161825449e-06, "loss": 0.4269, "step": 3 }, { "epoch": 0.9142857142857143, "grad_norm": 1.2498727257006212, "learning_rate": 5e-06, "loss": 0.3878, "step": 4 }, { "epoch": 1.1428571428571428, "grad_norm": 3.7667378605818533, "learning_rate": 3.0865828381745515e-06, "loss": 0.636, "step": 5 }, { "epoch": 1.3714285714285714, "grad_norm": 1.5297450321016075, "learning_rate": 1.4644660940672628e-06, "loss": 0.349, "step": 6 }, { "epoch": 1.6, "grad_norm": 1.1400630324559309, "learning_rate": 3.8060233744356634e-07, "loss": 0.3659, "step": 7 }, { "epoch": 1.8285714285714287, "grad_norm": 0.924455707385272, "learning_rate": 0.0, "loss": 0.3538, "step": 8 }, { "epoch": 1.8285714285714287, "step": 8, "total_flos": 4337782751232.0, "train_loss": 0.44431259483098984, "train_runtime": 223.1782, "train_samples_per_second": 1.246, "train_steps_per_second": 0.036 } ], "logging_steps": 1, "max_steps": 8, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 70000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4337782751232.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }