{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.02544529262086514, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002544529262086514, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.002544529262086514, "eval_loss": NaN, "eval_runtime": 10.766, "eval_samples_per_second": 15.419, "eval_steps_per_second": 7.709, "step": 1 }, { "epoch": 0.005089058524173028, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.007633587786259542, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.007633587786259542, "eval_loss": NaN, "eval_runtime": 10.0731, "eval_samples_per_second": 16.48, "eval_steps_per_second": 8.24, "step": 3 }, { "epoch": 0.010178117048346057, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.01272264631043257, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.015267175572519083, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.015267175572519083, "eval_loss": NaN, "eval_runtime": 10.095, "eval_samples_per_second": 16.444, "eval_steps_per_second": 8.222, "step": 6 }, { "epoch": 0.017811704834605598, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.020356234096692113, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.022900763358778626, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.022900763358778626, "eval_loss": NaN, "eval_runtime": 10.0533, "eval_samples_per_second": 16.512, "eval_steps_per_second": 8.256, "step": 9 }, { "epoch": 0.02544529262086514, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1628749242040320.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }