{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0017460386747566458, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00034920773495132916, "grad_norm": 1.3627785444259644, "learning_rate": 1e-05, "loss": 177.125, "step": 1 }, { "epoch": 0.00034920773495132916, "eval_loss": 11.080448150634766, "eval_runtime": 47.6686, "eval_samples_per_second": 101.178, "eval_steps_per_second": 50.599, "step": 1 }, { "epoch": 0.0006984154699026583, "grad_norm": 1.3236929178237915, "learning_rate": 2e-05, "loss": 177.4375, "step": 2 }, { "epoch": 0.0006984154699026583, "eval_loss": 11.080448150634766, "eval_runtime": 29.7935, "eval_samples_per_second": 161.881, "eval_steps_per_second": 80.957, "step": 2 }, { "epoch": 0.0010476232048539874, "grad_norm": 1.3055187463760376, "learning_rate": 3e-05, "loss": 177.1875, "step": 3 }, { "epoch": 0.0013968309398053166, "grad_norm": 1.3646769523620605, "learning_rate": 4e-05, "loss": 177.25, "step": 4 }, { "epoch": 0.0013968309398053166, "eval_loss": 11.080292701721191, "eval_runtime": 41.1821, "eval_samples_per_second": 117.114, "eval_steps_per_second": 58.569, "step": 4 }, { "epoch": 0.0017460386747566458, "grad_norm": 1.342670202255249, "learning_rate": 5e-05, "loss": 177.1875, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 14942208000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }