{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.020434227330779056, "eval_steps": 5, "global_step": 15, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001362281822051937, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.001362281822051937, "eval_loss": NaN, "eval_runtime": 162.8895, "eval_samples_per_second": 7.594, "eval_steps_per_second": 3.8, "step": 1 }, { "epoch": 0.002724563644103874, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.004086845466155811, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.005449127288207748, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.006811409110259685, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.006811409110259685, "eval_loss": NaN, "eval_runtime": 17.4662, "eval_samples_per_second": 70.823, "eval_steps_per_second": 35.44, "step": 5 }, { "epoch": 0.008173690932311623, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.00953597275436356, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.010898254576415497, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.012260536398467433, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.01362281822051937, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.01362281822051937, "eval_loss": NaN, "eval_runtime": 17.3489, "eval_samples_per_second": 71.301, "eval_steps_per_second": 35.679, "step": 10 }, { "epoch": 0.014985100042571307, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.016347381864623246, "grad_norm": NaN, "learning_rate": 9.045084971874738e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.017709663686675182, "grad_norm": NaN, "learning_rate": 7.938926261462366e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.01907194550872712, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.020434227330779056, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.020434227330779056, "eval_loss": NaN, "eval_runtime": 17.3499, "eval_samples_per_second": 71.297, "eval_steps_per_second": 35.678, "step": 15 } ], "logging_steps": 1, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3214497304018944.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }