{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.029038112522686024, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005807622504537205, "grad_norm": 0.14531674981117249, "learning_rate": 1e-05, "loss": 6.9369, "step": 1 }, { "epoch": 0.005807622504537205, "eval_loss": 6.937534809112549, "eval_runtime": 11.779, "eval_samples_per_second": 24.62, "eval_steps_per_second": 12.31, "step": 1 }, { "epoch": 0.01161524500907441, "grad_norm": 0.13701589405536652, "learning_rate": 2e-05, "loss": 6.9385, "step": 2 }, { "epoch": 0.01161524500907441, "eval_loss": 6.937504291534424, "eval_runtime": 1.9422, "eval_samples_per_second": 149.316, "eval_steps_per_second": 74.658, "step": 2 }, { "epoch": 0.017422867513611617, "grad_norm": 0.14229567348957062, "learning_rate": 3e-05, "loss": 6.9375, "step": 3 }, { "epoch": 0.02323049001814882, "grad_norm": 0.13301143050193787, "learning_rate": 4e-05, "loss": 6.937, "step": 4 }, { "epoch": 0.02323049001814882, "eval_loss": 6.9373087882995605, "eval_runtime": 1.9467, "eval_samples_per_second": 148.967, "eval_steps_per_second": 74.483, "step": 4 }, { "epoch": 0.029038112522686024, "grad_norm": 0.14114128053188324, "learning_rate": 5e-05, "loss": 6.9403, "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": 52733214720.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }