{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006769511163184274, "eval_steps": 13, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005207316279372519, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0005207316279372519, "eval_loss": NaN, "eval_runtime": 174.4791, "eval_samples_per_second": 18.541, "eval_steps_per_second": 9.273, "step": 1 }, { "epoch": 0.0010414632558745037, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0015621948838117556, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0020829265117490075, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.002603658139686259, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.003124389767623511, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.003645121395560763, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.004165853023498015, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.0046865846514352666, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.005207316279372518, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.00572804790730977, "grad_norm": NaN, "learning_rate": 9.98458666866564e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.006248779535247022, "grad_norm": NaN, "learning_rate": 9.938441702975689e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.006769511163184274, "grad_norm": NaN, "learning_rate": 9.861849601988383e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.006769511163184274, "eval_loss": NaN, "eval_runtime": 84.5989, "eval_samples_per_second": 38.239, "eval_steps_per_second": 19.126, "step": 13 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1135720399896576.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }