{ "best_metric": null, "best_model_checkpoint": null, "epoch": 8.619389316266943e-05, "eval_steps": 2, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.4365648860444904e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 1.4365648860444904e-05, "eval_loss": NaN, "eval_runtime": 3458.3695, "eval_samples_per_second": 8.475, "eval_steps_per_second": 4.238, "step": 1 }, { "epoch": 2.8731297720889808e-05, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 2.8731297720889808e-05, "eval_loss": NaN, "eval_runtime": 3458.607, "eval_samples_per_second": 8.475, "eval_steps_per_second": 4.237, "step": 2 }, { "epoch": 4.3096946581334714e-05, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 5.7462595441779616e-05, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 5.7462595441779616e-05, "eval_loss": NaN, "eval_runtime": 3460.8748, "eval_samples_per_second": 8.469, "eval_steps_per_second": 4.234, "step": 4 }, { "epoch": 7.182824430222452e-05, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 8.619389316266943e-05, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 8.619389316266943e-05, "eval_loss": NaN, "eval_runtime": 3456.2528, "eval_samples_per_second": 8.48, "eval_steps_per_second": 4.24, "step": 6 } ], "logging_steps": 1, "max_steps": 10, "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": false }, "attributes": {} } }, "total_flos": 2225661850681344.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }