{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0036071782847867254, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003607178284786726, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0003607178284786726, "eval_loss": NaN, "eval_runtime": 57.8759, "eval_samples_per_second": 20.181, "eval_steps_per_second": 10.091, "step": 1 }, { "epoch": 0.0007214356569573452, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0010821534854360177, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0010821534854360177, "eval_loss": NaN, "eval_runtime": 56.5539, "eval_samples_per_second": 20.653, "eval_steps_per_second": 10.326, "step": 3 }, { "epoch": 0.0014428713139146903, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0018035891423933627, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0021643069708720355, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0021643069708720355, "eval_loss": NaN, "eval_runtime": 56.5841, "eval_samples_per_second": 20.642, "eval_steps_per_second": 10.321, "step": 6 }, { "epoch": 0.002525024799350708, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0028857426278293807, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.003246460456308053, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.003246460456308053, "eval_loss": NaN, "eval_runtime": 56.5567, "eval_samples_per_second": 20.652, "eval_steps_per_second": 10.326, "step": 9 }, { "epoch": 0.0036071782847867254, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3067172125409280.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }