{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0022030475491096016, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0007343491830365339, "grad_norm": 0.7374667525291443, "learning_rate": 2e-05, "loss": 0.6968, "step": 1 }, { "epoch": 0.0007343491830365339, "eval_loss": 0.6995853185653687, "eval_runtime": 172.0393, "eval_samples_per_second": 6.667, "eval_steps_per_second": 1.668, "step": 1 }, { "epoch": 0.0014686983660730677, "grad_norm": 0.7952613234519958, "learning_rate": 4e-05, "loss": 0.6825, "step": 2 }, { "epoch": 0.0022030475491096016, "grad_norm": 0.7004721164703369, "learning_rate": 6e-05, "loss": 0.6528, "step": 3 }, { "epoch": 0.0022030475491096016, "eval_loss": 0.6738851070404053, "eval_runtime": 171.1769, "eval_samples_per_second": 6.701, "eval_steps_per_second": 1.677, "step": 3 } ], "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": false }, "attributes": {} } }, "total_flos": 3951230460100608.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }