{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.009706381946129581, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000970638194612958, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.000970638194612958, "eval_loss": NaN, "eval_runtime": 10.5597, "eval_samples_per_second": 41.1, "eval_steps_per_second": 20.55, "step": 1 }, { "epoch": 0.001941276389225916, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.002911914583838874, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.002911914583838874, "eval_loss": NaN, "eval_runtime": 9.6054, "eval_samples_per_second": 45.183, "eval_steps_per_second": 22.592, "step": 3 }, { "epoch": 0.003882552778451832, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0048531909730647905, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.005823829167677748, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.005823829167677748, "eval_loss": NaN, "eval_runtime": 9.7144, "eval_samples_per_second": 44.676, "eval_steps_per_second": 22.338, "step": 6 }, { "epoch": 0.006794467362290706, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.007765105556903664, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.008735743751516622, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.008735743751516622, "eval_loss": NaN, "eval_runtime": 9.6903, "eval_samples_per_second": 44.787, "eval_steps_per_second": 22.394, "step": 9 }, { "epoch": 0.009706381946129581, "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": 40051149373440.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }