{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.014657383657017223, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0014657383657017222, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0014657383657017222, "eval_loss": NaN, "eval_runtime": 27.867, "eval_samples_per_second": 41.268, "eval_steps_per_second": 5.167, "step": 1 }, { "epoch": 0.0029314767314034445, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.004397215097105167, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.004397215097105167, "eval_loss": NaN, "eval_runtime": 26.4891, "eval_samples_per_second": 43.414, "eval_steps_per_second": 5.436, "step": 3 }, { "epoch": 0.005862953462806889, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.007328691828508612, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.008794430194210334, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.008794430194210334, "eval_loss": NaN, "eval_runtime": 26.6353, "eval_samples_per_second": 43.176, "eval_steps_per_second": 5.406, "step": 6 }, { "epoch": 0.010260168559912056, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.011725906925613778, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0131916452913155, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0131916452913155, "eval_loss": NaN, "eval_runtime": 26.6068, "eval_samples_per_second": 43.222, "eval_steps_per_second": 5.412, "step": 9 }, { "epoch": 0.014657383657017223, "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": 1.045015069458432e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }