{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.004397215097105167, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0014657383657017222, "grad_norm": 0.12143966555595398, "learning_rate": 2e-05, "loss": 0.7919, "step": 1 }, { "epoch": 0.0014657383657017222, "eval_loss": 0.8369418978691101, "eval_runtime": 16.8675, "eval_samples_per_second": 68.179, "eval_steps_per_second": 8.537, "step": 1 }, { "epoch": 0.0029314767314034445, "grad_norm": 0.12046486139297485, "learning_rate": 4e-05, "loss": 0.788, "step": 2 }, { "epoch": 0.004397215097105167, "grad_norm": 0.1069972962141037, "learning_rate": 6e-05, "loss": 0.7388, "step": 3 }, { "epoch": 0.004397215097105167, "eval_loss": 0.832497775554657, "eval_runtime": 15.0036, "eval_samples_per_second": 76.648, "eval_steps_per_second": 9.598, "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": 3135045208375296.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }