{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.902439024390244, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.975609756097561, "eval_runtime": 31.2072, "eval_samples_per_second": 9.004, "eval_steps_per_second": 0.577, "step": 5 }, { "epoch": 1.951219512195122, "grad_norm": 0.05327402800321579, "learning_rate": 0.0001, "loss": 1.747, "step": 10 }, { "epoch": 1.951219512195122, "eval_runtime": 30.5362, "eval_samples_per_second": 9.202, "eval_steps_per_second": 0.589, "step": 10 }, { "epoch": 2.926829268292683, "eval_runtime": 30.4989, "eval_samples_per_second": 9.213, "eval_steps_per_second": 0.59, "step": 15 }, { "epoch": 3.902439024390244, "grad_norm": 0.0818428099155426, "learning_rate": 0.0001, "loss": 1.6888, "step": 20 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 20, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.846323699069747e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }