{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9256198347107438, "eval_steps": 30, "global_step": 7, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1322314049586777, "grad_norm": 1.7518984079360962, "learning_rate": 2.5714285714285714e-05, "loss": 10.1004, "step": 1 }, { "epoch": 0.2644628099173554, "grad_norm": 1.6565409898757935, "learning_rate": 2.1428571428571428e-05, "loss": 10.1618, "step": 2 }, { "epoch": 0.39669421487603307, "grad_norm": 1.7153880596160889, "learning_rate": 1.7142857142857142e-05, "loss": 10.1003, "step": 3 }, { "epoch": 0.5289256198347108, "grad_norm": 2.0842509269714355, "learning_rate": 1.2857142857142857e-05, "loss": 10.1771, "step": 4 }, { "epoch": 0.6611570247933884, "grad_norm": 2.1643295288085938, "learning_rate": 8.571428571428571e-06, "loss": 10.0969, "step": 5 }, { "epoch": 0.7933884297520661, "grad_norm": 1.9889191389083862, "learning_rate": 4.2857142857142855e-06, "loss": 9.9853, "step": 6 }, { "epoch": 0.9256198347107438, "grad_norm": 1.9943231344223022, "learning_rate": 0.0, "loss": 9.9356, "step": 7 }, { "epoch": 0.9256198347107438, "step": 7, "total_flos": 59812992852240.0, "train_loss": 10.079636437552315, "train_runtime": 297.4065, "train_samples_per_second": 0.407, "train_steps_per_second": 0.024 } ], "logging_steps": 1.0, "max_steps": 7, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 59812992852240.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }