{ "best_global_step": 40, "best_metric": 0.016541143879294395, "best_model_checkpoint": "/teamspace/studios/this_studio/Spider/output_medgemma_spider/checkpoint-40", "epoch": 5.0, "eval_steps": 20, "global_step": 40, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1411764705882353, "grad_norm": 5.023416042327881, "learning_rate": 0.0, "loss": 1.0696, "step": 1 }, { "epoch": 1.2823529411764705, "grad_norm": 1.8974823951721191, "learning_rate": 0.0001982287250728689, "loss": 0.4296, "step": 10 }, { "epoch": 2.564705882352941, "grad_norm": 0.24307900667190552, "learning_rate": 0.00016845471059286887, "loss": 0.0236, "step": 20 }, { "epoch": 2.564705882352941, "eval_loss": 0.028425313532352448, "eval_runtime": 78.4169, "eval_samples_per_second": 0.268, "eval_steps_per_second": 0.14, "step": 20 }, { "epoch": 3.847058823529412, "grad_norm": 0.06933124363422394, "learning_rate": 0.00011253332335643043, "loss": 0.0158, "step": 30 }, { "epoch": 5.0, "grad_norm": 0.2361319214105606, "learning_rate": 5.182463258982846e-05, "loss": 0.0153, "step": 40 }, { "epoch": 5.0, "eval_loss": 0.016541143879294395, "eval_runtime": 45.345, "eval_samples_per_second": 0.463, "eval_steps_per_second": 0.243, "step": 40 } ], "logging_steps": 10, "max_steps": 56, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 20, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 50, "early_stopping_threshold": 0.0001 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.1576923226589984e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }