{ "best_metric": 8.097002084978036e-05, "best_model_checkpoint": "./orion-finetuned-squad\\checkpoint-500", "epoch": 1.6, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.16, "grad_norm": 13.155216217041016, "learning_rate": 1.0000000000000002e-06, "loss": 7.6002, "step": 50 }, { "epoch": 0.32, "grad_norm": 9.965179443359375, "learning_rate": 2.0000000000000003e-06, "loss": 6.7941, "step": 100 }, { "epoch": 0.48, "grad_norm": 5.015015125274658, "learning_rate": 3e-06, "loss": 5.5048, "step": 150 }, { "epoch": 0.64, "grad_norm": 2.8797528743743896, "learning_rate": 4.000000000000001e-06, "loss": 4.688, "step": 200 }, { "epoch": 0.8, "grad_norm": 2.3939545154571533, "learning_rate": 5e-06, "loss": 4.2605, "step": 250 }, { "epoch": 0.96, "grad_norm": 1.693825364112854, "learning_rate": 6e-06, "loss": 4.0418, "step": 300 }, { "epoch": 1.12, "grad_norm": 1.439347267150879, "learning_rate": 7e-06, "loss": 3.9253, "step": 350 }, { "epoch": 1.28, "grad_norm": 1.3246393203735352, "learning_rate": 8.000000000000001e-06, "loss": 3.8597, "step": 400 }, { "epoch": 1.44, "grad_norm": 1.3454995155334473, "learning_rate": 9e-06, "loss": 3.813, "step": 450 }, { "epoch": 1.6, "grad_norm": 1.3214969635009766, "learning_rate": 1e-05, "loss": 3.774, "step": 500 }, { "epoch": 1.6, "eval_accuracy": 8.097002084978036e-05, "eval_loss": 3.5968761444091797, "eval_perplexity": 28132.972634939182, "eval_runtime": 4090.3007, "eval_samples_per_second": 0.098, "eval_steps_per_second": 0.098, "step": 500 } ], "logging_steps": 50, "max_steps": 936, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1045168128000000.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }