--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: best_model-sst-2-16-13 results: [] --- # best_model-sst-2-16-13 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co./bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6655 - Accuracy: 0.5938 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 1 | 0.7052 | 0.5312 | | No log | 2.0 | 2 | 0.7051 | 0.5312 | | No log | 3.0 | 3 | 0.7050 | 0.5312 | | No log | 4.0 | 4 | 0.7048 | 0.5312 | | No log | 5.0 | 5 | 0.7045 | 0.5312 | | No log | 6.0 | 6 | 0.7042 | 0.5312 | | No log | 7.0 | 7 | 0.7038 | 0.5312 | | No log | 8.0 | 8 | 0.7034 | 0.5312 | | No log | 9.0 | 9 | 0.7029 | 0.5312 | | 0.7492 | 10.0 | 10 | 0.7023 | 0.5312 | | 0.7492 | 11.0 | 11 | 0.7017 | 0.5312 | | 0.7492 | 12.0 | 12 | 0.7010 | 0.5312 | | 0.7492 | 13.0 | 13 | 0.7002 | 0.5312 | | 0.7492 | 14.0 | 14 | 0.6994 | 0.5312 | | 0.7492 | 15.0 | 15 | 0.6985 | 0.5312 | | 0.7492 | 16.0 | 16 | 0.6976 | 0.5312 | | 0.7492 | 17.0 | 17 | 0.6966 | 0.5312 | | 0.7492 | 18.0 | 18 | 0.6956 | 0.5312 | | 0.7492 | 19.0 | 19 | 0.6946 | 0.5312 | | 0.7304 | 20.0 | 20 | 0.6935 | 0.5312 | | 0.7304 | 21.0 | 21 | 0.6924 | 0.5 | | 0.7304 | 22.0 | 22 | 0.6912 | 0.5625 | | 0.7304 | 23.0 | 23 | 0.6900 | 0.5625 | | 0.7304 | 24.0 | 24 | 0.6887 | 0.5625 | | 0.7304 | 25.0 | 25 | 0.6875 | 0.5625 | | 0.7304 | 26.0 | 26 | 0.6861 | 0.5625 | | 0.7304 | 27.0 | 27 | 0.6849 | 0.5625 | | 0.7304 | 28.0 | 28 | 0.6836 | 0.5625 | | 0.7304 | 29.0 | 29 | 0.6823 | 0.5625 | | 0.6885 | 30.0 | 30 | 0.6812 | 0.5938 | | 0.6885 | 31.0 | 31 | 0.6800 | 0.5625 | | 0.6885 | 32.0 | 32 | 0.6789 | 0.5625 | | 0.6885 | 33.0 | 33 | 0.6779 | 0.5312 | | 0.6885 | 34.0 | 34 | 0.6772 | 0.5312 | | 0.6885 | 35.0 | 35 | 0.6763 | 0.5312 | | 0.6885 | 36.0 | 36 | 0.6753 | 0.5625 | | 0.6885 | 37.0 | 37 | 0.6744 | 0.5625 | | 0.6885 | 38.0 | 38 | 0.6734 | 0.5938 | | 0.6885 | 39.0 | 39 | 0.6724 | 0.5938 | | 0.6578 | 40.0 | 40 | 0.6715 | 0.625 | | 0.6578 | 41.0 | 41 | 0.6707 | 0.5938 | | 0.6578 | 42.0 | 42 | 0.6699 | 0.625 | | 0.6578 | 43.0 | 43 | 0.6692 | 0.625 | | 0.6578 | 44.0 | 44 | 0.6686 | 0.6562 | | 0.6578 | 45.0 | 45 | 0.6681 | 0.6562 | | 0.6578 | 46.0 | 46 | 0.6679 | 0.6562 | | 0.6578 | 47.0 | 47 | 0.6677 | 0.5938 | | 0.6578 | 48.0 | 48 | 0.6673 | 0.5938 | | 0.6578 | 49.0 | 49 | 0.6665 | 0.5938 | | 0.5964 | 50.0 | 50 | 0.6655 | 0.5938 | ### Framework versions - Transformers 4.32.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.4.0 - Tokenizers 0.13.3