| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: t5-small |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: t5-small-squad-qag |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # t5-small-squad-qag |
|
|
| This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.5660 |
|
|
| ## 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: 3e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 4 |
| - total_train_batch_size: 32 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 100 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-------:|:----:|:---------------:| |
| | 13.5664 | 0.5714 | 1 | 14.0489 | |
| | 18.6422 | 1.5714 | 2 | 13.0300 | |
| | 17.8287 | 2.5714 | 3 | 12.0308 | |
| | 17.0632 | 3.5714 | 4 | 11.0754 | |
| | 16.1516 | 4.5714 | 5 | 10.1440 | |
| | 14.6881 | 5.5714 | 6 | 9.1360 | |
| | 14.226 | 6.5714 | 7 | 8.1785 | |
| | 12.7129 | 7.5714 | 8 | 7.4610 | |
| | 11.9365 | 8.5714 | 9 | 6.7690 | |
| | 10.6449 | 9.5714 | 10 | 6.0893 | |
| | 9.8716 | 10.5714 | 11 | 5.4196 | |
| | 9.1578 | 11.5714 | 12 | 4.7783 | |
| | 9.1422 | 12.5714 | 13 | 4.1559 | |
| | 8.0235 | 13.5714 | 14 | 3.5585 | |
| | 7.2521 | 14.5714 | 15 | 3.0355 | |
| | 6.9468 | 15.5714 | 16 | 2.5595 | |
| | 6.3573 | 16.5714 | 17 | 2.1188 | |
| | 6.0266 | 17.5714 | 18 | 1.7322 | |
| | 5.9024 | 18.5714 | 19 | 1.3607 | |
| | 4.5874 | 19.5714 | 20 | 1.0799 | |
| | 4.7103 | 20.5714 | 21 | 0.9026 | |
| | 4.5861 | 21.5714 | 22 | 0.8025 | |
| | 4.1161 | 22.5714 | 23 | 0.7488 | |
| | 3.805 | 23.5714 | 24 | 0.7257 | |
| | 3.3272 | 24.5714 | 25 | 0.7164 | |
| | 3.2706 | 25.5714 | 26 | 0.7117 | |
| | 3.368 | 26.5714 | 27 | 0.7095 | |
| | 3.3499 | 27.5714 | 28 | 0.7062 | |
| | 2.9882 | 28.5714 | 29 | 0.7011 | |
| | 2.798 | 29.5714 | 30 | 0.6939 | |
| | 2.7807 | 30.5714 | 31 | 0.6856 | |
| | 2.6064 | 31.5714 | 32 | 0.6774 | |
| | 2.537 | 32.5714 | 33 | 0.6680 | |
| | 2.5005 | 33.5714 | 34 | 0.6602 | |
| | 2.4666 | 34.5714 | 35 | 0.6530 | |
| | 2.919 | 35.5714 | 36 | 0.6471 | |
| | 2.3748 | 36.5714 | 37 | 0.6416 | |
| | 2.3416 | 37.5714 | 38 | 0.6363 | |
| | 2.3233 | 38.5714 | 39 | 0.6312 | |
| | 2.2107 | 39.5714 | 40 | 0.6265 | |
| | 2.2191 | 40.5714 | 41 | 0.6220 | |
| | 2.1931 | 41.5714 | 42 | 0.6178 | |
| | 2.0958 | 42.5714 | 43 | 0.6136 | |
| | 1.9957 | 43.5714 | 44 | 0.6095 | |
| | 2.0614 | 44.5714 | 45 | 0.6055 | |
| | 2.0534 | 45.5714 | 46 | 0.6019 | |
| | 2.0221 | 46.5714 | 47 | 0.5987 | |
| | 1.8483 | 47.5714 | 48 | 0.5957 | |
| | 1.9068 | 48.5714 | 49 | 0.5929 | |
| | 1.9266 | 49.5714 | 50 | 0.5903 | |
| | 1.8266 | 50.5714 | 51 | 0.5882 | |
| | 1.7679 | 51.5714 | 52 | 0.5864 | |
| | 1.7766 | 52.5714 | 53 | 0.5851 | |
| | 1.7592 | 53.5714 | 54 | 0.5840 | |
| | 1.8102 | 54.5714 | 55 | 0.5832 | |
| | 1.6658 | 55.5714 | 56 | 0.5826 | |
| | 1.6261 | 56.5714 | 57 | 0.5820 | |
| | 1.6287 | 57.5714 | 58 | 0.5816 | |
| | 1.6453 | 58.5714 | 59 | 0.5814 | |
| | 1.5957 | 59.5714 | 60 | 0.5813 | |
| | 1.5529 | 60.5714 | 61 | 0.5813 | |
| | 1.524 | 61.5714 | 62 | 0.5814 | |
| | 1.5488 | 62.5714 | 63 | 0.5815 | |
| | 1.4817 | 63.5714 | 64 | 0.5817 | |
| | 1.5539 | 64.5714 | 65 | 0.5820 | |
| | 1.4465 | 65.5714 | 66 | 0.5821 | |
| | 1.4489 | 66.5714 | 67 | 0.5820 | |
| | 1.4475 | 67.5714 | 68 | 0.5820 | |
| | 1.4058 | 68.5714 | 69 | 0.5819 | |
| | 1.347 | 69.5714 | 70 | 0.5817 | |
| | 1.42 | 70.5714 | 71 | 0.5815 | |
| | 1.3531 | 71.5714 | 72 | 0.5813 | |
| | 1.5894 | 72.5714 | 73 | 0.5811 | |
| | 1.3858 | 73.5714 | 74 | 0.5808 | |
| | 1.3335 | 74.5714 | 75 | 0.5802 | |
| | 1.3272 | 75.5714 | 76 | 0.5796 | |
| | 1.3593 | 76.5714 | 77 | 0.5791 | |
| | 1.2942 | 77.5714 | 78 | 0.5785 | |
| | 1.3547 | 78.5714 | 79 | 0.5778 | |
| | 1.3148 | 79.5714 | 80 | 0.5767 | |
| | 1.3101 | 80.5714 | 81 | 0.5757 | |
| | 1.2415 | 81.5714 | 82 | 0.5747 | |
| | 1.2511 | 82.5714 | 83 | 0.5738 | |
| | 1.324 | 83.5714 | 84 | 0.5730 | |
| | 1.2649 | 84.5714 | 85 | 0.5723 | |
| | 1.2953 | 85.5714 | 86 | 0.5717 | |
| | 1.2885 | 86.5714 | 87 | 0.5711 | |
| | 1.2763 | 87.5714 | 88 | 0.5704 | |
| | 1.3113 | 88.5714 | 89 | 0.5698 | |
| | 1.3509 | 89.5714 | 90 | 0.5694 | |
| | 1.2008 | 90.5714 | 91 | 0.5689 | |
| | 1.2398 | 91.5714 | 92 | 0.5685 | |
| | 1.2502 | 92.5714 | 93 | 0.5680 | |
| | 1.2558 | 93.5714 | 94 | 0.5676 | |
| | 1.2674 | 94.5714 | 95 | 0.5672 | |
| | 1.1993 | 95.5714 | 96 | 0.5668 | |
| | 1.3029 | 96.5714 | 97 | 0.5665 | |
| | 1.2861 | 97.5714 | 98 | 0.5662 | |
| | 1.2414 | 98.5714 | 99 | 0.5661 | |
| | 1.2446 | 99.5714 | 100 | 0.5660 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.48.3 |
| - Pytorch 2.5.1+cu124 |
| - Datasets 3.3.0 |
| - Tokenizers 0.21.0 |
| |
