<!-- 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. -->
lesson-summarization
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0801
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8198 | 3.12 | 200 | 2.8048 |
| 2.5358 | 6.25 | 400 | 2.6645 |
| 2.333 | 9.38 | 600 | 2.6123 |
| 2.2096 | 12.5 | 800 | 2.5807 |
| 2.0783 | 15.62 | 1000 | 2.5703 |
| 1.9919 | 18.75 | 1200 | 2.5653 |
| 1.89 | 21.88 | 1400 | 2.5602 |
| 1.7865 | 25.0 | 1600 | 2.5650 |
| 1.7149 | 28.12 | 1800 | 2.5812 |
| 1.6651 | 31.25 | 2000 | 2.5813 |
| 1.5662 | 34.38 | 2200 | 2.5997 |
| 1.5333 | 37.5 | 2400 | 2.6097 |
| 1.4336 | 40.62 | 2600 | 2.6389 |
| 1.3986 | 43.75 | 2800 | 2.6564 |
| 1.352 | 46.88 | 3000 | 2.6720 |
| 1.3072 | 50.0 | 3200 | 2.6863 |
| 1.2773 | 53.12 | 3400 | 2.6931 |
| 1.2079 | 56.25 | 3600 | 2.7350 |
| 1.1768 | 59.38 | 3800 | 2.7521 |
| 1.1749 | 62.5 | 4000 | 2.7553 |
| 1.0857 | 65.62 | 4200 | 2.7921 |
| 1.0883 | 68.75 | 4400 | 2.7840 |
| 1.0307 | 71.88 | 4600 | 2.8110 |
| 1.0255 | 75.0 | 4800 | 2.8365 |
| 0.9992 | 78.12 | 5000 | 2.8358 |
| 0.9516 | 81.25 | 5200 | 2.8554 |
| 0.9363 | 84.38 | 5400 | 2.8742 |
| 0.91 | 87.5 | 5600 | 2.8923 |
| 0.895 | 90.62 | 5800 | 2.9057 |
| 0.8371 | 93.75 | 6000 | 2.9234 |
| 0.8588 | 96.88 | 6200 | 2.9443 |
| 0.8237 | 100.0 | 6400 | 2.9612 |
| 0.8147 | 103.12 | 6600 | 2.9633 |
| 0.7936 | 106.25 | 6800 | 2.9641 |
| 0.7883 | 109.38 | 7000 | 2.9711 |
| 0.7589 | 112.5 | 7200 | 2.9744 |
| 0.7277 | 115.62 | 7400 | 2.9879 |
| 0.7505 | 118.75 | 7600 | 2.9974 |
| 0.705 | 121.88 | 7800 | 3.0033 |
| 0.7111 | 125.0 | 8000 | 3.0032 |
| 0.7005 | 128.12 | 8200 | 3.0055 |
| 0.6961 | 131.25 | 8400 | 3.0168 |
| 0.6543 | 134.38 | 8600 | 3.0339 |
| 0.6482 | 137.5 | 8800 | 3.0312 |
| 0.6807 | 140.62 | 9000 | 3.0393 |
| 0.6365 | 143.75 | 9200 | 3.0413 |
| 0.648 | 146.88 | 9400 | 3.0461 |
| 0.6275 | 150.0 | 9600 | 3.0454 |
| 0.6284 | 153.12 | 9800 | 3.0552 |
| 0.6062 | 156.25 | 10000 | 3.0514 |
| 0.6312 | 159.38 | 10200 | 3.0487 |
| 0.6244 | 162.5 | 10400 | 3.0525 |
| 0.5792 | 165.62 | 10600 | 3.0547 |
| 0.5997 | 168.75 | 10800 | 3.0491 |
| 0.5972 | 171.88 | 11000 | 3.0542 |
| 0.5891 | 175.0 | 11200 | 3.0624 |
| 0.582 | 178.12 | 11400 | 3.0717 |
| 0.5934 | 181.25 | 11600 | 3.0683 |
| 0.5803 | 184.38 | 11800 | 3.0761 |
| 0.5724 | 187.5 | 12000 | 3.0777 |
| 0.6015 | 190.62 | 12200 | 3.0784 |
| 0.5874 | 193.75 | 12400 | 3.0792 |
| 0.5531 | 196.88 | 12600 | 3.0801 |
| 0.5863 | 200.0 | 12800 | 3.0801 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu116
- Datasets 2.12.0
- Tokenizers 0.13.3
