t5-small-english-to-sanskrit-translator
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1564
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 400 | 0.2102 |
| 0.3261 | 2.0 | 800 | 0.1905 |
| 0.2187 | 3.0 | 1200 | 0.1927 |
| 0.1987 | 4.0 | 1600 | 0.1738 |
| 0.1907 | 5.0 | 2000 | 0.1699 |
| 0.1907 | 6.0 | 2400 | 0.1795 |
| 0.185 | 7.0 | 2800 | 0.1662 |
| 0.1782 | 8.0 | 3200 | 0.1689 |
| 0.1788 | 9.0 | 3600 | 0.1631 |
| 0.1727 | 10.0 | 4000 | 0.1620 |
| 0.1727 | 11.0 | 4400 | 0.1611 |
| 0.1703 | 12.0 | 4800 | 0.1584 |
| 0.1674 | 13.0 | 5200 | 0.1583 |
| 0.1669 | 14.0 | 5600 | 0.1630 |
| 0.1629 | 15.0 | 6000 | 0.1563 |
| 0.1629 | 16.0 | 6400 | 0.1577 |
| 0.1614 | 17.0 | 6800 | 0.1583 |
| 0.1564 | 18.0 | 7200 | 0.1567 |
| 0.1594 | 19.0 | 7600 | 0.1591 |
| 0.154 | 20.0 | 8000 | 0.1568 |
| 0.154 | 21.0 | 8400 | 0.1577 |
| 0.153 | 22.0 | 8800 | 0.1581 |
| 0.1538 | 23.0 | 9200 | 0.1553 |
| 0.1505 | 24.0 | 9600 | 0.1574 |
| 0.146 | 25.0 | 10000 | 0.1589 |
| 0.146 | 26.0 | 10400 | 0.1607 |
| 0.151 | 27.0 | 10800 | 0.1587 |
| 0.1418 | 28.0 | 11200 | 0.1539 |
| 0.1455 | 29.0 | 11600 | 0.1537 |
| 0.1422 | 30.0 | 12000 | 0.1552 |
| 0.1422 | 31.0 | 12400 | 0.1571 |
| 0.1402 | 32.0 | 12800 | 0.1588 |
| 0.1429 | 33.0 | 13200 | 0.1573 |
| 0.142 | 34.0 | 13600 | 0.1558 |
| 0.138 | 35.0 | 14000 | 0.1620 |
| 0.138 | 36.0 | 14400 | 0.1582 |
| 0.1393 | 37.0 | 14800 | 0.1555 |
| 0.1371 | 38.0 | 15200 | 0.1534 |
| 0.1389 | 39.0 | 15600 | 0.1575 |
| 0.1356 | 40.0 | 16000 | 0.1551 |
| 0.1356 | 41.0 | 16400 | 0.1604 |
| 0.1332 | 42.0 | 16800 | 0.1584 |
| 0.1359 | 43.0 | 17200 | 0.1592 |
| 0.1385 | 44.0 | 17600 | 0.1576 |
| 0.1321 | 45.0 | 18000 | 0.1555 |
| 0.1321 | 46.0 | 18400 | 0.1556 |
| 0.1374 | 47.0 | 18800 | 0.1564 |
| 0.1332 | 48.0 | 19200 | 0.1567 |
| 0.1335 | 49.0 | 19600 | 0.1566 |
| 0.1354 | 50.0 | 20000 | 0.1564 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1