<!-- 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. -->
translation_flan_base_v5
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2874
- Bleu: 0.0
- Gen Len: 3.3333
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 138 | 0.2378 | 0.0 | 3.6667 |
| No log | 2.0 | 276 | 0.2617 | 0.0 | 3.6667 |
| No log | 3.0 | 414 | 0.2536 | 0.0 | 3.6667 |
| 0.3151 | 4.0 | 552 | 0.3378 | 0.0 | 3.6667 |
| 0.3151 | 5.0 | 690 | 0.2637 | 0.0 | 3.6667 |
| 0.3151 | 6.0 | 828 | 0.2609 | 0.0 | 3.6667 |
| 0.3151 | 7.0 | 966 | 0.2738 | 0.0 | 3.6667 |
| 0.2032 | 8.0 | 1104 | 0.3027 | 0.0 | 3.6667 |
| 0.2032 | 9.0 | 1242 | 0.2396 | 0.0 | 3.6667 |
| 0.2032 | 10.0 | 1380 | 0.2705 | 0.0 | 3.6667 |
| 0.1466 | 11.0 | 1518 | 0.2863 | 0.0 | 3.6667 |
| 0.1466 | 12.0 | 1656 | 0.2386 | 0.0 | 3.6667 |
| 0.1466 | 13.0 | 1794 | 0.2588 | 0.0 | 3.6667 |
| 0.1466 | 14.0 | 1932 | 0.2462 | 0.0 | 3.6667 |
| 0.1182 | 15.0 | 2070 | 0.2817 | 0.0 | 3.3333 |
| 0.1182 | 16.0 | 2208 | 0.3027 | 0.0 | 3.6667 |
| 0.1182 | 17.0 | 2346 | 0.2526 | 0.0 | 3.6667 |
| 0.1182 | 18.0 | 2484 | 0.1960 | 0.0 | 3.6667 |
| 0.0969 | 19.0 | 2622 | 0.2039 | 0.0 | 3.6667 |
| 0.0969 | 20.0 | 2760 | 0.1705 | 0.0 | 3.6667 |
| 0.0969 | 21.0 | 2898 | 0.2315 | 0.0 | 3.6667 |
| 0.0859 | 22.0 | 3036 | 0.3154 | 0.0 | 3.3333 |
| 0.0859 | 23.0 | 3174 | 0.3127 | 0.0 | 3.3333 |
| 0.0859 | 24.0 | 3312 | 0.2661 | 0.0 | 3.3333 |
| 0.0859 | 25.0 | 3450 | 0.2870 | 0.0 | 3.3333 |
| 0.0716 | 26.0 | 3588 | 0.3116 | 0.0 | 3.3333 |
| 0.0716 | 27.0 | 3726 | 0.2763 | 0.0 | 3.3333 |
| 0.0716 | 28.0 | 3864 | 0.2934 | 0.0 | 3.3333 |
| 0.0665 | 29.0 | 4002 | 0.3224 | 0.0 | 3.3333 |
| 0.0665 | 30.0 | 4140 | 0.3413 | 0.0 | 3.3333 |
| 0.0665 | 31.0 | 4278 | 0.3129 | 0.0 | 3.3333 |
| 0.0665 | 32.0 | 4416 | 0.2858 | 0.0 | 3.3333 |
| 0.0631 | 33.0 | 4554 | 0.2968 | 0.0 | 3.3333 |
| 0.0631 | 34.0 | 4692 | 0.3063 | 0.0 | 3.3333 |
| 0.0631 | 35.0 | 4830 | 0.2833 | 0.0 | 3.3333 |
| 0.0631 | 36.0 | 4968 | 0.2832 | 0.0 | 3.3333 |
| 0.057 | 37.0 | 5106 | 0.2888 | 0.0 | 3.3333 |
| 0.057 | 38.0 | 5244 | 0.2938 | 0.0 | 3.3333 |
| 0.057 | 39.0 | 5382 | 0.2866 | 0.0 | 3.3333 |
| 0.0546 | 40.0 | 5520 | 0.2874 | 0.0 | 3.3333 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
