<!-- 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_v7_96epochs
This model is a fine-tuned version of catweld/translation_flan_base_v7_64epochs on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0008
- Bleu: 50.8149
- Gen Len: 6.77
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: 32
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 139 | 0.0028 | 50.9693 | 6.7804 |
| No log | 2.0 | 278 | 0.0027 | 50.9443 | 6.7795 |
| No log | 3.0 | 417 | 0.0029 | 50.7243 | 6.7691 |
| 0.0125 | 4.0 | 556 | 0.0024 | 50.9387 | 6.7832 |
| 0.0125 | 5.0 | 695 | 0.0024 | 50.9741 | 6.7795 |
| 0.0125 | 6.0 | 834 | 0.0027 | 50.7106 | 6.7669 |
| 0.0125 | 7.0 | 973 | 0.0023 | 50.7461 | 6.7691 |
| 0.0088 | 8.0 | 1112 | 0.0018 | 50.8819 | 6.7836 |
| 0.0088 | 9.0 | 1251 | 0.0017 | 50.8804 | 6.7832 |
| 0.0088 | 10.0 | 1390 | 0.0016 | 50.8819 | 6.7836 |
| 0.0077 | 11.0 | 1529 | 0.0015 | 50.8867 | 6.7832 |
| 0.0077 | 12.0 | 1668 | 0.0018 | 50.751 | 6.7687 |
| 0.0077 | 13.0 | 1807 | 0.0012 | 50.7421 | 6.7669 |
| 0.0077 | 14.0 | 1946 | 0.0012 | 50.82 | 6.7723 |
| 0.0069 | 15.0 | 2085 | 0.0011 | 50.8267 | 6.77 |
| 0.0069 | 16.0 | 2224 | 0.0011 | 50.8298 | 6.77 |
| 0.0069 | 17.0 | 2363 | 0.0010 | 50.7508 | 6.77 |
| 0.0064 | 18.0 | 2502 | 0.0010 | 50.8163 | 6.77 |
| 0.0064 | 19.0 | 2641 | 0.0011 | 50.7341 | 6.77 |
| 0.0064 | 20.0 | 2780 | 0.0009 | 50.7358 | 6.77 |
| 0.0064 | 21.0 | 2919 | 0.0009 | 50.7823 | 6.7709 |
| 0.0057 | 22.0 | 3058 | 0.0009 | 50.7958 | 6.7705 |
| 0.0057 | 23.0 | 3197 | 0.0010 | 50.7958 | 6.7705 |
| 0.0057 | 24.0 | 3336 | 0.0009 | 50.8284 | 6.77 |
| 0.0057 | 25.0 | 3475 | 0.0009 | 50.8284 | 6.77 |
| 0.006 | 26.0 | 3614 | 0.0009 | 50.8284 | 6.77 |
| 0.006 | 27.0 | 3753 | 0.0008 | 50.8284 | 6.77 |
| 0.006 | 28.0 | 3892 | 0.0008 | 50.8149 | 6.77 |
| 0.0062 | 29.0 | 4031 | 0.0008 | 50.8149 | 6.77 |
| 0.0062 | 30.0 | 4170 | 0.0008 | 50.8149 | 6.77 |
| 0.0062 | 31.0 | 4309 | 0.0008 | 50.8149 | 6.77 |
| 0.0062 | 32.0 | 4448 | 0.0008 | 50.8149 | 6.77 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
