<!-- 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. -->
nmt-ted-id-en-lr_1e-3-ep_10-seq_128-bs_32
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4453
- Bleu: 18.1458
- Gen Len: 16.302
- Meteor: 0.3625
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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | Meteor |
---|---|---|---|---|---|---|
2.1173 | 1.0 | 1250 | 1.6843 | 13.743 | 16.5153 | 0.3068 |
1.7295 | 2.0 | 2500 | 1.5361 | 15.626 | 16.3687 | 0.3334 |
1.5784 | 3.0 | 3750 | 1.4767 | 16.3593 | 16.4234 | 0.3406 |
1.4435 | 4.0 | 5000 | 1.4511 | 17.1096 | 16.3199 | 0.3485 |
1.3611 | 5.0 | 6250 | 1.4410 | 17.2554 | 16.3183 | 0.3526 |
1.293 | 6.0 | 7500 | 1.4235 | 17.62 | 16.3605 | 0.356 |
1.2234 | 7.0 | 8750 | 1.4311 | 17.9807 | 16.3032 | 0.3605 |
1.1789 | 8.0 | 10000 | 1.4341 | 18.059 | 16.319 | 0.3612 |
1.1301 | 9.0 | 11250 | 1.4383 | 18.0404 | 16.308 | 0.3611 |
1.0921 | 10.0 | 12500 | 1.4453 | 18.1458 | 16.302 | 0.3625 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1