<!-- 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. -->
fine_tuned_t5_model
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0736
- Bleu: 0.0099
- Gen Len: 19.0
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: 0.002
- 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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 157 | 1.9566 | 0.0074 | 19.0 |
No log | 2.0 | 314 | 1.8330 | 0.026 | 19.0 |
No log | 3.0 | 471 | 1.7957 | 0.0405 | 19.0 |
1.9115 | 4.0 | 628 | 1.7441 | 0.0073 | 19.0 |
1.9115 | 5.0 | 785 | 1.7875 | 0.033 | 19.0 |
1.9115 | 6.0 | 942 | 2.0419 | 0.0093 | 19.0 |
1.5066 | 7.0 | 1099 | 2.0750 | 0.0099 | 19.0 |
1.5066 | 8.0 | 1256 | 2.0744 | 0.0099 | 19.0 |
1.5066 | 9.0 | 1413 | 2.0738 | 0.0099 | 19.0 |
1.6163 | 10.0 | 1570 | 2.0736 | 0.0099 | 19.0 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1