<!-- 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. -->
flan-t5-base-alphaX
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0018
- Rouge1: 68.4722
- Rouge2: 61.0119
- Rougel: 68.4722
- Rougelsum: 68.4722
- Gen Len: 8.6667
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 2.8280 | 16.5064 | 7.7922 | 16.5064 | 15.3846 | 9.6667 |
| No log | 2.0 | 2 | 2.3357 | 62.2756 | 44.697 | 58.109 | 58.109 | 9.0 |
| No log | 3.0 | 3 | 2.1559 | 70.609 | 61.9589 | 70.609 | 70.609 | 7.8333 |
| No log | 4.0 | 4 | 2.0521 | 68.4722 | 61.0119 | 68.4722 | 68.4722 | 8.6667 |
| No log | 5.0 | 5 | 2.0018 | 68.4722 | 61.0119 | 68.4722 | 68.4722 | 8.6667 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
