xsum_aligned_smallT5_full
This model is a fine-tuned version of google-t5/t5-small on the lilferrit/xsum_t5_distillation dataset. It achieves the following results on the evaluation set:
- Loss: 2.4093
- Rouge1: 22.8498
- Rouge2: 4.7818
- Rougel: 17.2861
- Rougelsum: 18.0665
- Gen Len: 33.6366
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adafactor
- lr_scheduler_type: constant
- training_steps: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 0.0 | 5 | 2.6444 | 22.3341 | 4.3395 | 16.2507 | 17.8303 | 46.2437 |
| No log | 0.0 | 10 | 2.4093 | 22.8498 | 4.7818 | 17.2861 | 18.0665 | 33.6366 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for paulh27/xsum_aligned_smallT5_full
Base model
google-t5/t5-smallDataset used to train paulh27/xsum_aligned_smallT5_full
Evaluation results
- Rouge1 on lilferrit/xsum_t5_distillationself-reported22.850