long-t5-tglobal-xl-qmsum-wip
⚠️ warning - this is a work in progress ⚠️
This model is a fine-tuned version of google/long-t5-tglobal-xl on the pszemraj/qmsum-cleaned dataset.
- Refer to the dataset card for details but this model was trained with the task/prompt prefixes at the start of
inputwhich means that inference should be run in a similar fashion. - an example of how to run inference is in the Colab notebook linked above.
It achieves the following results on the evaluation set:
- Loss: 2.0505
- Rouge1: 35.3881
- Rouge2: 11.509
- Rougel: 23.1543
- Rougelsum: 31.3295
- Gen Len: 80.8
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 2526
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.5376 | 1.0 | 99 | 2.0104 | 35.8802 | 11.4595 | 23.6656 | 31.49 | 77.77 |
| 1.499 | 2.0 | 198 | 2.0358 | 35.1265 | 11.549 | 23.1062 | 30.8815 | 88.88 |
| 1.5034 | 3.0 | 297 | 2.0505 | 35.3881 | 11.509 | 23.1543 | 31.3295 | 80.8 |
- Downloads last month
- 6