<!-- 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. -->
mt5-base-finetuned-notes-summaries
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 5.5563
- Rouge2: 1.1271
- Rougel: 5.1075
- Rougelsum: 5.1383
- Gen Len: 10.0222
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 446 | nan | 5.5563 | 1.1271 | 5.1075 | 5.1383 | 10.0222 |
| 0.0 | 2.0 | 892 | nan | 5.5563 | 1.1271 | 5.1075 | 5.1383 | 10.0222 |
| 0.0 | 3.0 | 1338 | nan | 5.5563 | 1.1271 | 5.1075 | 5.1383 | 10.0222 |
| 0.0 | 4.0 | 1784 | nan | 5.5563 | 1.1271 | 5.1075 | 5.1383 | 10.0222 |
| 0.0 | 5.0 | 2230 | nan | 5.5563 | 1.1271 | 5.1075 | 5.1383 | 10.0222 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
