<!-- 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. -->
T5-model-1-feedback-0611-4e
This model is a fine-tuned version of theojolliffe/T5-model-1-feedback-1109 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1221
- Rouge1: 93.9996
- Rouge2: 89.632
- Rougel: 93.4347
- Rougelsum: 93.4442
- Gen Len: 15.0185
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.2124 | 1.0 | 2571 | 0.1594 | 93.667 | 89.1053 | 93.052 | 93.0963 | 15.1218 |
| 0.1531 | 2.0 | 5142 | 0.1413 | 94.2879 | 89.9026 | 93.6752 | 93.7059 | 15.0332 |
| 0.1347 | 3.0 | 7713 | 0.1263 | 94.2554 | 90.1846 | 93.726 | 93.7635 | 15.0369 |
| 0.142 | 4.0 | 10284 | 0.1221 | 93.9996 | 89.632 | 93.4347 | 93.4442 | 15.0185 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
