<!-- 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-0510
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: 0.2334
- Rouge1: 91.6115
- Rouge2: 86.7084
- Rougel: 91.0616
- Rougelsum: 91.1197
- Gen Len: 14.7895
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 |
---|---|---|---|---|---|---|---|---|
0.4381 | 1.0 | 542 | 0.2731 | 90.324 | 84.2616 | 89.0178 | 89.1459 | 14.5614 |
0.2999 | 2.0 | 1084 | 0.2374 | 91.6458 | 86.2909 | 90.8275 | 90.8257 | 14.7719 |
0.273 | 3.0 | 1626 | 0.2382 | 91.4445 | 86.8218 | 91.1231 | 91.0886 | 14.8947 |
0.2248 | 4.0 | 2168 | 0.2334 | 91.6115 | 86.7084 | 91.0616 | 91.1197 | 14.7895 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1