metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-replycomments-finetuned-xsum
results: []
t5-small-replycomments-finetuned-xsum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0092
- Rouge1: 4.2177
- Rouge2: 0.0
- Rougel: 4.1508
- Rougelsum: 3.9608
- Gen Len: 18.2222
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: 16
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 7 | 5.5935 | 5.4081 | 1.8349 | 5.3241 | 5.0949 | 16.3333 |
| No log | 2.0 | 14 | 4.3785 | 6.0943 | 1.8349 | 5.7682 | 5.7452 | 18.2222 |
| No log | 3.0 | 21 | 4.1468 | 4.2177 | 0.0 | 4.1508 | 3.9608 | 18.2222 |
| No log | 4.0 | 28 | 4.0462 | 4.2177 | 0.0 | 4.1508 | 3.9608 | 18.2222 |
| No log | 5.0 | 35 | 4.0092 | 4.2177 | 0.0 | 4.1508 | 3.9608 | 18.2222 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3