<!-- 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-small-finetuned-cnndm3-wikihow3
This model is a fine-tuned version of Chikashi/t5-small-finetuned-cnndm3-wikihow2 on the wikihow dataset. It achieves the following results on the evaluation set:
- Loss: 2.3138
- Rouge1: 27.2654
- Rouge2: 10.5461
- Rougel: 23.2451
- Rougelsum: 26.6151
- Gen Len: 18.5263
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.5019 | 1.0 | 39313 | 2.3138 | 27.2654 | 10.5461 | 23.2451 | 26.6151 | 18.5263 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1
