<!-- 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. -->
flan-t5-subjective
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0394
- Rouge1: 97.6501
- Rouge2: 0.0
- Rougel: 97.6501
- Rougelsum: 97.6501
- Gen Len: 2.0026
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.1703 | 1.0 | 1149 | 0.0849 | 96.2576 | 0.0 | 96.2576 | 96.2576 | 2.0026 |
| 0.066 | 2.0 | 2298 | 0.0629 | 96.9539 | 0.0 | 96.9539 | 97.0409 | 2.0026 |
| 0.0496 | 3.0 | 3447 | 0.0394 | 97.6501 | 0.0 | 97.6501 | 97.6501 | 2.0026 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.3
