<!-- 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. -->
dreams
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8850
- Rouge1: 0.1304
- Rouge2: 0.0158
- Rougel: 0.0974
- Rougelsum: 0.0973
- Gen Len: 18.8978
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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 93 | 4.0104 | 0.1127 | 0.0106 | 0.0844 | 0.0843 | 18.9624 |
No log | 2.0 | 186 | 3.9313 | 0.1217 | 0.0125 | 0.093 | 0.0927 | 18.9543 |
No log | 3.0 | 279 | 3.9028 | 0.127 | 0.0135 | 0.0964 | 0.096 | 18.9355 |
No log | 4.0 | 372 | 3.8892 | 0.13 | 0.0159 | 0.0978 | 0.0976 | 18.8871 |
No log | 5.0 | 465 | 3.8850 | 0.1304 | 0.0158 | 0.0974 | 0.0973 | 18.8978 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2