t5-base-msmarco-nlgen-ob
This model is a fine-tuned version of t5-base on the MS MARCO Natural Language Generation dataset. It achieves the following results on the evaluation set:
- Loss: 0.3874
- Rougelsum: 14.4418
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: 8
- eval_batch_size: 8
- 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 | Rougelsum |
|---|---|---|---|---|
| 0.5472 | 0.13 | 2500 | 0.4383 | 14.2497 |
| 0.5238 | 0.26 | 5000 | 0.4252 | 14.4210 |
| 0.501 | 0.39 | 7500 | 0.4093 | 14.3315 |
| 0.4958 | 0.52 | 10000 | 0.4006 | 14.3347 |
| 0.4913 | 0.66 | 12500 | 0.3944 | 14.5925 |
| 0.4873 | 0.79 | 15000 | 0.3914 | 14.4193 |
| 0.466 | 0.92 | 17500 | 0.3874 | 14.4418 |
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.1+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1