ALL_bart_15_spider_new2
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4402
- Rouge2 Precision: 0.4522
- Rouge2 Recall: 0.3179
- Rouge2 Fmeasure: 0.3513
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: 5e-05
- train_batch_size: 30
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 0.7693 | 1.0 | 647 | 0.3306 | 0.3852 | 0.2571 | 0.2875 |
| 0.166 | 2.0 | 1294 | 0.3361 | 0.3785 | 0.2577 | 0.2858 |
| 0.1247 | 3.0 | 1941 | 0.3572 | 0.4176 | 0.2801 | 0.3132 |
| 0.0844 | 4.0 | 2588 | 0.3678 | 0.4189 | 0.2882 | 0.32 |
| 0.0711 | 5.0 | 3235 | 0.3778 | 0.4313 | 0.3021 | 0.3338 |
| 0.0619 | 6.0 | 3882 | 0.3928 | 0.4335 | 0.3012 | 0.3337 |
| 0.0474 | 7.0 | 4529 | 0.3987 | 0.4415 | 0.3064 | 0.3395 |
| 0.041 | 8.0 | 5176 | 0.4098 | 0.4289 | 0.2963 | 0.3288 |
| 0.0371 | 9.0 | 5823 | 0.4180 | 0.4404 | 0.3134 | 0.3447 |
| 0.0331 | 10.0 | 6470 | 0.4197 | 0.4359 | 0.3055 | 0.3375 |
| 0.0268 | 11.0 | 7117 | 0.4272 | 0.4406 | 0.3084 | 0.3409 |
| 0.025 | 12.0 | 7764 | 0.4337 | 0.4424 | 0.3105 | 0.3427 |
| 0.0229 | 13.0 | 8411 | 0.4355 | 0.4383 | 0.3104 | 0.3416 |
| 0.0198 | 14.0 | 9058 | 0.4391 | 0.4471 | 0.3157 | 0.3481 |
| 0.0187 | 15.0 | 9705 | 0.4402 | 0.4522 | 0.3179 | 0.3513 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.7.dev0
- Tokenizers 0.13.3
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.