<!-- 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. -->
NASca-finetuned-diego-2
This model is a fine-tuned version of ELiRF/NASCA on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9197
- Rouge1: 0.2930
- Rouge2: 0.1226
- Rougel: 0.2327
- Rougelsum: 0.2373
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: 1.3739167643078955e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- 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 |
---|---|---|---|---|---|---|---|
1.4353 | 0.09 | 15000 | 1.7848 | 0.2816 | 0.1157 | 0.2258 | 0.2305 |
1.3237 | 1.0 | 159149 | 1.7707 | 0.2831 | 0.1171 | 0.2267 | 0.2318 |
1.3836 | 2.0 | 318298 | 1.7924 | 0.2899 | 0.1211 | 0.2316 | 0.2361 |
1.274 | 3.0 | 477447 | 1.8809 | 0.2921 | 0.1225 | 0.2323 | 0.2368 |
1.2289 | 4.0 | 636596 | 1.9128 | 0.2926 | 0.1223 | 0.2322 | 0.2368 |
1.2424 | 5.0 | 795745 | 1.9197 | 0.2930 | 0.1226 | 0.2327 | 0.2373 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2