bart-finetuned-eli5_lfqa_best
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2150
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4037 | 0.1 | 500 | 1.1726 |
1.2748 | 0.2 | 1000 | 1.1755 |
1.3348 | 0.3 | 1500 | 1.1546 |
1.284 | 0.4 | 2000 | 1.1638 |
1.2273 | 0.5 | 2500 | 1.1461 |
1.2169 | 0.6 | 3000 | 1.1511 |
1.2477 | 0.7 | 3500 | 1.3051 |
1.306 | 0.8 | 4000 | 1.2678 |
1.2626 | 0.9 | 4500 | 1.2547 |
1.2556 | 1.0 | 5000 | 1.2430 |
1.2421 | 1.1 | 5500 | 1.2369 |
1.1927 | 1.2 | 6000 | 1.2348 |
1.187 | 1.3 | 6500 | 1.2278 |
1.2344 | 1.4 | 7000 | 1.2223 |
1.1958 | 1.5 | 7500 | 1.2152 |
1.1348 | 1.6 | 8000 | 1.2139 |
1.1661 | 1.7 | 8500 | 1.2161 |
1.1869 | 1.8 | 9000 | 1.2151 |
1.1554 | 1.9 | 9500 | 1.2143 |
1.1444 | 2.0 | 10000 | 1.2150 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 0