bart-finetuned-lyrlen-512-tokens
This model is a fine-tuned version of adamjweintraut/bart-finetuned-lyrlen-512-tokens on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9201
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: 4
- eval_batch_size: 4
- 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 |
---|---|---|---|
1.6489 | 0.08 | 500 | 1.9176 |
1.5992 | 0.17 | 1000 | 1.9000 |
1.6334 | 0.25 | 1500 | 1.9288 |
1.5383 | 0.33 | 2000 | 1.9420 |
1.5532 | 0.42 | 2500 | 1.9014 |
1.5539 | 0.5 | 3000 | 1.9023 |
1.5319 | 0.58 | 3500 | 1.8747 |
1.5108 | 0.67 | 4000 | 1.9123 |
1.5249 | 0.75 | 4500 | 1.8853 |
1.497 | 0.83 | 5000 | 1.9822 |
1.5314 | 0.92 | 5500 | 1.8954 |
1.5292 | 1.0 | 6000 | 1.9192 |
1.5169 | 1.08 | 6500 | 1.9198 |
1.4837 | 1.17 | 7000 | 1.9046 |
1.48 | 1.25 | 7500 | 1.8926 |
1.4353 | 1.33 | 8000 | 2.1276 |
1.4948 | 1.42 | 8500 | 1.9633 |
1.5048 | 1.5 | 9000 | 1.9023 |
1.4921 | 1.58 | 9500 | 1.9101 |
1.469 | 1.67 | 10000 | 1.9674 |
1.4422 | 1.75 | 10500 | 1.9043 |
1.461 | 1.83 | 11000 | 1.9131 |
1.4299 | 1.92 | 11500 | 1.9426 |
1.484 | 2.0 | 12000 | 1.9201 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
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.