opt-125m-tldr
This model is a fine-tuned version of facebook/opt-125m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6296
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: 1e-05
- 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
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.7992 | 0.07 | 1000 | 2.7158 |
2.7437 | 0.14 | 2000 | 2.6938 |
2.732 | 0.21 | 3000 | 2.6797 |
2.7157 | 0.27 | 4000 | 2.6691 |
2.7071 | 0.34 | 5000 | 2.6620 |
2.6998 | 0.41 | 6000 | 2.6557 |
2.696 | 0.48 | 7000 | 2.6495 |
2.6902 | 0.55 | 8000 | 2.6451 |
2.6791 | 0.62 | 9000 | 2.6408 |
2.6823 | 0.69 | 10000 | 2.6379 |
2.6806 | 0.75 | 11000 | 2.6345 |
2.6746 | 0.82 | 12000 | 2.6330 |
2.6765 | 0.89 | 13000 | 2.6306 |
2.6738 | 0.96 | 14000 | 2.6296 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2
- Downloads last month
- 17
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.