pythia-160m-deduped
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.4120
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: 2e-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: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
6.1275 | 1.0 | 2350 | 6.1444 |
5.5689 | 2.0 | 4700 | 5.8369 |
5.2369 | 3.0 | 7050 | 5.6571 |
5.0132 | 4.0 | 9400 | 5.5466 |
4.7901 | 5.0 | 11750 | 5.4800 |
4.6078 | 6.0 | 14100 | 5.4317 |
4.475 | 7.0 | 16450 | 5.4096 |
4.3359 | 8.0 | 18800 | 5.4028 |
4.2298 | 9.0 | 21150 | 5.4072 |
4.1611 | 10.0 | 23500 | 5.4120 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 1