smolm-autoreg-bpe-seed_221
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4752
- Accuracy: 0.4995
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: 0.003
- train_batch_size: 16
- eval_batch_size: 128
- seed: 221
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 24000
- num_epochs: 10.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
3.0423 | 1.0 | 2928 | 3.0116 | 0.4385 |
2.712 | 2.0 | 5856 | 2.7864 | 0.4594 |
2.5896 | 3.0 | 8784 | 2.6920 | 0.4697 |
2.5169 | 4.0 | 11712 | 2.6432 | 0.4748 |
2.4655 | 5.0 | 14640 | 2.6049 | 0.4804 |
2.4298 | 6.0 | 17568 | 2.5832 | 0.4831 |
2.3975 | 7.0 | 20496 | 2.5711 | 0.4838 |
2.3628 | 8.0 | 23424 | 2.5585 | 0.4859 |
2.2882 | 9.0 | 26352 | 2.5041 | 0.4934 |
2.144 | 10.0 | 29280 | 2.4752 | 0.4995 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 4