<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
smolm-mlm-bpe-unmask-seed_777
This model is a fine-tuned version of models/smolm-mlm/config.json on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7113
- Accuracy: 0.4480
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 512
- seed: 777
- 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 |
|---|---|---|---|---|
| 3.54 | 1.0 | 11938 | 3.4890 | 0.3516 |
| 3.3273 | 2.0 | 23876 | 3.3427 | 0.3628 |
| 3.1559 | 3.0 | 35814 | 3.1642 | 0.3866 |
| 3.0559 | 4.0 | 47752 | 3.0452 | 0.3995 |
| 2.9405 | 5.0 | 59690 | 2.9770 | 0.4121 |
| 2.8478 | 6.0 | 71628 | 2.8953 | 0.4208 |
| 2.7872 | 7.0 | 83566 | 2.8437 | 0.4273 |
| 2.7092 | 8.0 | 95504 | 2.7663 | 0.4386 |
| 2.6641 | 9.0 | 107442 | 2.7282 | 0.4471 |
| 2.6346 | 10.0 | 119380 | 2.6966 | 0.4522 |
Framework versions
- Transformers 4.32.1
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
