<!-- 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. -->
Authors
Kanishka Misra and Najoung Kim
smolm-mlm-bpe-unmask-seed_666
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: 2.6992
- Accuracy: 0.4500
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: 666
- 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 |
|---|---|---|---|---|
| 3.5563 | 1.0 | 11938 | 3.5327 | 0.3460 |
| 3.3111 | 2.0 | 23876 | 3.3614 | 0.3626 |
| 3.1505 | 3.0 | 35814 | 3.1647 | 0.3857 |
| 3.0774 | 4.0 | 47752 | 3.0538 | 0.3970 |
| 2.9331 | 5.0 | 59690 | 2.9540 | 0.4137 |
| 2.8411 | 6.0 | 71628 | 2.8855 | 0.4240 |
| 2.7907 | 7.0 | 83566 | 2.8185 | 0.4294 |
| 2.7201 | 8.0 | 95504 | 2.7614 | 0.4389 |
| 2.6691 | 9.0 | 107442 | 2.7250 | 0.4450 |
| 2.6016 | 10.0 | 119380 | 2.7179 | 0.4467 |
Framework versions
- Transformers 4.32.1
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
