<!-- 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_1709
This model is a fine-tuned version of models/smolm-mlm-bpe-unmask-seed_1709/config.json on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6838
- Accuracy: 0.4529
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: 1709
- 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 |
|---|---|---|---|---|
| 3.5536 | 1.0 | 11938 | 3.4863 | 0.3483 |
| 3.3453 | 2.0 | 23876 | 3.3396 | 0.3599 |
| 3.151 | 3.0 | 35814 | 3.1792 | 0.3818 |
| 3.0433 | 4.0 | 47752 | 3.0515 | 0.3981 |
| 2.9178 | 5.0 | 59690 | 2.9431 | 0.4131 |
| 2.841 | 6.0 | 71628 | 2.8881 | 0.4206 |
| 2.7902 | 7.0 | 83566 | 2.8051 | 0.4337 |
| 2.7053 | 8.0 | 95504 | 2.7643 | 0.4412 |
| 2.6808 | 9.0 | 107442 | 2.7301 | 0.4435 |
| 2.6344 | 10.0 | 119380 | 2.6952 | 0.4479 |
Framework versions
- Transformers 4.32.1
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
