metadata
base_model: models/smolm-mlm/config.json
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: smolm-mlm-bpe-unmask-seed_222
results: []
smolm-mlm-bpe-unmask-seed_222
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: 2.7005
- Accuracy: 0.4481
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: 222
- 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 |
|---|---|---|---|---|
| 3.5334 | 1.0 | 11938 | 3.4896 | 0.3463 |
| 3.3402 | 2.0 | 23876 | 3.3814 | 0.3590 |
| 3.1641 | 3.0 | 35814 | 3.1702 | 0.3844 |
| 3.0325 | 4.0 | 47752 | 3.0475 | 0.4019 |
| 2.951 | 5.0 | 59690 | 2.9666 | 0.4095 |
| 2.8583 | 6.0 | 71628 | 2.8908 | 0.4201 |
| 2.7872 | 7.0 | 83566 | 2.8299 | 0.4310 |
| 2.7348 | 8.0 | 95504 | 2.7900 | 0.4335 |
| 2.6584 | 9.0 | 107442 | 2.7272 | 0.4443 |
| 2.6462 | 10.0 | 119380 | 2.6962 | 0.4501 |
Framework versions
- Transformers 4.32.1
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3