<!-- 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-autoreg-bpe-babylm-no_aann-removal-3e-4
This model is a fine-tuned version of models/smolm-autoreg-bpe-babylm-no_aann-removal-3e-4/config.json on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1612
- Accuracy: 0.4307
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 32000
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.9242 | 1.0 | 9181 | 3.9677 | 0.3379 |
| 3.4055 | 2.0 | 18362 | 3.5095 | 0.3839 |
| 3.2333 | 3.0 | 27543 | 3.3686 | 0.3980 |
| 3.1274 | 4.0 | 36724 | 3.2789 | 0.4081 |
| 3.0374 | 5.0 | 45905 | 3.2199 | 0.4153 |
| 2.9706 | 6.0 | 55086 | 3.1906 | 0.4197 |
| 2.9196 | 7.0 | 64267 | 3.1616 | 0.4231 |
| 2.879 | 8.0 | 73448 | 3.1625 | 0.4245 |
| 2.8462 | 9.0 | 82629 | 3.1487 | 0.4261 |
| 2.8111 | 10.0 | 91810 | 3.1358 | 0.4284 |
| 2.7816 | 11.0 | 100991 | 3.1401 | 0.4283 |
| 2.7575 | 12.0 | 110172 | 3.1337 | 0.4293 |
| 2.7329 | 13.0 | 119353 | 3.1365 | 0.4296 |
| 2.7064 | 14.0 | 128534 | 3.1398 | 0.4301 |
| 2.6844 | 15.0 | 137715 | 3.1397 | 0.4303 |
| 2.6681 | 16.0 | 146896 | 3.1448 | 0.4307 |
| 2.6456 | 17.0 | 156077 | 3.1444 | 0.4308 |
| 2.6249 | 18.0 | 165258 | 3.1542 | 0.4307 |
| 2.6044 | 19.0 | 174439 | 3.1552 | 0.4309 |
| 2.5845 | 20.0 | 183620 | 3.1612 | 0.4307 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
