modernbert-CGEdit-AAE_cg_final
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8943
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.6163 | 1.0 | 183 | 0.9028 |
| 3.5821 | 2.0 | 366 | 0.8998 |
| 3.5796 | 3.0 | 549 | 0.8986 |
| 3.6004 | 4.0 | 732 | 0.8979 |
| 3.5550 | 5.0 | 915 | 0.8972 |
| 3.5406 | 6.0 | 1098 | 0.8960 |
| 3.5234 | 7.0 | 1281 | 0.8950 |
| 3.5427 | 8.0 | 1464 | 0.8945 |
| 3.5038 | 9.0 | 1647 | 0.8941 |
| 3.3334 | 10.0 | 1830 | 0.8946 |
| 3.5211 | 11.0 | 2013 | 0.8949 |
| 3.5114 | 12.0 | 2196 | 0.8940 |
| 3.5164 | 13.0 | 2379 | 0.8937 |
| 3.5044 | 14.0 | 2562 | 0.8945 |
| 3.4915 | 15.0 | 2745 | 0.8938 |
| 3.4984 | 16.0 | 2928 | 0.8939 |
| 3.4953 | 17.0 | 3111 | 0.8940 |
| 3.5025 | 18.0 | 3294 | 0.8943 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.5.1+cu121
- Tokenizers 0.22.1
- Downloads last month
- 22