experiment-distill-tree-babylm2024-360M-seq-1
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3179
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: 0.00025
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.9781 | 1.0 | 2065 | 5.2077 |
| 4.067 | 2.0 | 4130 | 4.2131 |
| 3.7294 | 3.0 | 6195 | 3.8683 |
| 3.6035 | 4.0 | 8260 | 3.7189 |
| 3.3807 | 5.0 | 10325 | 3.5719 |
| 3.3317 | 6.0 | 12390 | 3.4493 |
| 3.2038 | 7.0 | 14455 | 3.3726 |
| 3.1785 | 8.0 | 16520 | 3.3364 |
| 3.1046 | 9.0 | 18585 | 3.3218 |
| 3.1651 | 10.0 | 20650 | 3.3179 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Tokenizers 0.19.1
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.