experiment-distill-tree-babylm2024-95M-seq-1
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7385
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 |
|---|---|---|---|
| 5.9699 | 1.0 | 2065 | 6.2448 |
| 4.6549 | 2.0 | 4130 | 4.8993 |
| 4.2589 | 3.0 | 6195 | 4.4819 |
| 4.0998 | 4.0 | 8260 | 4.1964 |
| 3.8633 | 5.0 | 10325 | 4.0308 |
| 3.8233 | 6.0 | 12390 | 3.9305 |
| 3.6705 | 7.0 | 14455 | 3.8324 |
| 3.634 | 8.0 | 16520 | 3.7693 |
| 3.551 | 9.0 | 18585 | 3.7437 |
| 3.6128 | 10.0 | 20650 | 3.7385 |
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.