metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: rerun-09-19-2024-experiment-distill-tree-babylm2024-58-0
results: []
rerun-09-19-2024-experiment-distill-tree-babylm2024-58-0
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 8.8473
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 |
|---|---|---|---|
| 17.6398 | 1.0 | 2065 | 17.5817 |
| 12.108 | 2.0 | 4130 | 12.8574 |
| 10.4361 | 3.0 | 6195 | 11.2524 |
| 9.736 | 4.0 | 8260 | 10.4525 |
| 8.8776 | 5.0 | 10325 | 9.8839 |
| 8.7013 | 6.0 | 12390 | 9.4970 |
| 8.1128 | 7.0 | 14455 | 9.1750 |
| 7.8563 | 8.0 | 16520 | 8.9723 |
| 7.5679 | 9.0 | 18585 | 8.8712 |
| 7.7079 | 10.0 | 20650 | 8.8473 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Tokenizers 0.19.1