metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BABYLM_30000_41
results: []
BABYLM_30000_41
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8423
- Accuracy: 0.3664
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: 0.0006
- train_batch_size: 32
- eval_batch_size: 32
- seed: 41
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1428 | 1.0 | 1020 | 4.3943 | 0.3208 |
| 1.0267 | 2.0 | 2040 | 4.3414 | 0.3214 |
| 1.0196 | 3.0 | 3060 | 4.3037 | 0.3261 |
| 1.0028 | 4.0 | 4080 | 4.2439 | 0.3305 |
| 0.9826 | 5.0 | 5100 | 4.1674 | 0.3380 |
| 0.9647 | 6.0 | 6120 | 4.0897 | 0.3450 |
| 0.9376 | 7.0 | 7140 | 3.9938 | 0.3535 |
| 0.9117 | 8.0 | 8160 | 3.9159 | 0.3597 |
| 0.8938 | 9.0 | 9180 | 3.8661 | 0.3645 |
| 0.8816 | 10.0 | 10200 | 3.8423 | 0.3664 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1