metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BABYLM_10000_41
results: []
BABYLM_10000_41
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7911
- Accuracy: 0.3537
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 |
|---|---|---|---|---|
| 1.127 | 1.0 | 1073 | 4.3120 | 0.3059 |
| 1.0263 | 2.0 | 2146 | 4.3131 | 0.3048 |
| 1.0232 | 3.0 | 3219 | 4.2797 | 0.3070 |
| 1.0192 | 4.0 | 4292 | 4.2357 | 0.3116 |
| 1.0035 | 5.0 | 5365 | 4.1641 | 0.3180 |
| 0.9839 | 6.0 | 6438 | 4.0780 | 0.3267 |
| 0.9631 | 7.0 | 7511 | 3.9749 | 0.3359 |
| 0.9374 | 8.0 | 8584 | 3.8823 | 0.3452 |
| 0.9131 | 9.0 | 9657 | 3.8188 | 0.3512 |
| 0.8966 | 10.0 | 10730 | 3.7911 | 0.3537 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1