metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: NL_30000_41
results: []
NL_30000_41
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.1461
- Accuracy: 0.2990
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 |
|---|---|---|---|---|
| No log | 1.0 | 867 | 5.4512 | 0.1859 |
| 1.3675 | 2.0 | 1734 | 4.9265 | 0.2254 |
| 1.1799 | 3.0 | 2601 | 4.7038 | 0.2432 |
| 1.0961 | 4.0 | 3468 | 4.5697 | 0.2548 |
| 1.0515 | 5.0 | 4335 | 4.4518 | 0.2681 |
| 1.0172 | 6.0 | 5202 | 4.3518 | 0.2768 |
| 0.9873 | 7.0 | 6069 | 4.2935 | 0.2831 |
| 0.9873 | 8.0 | 6936 | 4.2205 | 0.2899 |
| 0.9636 | 9.0 | 7803 | 4.1697 | 0.2958 |
| 0.9396 | 10.0 | 8670 | 4.1461 | 0.2990 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1