|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: noditrans_cf_seed-63_1e-3 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# noditrans_cf_seed-63_1e-3 |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.5107 |
|
- Accuracy: 0.3634 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- seed: 63 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Use OptimizerNames.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: 32000 |
|
- num_epochs: 20.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:-----:|:---------------:|:--------:| |
|
| 6.0721 | 0.9999 | 1507 | 4.5216 | 0.2803 | |
|
| 4.1353 | 1.9998 | 3014 | 4.0893 | 0.3122 | |
|
| 3.94 | 2.9998 | 4521 | 3.8747 | 0.3281 | |
|
| 3.7064 | 3.9997 | 6028 | 3.7568 | 0.3374 | |
|
| 3.6181 | 4.9996 | 7535 | 3.6738 | 0.3454 | |
|
| 3.5108 | 5.9995 | 9042 | 3.6136 | 0.3513 | |
|
| 3.4484 | 6.9994 | 10549 | 3.5901 | 0.3528 | |
|
| 3.395 | 8.0 | 12057 | 3.5658 | 0.3555 | |
|
| 3.3481 | 8.9999 | 13564 | 3.5571 | 0.3568 | |
|
| 3.326 | 9.9998 | 15071 | 3.5395 | 0.3584 | |
|
| 3.2846 | 10.9998 | 16578 | 3.5257 | 0.3602 | |
|
| 3.2805 | 11.9997 | 18085 | 3.5198 | 0.3609 | |
|
| 3.2426 | 12.9996 | 19592 | 3.5322 | 0.3596 | |
|
| 3.2487 | 13.9995 | 21099 | 3.5246 | 0.3614 | |
|
| 3.2137 | 14.9994 | 22606 | 3.5166 | 0.3618 | |
|
| 3.2257 | 16.0 | 24114 | 3.5283 | 0.3608 | |
|
| 3.1932 | 16.9999 | 25621 | 3.5097 | 0.3632 | |
|
| 3.2104 | 17.9998 | 27128 | 3.5262 | 0.3601 | |
|
| 3.1805 | 18.9998 | 28635 | 3.5176 | 0.3619 | |
|
| 3.1995 | 19.9983 | 30140 | 3.5107 | 0.3634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.20.0 |
|
|
