|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: long_first_headfinal_seed-21_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. --> |
|
|
|
|
|
# long_first_headfinal_seed-21_1e-3 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 5.0807 |
|
|
- Accuracy: 0.2038 |
|
|
|
|
|
## 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: 21 |
|
|
- 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:|:--------:| |
|
|
| 6.1412 | 0.9994 | 1470 | 5.5240 | 0.1764 | |
|
|
| 4.5259 | 1.9992 | 2940 | 5.4067 | 0.1823 | |
|
|
| 3.8908 | 2.9991 | 4410 | 5.3111 | 0.1857 | |
|
|
| 3.7115 | 3.9996 | 5881 | 5.2018 | 0.1937 | |
|
|
| 3.4863 | 4.9994 | 7351 | 5.1925 | 0.1938 | |
|
|
| 3.4079 | 5.9992 | 8821 | 5.1520 | 0.1973 | |
|
|
| 3.3056 | 6.9991 | 10291 | 5.1326 | 0.1999 | |
|
|
| 3.258 | 7.9996 | 11762 | 5.1119 | 0.1997 | |
|
|
| 3.2065 | 8.9994 | 13232 | 5.1225 | 0.2009 | |
|
|
| 3.1699 | 9.9992 | 14702 | 5.1300 | 0.1987 | |
|
|
| 3.1451 | 10.9991 | 16172 | 5.0815 | 0.2020 | |
|
|
| 3.1079 | 11.9996 | 17643 | 5.1214 | 0.2012 | |
|
|
| 3.1043 | 12.9994 | 19113 | 5.0818 | 0.2012 | |
|
|
| 3.0668 | 13.9992 | 20583 | 5.1290 | 0.2022 | |
|
|
| 3.0777 | 14.9991 | 22053 | 5.1106 | 0.1996 | |
|
|
| 3.039 | 15.9996 | 23524 | 5.1058 | 0.2006 | |
|
|
| 3.0432 | 16.9994 | 24994 | 5.1083 | 0.2036 | |
|
|
| 3.0188 | 17.9992 | 26464 | 5.1309 | 0.2016 | |
|
|
| 3.0246 | 18.9991 | 27934 | 5.1190 | 0.1996 | |
|
|
| 3.0115 | 19.9962 | 29400 | 5.0807 | 0.2038 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.2 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.20.0 |
|
|
|
