|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: strict_balanced_cf_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. --> |
|
|
|
|
|
# strict_balanced_cf_seed-21_1e-3 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.1894 |
|
|
- Accuracy: 0.4008 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:|:--------:| |
|
|
| 5.9825 | 0.9998 | 1486 | 4.4171 | 0.2926 | |
|
|
| 4.3054 | 1.9997 | 2972 | 3.9050 | 0.3329 | |
|
|
| 3.6755 | 2.9997 | 4458 | 3.6276 | 0.3573 | |
|
|
| 3.4878 | 3.9996 | 5944 | 3.4715 | 0.3714 | |
|
|
| 3.2604 | 4.9995 | 7430 | 3.3707 | 0.3811 | |
|
|
| 3.1894 | 5.9994 | 8916 | 3.3120 | 0.3864 | |
|
|
| 3.0822 | 6.9993 | 10402 | 3.2720 | 0.3903 | |
|
|
| 3.0424 | 7.9999 | 11889 | 3.2489 | 0.3915 | |
|
|
| 2.9835 | 8.9998 | 13375 | 3.2300 | 0.3943 | |
|
|
| 2.9586 | 9.9997 | 14861 | 3.2202 | 0.3957 | |
|
|
| 2.9205 | 10.9997 | 16347 | 3.2069 | 0.3972 | |
|
|
| 2.901 | 11.9996 | 17833 | 3.2097 | 0.3975 | |
|
|
| 2.8789 | 12.9995 | 19319 | 3.1967 | 0.3987 | |
|
|
| 2.8594 | 13.9994 | 20805 | 3.1981 | 0.3986 | |
|
|
| 2.8502 | 14.9993 | 22291 | 3.1954 | 0.3996 | |
|
|
| 2.8349 | 15.9999 | 23778 | 3.1954 | 0.3996 | |
|
|
| 2.8319 | 16.9998 | 25264 | 3.1878 | 0.4001 | |
|
|
| 2.8127 | 17.9997 | 26750 | 3.1866 | 0.4005 | |
|
|
| 2.8195 | 18.9997 | 28236 | 3.1900 | 0.4002 | |
|
|
| 2.7995 | 19.9982 | 29720 | 3.1894 | 0.4008 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.2 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.20.0 |
|
|
|
