albert-large-v2_cls_subj
This model is a fine-tuned version of albert-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6940
- Accuracy: 0.4835
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: 4e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3156 | 1.0 | 500 | 0.2889 | 0.9305 |
| 0.4473 | 2.0 | 1000 | 0.6936 | 0.4835 |
| 0.7088 | 3.0 | 1500 | 0.7079 | 0.4835 |
| 0.7022 | 4.0 | 2000 | 0.6927 | 0.5165 |
| 0.6951 | 5.0 | 2500 | 0.6940 | 0.4835 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1