<!-- 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. -->
tabert-4k-indic_glue
This model is a fine-tuned version of livinNector/tabert-4k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2559
- Precision: 0.7973
- Recall: 0.8344
- F1: 0.8155
- Accuracy: 0.9194
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4975 | 0.31 | 200 | 0.3452 | 0.7323 | 0.7252 | 0.7287 | 0.8835 |
| 0.3362 | 0.62 | 400 | 0.3243 | 0.7366 | 0.8005 | 0.7672 | 0.8941 |
| 0.2884 | 0.94 | 600 | 0.2804 | 0.7689 | 0.8014 | 0.7849 | 0.9056 |
| 0.2141 | 1.25 | 800 | 0.2705 | 0.7904 | 0.8162 | 0.8031 | 0.9117 |
| 0.1707 | 1.56 | 1000 | 0.2504 | 0.8024 | 0.8228 | 0.8125 | 0.9191 |
| 0.1608 | 1.88 | 1200 | 0.2559 | 0.7973 | 0.8344 | 0.8155 | 0.9194 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
