<!-- 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-2k-indic_glue
This model is a fine-tuned version of livinNector/tabert-2k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2663
- Precision: 0.7940
- Recall: 0.8281
- F1: 0.8107
- Accuracy: 0.9164
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 |
---|---|---|---|---|---|---|---|
0.5342 | 0.31 | 200 | 0.3755 | 0.6758 | 0.7277 | 0.7008 | 0.8753 |
0.3625 | 0.62 | 400 | 0.3276 | 0.7279 | 0.7920 | 0.7586 | 0.8914 |
0.3065 | 0.94 | 600 | 0.2855 | 0.7827 | 0.7980 | 0.7903 | 0.9050 |
0.2321 | 1.25 | 800 | 0.2804 | 0.7860 | 0.8063 | 0.7960 | 0.9092 |
0.1849 | 1.56 | 1000 | 0.2735 | 0.7946 | 0.8154 | 0.8049 | 0.9143 |
0.1784 | 1.88 | 1200 | 0.2663 | 0.7940 | 0.8281 | 0.8107 | 0.9164 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3