<!-- 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. -->
bert_base_120
This model is a fine-tuned version of gokuls/bert_base_96 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3904
- Accuracy: 0.5602
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.7403 | 0.08 | 10000 | 2.6150 | 0.5307 |
| 2.6939 | 0.16 | 20000 | 2.5743 | 0.5360 |
| 2.6549 | 0.25 | 30000 | 2.5380 | 0.5408 |
| 2.6298 | 0.33 | 40000 | 2.5020 | 0.5455 |
| 2.5883 | 0.41 | 50000 | 2.4715 | 0.5494 |
| 2.5629 | 0.49 | 60000 | 2.4432 | 0.5533 |
| 2.5274 | 0.57 | 70000 | 2.4163 | 0.5568 |
| 2.5059 | 0.66 | 80000 | 2.3904 | 0.5602 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
