results
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2121
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: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.9506 | 0.02 | 500 | 2.8101 |
2.4301 | 0.05 | 1000 | 2.1858 |
2.0797 | 0.07 | 1500 | 1.9611 |
1.8886 | 0.09 | 2000 | 1.9707 |
1.8233 | 0.11 | 2500 | 1.8003 |
1.7206 | 0.14 | 3000 | 1.6781 |
1.8058 | 0.16 | 3500 | 1.6392 |
1.7295 | 0.18 | 4000 | 1.6737 |
1.5277 | 0.21 | 4500 | 1.5726 |
1.7119 | 0.23 | 5000 | 1.5483 |
1.5336 | 0.25 | 5500 | 1.5101 |
1.4941 | 0.27 | 6000 | 1.5148 |
1.5772 | 0.3 | 6500 | 1.4756 |
1.5502 | 0.32 | 7000 | 1.4674 |
1.5082 | 0.34 | 7500 | 1.4226 |
1.3915 | 0.37 | 8000 | 1.4724 |
1.4148 | 0.39 | 8500 | 1.4887 |
1.3679 | 0.41 | 9000 | 1.4886 |
1.5084 | 0.43 | 9500 | 1.4322 |
1.536 | 0.46 | 10000 | 1.4154 |
1.2947 | 0.48 | 10500 | 1.3504 |
1.4683 | 0.5 | 11000 | 1.3220 |
1.5612 | 0.53 | 11500 | 1.3240 |
1.4945 | 0.55 | 12000 | 1.3197 |
1.2196 | 0.57 | 12500 | 1.3212 |
1.3482 | 0.59 | 13000 | 1.3087 |
1.347 | 0.62 | 13500 | 1.3024 |
1.452 | 0.64 | 14000 | 1.2683 |
1.3566 | 0.66 | 14500 | 1.2739 |
1.4127 | 0.68 | 15000 | 1.2509 |
1.2698 | 0.71 | 15500 | 1.3120 |
1.3437 | 0.73 | 16000 | 1.3072 |
1.2282 | 0.75 | 16500 | 1.3101 |
1.3098 | 0.78 | 17000 | 1.3015 |
1.3029 | 0.8 | 17500 | 1.2327 |
1.1749 | 0.82 | 18000 | 1.3186 |
1.2526 | 0.84 | 18500 | 1.2593 |
1.2942 | 0.87 | 19000 | 1.2343 |
1.1729 | 0.89 | 19500 | 1.2555 |
1.2365 | 0.91 | 20000 | 1.2084 |
1.1355 | 0.94 | 20500 | 1.2242 |
1.196 | 0.96 | 21000 | 1.2084 |
1.3075 | 0.98 | 21500 | 1.2121 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Inference API (serverless) is not available, repository is disabled.
Model tree for Keerthana12/results
Base model
google-bert/bert-base-uncased
Finetuned
this model