bert-reg-crossencoder-mae
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: 0.2200
- Mse: 0.0781
- Mae: 0.2200
- Pearson Corr: 0.3461
- Spearman Corr: 0.3129
- Cosine Sim: 0.9050
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: 2e-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: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | Pearson Corr | Spearman Corr | Cosine Sim |
|---|---|---|---|---|---|---|---|---|
| 0.2886 | 1.0 | 41 | 0.2213 | 0.0742 | 0.2213 | 0.0650 | 0.0604 | 0.9037 |
| 0.2582 | 2.0 | 82 | 0.2223 | 0.0714 | 0.2223 | 0.1319 | 0.1417 | 0.9052 |
| 0.2615 | 3.0 | 123 | 0.2094 | 0.0670 | 0.2094 | 0.2859 | 0.2753 | 0.9113 |
| 0.2247 | 4.0 | 164 | 0.2152 | 0.0733 | 0.2152 | 0.3126 | 0.2705 | 0.9075 |
| 0.1942 | 5.0 | 205 | 0.2363 | 0.0890 | 0.2363 | 0.3631 | 0.3424 | 0.9112 |
| 0.1758 | 6.0 | 246 | 0.2193 | 0.0776 | 0.2193 | 0.3528 | 0.3247 | 0.9106 |
| 0.166 | 7.0 | 287 | 0.2200 | 0.0781 | 0.2200 | 0.3461 | 0.3129 | 0.9050 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1