<!-- 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. -->
Regression_distilbert-base-uncased
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1187
- Mse: 2.1187
- Mae: 1.3097
- R2: -0.0932
- Accuracy: 0.1429
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
- num_epochs: 25
Training results
Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 2 | 3.3933 | 3.3933 | 1.5228 | -2.1839 | 0.2857 |
No log | 2.0 | 4 | 3.0571 | 3.0571 | 1.4011 | -1.8684 | 0.4286 |
No log | 3.0 | 6 | 2.6747 | 2.6747 | 1.2786 | -1.5096 | 0.4286 |
No log | 4.0 | 8 | 2.3024 | 2.3024 | 1.2088 | -1.1603 | 0.4286 |
No log | 5.0 | 10 | 1.9496 | 1.9496 | 1.1459 | -0.8292 | 0.4286 |
No log | 6.0 | 12 | 1.6637 | 1.6637 | 1.1225 | -0.5610 | 0.2857 |
No log | 7.0 | 14 | 1.4167 | 1.4167 | 1.0938 | -0.3293 | 0.1429 |
No log | 8.0 | 16 | 1.2365 | 1.2365 | 1.0609 | -0.1602 | 0.0 |
No log | 9.0 | 18 | 1.1239 | 1.1239 | 1.0234 | -0.0545 | 0.0 |
No log | 10.0 | 20 | 1.0879 | 1.0879 | 0.9906 | -0.0207 | 0.0 |
No log | 11.0 | 22 | 1.1122 | 1.1122 | 0.9599 | -0.0436 | 0.2857 |
No log | 12.0 | 24 | 1.1879 | 1.1879 | 0.9374 | -0.1145 | 0.2857 |
No log | 13.0 | 26 | 1.2784 | 1.2784 | 0.9132 | -0.1995 | 0.4286 |
No log | 14.0 | 28 | 1.3756 | 1.3756 | 0.8905 | -0.2907 | 0.4286 |
No log | 15.0 | 30 | 1.4710 | 1.4710 | 0.9093 | -0.3802 | 0.4286 |
No log | 16.0 | 32 | 1.5513 | 1.5513 | 0.9333 | -0.4555 | 0.4286 |
No log | 17.0 | 34 | 1.6094 | 1.6094 | 0.9491 | -0.5101 | 0.5714 |
No log | 18.0 | 36 | 1.6446 | 1.6446 | 0.9567 | -0.5431 | 0.5714 |
No log | 19.0 | 38 | 1.6510 | 1.6510 | 0.9555 | -0.5491 | 0.5714 |
No log | 20.0 | 40 | 1.6425 | 1.6425 | 0.9503 | -0.5412 | 0.5714 |
No log | 21.0 | 42 | 1.6254 | 1.6254 | 0.9455 | -0.5251 | 0.5714 |
No log | 22.0 | 44 | 1.6025 | 1.6025 | 0.9378 | -0.5036 | 0.5714 |
No log | 23.0 | 46 | 1.5758 | 1.5758 | 0.9289 | -0.4786 | 0.5714 |
No log | 24.0 | 48 | 1.5583 | 1.5583 | 0.9233 | -0.4622 | 0.5714 |
No log | 25.0 | 50 | 1.5504 | 1.5504 | 0.9210 | -0.4547 | 0.5714 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2