Regression_electra
This model is a fine-tuned version of google/electra-small-generator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8817
- Mse: 3.8817
- Mae: 1.3788
- R2: -1.0029
- Accuracy: 0.5714
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 4 | 3.9672 | 3.9672 | 1.7046 | -2.7223 | 0.2857 |
| No log | 2.0 | 8 | 3.6507 | 3.6507 | 1.6091 | -2.4254 | 0.2857 |
| No log | 3.0 | 12 | 3.3083 | 3.3083 | 1.5005 | -2.1041 | 0.2857 |
| No log | 4.0 | 16 | 2.9698 | 2.9698 | 1.3825 | -1.7865 | 0.4286 |
| No log | 5.0 | 20 | 2.6694 | 2.6694 | 1.2744 | -1.5047 | 0.4286 |
| No log | 6.0 | 24 | 2.4048 | 2.4048 | 1.2286 | -1.2564 | 0.4286 |
| No log | 7.0 | 28 | 2.1518 | 2.1518 | 1.1790 | -1.0190 | 0.4286 |
| No log | 8.0 | 32 | 1.9522 | 1.9522 | 1.1423 | -0.8317 | 0.4286 |
| No log | 9.0 | 36 | 2.0610 | 2.0610 | 1.1825 | -0.9338 | 0.4286 |
| No log | 10.0 | 40 | 1.8352 | 1.8352 | 1.1380 | -0.7219 | 0.4286 |
| No log | 11.0 | 44 | 1.6168 | 1.6168 | 1.1210 | -0.5170 | 0.1429 |
| No log | 12.0 | 48 | 1.5023 | 1.5023 | 1.0944 | -0.4096 | 0.1429 |
| No log | 13.0 | 52 | 1.4374 | 1.4374 | 1.0865 | -0.3486 | 0.1429 |
| No log | 14.0 | 56 | 1.3763 | 1.3763 | 1.0785 | -0.2913 | 0.1429 |
| No log | 15.0 | 60 | 1.3164 | 1.3164 | 1.0703 | -0.2352 | 0.1429 |
| No log | 16.0 | 64 | 1.2879 | 1.2879 | 1.0727 | -0.2084 | 0.1429 |
| No log | 17.0 | 68 | 1.2538 | 1.2538 | 1.0665 | -0.1764 | 0.0 |
| No log | 18.0 | 72 | 1.2234 | 1.2234 | 1.0575 | -0.1479 | 0.0 |
| No log | 19.0 | 76 | 1.2146 | 1.2146 | 1.0594 | -0.1396 | 0.0 |
| No log | 20.0 | 80 | 1.2174 | 1.2174 | 1.0659 | -0.1422 | 0.0 |
| No log | 21.0 | 84 | 1.1976 | 1.1976 | 1.0614 | -0.1237 | 0.0 |
| No log | 22.0 | 88 | 1.1767 | 1.1767 | 1.0557 | -0.1041 | 0.0 |
| No log | 23.0 | 92 | 1.1603 | 1.1603 | 1.0510 | -0.0887 | 0.0 |
| No log | 24.0 | 96 | 1.1488 | 1.1488 | 1.0479 | -0.0779 | 0.0 |
| No log | 25.0 | 100 | 1.1380 | 1.1380 | 1.0444 | -0.0677 | 0.0 |
| No log | 26.0 | 104 | 1.1299 | 1.1299 | 1.0415 | -0.0602 | 0.0 |
| No log | 27.0 | 108 | 1.1245 | 1.1245 | 1.0395 | -0.0551 | 0.0 |
| No log | 28.0 | 112 | 1.1206 | 1.1206 | 1.0380 | -0.0514 | 0.0 |
| No log | 29.0 | 116 | 1.1185 | 1.1185 | 1.0371 | -0.0494 | 0.0 |
| No log | 30.0 | 120 | 1.1175 | 1.1175 | 1.0367 | -0.0485 | 0.0 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2