roberta_intent_ofis
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0013
- Accuracy: 1.0
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-06
- 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 | Accuracy |
---|---|---|---|---|
1.4951 | 1.0 | 127 | 1.5874 | 0.4853 |
0.9597 | 2.0 | 254 | 1.1933 | 0.6765 |
0.4618 | 3.0 | 381 | 0.6759 | 0.8088 |
0.1725 | 4.0 | 508 | 0.4578 | 0.8382 |
0.1115 | 5.0 | 635 | 0.4119 | 0.8529 |
0.0968 | 6.0 | 762 | 0.2263 | 0.9118 |
0.0392 | 7.0 | 889 | 0.2921 | 0.8824 |
0.0279 | 8.0 | 1016 | 0.1238 | 0.9706 |
0.0185 | 9.0 | 1143 | 0.1638 | 0.9559 |
0.0108 | 10.0 | 1270 | 0.1364 | 0.9559 |
0.0213 | 11.0 | 1397 | 0.0774 | 0.9706 |
0.2756 | 12.0 | 1524 | 0.0989 | 0.9706 |
0.0087 | 13.0 | 1651 | 0.0461 | 0.9853 |
0.0069 | 14.0 | 1778 | 0.0301 | 0.9853 |
0.0046 | 15.0 | 1905 | 0.0267 | 0.9853 |
0.0239 | 16.0 | 2032 | 0.0264 | 0.9853 |
0.0041 | 17.0 | 2159 | 0.0293 | 0.9853 |
0.0054 | 18.0 | 2286 | 0.0036 | 1.0 |
0.0277 | 19.0 | 2413 | 0.0035 | 1.0 |
0.2747 | 20.0 | 2540 | 0.0023 | 1.0 |
0.0028 | 21.0 | 2667 | 0.0025 | 1.0 |
0.0027 | 22.0 | 2794 | 0.0025 | 1.0 |
0.003 | 23.0 | 2921 | 0.0033 | 1.0 |
0.0024 | 24.0 | 3048 | 0.0017 | 1.0 |
0.0048 | 25.0 | 3175 | 0.0025 | 1.0 |
0.002 | 26.0 | 3302 | 0.0019 | 1.0 |
0.0019 | 27.0 | 3429 | 0.0017 | 1.0 |
0.0021 | 28.0 | 3556 | 0.0014 | 1.0 |
0.0023 | 29.0 | 3683 | 0.0014 | 1.0 |
0.002 | 30.0 | 3810 | 0.0013 | 1.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.