distilrubert-tiny-2ndfinetune-epru
This model is a fine-tuned version of mmillet/distilrubert-tiny-cased-conversational-v1_single_finetuned_on_cedr_augmented on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2085
- Accuracy: 0.9333
- F1: 0.9319
- Precision: 0.9336
- Recall: 0.9333
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.4825 | 1.0 | 13 | 0.2988 | 0.8848 | 0.8827 | 0.9056 | 0.8848 |
0.2652 | 2.0 | 26 | 0.2435 | 0.9212 | 0.9216 | 0.9282 | 0.9212 |
0.168 | 3.0 | 39 | 0.2120 | 0.9515 | 0.9501 | 0.9524 | 0.9515 |
0.1593 | 4.0 | 52 | 0.1962 | 0.9333 | 0.9330 | 0.9366 | 0.9333 |
0.1294 | 5.0 | 65 | 0.1855 | 0.9333 | 0.9334 | 0.9355 | 0.9333 |
0.1065 | 6.0 | 78 | 0.1780 | 0.9394 | 0.9393 | 0.9399 | 0.9394 |
0.0908 | 7.0 | 91 | 0.1967 | 0.9394 | 0.9388 | 0.9388 | 0.9394 |
0.0432 | 8.0 | 104 | 0.2085 | 0.9333 | 0.9319 | 0.9336 | 0.9333 |
Framework versions
- Transformers 4.19.3
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 9
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.