metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: uniBERT.distilBERT.1
results: []
uniBERT.distilBERT.1
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: 1.5970
- Accuracy: (0.48257372654155495,)
- F1: (0.48821617755360286,)
- Precision: (0.5906810375519806,)
- Recall: 0.4826
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 3.191 | 1.0 | 163 | 2.8674 | (0.13136729222520108,) | (0.10551643479608444,) | (0.13934178819155285,) | 0.1314 |
| 2.4168 | 2.0 | 326 | 2.2479 | (0.23771224307417338,) | (0.2196759312115438,) | (0.46668150798486385,) | 0.2377 |
| 1.8497 | 3.0 | 489 | 1.9548 | (0.30473637176050045,) | (0.30606381370679575,) | (0.5287854015073502,) | 0.3047 |
| 1.2962 | 4.0 | 652 | 1.7795 | (0.36371760500446826,) | (0.3751096263138952,) | (0.5125374899925749,) | 0.3637 |
| 1.176 | 5.0 | 815 | 1.7043 | (0.4066130473637176,) | (0.41869044107007675,) | (0.5244984950622734,) | 0.4066 |
| 0.8751 | 6.0 | 978 | 1.6665 | (0.4316353887399464,) | (0.44145109290311435,) | (0.532683425541351,) | 0.4316 |
| 0.7541 | 7.0 | 1141 | 1.6273 | (0.4450402144772118,) | (0.4544413917407461,) | (0.5812233728930422,) | 0.4450 |
| 0.6257 | 8.0 | 1304 | 1.6054 | (0.46291331546023234,) | (0.46971058022945406,) | (0.5769805019581083,) | 0.4629 |
| 0.5855 | 9.0 | 1467 | 1.5948 | (0.47542448614834676,) | (0.4826847668965276,) | (0.5865283417376732,) | 0.4754 |
| 0.5672 | 10.0 | 1630 | 1.5970 | (0.48257372654155495,) | (0.48821617755360286,) | (0.5906810375519806,) | 0.4826 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2