metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: metacognitive-cls
results: []
metacognitive-cls
This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1544
- Accuracy: 0.9477
- F1: 0.8277
- Precision: 0.8781
- Recall: 0.7827
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: 9.946303722432942e-06
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.692 | 1.0 | 61 | 0.6603 | 0.6342 | 0.2154 | 0.1642 | 0.3131 |
| 0.5269 | 2.0 | 122 | 0.3794 | 0.8719 | 0.5059 | 0.6632 | 0.4089 |
| 0.3652 | 3.0 | 183 | 0.3409 | 0.8770 | 0.4737 | 0.7552 | 0.3450 |
| 0.3282 | 4.0 | 244 | 0.3081 | 0.8940 | 0.5586 | 0.8397 | 0.4185 |
| 0.2936 | 5.0 | 305 | 0.2756 | 0.9022 | 0.5892 | 0.9013 | 0.4377 |
| 0.2529 | 6.0 | 366 | 0.2550 | 0.9129 | 0.6805 | 0.8265 | 0.5783 |
| 0.2141 | 7.0 | 427 | 0.2388 | 0.9221 | 0.7361 | 0.8061 | 0.6773 |
| 0.1802 | 8.0 | 488 | 0.2059 | 0.9278 | 0.7413 | 0.8707 | 0.6454 |
| 0.1494 | 9.0 | 549 | 0.2064 | 0.9221 | 0.7532 | 0.7657 | 0.7412 |
| 0.1179 | 10.0 | 610 | 0.1786 | 0.9401 | 0.8098 | 0.8245 | 0.7955 |
| 0.0941 | 11.0 | 671 | 0.1589 | 0.9457 | 0.8227 | 0.8632 | 0.7859 |
| 0.0816 | 12.0 | 732 | 0.1544 | 0.9477 | 0.8277 | 0.8781 | 0.7827 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1