metadata
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mdeberta-v3-base-finetuned-climate_explicit-classification
results: []
mdeberta-v3-base-finetuned-climate_explicit-classification
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0862
- Accuracy: 0.9837
- Accuracy Balanced: 0.9841
- F1 Macro: 0.9820
- F1 Weighted: 0.9837
- F1 Positive: 0.9764
- Precision Positive: 0.9677
- Recall Positive: 0.9854
- Precision Weighted: 0.9839
- Recall Weighted: 0.9837
- Mcc: 0.9641
- Roc Auc: 0.9950
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Accuracy Balanced | F1 Macro | F1 Weighted | F1 Positive | Precision Positive | Recall Positive | Precision Weighted | Recall Weighted | Mcc | Roc Auc |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1297 | 1.0 | 1863 | 0.1076 | 0.9806 | 0.9791 | 0.9785 | 0.9806 | 0.9717 | 0.9691 | 0.9744 | 0.9806 | 0.9806 | 0.9569 | 0.9923 |
| 0.0787 | 2.0 | 3726 | 0.0936 | 0.9828 | 0.9841 | 0.9810 | 0.9828 | 0.9752 | 0.9626 | 0.9881 | 0.9831 | 0.9828 | 0.9622 | 0.9954 |
| 0.0664 | 3.0 | 5589 | 0.0675 | 0.9853 | 0.9851 | 0.9837 | 0.9853 | 0.9786 | 0.9729 | 0.9844 | 0.9854 | 0.9853 | 0.9674 | 0.9948 |
| 0.0493 | 4.0 | 7452 | 0.0862 | 0.9837 | 0.9841 | 0.9820 | 0.9837 | 0.9764 | 0.9677 | 0.9854 | 0.9839 | 0.9837 | 0.9641 | 0.9950 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2