dv347/grammar-classifier

1---2library_name: transformers3license: mit4base_model: microsoft/deberta-v3-large5tags:6- generated_from_trainer7model-index:8- name: grammar-classifier9  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# grammar-classifier16 17This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.18It achieves the following results on the evaluation set:19- Loss: 4.096720- Exact Match: 0.021- Micro F1: 0.307522- Macro F1: 0.033423- Hamming Accuracy: 0.880624- Avg Pred Positives: 34.025- Avg Gold Positives: 13.573626 27## Model description28 29More information needed30 31## Intended uses & limitations32 33More information needed34 35## Training and evaluation data36 37More information needed38 39## Training procedure40 41### Training hyperparameters42 43The following hyperparameters were used during training:44- learning_rate: 2e-0545- train_batch_size: 3246- eval_batch_size: 6447- seed: 4248- gradient_accumulation_steps: 249- total_train_batch_size: 6450- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments51- lr_scheduler_type: cosine52- lr_scheduler_warmup_steps: 0.253- num_epochs: 1054 55### Training results56 57| Training Loss | Epoch | Step | Validation Loss | Exact Match | Micro F1 | Macro F1 | Hamming Accuracy | Avg Pred Positives | Avg Gold Positives |58|:-------------:|:-----:|:----:|:---------------:|:-----------:|:--------:|:--------:|:----------------:|:------------------:|:------------------:|59| 0.2930        | 0.5   | 164  | 0.5663          | 0.0         | 0.3139   | 0.0288   | 0.9041           | 25.0               | 13.5736            |60| 0.1928        | 1.0   | 328  | 0.2720          | 0.0         | 0.4392   | 0.0256   | 0.9460           | 13.0               | 13.5736            |61| 0.0751        | 1.5   | 492  | 0.0559          | 0.0         | 0.5244   | 0.0234   | 0.9628           | 8.0                | 13.5736            |62| 33.3599       | 2.0   | 656  | 13.5265         | 0.0         | 0.2931   | 0.0226   | 0.9114           | 21.0               | 13.5736            |63| 19.0859       | 2.5   | 820  | 10.5864         | 0.0         | 0.2214   | 0.0302   | 0.8376           | 44.0               | 13.5736            |64| 8.6145        | 3.0   | 984  | 4.0967          | 0.0         | 0.3075   | 0.0334   | 0.8806           | 34.0               | 13.5736            |65 66 67### Framework versions68 69- Transformers 5.2.070- Pytorch 2.10.0+cu12871- Datasets 4.5.072- Tokenizers 0.22.273