tcapelle/fluency-scorer

1---2library_name: transformers3license: apache-2.04base_model: answerdotai/ModernBERT-base5tags:6- generated_from_trainer7metrics:8- f19- accuracy10- precision11- recall12model-index:13- name: fluency-scorer14  results: []15---16 17<!-- This model card has been generated automatically according to the information the Trainer had access to. You18should probably proofread and complete it, then remove this comment. -->19 20# fluency-scorer21 22This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.23It achieves the following results on the evaluation set:24- Loss: 0.383025- F1: 0.818326- Accuracy: 0.821227- Precision: 0.817128- Recall: 0.821229 30## Model description31 32More information needed33 34## Intended uses & limitations35 36More information needed37 38## Training and evaluation data39 40More information needed41 42## Training procedure43 44### Training hyperparameters45 46The following hyperparameters were used during training:47- learning_rate: 3e-0548- train_batch_size: 849- eval_batch_size: 850- seed: 4251- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments52- lr_scheduler_type: cosine53- lr_scheduler_warmup_ratio: 0.154- num_epochs: 355 56### Training results57 58| Training Loss | Epoch | Step  | Validation Loss | F1     | Accuracy | Precision | Recall |59|:-------------:|:-----:|:-----:|:---------------:|:------:|:--------:|:---------:|:------:|60| No log        | 0     | 0     | 0.7214          | 0.5368 | 0.5168   | 0.6201    | 0.5168 |61| 0.5801        | 1.0   | 6158  | 0.4019          | 0.8069 | 0.8092   | 0.8056    | 0.8092 |62| 0.4354        | 2.0   | 12316 | 0.3835          | 0.8176 | 0.8212   | 0.8165    | 0.8212 |63| 0.4089        | 3.0   | 18474 | 0.3830          | 0.8183 | 0.8212   | 0.8171    | 0.8212 |64 65 66### Framework versions67 68- Transformers 4.48.169- Pytorch 2.4.1+cu12170- Datasets 3.0.171- Tokenizers 0.21.072