metadata
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: recitation-segmenter-v2
results: []
recitation-segmenter-v2
This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9958
- F1: 0.9964
- Loss: 0.0132
- Precision: 0.9976
- Recall: 0.9951
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: 5e-05
- train_batch_size: 50
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0701 | 0.2507 | 275 | 0.9953 | 0.9959 | 0.0249 | 0.9947 | 0.9971 |
| 0.0234 | 0.5014 | 550 | 0.9953 | 0.9959 | 0.0185 | 0.9940 | 0.9977 |
| 0.0186 | 0.7521 | 825 | 0.9958 | 0.9964 | 0.0132 | 0.9976 | 0.9951 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.2.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.1