metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
datasets:
- ontonotes5
model-index:
- name: deberta-v3-base_on5
results: []
deberta-v3-base_on5
This model is a fine-tuned version of microsoft/deberta-v3-base on the ontonotes5 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0776
- F1-type-match: 0.9325
- F1-partial: 0.9488
- F1-strict: 0.9046
- F1-exact: 0.9299
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-type-match | F1-partial | F1-strict | F1-exact |
|---|---|---|---|---|---|---|---|
| 0.0427 | 1.0 | 936 | 0.0674 | 0.9291 | 0.9452 | 0.8986 | 0.9246 |
| 0.0235 | 2.0 | 1873 | 0.0722 | 0.9281 | 0.9464 | 0.9002 | 0.9275 |
| 0.0148 | 3.0 | 2808 | 0.0776 | 0.9325 | 0.9488 | 0.9046 | 0.9299 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0