metadata
tags:
- generated_from_trainer
model-index:
- name: few_shot_ner
results: []
few_shot_ner
This model is a fine-tuned version of qgyd2021/few_shot_ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6024
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 100.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.563 | 0.08 | 1000 | 0.6020 |
| 0.578 | 0.15 | 2000 | 0.6043 |
| 0.5821 | 0.23 | 3000 | 0.6059 |
| 0.5799 | 0.3 | 4000 | 0.6048 |
| 0.5851 | 0.38 | 5000 | 0.6033 |
| 0.5811 | 0.46 | 6000 | 0.6024 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.13.0+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3