metadata
license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:
- generated_from_trainer
model-index:
- name: fine-tuned-Qwen2-0.5B-Instruct-NER
results: []
fine-tuned-Qwen2-0.5B-Instruct-NER
This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2041
- Exact Match: 0.0
- F1 Score: 71.2227
- Levenshtein Distance: 92.0833
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: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 Score | Levenshtein Distance |
|---|---|---|---|---|---|---|
| 0.442 | 1.0 | 527 | 0.2332 | 0.0 | 77.1207 | 117.0 |
| 0.3097 | 2.0 | 1054 | 0.1979 | 0.0 | 79.2137 | 86.5 |
| 0.2939 | 3.0 | 1581 | 0.2504 | 0.0 | 77.6862 | 108.3333 |
| 0.2654 | 4.0 | 2108 | 0.1907 | 0.0 | 79.5981 | 83.25 |
| 0.2375 | 5.0 | 2635 | 0.2449 | 0.0 | 75.8942 | 114.8333 |
| 0.2182 | 6.0 | 3162 | 0.2060 | 0.0 | 75.2855 | 92.0 |
| 0.2229 | 7.0 | 3689 | 0.1997 | 0.0 | 74.5991 | 93.3333 |
| 0.1791 | 8.0 | 4216 | 0.1989 | 0.0 | 72.7126 | 90.25 |
| 0.1688 | 9.0 | 4743 | 0.2180 | 0.0 | 72.6617 | 97.8333 |
| 0.1829 | 10.0 | 5270 | 0.2041 | 0.0 | 71.2227 | 92.0833 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1