# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("nhanv/cv_parser")
model = AutoModelForTokenClassification.from_pretrained("nhanv/cv_parser")Quick Links
cv-ner
This model is a fine-tuned version of microsoft/mdeberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0956
- Precision: 0.8906
- Recall: 0.9325
- F1: 0.9111
- Accuracy: 0.9851
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: 16
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 91 | 0.2049 | 0.6618 | 0.7362 | 0.6970 | 0.9534 |
| 0.5036 | 2.0 | 182 | 0.1156 | 0.7873 | 0.8630 | 0.8234 | 0.9722 |
| 0.1442 | 3.0 | 273 | 0.1078 | 0.8262 | 0.9039 | 0.8633 | 0.9771 |
| 0.0757 | 4.0 | 364 | 0.1179 | 0.8652 | 0.9059 | 0.8851 | 0.9780 |
| 0.0526 | 5.0 | 455 | 0.0907 | 0.888 | 0.9080 | 0.8979 | 0.9837 |
| 0.0342 | 6.0 | 546 | 0.0972 | 0.8926 | 0.9346 | 0.9131 | 0.9832 |
| 0.0245 | 7.0 | 637 | 0.1064 | 0.8937 | 0.9284 | 0.9107 | 0.9834 |
| 0.0188 | 8.0 | 728 | 0.0965 | 0.8980 | 0.9366 | 0.9169 | 0.9850 |
| 0.0159 | 9.0 | 819 | 0.0999 | 0.91 | 0.9305 | 0.9201 | 0.9846 |
| 0.0141 | 10.0 | 910 | 0.0956 | 0.8906 | 0.9325 | 0.9111 | 0.9851 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 17
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="nhanv/cv_parser")