metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: billm-mistral-7b-conll03-ner
results: []
billm-mistral-7b-conll03-ner
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2046
- Precision: 0.9273
- Recall: 0.9393
- F1: 0.9333
- Accuracy: 0.9864
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: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0499 | 1.0 | 1756 | 0.1085 | 0.9196 | 0.9287 | 0.9241 | 0.9845 |
| 0.0233 | 2.0 | 3512 | 0.0997 | 0.9249 | 0.9226 | 0.9237 | 0.9845 |
| 0.0097 | 3.0 | 5268 | 0.1343 | 0.9292 | 0.9386 | 0.9339 | 0.9870 |
| 0.0036 | 4.0 | 7024 | 0.1651 | 0.9245 | 0.9386 | 0.9315 | 0.9864 |
| 0.0012 | 5.0 | 8780 | 0.1839 | 0.9257 | 0.9373 | 0.9315 | 0.9863 |
| 0.0005 | 6.0 | 10536 | 0.2027 | 0.9258 | 0.9386 | 0.9321 | 0.9864 |
| 0.0002 | 7.0 | 12292 | 0.2022 | 0.9276 | 0.9384 | 0.9330 | 0.9864 |
| 0.0002 | 8.0 | 14048 | 0.2040 | 0.9274 | 0.9388 | 0.9331 | 0.9864 |
| 0.0001 | 9.0 | 15804 | 0.2048 | 0.9270 | 0.9393 | 0.9331 | 0.9864 |
| 0.0001 | 10.0 | 17560 | 0.2046 | 0.9273 | 0.9393 | 0.9333 | 0.9864 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.0.1
- Datasets 2.16.0
- Tokenizers 0.15.0