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: 0.1873
- Precision: 0.9299
- Recall: 0.9409
- F1: 0.9354
- Accuracy: 0.9871
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.0417 | 1.0 | 1756 | 0.0945 | 0.9322 | 0.9337 | 0.9330 | 0.9857 |
| 0.0193 | 2.0 | 3512 | 0.1109 | 0.9271 | 0.9368 | 0.9319 | 0.9862 |
| 0.0083 | 3.0 | 5268 | 0.1277 | 0.9273 | 0.9397 | 0.9335 | 0.9869 |
| 0.0035 | 4.0 | 7024 | 0.1552 | 0.9256 | 0.9404 | 0.9329 | 0.9868 |
| 0.0015 | 5.0 | 8780 | 0.1725 | 0.9283 | 0.9397 | 0.9340 | 0.9869 |
| 0.0006 | 6.0 | 10536 | 0.1843 | 0.9304 | 0.9404 | 0.9354 | 0.9870 |
| 0.0005 | 7.0 | 12292 | 0.1863 | 0.9304 | 0.9408 | 0.9355 | 0.9871 |
| 0.0004 | 8.0 | 14048 | 0.1874 | 0.9294 | 0.9406 | 0.9349 | 0.9871 |
| 0.0002 | 9.0 | 15804 | 0.1872 | 0.9299 | 0.9409 | 0.9354 | 0.9871 |
| 0.0002 | 10.0 | 17560 | 0.1873 | 0.9299 | 0.9409 | 0.9354 | 0.9871 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.0.1
- Datasets 2.16.0
- Tokenizers 0.15.0