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: 0.1725
- Precision: 0.9280
- Recall: 0.9400
- F1: 0.9340
- Accuracy: 0.9863
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: 8e-05
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0463 | 1.0 | 1756 | 0.0851 | 0.9234 | 0.9328 | 0.9281 | 0.9856 |
| 0.0213 | 2.0 | 3512 | 0.1022 | 0.9292 | 0.9282 | 0.9287 | 0.9849 |
| 0.0108 | 3.0 | 5268 | 0.1213 | 0.9228 | 0.9363 | 0.9295 | 0.9857 |
| 0.0056 | 4.0 | 7024 | 0.1457 | 0.9261 | 0.9408 | 0.9334 | 0.9864 |
| 0.0022 | 5.0 | 8780 | 0.1604 | 0.9261 | 0.9388 | 0.9324 | 0.9862 |
| 0.0011 | 6.0 | 10536 | 0.1701 | 0.9270 | 0.9402 | 0.9336 | 0.9863 |
| 0.0008 | 7.0 | 12292 | 0.1718 | 0.9289 | 0.9411 | 0.9350 | 0.9864 |
| 0.0005 | 8.0 | 14048 | 0.1719 | 0.9285 | 0.9402 | 0.9343 | 0.9864 |
| 0.0003 | 9.0 | 15804 | 0.1727 | 0.9280 | 0.9400 | 0.9340 | 0.9864 |
| 0.0003 | 10.0 | 17560 | 0.1725 | 0.9280 | 0.9400 | 0.9340 | 0.9863 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.0.1
- Datasets 2.16.0
- Tokenizers 0.15.0