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: 0.1704
- Precision: 0.9275
- Recall: 0.9391
- F1: 0.9333
- Accuracy: 0.9868
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 |
---|---|---|---|---|---|---|---|
0.0449 | 1.0 | 1756 | 0.1034 | 0.9239 | 0.9330 | 0.9284 | 0.9857 |
0.0225 | 2.0 | 3512 | 0.1098 | 0.9210 | 0.9301 | 0.9256 | 0.9853 |
0.0121 | 3.0 | 5268 | 0.1104 | 0.9276 | 0.9346 | 0.9311 | 0.9864 |
0.0057 | 4.0 | 7024 | 0.1408 | 0.9232 | 0.9370 | 0.9300 | 0.9863 |
0.0023 | 5.0 | 8780 | 0.1538 | 0.9245 | 0.9373 | 0.9309 | 0.9865 |
0.0011 | 6.0 | 10536 | 0.1660 | 0.9275 | 0.9393 | 0.9334 | 0.9868 |
0.0008 | 7.0 | 12292 | 0.1708 | 0.9283 | 0.9393 | 0.9338 | 0.9869 |
0.0006 | 8.0 | 14048 | 0.1710 | 0.9280 | 0.9395 | 0.9337 | 0.9869 |
0.0004 | 9.0 | 15804 | 0.1706 | 0.9276 | 0.9391 | 0.9333 | 0.9869 |
0.0003 | 10.0 | 17560 | 0.1704 | 0.9275 | 0.9391 | 0.9333 | 0.9868 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.0.1
- Datasets 2.16.0
- Tokenizers 0.15.0