metadata
base_model: mistralai/Mistral-7B-v0.1
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: ncis
results: []
ncis
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1321
- Accuracy: 0.9596
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5872 | 1.0 | 37 | 0.3532 | 0.8535 |
| 0.3902 | 2.0 | 74 | 0.2625 | 0.8737 |
| 0.169 | 3.0 | 111 | 0.1820 | 0.9495 |
| 0.1978 | 4.0 | 148 | 0.1502 | 0.9596 |
| 0.1401 | 5.0 | 185 | 0.1321 | 0.9596 |
| 0.0175 | 6.0 | 222 | 0.2037 | 0.9394 |
| 0.0101 | 7.0 | 259 | 0.1677 | 0.9495 |
| 0.0001 | 8.0 | 296 | 0.1633 | 0.9545 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1