metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
metrics:
- accuracy
- precision
- recall
model-index:
- name: Mistral_final_Task2_2.0
results: []
Mistral_final_Task2_2.0
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: 0.5570
- Accuracy: 0.8943
- Precision: 0.9184
- Recall: 0.8661
- F1 score: 0.8915
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|---|---|---|
| 0.9274 | 0.5450 | 200 | 0.6669 | 0.8371 | 0.9072 | 0.7521 | 0.8224 |
| 0.5321 | 1.0899 | 400 | 1.0293 | 0.7986 | 0.9861 | 0.6068 | 0.7513 |
| 0.4279 | 1.6349 | 600 | 1.0278 | 0.7586 | 0.6904 | 0.9402 | 0.7961 |
| 0.3054 | 2.1798 | 800 | 0.4428 | 0.8714 | 0.8575 | 0.8917 | 0.8743 |
| 0.2297 | 2.7248 | 1000 | 0.5243 | 0.8743 | 0.9428 | 0.7977 | 0.8642 |
| 0.1798 | 3.2698 | 1200 | 0.4710 | 0.8971 | 0.9043 | 0.8889 | 0.8966 |
| 0.158 | 3.8147 | 1400 | 0.5673 | 0.8986 | 0.9545 | 0.8376 | 0.8923 |
| 0.0921 | 4.3597 | 1600 | 0.5847 | 0.8743 | 0.8380 | 0.9288 | 0.8811 |
| 0.063 | 4.9046 | 1800 | 0.5570 | 0.8943 | 0.9184 | 0.8661 | 0.8915 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1