metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: results
results: []
pipeline_tag: text-generation
results
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1935
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: 5
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6252 | 0.03 | 20 | 0.5953 |
| 0.417 | 0.07 | 40 | 0.5440 |
| 0.857 | 0.1 | 60 | 0.3897 |
| 0.6156 | 0.14 | 80 | 0.3202 |
| 0.5295 | 0.17 | 100 | 0.4571 |
| 0.4544 | 0.21 | 120 | 0.3307 |
| 0.3611 | 0.24 | 140 | 0.3324 |
| 0.3134 | 0.28 | 160 | 0.4065 |
| 0.3359 | 0.31 | 180 | 0.4316 |
| 0.3603 | 0.35 | 200 | 0.4051 |
| 0.4473 | 0.38 | 220 | 0.1733 |
| 0.4792 | 0.42 | 240 | 0.2714 |
| 0.2066 | 0.45 | 260 | 0.2992 |
| 0.2047 | 0.49 | 280 | 0.1973 |
| 0.1326 | 0.52 | 300 | 0.1935 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0