metadata
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: sqlm
results: []
sqlm
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3241
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5521 | 0.03 | 20 | 0.4444 |
| 0.3942 | 0.05 | 40 | 0.3773 |
| 0.3777 | 0.08 | 60 | 0.3571 |
| 0.3452 | 0.11 | 80 | 0.3451 |
| 0.3219 | 0.13 | 100 | 0.3431 |
| 0.3339 | 0.16 | 120 | 0.3366 |
| 0.3147 | 0.19 | 140 | 0.3334 |
| 0.307 | 0.21 | 160 | 0.3341 |
| 0.3283 | 0.24 | 180 | 0.3259 |
| 0.3174 | 0.27 | 200 | 0.3241 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2