metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- generator
model-index:
- name: mistral_instruct_generation
results: []
mistral_instruct_generation
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.7257
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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0986 | 0.1709 | 20 | 1.8805 |
| 2.0093 | 0.3419 | 40 | 1.7881 |
| 2.0904 | 0.5128 | 60 | 1.7578 |
| 1.8353 | 0.6838 | 80 | 1.7418 |
| 1.7356 | 0.8547 | 100 | 1.7257 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1