metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: mistral_instruct_generation
results: []
mistral_instruct_generation
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.1519
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 |
|---|---|---|---|
| 1.1307 | 1.11 | 20 | 1.0842 |
| 0.6826 | 2.22 | 40 | 0.6897 |
| 0.4163 | 3.33 | 60 | 0.3940 |
| 0.2125 | 4.44 | 80 | 0.2545 |
| 0.1186 | 5.56 | 100 | 0.1905 |
| 0.085 | 6.67 | 120 | 0.1641 |
| 0.0693 | 7.78 | 140 | 0.1562 |
| 0.0604 | 8.89 | 160 | 0.1516 |
| 0.0516 | 10.0 | 180 | 0.1436 |
| 0.044 | 11.11 | 200 | 0.1519 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1