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: 2.1470
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: 2e-07
- train_batch_size: 1
- 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: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1531 | 0.2105 | 20 | 2.1534 |
| 2.1759 | 0.4211 | 40 | 2.1520 |
| 2.1599 | 0.6316 | 60 | 2.1506 |
| 2.1287 | 0.8421 | 80 | 2.1487 |
| 2.1205 | 1.0526 | 100 | 2.1470 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1