metadata
base_model: mistralai/Mistral-7B-Instruct-v0.1
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: mistral_fiction_generation2
results: []
mistral_fiction_generation2
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5197
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
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7344 | 0.0015 | 20 | 2.5952 |
| 2.6785 | 0.0030 | 40 | 2.5684 |
| 2.5757 | 0.0045 | 60 | 2.5411 |
| 2.6747 | 0.0060 | 80 | 2.5273 |
| 2.4986 | 0.0075 | 100 | 2.5197 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1