metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
datasets:
- generator
model-index:
- name: models
results: []
models
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: 0.4428
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7386 | 0.21 | 20 | 0.6957 |
| 0.6098 | 0.42 | 40 | 0.5837 |
| 0.4906 | 0.63 | 60 | 0.4980 |
| 0.4866 | 0.84 | 80 | 0.4428 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0
- Datasets 2.18.0
- Tokenizers 0.15.2