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_classify10k
results: []
mistral_instruct_classify10k
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: 0.6021
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: 6
- 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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7548 | 1.0 | 49 | 0.7252 |
| 0.6684 | 2.0 | 98 | 0.6725 |
| 0.5849 | 3.0 | 147 | 0.6398 |
| 0.5236 | 4.0 | 196 | 0.6159 |
| 0.4733 | 5.0 | 245 | 0.6021 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2