metadata
base_model: mistralai/Mistral-7B-Instruct-v0.1
datasets:
- generator
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: mistral_instruct_generation_dolly_hhrlhf
results: []
mistral_instruct_generation_dolly_hhrlhf
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: 1.3456
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_ratio: 0.03
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5496 | 0.1626 | 20 | 1.4047 |
| 1.4614 | 0.3252 | 40 | 1.3688 |
| 1.4387 | 0.4878 | 60 | 1.3582 |
| 1.4483 | 0.6504 | 80 | 1.3496 |
| 1.4456 | 0.8130 | 100 | 1.3456 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1