metadata
license: apache-2.0
datasets:
- generator
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: mistral_instruct_generation
results: []
language:
- en
tags:
- peft
- trl
- mistral
- sft
- generated_from_trainer
pipeline_tag: question-answering
library_name: transformers
mistral_instruct_generation
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: 1.3103
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_steps: 0.03
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5421 | 0.16 | 20 | 1.3708 |
| 1.4609 | 0.33 | 40 | 1.3335 |
| 1.4646 | 0.49 | 60 | 1.3222 |
| 1.4732 | 0.65 | 80 | 1.3158 |
| 1.4525 | 0.81 | 100 | 1.3103 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1