metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: persuasive_adversarial_mistral_v2
results: []
persuasive_adversarial_mistral_v2
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3241
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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.809 | 0.9943 | 131 | 0.3680 |
0.3438 | 1.9962 | 263 | 0.3325 |
0.3176 | 2.9829 | 393 | 0.3241 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.1.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1