metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: mistral-instruct-resumebot-v2
results: []
mistral-instruct-resumebot-v2
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8843
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.748 | 0.8 | 2 | 2.9454 |
| 2.2982 | 2.0 | 5 | 2.5691 |
| 3.0389 | 2.8 | 7 | 2.3823 |
| 1.8758 | 4.0 | 10 | 2.1773 |
| 2.5643 | 4.8 | 12 | 2.0769 |
| 1.6191 | 6.0 | 15 | 1.9662 |
| 2.2941 | 6.8 | 17 | 1.9178 |
| 1.496 | 8.0 | 20 | 1.8843 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1