metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: buffettgpt-ft
results: []
buffettgpt-ft
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: 0.8966
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 |
|---|---|---|---|
| 1.2337 | 0.92 | 3 | 1.1163 |
| 1.0176 | 1.85 | 6 | 1.0010 |
| 0.9192 | 2.77 | 9 | 0.9417 |
| 0.6724 | 4.0 | 13 | 0.9083 |
| 0.8644 | 4.92 | 16 | 0.9032 |
| 0.8662 | 5.85 | 19 | 0.9031 |
| 0.8187 | 6.77 | 22 | 0.8942 |
| 0.6121 | 8.0 | 26 | 0.8920 |
| 0.8024 | 8.92 | 29 | 0.8963 |
| 0.5432 | 9.23 | 30 | 0.8966 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2