metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/zephyr-7B-beta-GPTQ
model-index:
- name: outputs_gptq_training
results: []
outputs_gptq_training
This model is a fine-tuned version of TheBloke/zephyr-7B-beta-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2808
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3461 | 0.01 | 100 | 0.3273 |
| 0.2884 | 0.01 | 200 | 0.2983 |
| 0.2665 | 0.02 | 300 | 0.2891 |
| 0.2841 | 0.03 | 400 | 0.2835 |
| 0.2649 | 0.03 | 500 | 0.2808 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.0.dev0
- Pytorch 2.1.0.dev20230621+cu117
- Datasets 2.17.0
- Tokenizers 0.15.0