metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/zephyr-7B-beta-GPTQ
model-index:
- name: movies_gptq_recommend_v0
results: []
movies_gptq_recommend_v0
This model is a fine-tuned version of TheBloke/zephyr-7B-beta-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2649
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: 1
- 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4003 | 0.0 | 100 | 0.3292 |
| 0.3077 | 0.01 | 200 | 0.3024 |
| 0.2775 | 0.01 | 300 | 0.2978 |
| 0.2873 | 0.01 | 400 | 0.2866 |
| 0.2782 | 0.02 | 500 | 0.2805 |
| 0.2859 | 0.02 | 600 | 0.2740 |
| 0.2573 | 0.02 | 700 | 0.2709 |
| 0.2753 | 0.03 | 800 | 0.2679 |
| 0.265 | 0.03 | 900 | 0.2660 |
| 0.263 | 0.03 | 1000 | 0.2649 |
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