metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: watch-promo-ft
results: []
watch-promo-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: 1.3069
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 |
|---|---|---|---|
| 5.2643 | 0.86 | 3 | 4.1706 |
| 3.3604 | 2.0 | 7 | 3.2708 |
| 3.6248 | 2.86 | 10 | 2.7960 |
| 2.3198 | 4.0 | 14 | 2.3721 |
| 2.68 | 4.86 | 17 | 2.0909 |
| 1.7329 | 6.0 | 21 | 1.7454 |
| 1.9709 | 6.86 | 24 | 1.5187 |
| 1.2854 | 8.0 | 28 | 1.3384 |
| 1.3737 | 8.57 | 30 | 1.3069 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2