metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-AWQ
model-index:
- name: Mistral-7B-Instruct-v0.2-AWQ-FaVe-rank8-2epochs
results: []
Mistral-7B-Instruct-v0.2-AWQ-FaVe-rank8-2epochs
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-AWQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4099
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: 0.0005
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.2685 | 10 | 1.6147 |
| 1.9334 | 0.5369 | 20 | 0.7459 |
| 1.9334 | 0.8054 | 30 | 0.5961 |
| 0.6653 | 1.0738 | 40 | 0.5019 |
| 0.6653 | 1.3423 | 50 | 0.4420 |
| 0.4616 | 1.6107 | 60 | 0.4234 |
| 0.4616 | 1.8792 | 70 | 0.4099 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1