metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: mistral-sum-r16a16
results: []
mistral-sum-r16a16
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6871
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: 8
- 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: 20
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1929 | 0.0331 | 20 | 1.8011 |
| 1.6963 | 0.0663 | 40 | 1.7273 |
| 1.6459 | 0.0994 | 60 | 1.7028 |
| 1.6819 | 0.1326 | 80 | 1.6925 |
| 1.6351 | 0.1657 | 100 | 1.6871 |
Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.42.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1