metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: ZeroShot-3.3.12-Mistral-7b-Multilanguage-3.2.0
results: []
ZeroShot-3.3.12-Mistral-7b-Multilanguage-3.2.0
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4682
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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5918 | 0.13 | 100 | 0.5496 |
| 0.5301 | 0.27 | 200 | 0.5062 |
| 0.4998 | 0.4 | 300 | 0.4911 |
| 0.4977 | 0.53 | 400 | 0.4820 |
| 0.477 | 0.67 | 500 | 0.4747 |
| 0.4785 | 0.8 | 600 | 0.4698 |
| 0.4699 | 0.94 | 700 | 0.4682 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2