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-3.3.16-Mistral-7b-Multilanguage-3.2.0
results: []
ZeroShot-3.3.16-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: 0.0500
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 |
|---|---|---|---|
| 0.1338 | 0.06 | 100 | 0.1081 |
| 0.1163 | 0.12 | 200 | 0.1049 |
| 0.1064 | 0.19 | 300 | 0.1000 |
| 0.0831 | 0.25 | 400 | 0.0893 |
| 0.0848 | 0.31 | 500 | 0.0807 |
| 0.0765 | 0.37 | 600 | 0.0747 |
| 0.0797 | 0.43 | 700 | 0.0738 |
| 0.0575 | 0.5 | 800 | 0.0724 |
| 0.064 | 0.56 | 900 | 0.0668 |
| 0.0518 | 0.62 | 1000 | 0.0656 |
| 0.061 | 0.68 | 1100 | 0.0585 |
| 0.0505 | 0.74 | 1200 | 0.0556 |
| 0.0633 | 0.81 | 1300 | 0.0522 |
| 0.0428 | 0.87 | 1400 | 0.0501 |
| 0.0393 | 0.93 | 1500 | 0.0500 |
| 0.0414 | 0.99 | 1600 | 0.0501 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2