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-3.3.25-Mistral-7b-Multilanguage-3.2.0
results: []
ZeroShot-3.3.25-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: 0.0503
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 |
|---|---|---|---|
| 0.1409 | 0.06 | 100 | 0.0993 |
| 0.0916 | 0.12 | 200 | 0.0877 |
| 0.0965 | 0.19 | 300 | 0.0970 |
| 0.0933 | 0.25 | 400 | 0.0898 |
| 0.0776 | 0.31 | 500 | 0.0749 |
| 0.0793 | 0.37 | 600 | 0.0850 |
| 0.0768 | 0.43 | 700 | 0.0701 |
| 0.0597 | 0.5 | 800 | 0.0767 |
| 0.0648 | 0.56 | 900 | 0.0766 |
| 0.0635 | 0.62 | 1000 | 0.0649 |
| 0.0536 | 0.68 | 1100 | 0.0641 |
| 0.0511 | 0.74 | 1200 | 0.0559 |
| 0.0638 | 0.81 | 1300 | 0.0507 |
| 0.0462 | 0.87 | 1400 | 0.0512 |
| 0.0494 | 0.93 | 1500 | 0.0507 |
| 0.0457 | 0.99 | 1600 | 0.0503 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2