ZeroShot-3.3.4-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: 0.0438
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 |
---|---|---|---|
7.6354 | 0.03 | 50 | 0.1640 |
0.1141 | 0.06 | 100 | 0.1148 |
0.1174 | 0.09 | 150 | 0.1069 |
0.1097 | 0.12 | 200 | 0.0912 |
0.0964 | 0.16 | 250 | 0.0870 |
0.0852 | 0.19 | 300 | 0.0978 |
0.0972 | 0.22 | 350 | 0.0842 |
0.0839 | 0.25 | 400 | 0.0822 |
0.0914 | 0.28 | 450 | 0.0775 |
0.0811 | 0.31 | 500 | 0.0749 |
0.0972 | 0.34 | 550 | 0.0795 |
0.0856 | 0.37 | 600 | 0.0756 |
0.0758 | 0.4 | 650 | 0.0727 |
0.066 | 0.43 | 700 | 0.0778 |
0.068 | 0.47 | 750 | 0.0644 |
0.063 | 0.5 | 800 | 0.0686 |
0.0667 | 0.53 | 850 | 0.0665 |
0.0653 | 0.56 | 900 | 0.0793 |
0.0567 | 0.59 | 950 | 0.0644 |
0.0648 | 0.62 | 1000 | 0.0568 |
0.0604 | 0.65 | 1050 | 0.0569 |
0.0549 | 0.68 | 1100 | 0.0534 |
0.0525 | 0.71 | 1150 | 0.0532 |
0.0476 | 0.74 | 1200 | 0.0607 |
0.0582 | 0.78 | 1250 | 0.0529 |
0.0438 | 0.81 | 1300 | 0.0483 |
0.0555 | 0.84 | 1350 | 0.0465 |
0.0451 | 0.87 | 1400 | 0.0455 |
0.0582 | 0.9 | 1450 | 0.0441 |
0.0478 | 0.93 | 1500 | 0.0440 |
0.0486 | 0.96 | 1550 | 0.0438 |
0.0444 | 0.99 | 1600 | 0.0438 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for Weni/ZeroShot-3.3.4-Mistral-7b-Multilanguage-3.2.0
Base model
mistralai/Mistral-7B-Instruct-v0.2
Adapter
this model