metadata
license: mit
base_model: NousResearch/Nous-Hermes-Llama2-13b
tags:
- generated_from_trainer
model-index:
- name: ZeroShot-2.2.1-Llama2-13b-Multilanguage-3.0.3
results: []
ZeroShot-2.2.1-Llama2-13b-Multilanguage-3.0.3
This model is a fine-tuned version of NousResearch/Nous-Hermes-Llama2-13b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7250
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: 0.0004
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8523 | 1.0 | 3386 | 0.8460 |
| 0.7686 | 2.0 | 6773 | 0.7882 |
| 0.6856 | 3.0 | 10159 | 0.7563 |
| 0.6011 | 4.0 | 13546 | 0.7390 |
| 0.5217 | 5.0 | 16932 | 0.7306 |
| 0.4411 | 6.0 | 20319 | 0.7250 |
| 0.3773 | 7.0 | 23705 | 0.7292 |
| 0.3103 | 8.0 | 27092 | 0.7369 |
| 0.273 | 9.0 | 30478 | 0.7521 |
| 0.2599 | 10.0 | 33860 | 0.7618 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3