metadata
base_model: meta-llama/Llama-2-13b-hf
tags:
- generated_from_trainer
model-index:
- name: Llama-2-13b-hf-ds_wiki_1024_full_r_64_alpha_16
results: []
Llama-2-13b-hf-ds_wiki_1024_full_r_64_alpha_16
This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1614
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2264 | 0.1 | 51 | 1.1930 |
| 1.2074 | 0.2 | 102 | 1.1818 |
| 1.1872 | 0.3 | 153 | 1.1759 |
| 1.2033 | 0.4 | 204 | 1.1718 |
| 1.1837 | 0.5 | 255 | 1.1691 |
| 1.2006 | 0.6 | 306 | 1.1667 |
| 1.1817 | 0.7 | 357 | 1.1648 |
| 1.2066 | 0.8 | 408 | 1.1630 |
| 1.1766 | 0.9 | 459 | 1.1614 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3