metadata
base_model: meta-llama/Llama-2-13b-hf
tags:
- generated_from_trainer
model-index:
- name: Llama-2-13b-hf-ds_eli5_1024_r_64_alpha_16
results: []
Llama-2-13b-hf-ds_eli5_1024_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: 2.1196
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 |
|---|---|---|---|
| 2.0837 | 0.1 | 33 | 2.1338 |
| 2.0369 | 0.2 | 66 | 2.1293 |
| 2.0893 | 0.31 | 99 | 2.1324 |
| 2.0821 | 0.41 | 132 | 2.1231 |
| 2.0298 | 0.51 | 165 | 2.1225 |
| 2.0817 | 0.61 | 198 | 2.1231 |
| 2.0617 | 0.72 | 231 | 2.1205 |
| 2.0323 | 0.82 | 264 | 2.1206 |
| 2.0552 | 0.92 | 297 | 2.1196 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3