metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: meta-llama/Llama-2-13b-hf
model-index:
- name: train_2024-01-03-02-43-22
results: []
train_2024-01-03-02-43-22
This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on the anli_train_r1_contradiction dataset. It achieves the following results on the evaluation set:
- Loss: 1.0611
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0228 | 0.44 | 100 | 1.0888 |
| 1.0068 | 0.88 | 200 | 1.0738 |
| 1.0218 | 1.33 | 300 | 1.0680 |
| 1.084 | 1.77 | 400 | 1.0611 |
| 0.897 | 2.21 | 500 | 1.0757 |
| 0.9597 | 2.65 | 600 | 1.0745 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0