metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: microsoft/Orca-2-7b
model-index:
- name: lora
results: []
lora
This model is a fine-tuned version of microsoft/Orca-2-7b on the Pretrain_Basic dataset. It achieves the following results on the evaluation set:
- Loss: 0.4452
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 2
- 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
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5009 | 0.1586 | 500 | 0.4964 |
| 0.4641 | 0.3172 | 1000 | 0.4591 |
| 0.4514 | 0.4758 | 1500 | 0.4516 |
| 0.4522 | 0.6344 | 2000 | 0.4482 |
| 0.4436 | 0.7930 | 2500 | 0.4459 |
| 0.4463 | 0.9516 | 3000 | 0.4452 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.0.1+cu118
- Datasets 2.17.1
- Tokenizers 0.19.1