metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: /data1/model/llama2/meta-llama/Llama2-13b
model-index:
- name: unit_conversion_no_sys
results: []
unit_conversion_no_sys
This model is a fine-tuned version of /data1/model/llama2/meta-llama/Llama2-13b on the unit_conversion_no_sys dataset. It achieves the following results on the evaluation set:
- Loss: 0.3370
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5422 | 0.39 | 200 | 0.4792 |
| 0.319 | 0.79 | 400 | 0.4168 |
| 0.3583 | 1.18 | 600 | 0.3873 |
| 0.3048 | 1.57 | 800 | 0.3692 |
| 0.4185 | 1.96 | 1000 | 0.3550 |
| 0.3737 | 2.36 | 1200 | 0.3487 |
| 0.2418 | 2.75 | 1400 | 0.3422 |
| 0.2528 | 3.14 | 1600 | 0.3390 |
| 0.3192 | 3.54 | 1800 | 0.3393 |
| 0.2834 | 3.93 | 2000 | 0.3370 |
| 0.3612 | 4.32 | 2200 | 0.3375 |
| 0.2732 | 4.72 | 2400 | 0.3369 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2