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: vitaminc_fact_verification_no_sys
results: []
vitaminc_fact_verification_no_sys
This model is a fine-tuned version of /data1/model/llama2/meta-llama/Llama2-13b on the vitaminc_fact_verification_no_sys dataset. It achieves the following results on the evaluation set:
- Loss: 0.1413
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- total_train_batch_size: 24
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4369 | 0.03 | 50 | 0.3792 |
| 0.2145 | 0.06 | 100 | 0.2272 |
| 0.2037 | 0.1 | 150 | 0.1837 |
| 0.1913 | 0.13 | 200 | 0.2707 |
| 0.1781 | 0.16 | 250 | 0.1783 |
| 0.2087 | 0.19 | 300 | 0.2067 |
| 0.2029 | 0.23 | 350 | 0.1516 |
| 0.1081 | 0.26 | 400 | 0.1555 |
| 0.1619 | 0.29 | 450 | 0.1446 |
| 0.111 | 0.32 | 500 | 0.1413 |
| 0.1546 | 0.36 | 550 | 0.1476 |
| 0.14 | 0.39 | 600 | 0.1437 |
| 0.1082 | 0.42 | 650 | 0.1483 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2