metadata
library_name: peft
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
- llama-factory
- transformers
pipeline_tag: text-generation
model-index:
- name: train_math_qa_123_1760637721
results: []
train_math_qa_123_1760637721
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the math_qa dataset. It achieves the following results on the evaluation set:
- Loss: 0.7989
- Num Input Tokens Seen: 77961608
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: 0.03
- train_batch_size: 4
- eval_batch_size: 4
- seed: 123
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 0.8045 | 1.0 | 6714 | 0.8024 | 3894688 |
| 0.8422 | 2.0 | 13428 | 0.8020 | 7789256 |
| 0.792 | 3.0 | 20142 | 0.8027 | 11683856 |
| 0.7935 | 4.0 | 26856 | 0.8017 | 15585872 |
| 0.8031 | 5.0 | 33570 | 0.8017 | 19482128 |
| 0.815 | 6.0 | 40284 | 0.8029 | 23376776 |
| 0.8242 | 7.0 | 46998 | 0.8019 | 27278720 |
| 0.7873 | 8.0 | 53712 | 0.8020 | 31180904 |
| 0.8132 | 9.0 | 60426 | 0.8010 | 35077032 |
| 0.8102 | 10.0 | 67140 | 0.8017 | 38976336 |
| 0.7992 | 11.0 | 73854 | 0.8003 | 42875264 |
| 0.7982 | 12.0 | 80568 | 0.8000 | 46772480 |
| 0.8272 | 13.0 | 87282 | 0.7996 | 50673016 |
| 0.8153 | 14.0 | 93996 | 0.7991 | 54573896 |
| 0.8029 | 15.0 | 100710 | 0.8003 | 58472760 |
| 0.7927 | 16.0 | 107424 | 0.7989 | 62371472 |
| 0.7752 | 17.0 | 114138 | 0.8002 | 66268336 |
| 0.81 | 18.0 | 120852 | 0.7994 | 70167432 |
| 0.8225 | 19.0 | 127566 | 0.7995 | 74065984 |
| 0.8063 | 20.0 | 134280 | 0.7992 | 77961608 |
Framework versions
- PEFT 0.17.1
- Transformers 4.51.3
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4