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_456_1760637836
results: []
train_math_qa_456_1760637836
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: 0.7729
- Num Input Tokens Seen: 77891968
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 456
- 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 |
|---|---|---|---|---|
| 0.8144 | 1.0 | 6714 | 0.8044 | 3900904 |
| 0.8048 | 2.0 | 13428 | 0.8056 | 7795688 |
| 0.7852 | 3.0 | 20142 | 0.7398 | 11690736 |
| 0.6744 | 4.0 | 26856 | 0.6758 | 15583992 |
| 0.6056 | 5.0 | 33570 | 0.6689 | 19477680 |
| 0.6001 | 6.0 | 40284 | 0.6656 | 23372072 |
| 0.571 | 7.0 | 46998 | 0.6610 | 27267240 |
| 0.5573 | 8.0 | 53712 | 0.6567 | 31161216 |
| 0.5417 | 9.0 | 60426 | 0.6567 | 35058040 |
| 0.5279 | 10.0 | 67140 | 0.6782 | 38955336 |
| 0.491 | 11.0 | 73854 | 0.6672 | 42849552 |
| 0.4705 | 12.0 | 80568 | 0.6986 | 46744544 |
| 0.4584 | 13.0 | 87282 | 0.7088 | 50638504 |
| 0.2365 | 14.0 | 93996 | 0.7527 | 54532704 |
| 0.5157 | 15.0 | 100710 | 0.7999 | 58424776 |
| 0.2978 | 16.0 | 107424 | 0.8175 | 62319120 |
| 0.4732 | 17.0 | 114138 | 0.9005 | 66209648 |
| 0.2986 | 18.0 | 120852 | 0.9290 | 70104328 |
| 0.38 | 19.0 | 127566 | 0.9597 | 73997656 |
| 0.1678 | 20.0 | 134280 | 0.9709 | 77891968 |
Framework versions
- PEFT 0.17.1
- Transformers 4.51.3
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4