metadata
license: other
base_model: MathSymbol/BasicSFT_1.8_Pretrain_Lightning
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: WordProblem
results: []
WordProblem
This model is a fine-tuned version of MathSymbol/BasicSFT_1.8_Pretrain_Lightning on the WordProblems_SFT dataset. It achieves the following results on the evaluation set:
- Loss: 0.1677
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: 4
- 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: 500
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1923 | 0.1645 | 1500 | 0.1849 |
| 0.176 | 0.3289 | 3000 | 0.1761 |
| 0.1736 | 0.4934 | 4500 | 0.1709 |
| 0.1688 | 0.6579 | 6000 | 0.1682 |
| 0.1689 | 0.8223 | 7500 | 0.1677 |
| 0.168 | 0.9868 | 9000 | 0.1677 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1