Orca_End
This model is a fine-tuned version of /home/ray/default/save/SFT_merge on the WordProblems_SFT_LLama_End dataset.
It achieves the following results on the evaluation set:
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: 2
- 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: 1000
- num_epochs: 2.0
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
| 0.2267 |
0.2341 |
500 |
0.2229 |
| 0.177 |
0.4682 |
1000 |
0.1735 |
| 0.1592 |
0.7022 |
1500 |
0.1591 |
| 0.1572 |
0.9363 |
2000 |
0.1515 |
| 0.142 |
1.1704 |
2500 |
0.1472 |
| 0.1376 |
1.4045 |
3000 |
0.1441 |
| 0.1569 |
1.6386 |
3500 |
0.1425 |
| 0.1413 |
1.8727 |
4000 |
0.1417 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1
