starchat2-15b-sft-v0.1
HuggingFaceH4's 15.9B code chat model built on StarCoder2 via supervised fine-tuning on coding, math, and instruction datasets.
Base model
bigcode/starcoder2-15b
Model Card
This model is a fine-tuned version of bigcode/starcoder2-15b on the HuggingFaceH4/airoboros-3.2, the HuggingFaceH4/Code-Feedback, the HuggingFaceH4/orca-math-word-problems-200k, the HuggingFaceH4/SystemChat and the HuggingFaceH4/capybara datasets. It achieves the following results on the evaluation set:
- Loss: 0.6614
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6422 | 1.0 | 910 | 0.6910 |
| 0.5701 | 2.0 | 1820 | 0.6639 |
| 0.5227 | 3.0 | 2730 | 0.6614 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
Author
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Author
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.