|
--- |
|
license: bigcode-openrail-m |
|
base_model: bigcode/starcoderbase-7b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: starcoderbase_4096_context_length |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# starcoderbase_4096_context_length |
|
|
|
This model is a fine-tuned version of [bigcode/starcoderbase-7b](https://huggingface.co/bigcode/starcoderbase-7b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8997 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 30 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4976 | 0.05 | 100 | 0.5844 | |
|
| 0.2996 | 0.1 | 200 | 0.5433 | |
|
| 0.1736 | 0.15 | 300 | 0.5837 | |
|
| 0.1341 | 0.2 | 400 | 0.6009 | |
|
| 0.1716 | 0.25 | 500 | 0.6422 | |
|
| 0.8849 | 0.3 | 600 | 0.7839 | |
|
| 0.0851 | 0.35 | 700 | 0.7452 | |
|
| 0.4099 | 0.4 | 800 | 0.7286 | |
|
| 0.0489 | 0.45 | 900 | 0.6492 | |
|
| 0.0506 | 0.5 | 1000 | 0.7042 | |
|
| 0.0377 | 0.55 | 1100 | 0.7663 | |
|
| 0.0343 | 0.6 | 1200 | 0.7914 | |
|
| 0.0226 | 0.65 | 1300 | 0.8043 | |
|
| 0.0251 | 0.7 | 1400 | 0.8287 | |
|
| 0.0212 | 0.75 | 1500 | 0.8671 | |
|
| 0.0205 | 0.8 | 1600 | 0.8662 | |
|
| 0.0195 | 0.85 | 1700 | 0.8908 | |
|
| 0.0178 | 0.9 | 1800 | 0.8834 | |
|
| 0.0185 | 0.95 | 1900 | 0.9005 | |
|
| 0.0159 | 1.0 | 2000 | 0.8997 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.3 |
|
- Pytorch 2.4.0a0+07cecf4168.nv24.05 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
