starcoderbase-finetuned-thestack
This model is a fine-tuned version of bigcode/starcoderbase-3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9183
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8487 | 1.0 | 83729 | 0.9170 |
| 0.8132 | 2.0 | 167458 | 0.9169 |
| 0.788 | 3.0 | 251187 | 0.9183 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.1
- Pytorch 2.1.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ArneKreuz/starcoderbase-finetuned-thestack
Base model
bigcode/starcoderbase-3b
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase-3b") model = PeftModel.from_pretrained(base_model, "ArneKreuz/starcoderbase-finetuned-thestack")