# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("cppbear/codeparrot-ds")
model = AutoModelForCausalLM.from_pretrained("cppbear/codeparrot-ds", device_map="auto")Quick Links
codeparrot-ds
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0585
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5498 | 0.0766 | 5000 | 1.7429 |
| 1.6671 | 0.1533 | 10000 | 1.5218 |
| 1.519 | 0.2299 | 15000 | 1.4193 |
| 1.4405 | 0.3065 | 20000 | 1.3529 |
| 1.3811 | 0.3832 | 25000 | 1.3025 |
| 1.3302 | 0.4598 | 30000 | 1.2536 |
| 1.2848 | 0.5365 | 35000 | 1.2101 |
| 1.2387 | 0.6131 | 40000 | 1.1680 |
| 1.1982 | 0.6897 | 45000 | 1.1297 |
| 1.1605 | 0.7664 | 50000 | 1.0966 |
| 1.1337 | 0.8430 | 55000 | 1.0736 |
| 1.1124 | 0.9196 | 60000 | 1.0614 |
| 1.1051 | 0.9963 | 65000 | 1.0585 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.8.0.dev20250529+rocm6.4
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 26
Model tree for cppbear/codeparrot-ds
Base model
openai-community/gpt2
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cppbear/codeparrot-ds")