cppbear/codeparrot-ds

1---2library_name: transformers3license: mit4base_model: gpt25tags:6- generated_from_trainer7model-index:8- name: codeparrot-ds9  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# codeparrot-ds16 17This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.18It achieves the following results on the evaluation set:19- Loss: 1.058520 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 0.000539- train_batch_size: 3240- eval_batch_size: 3241- seed: 4242- gradient_accumulation_steps: 843- total_train_batch_size: 25644- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments45- lr_scheduler_type: cosine46- lr_scheduler_warmup_steps: 100047- num_epochs: 148- mixed_precision_training: Native AMP49 50### Training results51 52| Training Loss | Epoch  | Step  | Validation Loss |53|:-------------:|:------:|:-----:|:---------------:|54| 2.5498        | 0.0766 | 5000  | 1.7429          |55| 1.6671        | 0.1533 | 10000 | 1.5218          |56| 1.519         | 0.2299 | 15000 | 1.4193          |57| 1.4405        | 0.3065 | 20000 | 1.3529          |58| 1.3811        | 0.3832 | 25000 | 1.3025          |59| 1.3302        | 0.4598 | 30000 | 1.2536          |60| 1.2848        | 0.5365 | 35000 | 1.2101          |61| 1.2387        | 0.6131 | 40000 | 1.1680          |62| 1.1982        | 0.6897 | 45000 | 1.1297          |63| 1.1605        | 0.7664 | 50000 | 1.0966          |64| 1.1337        | 0.8430 | 55000 | 1.0736          |65| 1.1124        | 0.9196 | 60000 | 1.0614          |66| 1.1051        | 0.9963 | 65000 | 1.0585          |67 68 69### Framework versions70 71- Transformers 4.52.472- Pytorch 2.8.0.dev20250529+rocm6.473- Datasets 3.6.074- Tokenizers 0.21.175