thmk/codegpt-java-10.2

1---2license: mit3tags:4- generated_from_trainer5model-index:6- name: codegpt-java-10.27  results: []8---9 10<!-- This model card has been generated automatically according to the information the Trainer had access to. You11should probably proofread and complete it, then remove this comment. -->12 13# codegpt-java-10.214 15This model is a fine-tuned version of [thmk/codegpt-java-8](https://huggingface.co/thmk/codegpt-java-8) on the None dataset.16 17## Model description18 19More information needed20 21## Intended uses & limitations22 23More information needed24 25## Training and evaluation data26 27More information needed28 29## Training procedure30 31### Training hyperparameters32 33The following hyperparameters were used during training:34- learning_rate: 0.000235- train_batch_size: 3236- eval_batch_size: 3237- seed: 4238- gradient_accumulation_steps: 839- total_train_batch_size: 25640- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0841- lr_scheduler_type: cosine42- lr_scheduler_warmup_steps: 100043- num_epochs: 144- mixed_precision_training: Native AMP45 46### Training results47 48 49 50### Framework versions51 52- Transformers 4.26.153- Pytorch 1.13.1+cu11654- Datasets 2.9.055- Tokenizers 0.13.256