peft-starcoder-finetuned

This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: nan
• eval_runtime: 51.0638
• eval_samples_per_second: 1.43
• eval_steps_per_second: 1.43
• epoch: 0.3
• step: 60

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• 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: 10
• training_steps: 200

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3