santacoder-finetuned-the-stack-bash

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

• Loss: 1.3654

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
1.6322	0.25	500	1.5498
3.9791	0.5	1000	1.4721
0.3946	0.75	1500	1.3971
1.5232	1.0	2000	1.3654

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3