iHateNLP/deepseek-coder-1.3b-base-JUnit

sft_00

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the Sohaib9920/code_tests dataset. It achieves the following results on the evaluation set:

• Loss: 0.2291

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: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4228	0.4996	623	0.3337
0.3632	0.9993	1246	0.2687
0.264	1.4989	1869	0.2418
0.2535	1.9986	2492	0.2291

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1