coding_llamaduo_result2

This model is a fine-tuned version of google/gemma-7b on the chansung/merged_ds_coding dataset. It achieves the following results on the evaluation set:

• Loss: 1.2247

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.8192	1.0	122	1.2006
0.6377	2.0	245	1.1304
0.5334	3.0	367	1.1456
0.4454	4.0	490	1.1935
0.408	4.98	610	1.2247

Framework versions

• PEFT 0.7.1
• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2