coding_llamaduo_result3

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: 1.7502

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: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.987	1.0	82	1.2808
0.6859	2.0	164	1.1719
0.5836	3.0	246	1.1480
0.5178	4.0	328	1.1717
0.4668	5.0	410	1.2044
0.3955	6.0	492	1.3252
0.3233	7.0	574	1.4225
0.2669	8.0	656	1.6119
0.2591	9.0	738	1.7353
0.2367	10.0	820	1.7502

Framework versions

• PEFT 0.7.1
• Transformers 4.40.0
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1