coding_llamaduo_60k

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: 1.6318

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
0.6618	1.0	252	1.2071
0.5731	2.0	504	1.1436
0.5198	3.0	756	1.1346
0.4783	4.0	1008	1.1536
0.4378	5.0	1260	1.2225
0.3836	6.0	1512	1.2893
0.3381	7.0	1764	1.4050
0.3043	8.0	2016	1.5185
0.2778	9.0	2268	1.6143
0.2748	10.0	2520	1.6318

Framework versions

• PEFT 0.7.1
• Transformers 4.40.1
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1