gemma-7b-sft-qlora-no-robots2

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

• Loss: 1.3843

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
20.4692	0.91	5	7.4399
12.9912	2.0	11	6.6074
10.1734	2.91	16	6.0225
9.8269	4.0	22	3.5503
5.2353	4.91	27	1.6505
1.6367	6.0	33	1.4912
1.4714	6.91	38	1.4201
1.3916	8.0	44	1.3933
1.2832	8.91	49	1.3882
1.2863	9.09	50	1.3843

Framework versions

• PEFT 0.7.1
• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2