gemma-sft-qlora

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

• Loss: 0.6385

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.1537	0.99	94	1.0988
0.9028	1.99	189	0.8056
0.6553	2.99	284	0.6577
0.4936	3.96	376	0.6385

Framework versions

• PEFT 0.7.1
• Transformers 4.38.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2