gemma-2-2b-DottedWSD

This model is a fine-tuned version of google/gemma-2-2b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1367
• Accuracy: 0.9537

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 512
• optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1581	0.9997	770	0.1353	0.9444
0.1096	1.9994	1540	0.1188	0.9515
0.0538	2.9991	2310	0.1367	0.9537

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1