medgemma-temporal-lora-v2-exp

This model is a fine-tuned version of google/medgemma-1.5-4b-it on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0099

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0603	0.3175	25	0.0557
0.0114	0.6349	50	0.0083
0.0108	0.9524	75	0.0084
0.0168	1.2667	100	0.0099

Framework versions

• PEFT 0.18.1
• Transformers 5.0.0
• Pytorch 2.8.0+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2