gemma3_lora_sft_011

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

gemma3_lora_sft_011

This model is a fine-tuned version of google/gemma-3-4b-it on the gulaschnascher4000/german_alpaca_under_512_tokens, the gulaschnascher4000/german_alpaca_under_512_tokens_001, the gulaschnascher4000/identity-chatgulaschpt and the gulaschnascher4000/german_alpaca_under_512_tokens_002 datasets. It achieves the following results on the evaluation set:

• Loss: 2.1317
• Num Input Tokens Seen: 18648024

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Framework versions

• PEFT 0.15.2
• Transformers 4.55.0
• Pytorch 2.8.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1