gemma3_bilingual_cpt_fast

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0043
• Model Preparation Time: 0.0337

Model description

Simple Continued pretraining of gemma-3-270m for Irish (80%) and English (20%) as a test for generating better Irish understanding. Heavily influenced by the work done by reliableai

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: 0.0004
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
3.8479	0.1414	400	3.7987	0.0337
3.6146	0.2828	800	3.5188	0.0337
3.3704	0.4242	1200	3.3405	0.0337
3.2304	0.5655	1600	3.2068	0.0337
3.1446	0.7069	2000	3.1178	0.0337

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0