olmo2-1b-sft-deu

This model is a fine-tuned version of allenai/OLMo-2-0425-1B-Instruct on the aya_deu_train dataset. It achieves the following results on the evaluation set:

• Loss: 1.6937

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 4
• total_eval_batch_size: 2
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.8079	0.1501	500	1.8882
1.8346	0.3001	1000	1.8436
1.9325	0.4502	1500	1.7854
1.8923	0.6002	2000	1.7436
1.8412	0.7503	2500	1.7098
1.5772	0.9004	3000	1.6953

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.1+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1