modernbert-medium-amharic-50k

This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.3994
• eval_model_preparation_time: 0.003
• eval_runtime: 10.1346
• eval_samples_per_second: 973.794
• eval_steps_per_second: 6.118
• epoch: 28.0983
• step: 178649

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: 0.0003
• train_batch_size: 160
• eval_batch_size: 160
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 10000
• num_epochs: 32
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1