ltg_norbert3-small_mask_values

This model is a fine-tuned version of ltg/norbert3-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6299

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.9855	0.1953	100	2.8386
1.588	0.3906	200	0.8918
1.3225	0.5859	300	0.7285
1.3289	0.7812	400	0.6746
1.3128	0.9766	500	0.6645
1.1002	1.1719	600	0.6299
1.5811	1.3672	700	0.6333
1.203	1.5625	800	0.6611

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu118
• Datasets 3.5.1
• Tokenizers 0.21.1