demo-ossbert

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5070

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: 8
• 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: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.4098	200	2.2526
No log	0.8197	400	2.0533
No log	1.2295	600	1.9284
No log	1.6393	800	1.8373
No log	2.0492	1000	1.7617
No log	2.4590	1200	1.6901
No log	2.8689	1400	1.6629
No log	3.2787	1600	1.6144
No log	3.6885	1800	1.5676
No log	4.0984	2000	1.5337
No log	4.5082	2200	1.5168
No log	4.9180	2400	1.5070

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1