bert_distillation_tiny

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4804
• Model Preparation Time: 0.0009
• Accuracy: 0.8303

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: 0.0001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 2023
• 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: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Accuracy
0.4157	1.0	527	0.4127	0.0009	0.8131
0.2693	2.0	1054	0.4429	0.0009	0.8211
0.2189	3.0	1581	0.4804	0.0009	0.8303
0.1907	4.0	2108	0.4995	0.0009	0.8200
0.1712	5.0	2635	0.5311	0.0009	0.8165
0.1597	6.0	3162	0.5561	0.0009	0.8131
0.1536	7.0	3689	0.5604	0.0009	0.8142

Framework versions

• Transformers 4.57.6
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2