tinybert

This model is a fine-tuned version of DedalusHealthCare/tinybert-mlm-en on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5185
• Accuracy: 0.9816
• F1: 0.0
• Precision: 0.0
• Recall: 0.0

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.2857	1	0.6663	0.7953	0.0	0.0	0.0
No log	0.5714	2	0.6612	0.8189	0.0	0.0	0.0
No log	0.8571	3	0.6516	0.8766	0.0	0.0	0.0
No log	1.1429	4	0.6373	0.9081	0.0	0.0	0.0
No log	1.4286	5	0.6185	0.9423	0.0	0.0	0.0
No log	1.7143	6	0.5955	0.9685	0.0	0.0	0.0
No log	2.0	7	0.5687	0.9790	0.0	0.0	0.0
No log	2.2857	8	0.5431	0.9816	0.0	0.0	0.0
No log	2.5714	9	0.5185	0.9816	0.0	0.0	0.0

Framework versions

• Transformers 4.45.1
• Pytorch 2.6.0+cu124
• Datasets 2.16.0
• Tokenizers 0.20.3