turkish_mmlu_base-bert-uncased

This model is a fine-tuned version of ytu-ce-cosmos/turkish-base-bert-uncased on the alibayram/turkish_mmlu dataset. It achieves the following results on the evaluation set:

• Loss: 1.5043
• Accuracy: 0.3119

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5725	0.9998	2063	1.5487	0.2739
1.5254	1.9995	4126	1.5090	0.3057
1.4895	2.9993	6189	1.5043	0.3119

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1