turkish-gpt2-medium-finetuned-corpus

This model is a fine-tuned version of ytu-ce-cosmos/turkish-gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.3479

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: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• total_eval_batch_size: 32
• optimizer: Use 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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
2.536	0.0823	200	2.4685
2.4871	0.1646	400	2.4177
2.4659	0.2469	600	2.3919
2.4385	0.3292	800	2.3762
2.4381	0.4115	1000	2.3646
2.4167	0.4938	1200	2.3573
2.4163	0.5761	1400	2.3525
2.4225	0.6584	1600	2.3497
2.4252	0.7407	1800	2.3484
2.407	0.8230	2000	2.3480
2.3911	0.9053	2200	2.3480
2.4119	0.9876	2400	2.3479

Framework versions

• Transformers 4.50.0
• Pytorch 2.5.1+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1