deberta-large_spell_5k_6_p3

This model is a fine-tuned version of model_saves/deberta-large_spell_5k_6_p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4161
• Accuracy: 0.9410

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 92
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 15.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	268	0.4161	0.9410
No log	2.0	536	0.4395	0.9409
No log	3.0	804	0.4750	0.9400
0.2544	4.0	1072	0.5293	0.9395

Framework versions

• Transformers 4.21.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1