xlnet-large_spell_10k_3_p3

This model is a fine-tuned version of model_saves/xlnet-large_spell_10k_3_p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4498
• Accuracy: 0.9403

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: 62
• 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	0.4410	0.9399
No log	2.0	536	0.4498	0.9403
No log	3.0	804	0.4809	0.9393
0.323	4.0	1072	0.5204	0.9394
0.323	5.0	1340	0.5857	0.9399

Framework versions

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