xlnet-large_spell_10k_1_p3

This model is a fine-tuned version of model_saves/xlnet-large_spell_10k_1_p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4756
• Accuracy: 0.9404

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: 42
• 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	0.4472	0.9398
No log	2.0	536	0.4756	0.9404
No log	3.0	804	0.5032	0.9397
0.2921	4.0	1072	0.5414	0.9390
0.2921	5.0	1340	0.6040	0.9389

Framework versions

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