nep-spell-hft-993-01-05

This model is a fine-tuned version of duraad/nep-spell-hft on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.2828
• Precision: 0.2828
• Recall: 0.2828
• F1: 0.2828

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-06
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0	0.75	100	nan	0.2828	0.2828	0.2828	0.2828
0.0	1.5	200	nan	0.2828	0.2828	0.2828	0.2828
0.0	2.26	300	nan	0.2828	0.2828	0.2828	0.2828
0.0	3.01	400	nan	0.2828	0.2828	0.2828	0.2828
0.0	3.76	500	nan	0.2828	0.2828	0.2828	0.2828
0.0	4.51	600	nan	0.2828	0.2828	0.2828	0.2828

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2