t5_small_NCC_lm-finetuned-sv-frp-classifier-3

This model is a fine-tuned version of north/t5_small_NCC_lm on the norwegian_parliament dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Sequence Accuracy: 0.0

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: 0.001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sequence Accuracy
No log	1.0	113	nan	0.0
No log	2.0	226	nan	0.0
No log	3.0	339	nan	0.0
No log	4.0	452	nan	0.0
0.0	5.0	565	nan	0.0
0.0	6.0	678	nan	0.0
0.0	7.0	791	nan	0.0
0.0	8.0	904	nan	0.0
0.0	9.0	1017	nan	0.0
0.0	10.0	1130	nan	0.0

Framework versions

• Transformers 4.16.2
• Pytorch 1.9.0
• Datasets 2.3.2
• Tokenizers 0.11.0