scenario-TCR-data-glue-stsb-model-bert-base-uncased

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4806
• Pearson: nan
• Spearmanr: nan

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: 5e-05
• 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: 6969

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr
No log	1.0	180	0.5620	nan	nan
No log	2.0	360	0.5905	nan	nan
0.606	3.0	540	0.5036	nan	nan
0.606	4.0	720	0.5073	nan	nan
0.606	5.0	900	0.4840	nan	nan
0.1567	6.0	1080	0.4806	nan	nan

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.16.0
• Tokenizers 0.15.0