interpro_bert

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

• Loss: 0.7610

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: 2e-05
• train_batch_size: 256
• eval_batch_size: 128
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 2048
• total_eval_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
4.7929	1.0	14395	4.4007
2.6085	2.0	28790	2.4082
1.7765	3.0	43185	1.6582
1.3909	4.0	57580	1.3030
1.1805	5.0	71975	1.1146
1.0593	6.0	86370	1.0107
0.9726	7.0	100765	0.9359
0.9167	8.0	115160	0.8880
0.8683	9.0	129555	0.8475
0.8436	10.0	143950	0.8224
0.8167	11.0	158345	0.7974
0.8009	12.0	172740	0.7850
0.7874	13.0	187135	0.7682
0.7772	14.0	201530	0.7654
0.7738	15.0	215925	0.7610

Framework versions

• Transformers 4.39.2
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2