relation_classification_single_label

This model is a fine-tuned version of Musixmatch/umberto-commoncrawl-cased-v1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8861
• Accuracy: 0.6822
• F1: 0.6573

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	121	0.8453	0.6357	0.6305
No log	2.0	242	0.9264	0.6434	0.6392
No log	3.0	363	0.8861	0.6822	0.6573
No log	4.0	484	1.0027	0.6822	0.6558
0.6343	5.0	605	1.1278	0.6667	0.6356
0.6343	6.0	726	1.3472	0.6512	0.6100
0.6343	7.0	847	1.4766	0.6434	0.5919
0.6343	8.0	968	1.5769	0.6667	0.6303
0.1581	9.0	1089	1.6284	0.6434	0.5971
0.1581	10.0	1210	1.6729	0.6589	0.6175

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1