DrishtiSharma/roberta-large-lora-patent-classification-2e-4

roberta-large-flash-attention-2-lora-patent-classification-2e-4

This model is a fine-tuned version of roberta-large on the patent-classification dataset. It achieves the following results on the evaluation set:

• Loss: 0.8264
• Accuracy: 0.659
• Precision Macro: 0.6268
• Recall Macro: 0.6433
• F1-score Macro: 0.6295

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: 0.0002
• train_batch_size: 6
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Macro	Recall Macro	F1-score Macro
0.8107	1.0	4167	0.9531	0.5096	0.6495	0.4554	0.4831
0.7105	2.0	8334	0.8408	0.6426	0.6307	0.6261	0.6208
0.6299	3.0	12501	0.8264	0.659	0.6268	0.6433	0.6295

Framework versions

• PEFT 0.7.2.dev0
• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.2.dev0
• Tokenizers 0.15.0