citation_intent_classification_roberta_dapt

This model is a fine-tuned version of ltuzova/cs_domain_pretrained_model on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5175
• Accuracy: 0.5108
• F1 Macro: 0.1127

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: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.06
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
1.6621	1.0	105	1.5071	0.5175	0.1137
1.4561	2.0	211	1.3867	0.5175	0.1137
1.4054	3.0	316	1.3482	0.5175	0.1137
1.3753	4.0	422	1.3319	0.5175	0.1137

Framework versions

• Transformers 4.30.2
• Pytorch 1.13.1+cu117
• Datasets 2.13.2
• Tokenizers 0.13.3