Lolimorimorf/feature_extraction_model_damage_trigger_effect_location_naacl_2025

damage_trigger_effect_2023-12-19_13_42

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

• Loss: 0.5476
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.8690

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: 16
• eval_batch_size: 16
• seed: 42
• 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	Precision	Recall	F1	Accuracy
No log	1.0	34	0.6317	0.0	0.0	0.0	0.8083
No log	2.0	68	0.4823	0.0	0.0	0.0	0.8318
No log	3.0	102	0.4314	0.0	0.0	0.0	0.8563
No log	4.0	136	0.4323	0.0	0.0	0.0	0.8549
No log	5.0	170	0.4324	0.0	0.0	0.0	0.8586
No log	6.0	204	0.4647	0.0	0.0	0.0	0.8590
No log	7.0	238	0.4629	0.0	0.0	0.0	0.8686
No log	8.0	272	0.4958	0.0	0.0	0.0	0.8519
No log	9.0	306	0.4954	0.0	0.0	0.0	0.8675
No log	10.0	340	0.5220	0.0	0.0	0.0	0.8608
No log	11.0	374	0.5356	0.0	0.0	0.0	0.8616
No log	12.0	408	0.5416	0.0	0.0	0.0	0.8642
No log	13.0	442	0.5315	0.0	0.0	0.0	0.8660
No log	14.0	476	0.5496	0.0	0.0	0.0	0.8675
0.248	15.0	510	0.5476	0.0	0.0	0.0	0.8690

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0