damage_trigger_effect_2023-12-19_14_11

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

• Loss: 0.6940
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.8550

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	0.6583	0.0	0.0	0.0	0.8158
No log	2.0	68	0.5418	0.0	0.0	0.0	0.8094
No log	3.0	102	0.4800	0.0	0.0	0.0	0.8418
No log	4.0	136	0.4383	0.0	0.0	0.0	0.8579
No log	5.0	170	0.4956	0.0	0.0	0.0	0.8449
No log	6.0	204	0.5156	0.0	0.0	0.0	0.8591
No log	7.0	238	0.5127	0.0	0.0	0.0	0.8591
No log	8.0	272	0.5488	0.0	0.0	0.0	0.8529
No log	9.0	306	0.6051	0.0	0.0	0.0	0.8529
No log	10.0	340	0.6026	0.0	0.0	0.0	0.8605
No log	11.0	374	0.6523	0.0	0.0	0.0	0.8506
No log	12.0	408	0.6824	0.0	0.0	0.0	0.8520
No log	13.0	442	0.6777	0.0	0.0	0.0	0.8550
No log	14.0	476	0.7056	0.0	0.0	0.0	0.8508
0.2478	15.0	510	0.6940	0.0	0.0	0.0	0.8550

Framework versions

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