scenario-kd-scr-ner-full-xlmr_data-univner_en55

This model is a fine-tuned version of haryoaw/scenario-TCR-NER_data-univner_en on the None dataset. It achieves the following results on the evaluation set:

• Loss: 257.7743
• Precision: 0.4158
• Recall: 0.3168
• F1: 0.3596
• Accuracy: 0.9539

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 32
• seed: 55
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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	Precision	Recall	F1	Accuracy
437.2599	1.2755	500	353.7681	0.5556	0.0207	0.0399	0.9412
326.1208	2.5510	1000	314.6490	0.2723	0.1770	0.2146	0.9460
296.4329	3.8265	1500	293.4004	0.3321	0.2754	0.3011	0.9499
276.9196	5.1020	2000	278.3865	0.3868	0.2795	0.3245	0.9513
263.684	6.3776	2500	269.1346	0.3916	0.3178	0.3509	0.9522
255.104	7.6531	3000	261.8210	0.3961	0.2961	0.3389	0.9530
248.9325	8.9286	3500	257.7743	0.4158	0.3168	0.3596	0.9539

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.19.1