scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66

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

• Loss: 250.6721
• Precision: 0.4368
• Recall: 0.2754
• F1: 0.3378
• Accuracy: 0.9532

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: 66
• 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
426.5331	1.28	500	343.1131	0.4717	0.0259	0.0491	0.9413
317.8317	2.55	1000	306.4857	0.3815	0.1066	0.1667	0.9449
288.4479	3.83	1500	285.8158	0.4429	0.1284	0.1990	0.9461
270.6268	5.1	2000	271.5317	0.3921	0.2050	0.2692	0.9494
257.3109	6.38	2500	260.7265	0.3853	0.2381	0.2943	0.9517
248.4864	7.65	3000	253.9278	0.3950	0.2940	0.3371	0.9527
242.8456	8.93	3500	250.6721	0.4368	0.2754	0.3378	0.9532

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3