fine-tuned-Qwen2-0.5B-Instruct-NER

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7071
• Exact Match: 0.0
• F1 Score: 47.2556
• Format Score: 0.0
• Content Score: 83.3333
• Pred Items: 0
• True Items: 23
• Common Items: 0
• Levenshtein Distance: 196.1667

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1 Score	Format Score	Content Score	Pred Items	True Items	Common Items	Levenshtein Distance
0.2192	9.4877	5000	0.3631	0.0	50.5576	0.0	50.0	0	37	0	164.3333
0.154	18.9753	10000	0.3042	0.0	34.6132	0.0	83.3333	0	19	0	133.8333
0.1439	28.4630	15000	0.2594	0.0	38.6508	0.0	66.6667	1	11	0	102.0
0.1315	37.9507	20000	0.2014	0.0	43.9169	0.0	66.6667	2	10	0	79.0
0.1204	47.4383	25000	0.7071	0.0	47.2556	0.0	83.3333	0	23	0	196.1667

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1