CeLLaTe3.0_Base_with_vague_adapted_pubmed

This model is a fine-tuned version of Mardiyyah/cellate2.0-tapt_base-LR_5e-05 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1772
• Precision: 0.8182
• Recall: 0.8137
• F1: 0.8159
• Accuracy: 0.9653

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: 32
• eval_batch_size: 16
• seed: 3407
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.3264	0.9901	100	0.5441	0.0	0.0	0.0	0.8638
0.3521	1.9802	200	0.2055	0.6063	0.6410	0.6232	0.9449
0.1509	2.9703	300	0.1518	0.7501	0.7951	0.7719	0.9606
0.0956	3.9604	400	0.1514	0.7748	0.8143	0.7940	0.9612
0.0718	4.9505	500	0.1576	0.8218	0.7933	0.8073	0.9637
0.0525	5.9406	600	0.1739	0.7909	0.8148	0.8027	0.9628
0.0415	6.9307	700	0.1687	0.8002	0.8256	0.8127	0.9644
0.034	7.9208	800	0.1774	0.8182	0.8137	0.8159	0.9653
0.0269	8.9109	900	0.2185	0.8034	0.7199	0.7594	0.9579
0.0242	9.9010	1000	0.2003	0.8134	0.7753	0.7939	0.9627
0.0214	10.8911	1100	0.1892	0.7831	0.8443	0.8126	0.9634

Framework versions

• Transformers 4.48.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.2
• Tokenizers 0.21.0