CeLLaTe3.0_with_vague_adapted_pubmed_bert

This model is a fine-tuned version of Mardiyyah/cellate1.0-tapt_freeze_llrd_ww_mask-LR_2e-05 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
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 Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.0049	1.0	202	0.2790	0.4807	0.4178	0.4470	0.9292
0.2072	2.0	404	0.1581	0.6347	0.8190	0.7152	0.9579
0.1088	3.0	606	0.1444	0.6869	0.7637	0.7233	0.9599
0.0717	4.0	808	0.1373	0.7083	0.7955	0.7493	0.9645
0.0495	5.0	1010	0.1630	0.7624	0.8042	0.7827	0.9658
0.036	6.0	1212	0.1644	0.7579	0.8312	0.7929	0.9658
0.0265	7.0	1414	0.1893	0.7819	0.8316	0.8060	0.9673
0.02	8.0	1616	0.2116	0.7381	0.8277	0.7803	0.9637
0.0158	9.0	1818	0.2020	0.7583	0.8246	0.7901	0.9666
0.0134	10.0	2020	0.2256	0.7283	0.7955	0.7604	0.9638
0.0103	11.0	2222	0.2269	0.7635	0.8290	0.7949	0.9663
0.0083	12.0	2424	0.2436	0.7576	0.8133	0.7845	0.9655
0.007	13.0	2626	0.2523	0.7593	0.8181	0.7876	0.9654
0.0059	14.0	2828	0.2478	0.7544	0.8259	0.7885	0.9657
0.005	15.0	3030	0.2439	0.7573	0.8107	0.7831	0.9662
0.0044	16.0	3232	0.2628	0.7586	0.8138	0.7852	0.9655
0.0042	17.0	3434	0.2458	0.7730	0.8151	0.7935	0.9668
0.0039	18.0	3636	0.2644	0.7589	0.8151	0.7860	0.9662
0.0029	19.0	3838	0.2629	0.7667	0.8081	0.7869	0.9659
0.0029	20.0	4040	0.2603	0.7596	0.8124	0.7851	0.9661

Safetensors

Model size

0.1B params

Tensor type

F32

Base model

Finetuned

Finetuned

(4)

this model