cwe-parent-vulnerability-classification-microsoft-graphcodebert-base

This model is a fine-tuned version of microsoft/graphcodebert-base 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: 1e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
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
num_epochs: 40

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
3.255	1.0	25	3.2962	0.0225	0.0083
3.1345	2.0	50	3.3120	0.2697	0.0544
3.0539	3.0	75	3.3627	0.3820	0.0582
2.9349	4.0	100	3.3122	0.3596	0.0921
2.9555	5.0	125	3.2926	0.4045	0.1695
2.7748	6.0	150	3.3514	0.4607	0.1757
2.803	7.0	175	3.3219	0.5169	0.1884
2.67	8.0	200	3.2696	0.4831	0.2198
2.5684	9.0	225	3.2657	0.4944	0.2445
2.4226	10.0	250	3.1999	0.3371	0.1697
2.4615	11.0	275	3.1954	0.4270	0.1996
2.2738	12.0	300	3.1108	0.4157	0.1954
2.2423	13.0	325	3.0714	0.3933	0.1862
2.2066	14.0	350	3.0598	0.3820	0.1975
1.9919	15.0	375	3.0252	0.4382	0.1992
1.9622	16.0	400	2.9873	0.3708	0.1981
1.9415	17.0	425	2.9783	0.4494	0.2166
1.8459	18.0	450	2.9570	0.4831	0.2304
1.7008	19.0	475	2.9116	0.4607	0.2104
1.6705	20.0	500	2.9134	0.4607	0.2152
1.6422	21.0	525	2.9341	0.4607	0.2554
1.4982	22.0	550	2.8852	0.5056	0.2604
1.5523	23.0	575	2.9029	0.5056	0.2555
1.3784	24.0	600	2.8782	0.5393	0.2840
1.4479	25.0	625	2.8525	0.5730	0.2558
1.2508	26.0	650	2.9039	0.5730	0.2563
1.3662	27.0	675	2.8784	0.6067	0.3081
1.2199	28.0	700	2.8704	0.6180	0.2729
1.1903	29.0	725	2.8577	0.6404	0.2811
1.1881	30.0	750	2.8612	0.6404	0.2890
1.1572	31.0	775	2.8371	0.6292	0.2968
1.0623	32.0	800	2.8413	0.6404	0.2969
1.0405	33.0	825	2.8233	0.6517	0.3050
1.1084	34.0	850	2.8323	0.6404	0.3012
1.0211	35.0	875	2.8341	0.6404	0.3042
1.0215	36.0	900	2.8391	0.6404	0.3006
0.9438	37.0	925	2.8321	0.6404	0.3006
0.9383	38.0	950	2.8266	0.6404	0.3012
1.017	39.0	975	2.8236	0.6404	0.3037
0.9262	40.0	1000	2.8264	0.6404	0.3037