Regression_albert_11_aug

This model is a fine-tuned version of albert-base-v2 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:

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2	Accuracy
No log	1.0	263	0.2010	0.2010	0.3575	0.5311	0.7367
0.2435	2.0	526	0.1490	0.1490	0.2495	0.6523	0.8733
0.2435	3.0	789	0.0972	0.0972	0.2068	0.7732	0.9067
0.0906	4.0	1052	0.1115	0.1115	0.2082	0.7399	0.9067
0.0906	5.0	1315	0.0904	0.0904	0.1684	0.7890	0.9
0.0421	6.0	1578	0.0791	0.0791	0.1542	0.8153	0.93
0.0421	7.0	1841	0.0843	0.0843	0.1415	0.8034	0.9133
0.0274	8.0	2104	0.0694	0.0694	0.1152	0.8380	0.9333
0.0274	9.0	2367	0.0742	0.0742	0.1435	0.8269	0.93
0.0213	10.0	2630	0.0659	0.0659	0.1022	0.8463	0.9367
0.0213	11.0	2893	0.0600	0.0600	0.1054	0.8599	0.9433
0.0127	12.0	3156	0.0540	0.0540	0.0988	0.8739	0.9433
0.0127	13.0	3419	0.0479	0.0479	0.0854	0.8883	0.9567
0.0077	14.0	3682	0.0517	0.0517	0.0848	0.8793	0.95
0.0077	15.0	3945	0.0405	0.0405	0.0851	0.9054	0.9633
0.0051	16.0	4208	0.0430	0.0430	0.0742	0.8996	0.9533
0.0051	17.0	4471	0.0368	0.0368	0.0721	0.9142	0.96
0.0036	18.0	4734	0.0352	0.0352	0.0709	0.9180	0.96
0.0036	19.0	4997	0.0345	0.0345	0.0654	0.9195	0.9567
0.0029	20.0	5260	0.0366	0.0366	0.0671	0.9146	0.96