CS221-xlm-roberta-base-finetuned-semeval-NT

This model is a fine-tuned version of xlm-roberta-base on the None 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: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.5425	1.0	277	0.5496	0.2089	0.5420	0.1733
0.4481	2.0	554	0.4624	0.5030	0.6694	0.3303
0.3721	3.0	831	0.4452	0.5908	0.7042	0.3592
0.2685	4.0	1108	0.4686	0.6050	0.7126	0.3682
0.2718	5.0	1385	0.5025	0.6347	0.7226	0.3448
0.2484	6.0	1662	0.5104	0.6207	0.7129	0.3357
0.1517	7.0	1939	0.5261	0.6584	0.7419	0.3773
0.107	8.0	2216	0.5936	0.6291	0.7359	0.3700
0.0836	9.0	2493	0.6273	0.6502	0.7472	0.3700
0.0809	10.0	2770	0.6281	0.6598	0.7423	0.3809
0.0348	11.0	3047	0.6834	0.6415	0.7339	0.3520
0.0316	12.0	3324	0.7265	0.6563	0.7474	0.3700
0.0205	13.0	3601	0.7280	0.6604	0.7421	0.3592
0.0186	14.0	3878	0.7401	0.6625	0.7420	0.3682
0.014	15.0	4155	0.7549	0.6591	0.7430	0.3700
0.0297	16.0	4432	0.7652	0.6674	0.7481	0.3755
0.0175	17.0	4709	0.7736	0.6629	0.7459	0.3827
0.022	18.0	4986	0.7772	0.6721	0.7524	0.3827
0.014	19.0	5263	0.7781	0.6655	0.7487	0.3791
0.0091	20.0	5540	0.7784	0.6642	0.7476	0.3791