012-microsoft-deberta-v3-base-finetuned-yahoo-8000_2000

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9425
• F1: 0.7138
• Accuracy: 0.718
• Precision: 0.7184
• Recall: 0.718
• System Ram Used: 4.1370
• System Ram Total: 83.4807
• Gpu Ram Allocated: 2.0897
• Gpu Ram Cached: 25.8555
• Gpu Ram Total: 39.5640
• Gpu Utilization: 46
• Disk Space Used: 29.6434
• Disk Space Total: 78.1898

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: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy	Precision	Recall	System Ram Used	System Ram Total	Gpu Ram Allocated	Gpu Ram Cached	Gpu Ram Total	Gpu Utilization	Disk Space Used	Disk Space Total
2.2963	0.2	50	2.2150	0.1298	0.2015	0.2090	0.2015	3.9807	83.4807	2.0898	25.8457	39.5640	48	24.8073	78.1898
1.8843	0.4	100	1.4590	0.5588	0.592	0.6418	0.592	3.9979	83.4807	2.0898	25.8477	39.5640	49	24.8074	78.1898
1.3348	0.6	150	1.1809	0.6613	0.668	0.6736	0.668	3.9836	83.4807	2.0898	25.8555	39.5640	49	24.8074	78.1898
1.1501	0.8	200	1.0484	0.6929	0.695	0.6981	0.695	3.9695	83.4807	2.0898	25.8555	39.5640	51	24.8074	78.1898
1.0842	1.0	250	1.0265	0.6825	0.6905	0.6894	0.6905	3.9755	83.4807	2.0898	25.8555	39.5640	50	24.8075	78.1898
0.8618	1.2	300	0.9904	0.7024	0.704	0.7048	0.704	3.9708	83.4807	2.0898	25.8555	39.5640	50	24.8075	78.1898
0.9329	1.4	350	0.9927	0.6825	0.686	0.6939	0.686	3.9595	83.4807	2.0898	25.8555	39.5640	48	24.8076	78.1898
0.9053	1.6	400	0.9795	0.7021	0.705	0.7048	0.705	3.9837	83.4807	2.0898	25.8555	39.5640	48	24.8076	78.1898
0.9173	1.8	450	0.9749	0.7024	0.709	0.7140	0.709	3.9851	83.4807	2.0898	25.8555	39.5640	48	24.8077	78.1898
0.9189	2.0	500	0.9425	0.7138	0.718	0.7184	0.718	3.9949	83.4807	2.0898	25.8555	39.5640	48	24.8077	78.1898
0.7727	2.2	550	0.9590	0.7101	0.7155	0.7150	0.7155	4.1847	83.4807	2.0898	25.8555	39.5640	45	29.6429	78.1898
0.7092	2.4	600	0.9389	0.7180	0.7215	0.7177	0.7215	4.1798	83.4807	2.0901	25.8555	39.5640	47	29.6429	78.1898
0.737	2.6	650	0.9606	0.7074	0.715	0.7144	0.715	4.1766	83.4807	2.0898	25.8555	39.5640	51	29.6430	78.1898
0.7334	2.8	700	0.9348	0.7175	0.72	0.7180	0.72	4.1699	83.4807	2.0898	25.8555	39.5640	50	29.6430	78.1898
0.7316	3.0	750	0.9407	0.7230	0.7275	0.7238	0.7275	4.1785	83.4807	2.0898	25.8555	39.5640	50	29.6431	78.1898
0.6045	3.2	800	0.9300	0.7208	0.721	0.7253	0.721	4.1864	83.4807	2.0898	25.8555	39.5640	48	29.6431	78.1898
0.6262	3.4	850	0.9416	0.7165	0.7175	0.7184	0.7175	4.1847	83.4807	2.0898	25.8555	39.5640	49	29.6431	78.1898
0.5999	3.6	900	0.9542	0.7155	0.718	0.7156	0.718	4.1891	83.4807	2.0898	25.8555	39.5640	47	29.6431	78.1898
0.6436	3.8	950	0.9580	0.7085	0.7115	0.7127	0.7115	4.1644	83.4807	2.0898	25.8555	39.5640	49	29.6431	78.1898
0.59	4.0	1000	0.9476	0.7209	0.723	0.7208	0.723	4.1608	83.4807	2.0898	25.8555	39.5640	47	29.6432	78.1898
0.5422	4.2	1050	0.9658	0.7201	0.7205	0.7224	0.7205	4.1462	83.4807	2.0898	25.8555	39.5640	46	31.7150	78.1898
0.5205	4.4	1100	0.9674	0.7122	0.7155	0.7128	0.7155	4.1598	83.4807	2.0898	25.8555	39.5640	49	31.7151	78.1898
0.5253	4.6	1150	0.9563	0.7175	0.7195	0.7185	0.7195	4.1854	83.4807	2.0898	25.8555	39.5640	49	31.7151	78.1898
0.5109	4.8	1200	0.9621	0.7201	0.722	0.7192	0.722	4.1908	83.4807	2.0898	25.8555	39.5640	49	31.7151	78.1898
0.5216	5.0	1250	0.9635	0.7190	0.7215	0.7189	0.7215	4.1862	83.4807	2.0898	25.8555	39.5640	50	31.7151	78.1898

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3