014-microsoft-deberta-v3-base-finetuned-yahoo-80_20

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: 3.3983
• F1: 0.2344
• Accuracy: 0.3
• Precision: 0.2369
• Recall: 0.3
• System Ram Used: 4.9456
• System Ram Total: 83.4807
• Gpu Ram Allocated: 4.8430
• Gpu Ram Cached: 7.0469
• Gpu Ram Total: 39.5640
• Gpu Utilization: 11
• Disk Space Used: 40.4033
• 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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

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
2.311	2.5	25	2.3033	0.0857	0.15	0.1105	0.15	5.0008	83.4807	4.8431	7.0469	39.5640	40	36.2797	78.1898
2.2703	5.0	50	2.3011	0.0686	0.2	0.0417	0.2	5.0121	83.4807	4.8431	7.0469	39.5640	38	36.2797	78.1898
2.0062	7.5	75	2.2817	0.0794	0.15	0.0543	0.15	4.9856	83.4807	4.8431	7.0469	39.5640	42	36.2797	78.1898
1.49	10.0	100	2.3281	0.1178	0.2	0.0869	0.2	4.9824	83.4807	4.8431	7.0469	39.5640	37	36.2797	78.1898
0.9424	12.5	125	2.3475	0.1733	0.25	0.1417	0.25	4.9446	83.4807	4.8431	7.0469	39.5640	42	36.2798	78.1898
0.5591	15.0	150	2.4503	0.1744	0.25	0.1452	0.25	4.9201	83.4807	4.8431	7.0469	39.5640	29	36.2798	78.1898
0.2893	17.5	175	2.5557	0.1744	0.25	0.1452	0.25	4.9618	83.4807	4.8431	7.0469	39.5640	43	36.2798	78.1898
0.1623	20.0	200	2.6218	0.2411	0.3	0.2452	0.3	4.9110	83.4807	4.8431	7.0469	39.5640	30	36.2799	78.1898
0.0817	22.5	225	2.7346	0.24	0.3	0.2417	0.3	4.9413	83.4807	4.8431	7.0469	39.5640	38	36.2799	78.1898
0.0475	25.0	250	2.9325	0.2344	0.3	0.2369	0.3	4.9314	83.4807	4.8431	7.0469	39.5640	40	36.2800	78.1898
0.0322	27.5	275	3.1235	0.2511	0.3	0.2869	0.3	4.9336	83.4807	4.8431	7.0469	39.5640	42	36.2800	78.1898
0.0254	30.0	300	3.1455	0.2344	0.3	0.2369	0.3	4.9387	83.4807	4.8431	7.0469	39.5640	30	36.2800	78.1898
0.0195	32.5	325	3.2767	0.2344	0.3	0.2369	0.3	4.9198	83.4807	4.8431	7.0469	39.5640	38	36.2801	78.1898
0.0163	35.0	350	3.3281	0.2344	0.3	0.2369	0.3	4.9709	83.4807	4.8431	7.0469	39.5640	42	40.4031	78.1898
0.015	37.5	375	3.3318	0.2344	0.3	0.2369	0.3	4.9642	83.4807	4.8431	7.0469	39.5640	41	40.4032	78.1898
0.0133	40.0	400	3.3617	0.2511	0.3	0.2869	0.3	4.9608	83.4807	4.8431	7.0469	39.5640	37	40.4032	78.1898
0.0127	42.5	425	3.3788	0.2344	0.3	0.2369	0.3	4.9617	83.4807	4.8431	7.0469	39.5640	39	40.4032	78.1898
0.0129	45.0	450	3.3928	0.2511	0.3	0.2869	0.3	4.9576	83.4807	4.8431	7.0469	39.5640	41	40.4032	78.1898
0.0121	47.5	475	3.3897	0.2344	0.3	0.2369	0.3	4.9421	83.4807	4.8431	7.0469	39.5640	37	40.4033	78.1898
0.0124	50.0	500	3.3983	0.2344	0.3	0.2369	0.3	4.9581	83.4807	4.8431	7.0469	39.5640	38	40.4033	78.1898

Framework versions

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