README.md

metadata

license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
  - precision
  - recall
model-index:
  - name: 011-microsoft-deberta-v3-base-finetuned-yahoo-8000_2000
    results: []

011-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: 1.8660
• F1: 0.7055
• Accuracy: 0.7045
• Precision: 0.7076
• Recall: 0.7045
• System Ram Used: 4.2773
• System Ram Total: 83.4807
• Gpu Ram Allocated: 2.0897
• Gpu Ram Cached: 25.8555
• Gpu Ram Total: 39.5640
• Gpu Utilization: 48
• Disk Space Used: 35.8287
• 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: 15

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
1.6916	0.75	188	1.1063	0.6708	0.6755	0.6900	0.6755	4.0191	83.4807	2.0898	25.8555	39.5640	50	24.8064	78.1898
0.9694	1.5	376	0.9586	0.7181	0.7195	0.7198	0.7195	4.2536	83.4807	2.0898	25.8555	39.5640	50	29.6418	78.1898
0.8509	2.26	564	0.9748	0.7070	0.712	0.7161	0.712	4.1602	83.4807	2.0898	25.8555	39.5640	46	29.6418	78.1898
0.7475	3.01	752	0.9447	0.7122	0.714	0.7148	0.714	4.1607	83.4807	2.0898	25.8555	39.5640	50	29.6420	78.1898
0.5841	3.76	940	1.0064	0.7077	0.711	0.7225	0.711	4.1889	83.4807	2.0898	25.8555	39.5640	47	29.6420	78.1898
0.4972	4.51	1128	1.0585	0.7110	0.714	0.7129	0.714	4.1766	83.4807	2.0898	25.8555	39.5640	47	29.6421	78.1898
0.4555	5.26	1316	1.1175	0.7086	0.7075	0.7151	0.7075	4.2257	83.4807	2.0898	25.8555	39.5640	46	33.7652	78.1898
0.3535	6.02	1504	1.1749	0.7032	0.708	0.7077	0.708	4.2302	83.4807	2.0898	25.8555	39.5640	50	33.7653	78.1898
0.2614	6.77	1692	1.2028	0.7056	0.709	0.7079	0.709	4.2376	83.4807	2.0898	25.8555	39.5640	49	33.7654	78.1898
0.2321	7.52	1880	1.2961	0.7019	0.698	0.7085	0.698	4.2248	83.4807	2.0898	25.8555	39.5640	49	33.7656	78.1898
0.197	8.27	2068	1.3960	0.7098	0.712	0.7137	0.712	4.2194	83.4807	2.0898	25.8555	39.5640	45	33.7657	78.1898
0.1505	9.02	2256	1.4310	0.7093	0.7075	0.7133	0.7075	4.2418	83.4807	2.0898	25.8555	39.5640	48	35.8277	78.1898
0.1132	9.78	2444	1.5454	0.7053	0.7045	0.7097	0.7045	4.2931	83.4807	2.0898	25.8555	39.5640	48	35.8278	78.1898
0.0979	10.53	2632	1.6420	0.7090	0.708	0.7171	0.708	4.2793	83.4807	2.0898	25.8555	39.5640	45	35.8281	78.1898
0.0818	11.28	2820	1.6869	0.7062	0.7065	0.7102	0.7065	4.2822	83.4807	2.0898	25.8555	39.5640	49	35.8281	78.1898
0.062	12.03	3008	1.7818	0.7043	0.701	0.7123	0.701	4.2864	83.4807	2.0901	25.8555	39.5640	50	35.8282	78.1898
0.0433	12.78	3196	1.7981	0.7080	0.707	0.7110	0.707	4.2666	83.4807	2.0898	25.8555	39.5640	49	35.8282	78.1898
0.0368	13.54	3384	1.8403	0.7079	0.7055	0.7131	0.7055	4.2783	83.4807	2.0898	25.8555	39.5640	47	35.8285	78.1898
0.0379	14.29	3572	1.8536	0.7052	0.705	0.7074	0.705	4.3013	83.4807	2.0898	25.8555	39.5640	47	35.8286	78.1898

Framework versions

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