README.md

metadata

license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
  - precision
  - recall
model-index:
  - name: 009-microsoft-deberta-v3-base-finetuned-yahoo-800_200
    results: []

009-microsoft-deberta-v3-base-finetuned-yahoo-800_200

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: 1.1599
• F1: 0.6588
• Accuracy: 0.66
• Precision: 0.6659
• Recall: 0.66
• System Ram Used: 5.0546
• System Ram Total: 83.4807
• Gpu Ram Allocated: 4.1727
• Gpu Ram Cached: 26.7715
• Gpu Ram Total: 39.5640
• Gpu Utilization: 56
• Disk Space Used: 40.6642
• 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
2.3022	0.76	19	2.3012	0.0182	0.1	0.01	0.1	4.4456	83.4807	4.1727	26.7598	39.5640	45	33.7570	78.1898
2.2979	1.52	38	2.2854	0.0635	0.155	0.0449	0.155	5.0347	83.4807	4.1727	26.7715	39.5640	43	38.5922	78.1898
2.2316	2.28	57	2.1098	0.2285	0.305	0.2806	0.305	5.1781	83.4807	4.1727	26.7715	39.5640	44	40.6639	78.1898
1.9915	3.04	76	1.8477	0.4148	0.43	0.5040	0.43	5.1741	83.4807	4.1727	26.7715	39.5640	50	40.6639	78.1898
1.684	3.8	95	1.6027	0.5272	0.55	0.5666	0.55	5.1766	83.4807	4.1728	26.7715	39.5640	47	40.6639	78.1898
1.3911	4.56	114	1.4365	0.6060	0.615	0.6199	0.615	5.1746	83.4807	4.1728	26.7715	39.5640	49	40.6640	78.1898
1.1477	5.32	133	1.2565	0.6215	0.615	0.6419	0.615	5.1586	83.4807	4.1728	26.7715	39.5640	52	40.6640	78.1898
0.9198	6.08	152	1.1759	0.6400	0.64	0.6532	0.64	5.1810	83.4807	4.1727	26.7715	39.5640	55	40.6640	78.1898
0.7605	6.84	171	1.1128	0.6418	0.645	0.6564	0.645	5.1415	83.4807	4.1727	26.7715	39.5640	45	40.6640	78.1898
0.6093	7.6	190	1.0767	0.6678	0.67	0.6758	0.67	5.1347	83.4807	4.1728	26.7715	39.5640	43	40.6640	78.1898
0.5111	8.36	209	1.1033	0.6552	0.655	0.6742	0.655	5.1206	83.4807	4.1728	26.7715	39.5640	52	40.6641	78.1898
0.3828	9.12	228	1.1063	0.6875	0.69	0.6927	0.69	5.1484	83.4807	4.1727	26.7715	39.5640	44	40.6641	78.1898
0.3082	9.88	247	1.1240	0.6573	0.665	0.6595	0.665	5.1437	83.4807	4.1728	26.7715	39.5640	45	40.6641	78.1898
0.2716	10.64	266	1.1572	0.6604	0.665	0.6665	0.665	5.0689	83.4807	4.1728	26.7715	39.5640	45	40.6641	78.1898
0.2442	11.4	285	1.1058	0.6765	0.675	0.6827	0.675	5.0316	83.4807	4.1728	26.7715	39.5640	42	40.6641	78.1898
0.1791	12.16	304	1.1455	0.6445	0.645	0.6515	0.645	5.0715	83.4807	4.1728	26.7715	39.5640	46	40.6641	78.1898
0.1604	12.92	323	1.1514	0.6578	0.66	0.6686	0.66	5.0728	83.4807	4.1728	26.7715	39.5640	57	40.6641	78.1898
0.1389	13.68	342	1.1600	0.6715	0.675	0.6808	0.675	5.0655	83.4807	4.1727	26.7715	39.5640	48	40.6642	78.1898
0.151	14.44	361	1.1573	0.6626	0.665	0.6687	0.665	5.0588	83.4807	4.1727	26.7715	39.5640	48	40.6642	78.1898

Framework versions

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