README.md

metadata

license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
  - precision
  - recall
model-index:
  - name: 010-microsoft-deberta-v3-base-finetuned-yahoo-800_200
    results: []

010-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: 1.1327
• F1: 0.6339
• Accuracy: 0.64
• Precision: 0.6436
• Recall: 0.64
• System Ram Used: 4.1191
• System Ram Total: 83.4807
• Gpu Ram Allocated: 2.0916
• Gpu Ram Cached: 24.6602
• Gpu Ram Total: 39.5640
• Gpu Utilization: 46
• Disk Space Used: 42.7346
• 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: 10

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
2.3122	0.4	10	2.3038	0.0182	0.1	0.01	0.1	3.9481	83.4807	2.0915	24.6484	39.5640	44	42.7345	78.1898
2.3122	0.8	20	2.3008	0.0182	0.1	0.01	0.1	3.9500	83.4807	2.0916	24.6602	39.5640	64	42.7345	78.1898
2.3122	1.2	30	2.2951	0.0182	0.1	0.01	0.1	3.9885	83.4807	2.0915	24.6602	39.5640	44	42.7345	78.1898
2.3122	1.6	40	2.2860	0.0830	0.15	0.0948	0.15	4.0161	83.4807	2.0915	24.6602	39.5640	43	42.7345	78.1898
2.3122	2.0	50	2.2335	0.0916	0.195	0.1010	0.195	4.0651	83.4807	2.0916	24.6602	39.5640	43	42.7345	78.1898
2.3122	2.4	60	2.1085	0.2197	0.295	0.2090	0.295	4.0829	83.4807	2.0915	24.6602	39.5640	42	42.7345	78.1898
2.3122	2.8	70	1.9703	0.2923	0.33	0.3951	0.33	4.1017	83.4807	2.0915	24.6602	39.5640	47	42.7345	78.1898
2.3122	3.2	80	1.8818	0.3441	0.395	0.4073	0.395	4.1170	83.4807	2.0915	24.6602	39.5640	49	42.7345	78.1898
2.3122	3.6	90	1.7649	0.4158	0.44	0.4853	0.44	4.1182	83.4807	2.0915	24.6602	39.5640	45	42.7345	78.1898
2.3122	4.0	100	1.6408	0.5143	0.53	0.5429	0.53	4.1156	83.4807	2.0916	24.6602	39.5640	48	42.7345	78.1898
2.3122	4.4	110	1.5896	0.5167	0.535	0.5320	0.535	4.1162	83.4807	2.0915	24.6602	39.5640	46	42.7345	78.1898
2.3122	4.8	120	1.4783	0.5627	0.575	0.5692	0.575	4.1160	83.4807	2.0915	24.6602	39.5640	51	42.7345	78.1898
2.3122	5.2	130	1.3900	0.5844	0.595	0.6033	0.595	4.1169	83.4807	2.0915	24.6602	39.5640	57	42.7345	78.1898
2.3122	5.6	140	1.3547	0.6052	0.625	0.6127	0.625	4.1181	83.4807	2.0915	24.6602	39.5640	46	42.7345	78.1898
2.3122	6.0	150	1.2983	0.6032	0.6	0.6455	0.6	4.0997	83.4807	2.0915	24.6602	39.5640	48	42.7345	78.1898
2.3122	6.4	160	1.2805	0.5972	0.615	0.6058	0.615	4.1017	83.4807	2.0915	24.6602	39.5640	55	42.7345	78.1898
2.3122	6.8	170	1.2105	0.6213	0.62	0.6325	0.62	4.1238	83.4807	2.0915	24.6602	39.5640	50	42.7345	78.1898
2.3122	7.2	180	1.2458	0.5944	0.615	0.5958	0.615	4.1257	83.4807	2.0915	24.6602	39.5640	45	42.7345	78.1898
2.3122	7.6	190	1.1695	0.6629	0.665	0.6736	0.665	4.1261	83.4807	2.0915	24.6602	39.5640	52	42.7345	78.1898
2.3122	8.0	200	1.1737	0.6383	0.645	0.6425	0.645	4.1259	83.4807	2.0915	24.6602	39.5640	54	42.7345	78.1898
2.3122	8.4	210	1.1540	0.6347	0.635	0.6418	0.635	4.1258	83.4807	2.0915	24.6602	39.5640	47	42.7345	78.1898
2.3122	8.8	220	1.1422	0.6322	0.64	0.6413	0.64	4.1251	83.4807	2.0915	24.6602	39.5640	50	42.7346	78.1898
2.3122	9.2	230	1.1422	0.6443	0.65	0.6575	0.65	4.1251	83.4807	2.0916	24.6602	39.5640	47	42.7346	78.1898
2.3122	9.6	240	1.1345	0.6345	0.64	0.6483	0.64	4.1032	83.4807	2.0915	24.6602	39.5640	44	42.7346	78.1898
2.3122	10.0	250	1.1327	0.6339	0.64	0.6436	0.64	4.1084	83.4807	2.0915	24.6602	39.5640	44	42.7346	78.1898

Framework versions

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