006-microsoft-deberta-v3-base-finetuned-yahoo-80_20k

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: 1.5718
F1: 0.7212
Accuracy: 0.7212
Precision: 0.7217
Recall: 0.7212
System Ram Used: 4.3510
System Ram Total: 83.4807
Gpu Ram Allocated: 2.0903
Gpu Ram Cached: 34.3125
Gpu Ram Total: 39.5640
Gpu Utilization: 26
Disk Space Used: 42.2252
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: 8
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
1.0576	0.5	1250	0.8850	0.7207	0.727	0.7338	0.727	4.0147	83.4807	2.0903	34.3125	39.5640	26	24.9911	78.1898
0.853	1.0	2500	0.8239	0.7432	0.7461	0.7462	0.7461	4.0251	83.4807	2.0903	34.3125	39.5640	26	24.9919	78.1898
0.7364	1.5	3750	0.8151	0.7429	0.7478	0.7431	0.7478	4.0743	83.4807	2.0903	34.3125	39.5640	25	29.8278	78.1898
0.7345	2.0	5000	0.8102	0.7433	0.7470	0.7460	0.7470	4.0763	83.4807	2.0903	34.3125	39.5640	27	29.8285	78.1898
0.6184	2.5	6250	0.8222	0.7498	0.7518	0.7505	0.7518	4.0937	83.4807	2.0903	34.3125	39.5640	27	33.9630	78.1898
0.6174	3.0	7500	0.8322	0.7516	0.7545	0.7530	0.7545	4.0717	83.4807	2.0903	34.3125	39.5640	25	33.9634	78.1898
0.5036	3.5	8750	0.8948	0.7435	0.7476	0.7428	0.7476	4.1335	83.4807	2.0903	34.3125	39.5640	26	38.0971	78.1898
0.5149	4.0	10000	0.8892	0.7416	0.7451	0.7433	0.7451	4.1251	83.4807	2.0903	34.3125	39.5640	26	38.0980	78.1898
0.4106	4.5	11250	0.9957	0.7336	0.7345	0.7348	0.7345	4.1319	83.4807	2.0903	34.3125	39.5640	24	40.1601	78.1898
0.407	5.0	12500	0.9997	0.7318	0.7344	0.7332	0.7344	4.1372	83.4807	2.0903	34.3125	39.5640	25	40.1605	78.1898
0.3195	5.5	13750	1.0747	0.7320	0.736	0.7318	0.736	4.1359	83.4807	2.0903	34.3125	39.5640	25	42.2225	78.1898
0.3281	6.0	15000	1.1199	0.7300	0.7323	0.7313	0.7323	4.1438	83.4807	2.0903	34.3125	39.5640	26	42.2234	78.1898
0.2519	6.5	16250	1.2232	0.7299	0.7321	0.7295	0.7321	4.1640	83.4807	2.0903	34.3125	39.5640	26	42.2237	78.1898
0.2482	7.0	17500	1.2532	0.7274	0.7272	0.7282	0.7272	4.1578	83.4807	2.0903	34.3125	39.5640	26	42.2238	78.1898
0.1939	7.5	18750	1.3487	0.7222	0.7248	0.7215	0.7248	4.1702	83.4807	2.0903	34.3125	39.5640	26	42.2241	78.1898
0.1992	8.0	20000	1.3886	0.7197	0.7186	0.7218	0.7186	4.1572	83.4807	2.0903	34.3125	39.5640	27	42.2247	78.1898
0.1511	8.5	21250	1.4716	0.7197	0.7195	0.7204	0.7195	4.1566	83.4807	2.0903	34.3125	39.5640	25	42.2249	78.1898
0.1563	9.0	22500	1.4829	0.7223	0.7237	0.7221	0.7237	4.1650	83.4807	2.0903	34.3125	39.5640	27	42.2249	78.1898
0.1286	9.5	23750	1.5533	0.7210	0.7217	0.7210	0.7217	4.1784	83.4807	2.0903	34.3125	39.5640	26	42.2251	78.1898
0.1223	10.0	25000	1.5718	0.7212	0.7212	0.7217	0.7212	4.1618	83.4807	2.0903	34.3125	39.5640	26	42.2251	78.1898

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

diogopaes10/006-microsoft-deberta-v3-base-finetuned-yahoo-80_20k

006-microsoft-deberta-v3-base-finetuned-yahoo-80_20k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model