019-microsoft-MiniLM-finetuned-yahoo-80000_20000

This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8508
F1: 0.7322
Accuracy: 0.7357
Precision: 0.7318
Recall: 0.7357
System Ram Used: 4.0900
System Ram Total: 83.4807
Gpu Ram Allocated: 0.3934
Gpu Ram Cached: 16.0508
Gpu Ram Total: 39.5640
Gpu Utilization: 31
Disk Space Used: 26.4706
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: 5

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
1.5316	0.25	625	1.1302	0.6824	0.6928	0.6859	0.6928	4.1089	83.4807	0.3935	16.0508	39.5640	33	25.7180	78.1898
1.0615	0.5	1250	1.0022	0.7011	0.7049	0.7065	0.7049	3.8585	83.4807	0.3936	16.0508	39.5640	33	26.0913	78.1898
0.9804	0.75	1875	0.9258	0.7158	0.7191	0.7201	0.7191	3.8640	83.4807	0.3935	16.0508	39.5640	33	26.4646	78.1898
0.9244	1.0	2500	0.8795	0.7219	0.7286	0.7266	0.7286	3.8815	83.4807	0.3935	16.0508	39.5640	32	26.4649	78.1898
0.8471	1.25	3125	0.8886	0.7243	0.7305	0.7280	0.7305	4.0318	83.4807	0.3935	16.0508	39.5640	31	26.4653	78.1898
0.8294	1.5	3750	0.8648	0.7285	0.7303	0.7304	0.7303	3.8228	83.4807	0.3935	16.0508	39.5640	33	26.4656	78.1898
0.8229	1.75	4375	0.8477	0.7306	0.7347	0.7314	0.7347	3.8704	83.4807	0.3935	16.0508	39.5640	32	26.4658	78.1898
0.8227	2.0	5000	0.8514	0.7300	0.7321	0.7343	0.7321	3.8656	83.4807	0.3935	16.0508	39.5640	34	26.4661	78.1898
0.7515	2.25	5625	0.8580	0.7286	0.7327	0.7324	0.7327	4.0576	83.4807	0.3935	16.0508	39.5640	32	26.4664	78.1898
0.7523	2.5	6250	0.8498	0.7296	0.734	0.7314	0.734	3.8656	83.4807	0.3935	16.0508	39.5640	32	26.4666	78.1898
0.7396	2.75	6875	0.8403	0.7326	0.7365	0.7323	0.7365	3.8686	83.4807	0.3935	16.0508	39.5640	33	26.4669	78.1898
0.7308	3.0	7500	0.8414	0.7348	0.7378	0.7339	0.7378	3.8611	83.4807	0.3935	16.0508	39.5640	26	26.4671	78.1898
0.6929	3.25	8125	0.8551	0.7322	0.7350	0.7376	0.7350	4.0565	83.4807	0.3936	16.0508	39.5640	29	26.4680	78.1898
0.6772	3.5	8750	0.8471	0.7335	0.738	0.7327	0.738	3.8351	83.4807	0.3935	16.0508	39.5640	31	26.4684	78.1898
0.682	3.75	9375	0.8460	0.7311	0.735	0.7311	0.735	3.8782	83.4807	0.3935	16.0508	39.5640	34	26.4686	78.1898
0.6741	4.0	10000	0.8409	0.7335	0.7376	0.7330	0.7376	3.8848	83.4807	0.3935	16.0508	39.5640	31	26.4690	78.1898
0.6247	4.25	10625	0.8500	0.7332	0.736	0.7324	0.736	4.0838	83.4807	0.3935	16.0508	39.5640	32	26.4694	78.1898
0.6446	4.5	11250	0.8464	0.7323	0.7358	0.7320	0.7358	3.8687	83.4807	0.3936	16.0508	39.5640	31	26.4697	78.1898
0.6355	4.75	11875	0.8503	0.7311	0.7349	0.7308	0.7349	3.8853	83.4807	0.3935	16.0508	39.5640	30	26.4700	78.1898
0.6396	5.0	12500	0.8508	0.7322	0.7357	0.7318	0.7357	3.8995	83.4807	0.3935	16.0508	39.5640	33	26.4704	78.1898

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

diogopaes10/019-microsoft-MiniLM-finetuned-yahoo-80000_20000

019-microsoft-MiniLM-finetuned-yahoo-80000_20000

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions