017-microsoft-MiniLM-finetuned-yahoo-800_200

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: 1.4048
F1: 0.6237
Accuracy: 0.63
Precision: 0.6273
Recall: 0.63
System Ram Used: 3.8778
System Ram Total: 83.4807
Gpu Ram Allocated: 0.3903
Gpu Ram Cached: 12.8340
Gpu Ram Total: 39.5640
Gpu Utilization: 32
Disk Space Used: 25.4337
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: 25

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
2.3021	1.28	32	2.2975	0.0519	0.12	0.1102	0.12	3.8424	83.4807	0.3904	12.8340	39.5640	29	24.5606	78.1898
2.2615	2.56	64	2.1926	0.2339	0.31	0.4649	0.31	3.8514	83.4807	0.3904	12.8340	39.5640	30	24.5606	78.1898
2.0677	3.84	96	1.9658	0.4301	0.51	0.3950	0.51	3.8537	83.4807	0.3905	12.8340	39.5640	22	24.5606	78.1898
1.8562	5.12	128	1.8383	0.4655	0.545	0.4587	0.545	3.8574	83.4807	0.3904	12.8340	39.5640	41	24.5606	78.1898
1.6929	6.4	160	1.7403	0.4942	0.555	0.5261	0.555	3.8549	83.4807	0.3904	12.8340	39.5640	29	24.5607	78.1898
1.5569	7.68	192	1.6663	0.5467	0.585	0.6496	0.585	3.8549	83.4807	0.3904	12.8340	39.5640	37	24.5607	78.1898
1.4636	8.96	224	1.6123	0.5475	0.58	0.5539	0.58	3.8539	83.4807	0.3904	12.8340	39.5640	30	24.5607	78.1898
1.3683	10.24	256	1.5615	0.5829	0.595	0.6016	0.595	3.8527	83.4807	0.3904	12.8340	39.5640	41	24.5607	78.1898
1.2649	11.52	288	1.5261	0.5904	0.61	0.6243	0.61	3.8646	83.4807	0.3904	12.8340	39.5640	30	24.5607	78.1898
1.1968	12.8	320	1.4976	0.6012	0.615	0.6070	0.615	3.8766	83.4807	0.3904	12.8340	39.5640	45	24.5607	78.1898
1.1291	14.08	352	1.4756	0.5983	0.615	0.6164	0.615	3.8749	83.4807	0.3905	12.8340	39.5640	47	24.5607	78.1898
1.0673	15.36	384	1.4660	0.6064	0.62	0.6258	0.62	3.8752	83.4807	0.3907	12.8340	39.5640	35	24.5607	78.1898
0.9884	16.64	416	1.4410	0.6135	0.625	0.6204	0.625	3.8757	83.4807	0.3904	12.8340	39.5640	33	24.5608	78.1898
0.9743	17.92	448	1.4328	0.6233	0.635	0.6343	0.635	3.8747	83.4807	0.3905	12.8340	39.5640	44	24.5608	78.1898
0.926	19.2	480	1.4344	0.6088	0.615	0.6238	0.615	3.8742	83.4807	0.3904	12.8340	39.5640	31	24.5608	78.1898
0.8815	20.48	512	1.4282	0.6235	0.625	0.6350	0.625	4.0591	83.4807	0.3904	12.8340	39.5640	43	25.4337	78.1898
0.8613	21.76	544	1.4146	0.6329	0.635	0.6408	0.635	4.0655	83.4807	0.3904	12.8340	39.5640	26	25.4337	78.1898
0.8466	23.04	576	1.4086	0.6318	0.635	0.6415	0.635	4.0544	83.4807	0.3904	12.8340	39.5640	35	25.4337	78.1898
0.8282	24.32	608	1.4058	0.6243	0.63	0.6319	0.63	3.8886	83.4807	0.3904	12.8340	39.5640	27	25.4337	78.1898

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

diogopaes10/017-microsoft-MiniLM-finetuned-yahoo-800_200

017-microsoft-MiniLM-finetuned-yahoo-800_200

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions