ft_bs16_lr7_base_x8

damgomz/ft_bs16_lr7_base_x8

ft_bs16_lr7_base_x8 is a fill-mask model from damgomz. Use it when you need the model to fill a missing word. It is set up for transformers.

Downloads · 30 days

28% of all-time downloads

All-time downloads

Public

Parameters

61.3M

4.9 GB on disk

Likes

Public

Repo makeup

Click a slice to open those files.

.safetensors245 MB · 99%

From the Hugging Face model README

Metric	Value
Duration (in seconds)	29341.298537492752
Emissions (Co2eq in kg)	0.0191944486380988
CPU power (W)	42.5
GPU power (W)	[No GPU]
RAM power (W)	7.5
CPU energy (kWh)	0.3463896830707782
GPU energy (kWh)	[No GPU]
RAM energy (kWh)	0.0611271135598421
Consumed energy (kWh)	0.4075167966306212
Country name	Switzerland
Cloud provider	nan
Cloud region	nan
CPU count	3
CPU model	Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz
GPU count	nan
GPU model	nan

Metric	Value
CPU energy (kWh)	0.056481999684673545
Emissions (Co2eq in kg)	0.011492008593851327

20 May 2024

Epoch	Train Loss	Test Loss	Accuracy	Recall
0	0.544017	0.498747	0.756259	0.820552
1	0.458398	0.447891	0.789396	0.815951
2	0.412619	0.418534	0.809278	0.809816
3	0.383563	0.402267	0.819588	0.832822
4	0.362502	0.394697	0.828424	0.868098
5	0.350171	0.388855	0.824742	0.814417
6	0.338813	0.390055	0.827688	0.822086
7	0.331673	0.384974	0.829897	0.820552
8	0.321403	0.382093	0.830633	0.832822
9	0.310836	0.387218	0.823270	0.783742
10	0.304103	0.398507	0.818115	0.763804
11	0.296614	0.390856	0.832106	0.888037
12	0.288897	0.393553	0.825479	0.792945
13	0.282550	0.395344	0.830633	0.878834
14	0.273857	0.394697	0.829897	0.846626
15	0.263546	0.403545	0.824006	0.796012
16	0.262119	0.399805	0.826215	0.806748
17	0.249052	0.404904	0.826215	0.799080
18	0.239922	0.407600	0.823270	0.846626
19	0.231717	0.422615	0.819588	0.780675