ft_bs64_lr7_base_x8

damgomz/ft_bs64_lr7_base_x8

ft_bs64_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

18% 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)	28945.63649892807
Emissions (Co2eq in kg)	0.0189356286432173
CPU power (W)	42.5
GPU power (W)	[No GPU]
RAM power (W)	7.5
CPU energy (kWh)	0.341718781052364
GPU energy (kWh)	[No GPU]
RAM energy (kWh)	0.0603030155807732
Consumed energy (kWh)	0.4020217966331371
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)	0.05572035026043654
Emissions (Co2eq in kg)	0.011337040962080162

20 May 2024

Epoch	Train Loss	Test Loss	Accuracy	Recall
0	0.605284	0.559398	0.727541	0.823620
1	0.521418	0.518530	0.740795	0.834356
2	0.487186	0.492726	0.758468	0.835890
3	0.459882	0.469925	0.776141	0.832822
4	0.436708	0.451493	0.786451	0.848160
5	0.414721	0.432541	0.798233	0.815951
6	0.395287	0.419788	0.806333	0.819018
7	0.381209	0.413589	0.805596	0.868098
8	0.371399	0.402106	0.821060	0.858896
9	0.362982	0.403256	0.814433	0.878834
10	0.353726	0.393290	0.826215	0.848160
11	0.346824	0.389223	0.826215	0.852761
12	0.341413	0.385427	0.829161	0.846626
13	0.339145	0.385045	0.830633	0.835890
14	0.329240	0.386728	0.826215	0.874233
15	0.325913	0.383079	0.834315	0.825153
16	0.319987	0.381838	0.831370	0.840491
17	0.314436	0.383904	0.834315	0.871166
18	0.309196	0.386049	0.833579	0.881902
19	0.309234	0.411747	0.818115	0.923313