NyayaLabs98/nyaya-3b-v3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: NyayaLabs98/nyaya-3b-v3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-27 22:08:26 +08:00
commit ff5f5ef338
37 changed files with 2009 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
training/figures/training_v1.csv Normal file
View File

@@ -0,0 +1,20 @@
step,epoch,loss,learning_rate,grad_norm,mean_token_accuracy
10,0.050761421319796954,2.3324300765991213,9.993914063644052e-05,1.1503950357437134,0.5158391281962394
20,0.10152284263959391,1.2313983917236329,9.886131295443003e-05,0.4007212817668915,0.6984569907188416
30,0.15228426395939088,1.0970629692077636,9.646456421395446e-05,0.34395045042037964,0.7340504214167595
40,0.20304568527918782,1.0139848709106445,9.281359022841965e-05,0.3407576382160187,0.7466330319643021
50,0.25380710659898476,0.9398991584777832,8.800694230932884e-05,0.305820107460022,0.759013494849205
60,0.30456852791878175,0.9580072402954102,8.2174367055326e-05,0.3269255459308624,0.7577866345643998
70,0.3553299492385787,0.920842170715332,7.547330408197695e-05,0.3835376501083374,0.7638022676110268
80,0.40609137055837563,0.8990132331848144,6.808463622961578e-05,0.3853282332420349,0.7671428829431534
90,0.45685279187817257,0.8844776153564453,6.0207806964560584e-05,0.3447255492210388,0.7684156641364097
100,0.5076142131979695,0.8999717712402344,5.205543677045049e-05,0.44750770926475525,0.7692662417888642
110,0.5583756345177665,0.8709278106689453,4.384758385029457e-05,0.41725635528564453,0.772255252301693
120,0.6091370558375635,0.8635953903198242,3.580580406099893e-05,0.4176587164402008,0.7729698359966278
130,0.6598984771573604,0.8605537414550781,2.8147170421488272e-05,0.42824825644493103,0.7755630746483803
140,0.7106598984771574,0.8298810005187989,2.1078413626773546e-05,0.42753881216049194,0.7806227177381515
150,0.7614213197969543,0.848197078704834,1.4790341733986085e-05,0.37514036893844604,0.7789115384221077
160,0.8121827411167513,0.8550724983215332,9.452689650664515e-06,0.44037938117980957,0.778565688431263
170,0.8629441624365483,0.8581902503967285,5.209537453863289e-06,0.42417141795158386,0.7754479616880416
180,0.9137055837563451,0.8792120933532714,2.1754212141102346e-06,0.47580745816230774,0.7731257915496826
190,0.9644670050761421,0.8656046867370606,4.322413053509944e-07,0.474467396736145,0.7720748305320739
1 step epoch loss learning_rate grad_norm mean_token_accuracy
2 10 0.050761421319796954 2.3324300765991213 9.993914063644052e-05 1.1503950357437134 0.5158391281962394
3 20 0.10152284263959391 1.2313983917236329 9.886131295443003e-05 0.4007212817668915 0.6984569907188416
4 30 0.15228426395939088 1.0970629692077636 9.646456421395446e-05 0.34395045042037964 0.7340504214167595
5 40 0.20304568527918782 1.0139848709106445 9.281359022841965e-05 0.3407576382160187 0.7466330319643021
6 50 0.25380710659898476 0.9398991584777832 8.800694230932884e-05 0.305820107460022 0.759013494849205
7 60 0.30456852791878175 0.9580072402954102 8.2174367055326e-05 0.3269255459308624 0.7577866345643998
8 70 0.3553299492385787 0.920842170715332 7.547330408197695e-05 0.3835376501083374 0.7638022676110268
9 80 0.40609137055837563 0.8990132331848144 6.808463622961578e-05 0.3853282332420349 0.7671428829431534
10 90 0.45685279187817257 0.8844776153564453 6.0207806964560584e-05 0.3447255492210388 0.7684156641364097
11 100 0.5076142131979695 0.8999717712402344 5.205543677045049e-05 0.44750770926475525 0.7692662417888642
12 110 0.5583756345177665 0.8709278106689453 4.384758385029457e-05 0.41725635528564453 0.772255252301693
13 120 0.6091370558375635 0.8635953903198242 3.580580406099893e-05 0.4176587164402008 0.7729698359966278
14 130 0.6598984771573604 0.8605537414550781 2.8147170421488272e-05 0.42824825644493103 0.7755630746483803
15 140 0.7106598984771574 0.8298810005187989 2.1078413626773546e-05 0.42753881216049194 0.7806227177381515
16 150 0.7614213197969543 0.848197078704834 1.4790341733986085e-05 0.37514036893844604 0.7789115384221077
17 160 0.8121827411167513 0.8550724983215332 9.452689650664515e-06 0.44037938117980957 0.778565688431263
18 170 0.8629441624365483 0.8581902503967285 5.209537453863289e-06 0.42417141795158386 0.7754479616880416
19 180 0.9137055837563451 0.8792120933532714 2.1754212141102346e-06 0.47580745816230774 0.7731257915496826
20 190 0.9644670050761421 0.8656046867370606 4.322413053509944e-07 0.474467396736145 0.7720748305320739