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

44
training/figures/training_v4.csv Normal file
View File

@@ -0,0 +1,44 @@
step,epoch,loss,eval_loss
10,0.056617126680820945,1.5663956642150878,
20,0.11323425336164189,1.3516300201416016,
30,0.16985138004246284,1.1845409393310546,
40,0.22646850672328378,1.1037321090698242,
50,0.28308563340410475,1.0377551078796388,
50,0.28308563340410475,,1.010231852531433
60,0.33970276008492567,0.9829194068908691,
70,0.39631988676574664,0.8914342880249023,
80,0.45293701344656756,0.79852294921875,
90,0.5095541401273885,0.7313865184783935,
100,0.5661712668082095,0.6939316749572754,
100,0.5661712668082095,,0.6673692464828491
110,0.6227883934890305,0.6318693161010742,
120,0.6794055201698513,0.5733372211456299,
130,0.7360226468506723,0.5655224800109864,
140,0.7926397735314933,0.49826998710632325,
150,0.8492569002123143,0.48117914199829104,
150,0.8492569002123143,,0.474189430475235
160,0.9058740268931351,0.4512802600860596,
170,0.9624911535739561,0.43169336318969725,
180,1.0169851380042463,0.39495258331298827,
190,1.0736022646850671,0.37260124683380125,
200,1.1302193913658882,0.3555767059326172,
200,1.1302193913658882,,0.3825647532939911
210,1.186836518046709,0.3555564880371094,
220,1.2434536447275302,0.3253514528274536,
230,1.300070771408351,0.3274040222167969,
240,1.356687898089172,0.31757657527923583,
250,1.413305024769993,0.32180213928222656,
250,1.413305024769993,,0.3373807370662689
260,1.4699221514508138,0.2948040008544922,
270,1.5265392781316347,0.2999974489212036,
280,1.5831564048124558,0.2915226936340332,
290,1.6397735314932769,0.28573825359344485,
300,1.6963906581740975,0.28896660804748536,
300,1.6963906581740975,,0.31564027070999146
310,1.7530077848549186,0.28694982528686525,
320,1.8096249115357397,0.27899909019470215,
330,1.8662420382165605,0.2718695878982544,
340,1.9228591648973814,0.28831920623779295,
350,1.9794762915782025,0.28850746154785156,
350,1.9794762915782025,,0.30873769521713257
354,2.0,,0.3087170422077179
1 step epoch loss eval_loss
2 10 0.056617126680820945 1.5663956642150878
3 20 0.11323425336164189 1.3516300201416016
4 30 0.16985138004246284 1.1845409393310546
5 40 0.22646850672328378 1.1037321090698242
6 50 0.28308563340410475 1.0377551078796388
7 50 0.28308563340410475 1.010231852531433
8 60 0.33970276008492567 0.9829194068908691
9 70 0.39631988676574664 0.8914342880249023
10 80 0.45293701344656756 0.79852294921875
11 90 0.5095541401273885 0.7313865184783935
12 100 0.5661712668082095 0.6939316749572754
13 100 0.5661712668082095 0.6673692464828491
14 110 0.6227883934890305 0.6318693161010742
15 120 0.6794055201698513 0.5733372211456299
16 130 0.7360226468506723 0.5655224800109864
17 140 0.7926397735314933 0.49826998710632325
18 150 0.8492569002123143 0.48117914199829104
19 150 0.8492569002123143 0.474189430475235
20 160 0.9058740268931351 0.4512802600860596
21 170 0.9624911535739561 0.43169336318969725
22 180 1.0169851380042463 0.39495258331298827
23 190 1.0736022646850671 0.37260124683380125
24 200 1.1302193913658882 0.3555767059326172
25 200 1.1302193913658882 0.3825647532939911
26 210 1.186836518046709 0.3555564880371094
27 220 1.2434536447275302 0.3253514528274536
28 230 1.300070771408351 0.3274040222167969
29 240 1.356687898089172 0.31757657527923583
30 250 1.413305024769993 0.32180213928222656
31 250 1.413305024769993 0.3373807370662689
32 260 1.4699221514508138 0.2948040008544922
33 270 1.5265392781316347 0.2999974489212036
34 280 1.5831564048124558 0.2915226936340332
35 290 1.6397735314932769 0.28573825359344485
36 300 1.6963906581740975 0.28896660804748536
37 300 1.6963906581740975 0.31564027070999146
38 310 1.7530077848549186 0.28694982528686525
39 320 1.8096249115357397 0.27899909019470215
40 330 1.8662420382165605 0.2718695878982544
41 340 1.9228591648973814 0.28831920623779295
42 350 1.9794762915782025 0.28850746154785156
43 350 1.9794762915782025 0.30873769521713257
44 354 2.0 0.3087170422077179