Commit History

Step... (249001/250000 | Loss: 1.678702473640442, Acc: 0.660828173160553): 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 189999/250000 [97:45:10<29:36:08, 1.78s/it]
eafe079

versae commited on

Step... (238001/250000 | Loss: 1.6818329095840454, Acc: 0.660420298576355): 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 178271/250000 [91:38:03<37:33:10, 1.88s/it]
85052d2

versae commited on

Step... (232001/250000 | Loss: 1.6789664030075073, Acc: 0.6606228351593018): 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 172256/250000 [88:28:48<44:13:31, 2.05s/it]
f14b67f

versae commited on

Step... (219001/250000 | Loss: 1.6840890645980835, Acc: 0.6597731709480286): 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 159238/250000 [81:41:37<54:11:57, 2.15s/it]
491ee7c

versae commited on

Step... (214001/250000 | Loss: 1.6834079027175903, Acc: 0.6600053906440735): 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 154922/250000 [79:19:10<50:28:22, 1.91s/it]
eebed33

versae commited on

Step... (212001/250000 | Loss: 1.6889899969100952, Acc: 0.6588694453239441): 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 152455/250000 [78:01:35<56:19:35, 2.08s/it]
5b8d14e

versae commited on

Step... (208001/250000 | Loss: 1.6939743757247925, Acc: 0.6590701937675476): 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 148622/250000 [76:01:19<63:54:00, 2.27s/it]
2f2bdfd

versae commited on

Step... (200001/250000 | Loss: 1.6965291500091553, Acc: 0.6575480699539185): 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 140093/250000 [71:33:45<52:41:15, 1.73s/it]
61f844c

versae commited on

Model at 191k steps, acc 0.6562. Dataset stats
7163631

versae commited on

Step... (190001/250000 | Loss: 1.705819845199585, Acc: 0.6563901901245117): 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 130628/250000 [66:37:26<59:10:21, 1.78s/it]
e2f72a0

versae commited on

Dump 187k steps, acc 0.6574
9d93315

versae commited on