Automatic correction of README.md metadata. Contact website@huggingface.co for any question

Step... (249000/250000 | Loss: 1.714625358581543, Acc: 0.6543225646018982): 100%|██████████████████████████| 250000/250000 [35:27:20<00:00, 1.68s/it]

Step... (249000/250000 | Loss: 1.714625358581543, Acc: 0.6543225646018982): 100%|█████████████████████████▉| 249284/250000 [35:05:32<22:25, 1.88s/it]

Step... (247000/250000 | Loss: 1.7176971435546875, Acc: 0.6535604000091553): 99%|██████████████████████▊| 247327/250000 [34:04:54<1:23:09, 1.87s/it]

Step... (245000/250000 | Loss: 1.7181611061096191, Acc: 0.6538485884666443): 98%|██████████████████████▌| 245373/250000 [33:04:15<2:34:03, 2.00s/it]

Step... (243000/250000 | Loss: 1.716979742050171, Acc: 0.6531366109848022): 97%|███████████████████████▎| 243425/250000 [32:03:40<3:43:41, 2.04s/it]

Step... (241000/250000 | Loss: 1.715268850326538, Acc: 0.6540905833244324): 97%|███████████████████████▏| 241474/250000 [31:03:03<4:14:55, 1.79s/it]

Step... (239000/250000 | Loss: 1.7167365550994873, Acc: 0.6534386873245239): 96%|██████████████████████ | 239519/250000 [30:02:28<5:07:00, 1.76s/it]

Step... (237000/250000 | Loss: 1.718358039855957, Acc: 0.6541662812232971): 95%|██████████████████████▊ | 237537/250000 [29:01:07<6:13:02, 1.80s/it]

Step... (235000/250000 | Loss: 1.7170510292053223, Acc: 0.6536755561828613): 94%|█████████████████████▋ | 235578/250000 [28:00:29<6:44:34, 1.68s/it]

Step... (233000/250000 | Loss: 1.7149814367294312, Acc: 0.6539548635482788): 93%|█████████████████████▍ | 233614/250000 [26:59:54<9:31:17, 2.09s/it]

Step... (231000/250000 | Loss: 1.7201117277145386, Acc: 0.6534011363983154): 93%|█████████████████████▎ | 231640/250000 [25:59:01<9:47:10, 1.92s/it]

Step... (229000/250000 | Loss: 1.7163493633270264, Acc: 0.6544609665870667): 92%|█████████████████████▏ | 229680/250000 [24:58:27<9:50:45, 1.74s/it]

Step... (227000/250000 | Loss: 1.7146042585372925, Acc: 0.6542283296585083): 91%|████████████████████ | 227713/250000 [23:57:48<11:56:53, 1.93s/it]

Step... (225000/250000 | Loss: 1.7183051109313965, Acc: 0.653299868106842): 90%|████████████████████▊ | 225735/250000 [22:56:46<14:48:36, 2.20s/it]

Step... (223000/250000 | Loss: 1.7223879098892212, Acc: 0.6536948680877686): 90%|███████████████████▋ | 223771/250000 [21:56:09<13:03:27, 1.79s/it]

Step... (221000/250000 | Loss: 1.7178878784179688, Acc: 0.6537612080574036): 89%|███████████████████▌ | 221765/250000 [20:54:21<15:22:31, 1.96s/it]

Step... (219000/250000 | Loss: 1.7199716567993164, Acc: 0.6531535983085632): 88%|███████████████████▎ | 219795/250000 [19:53:40<15:42:29, 1.87s/it]

Step... (217000/250000 | Loss: 1.7164013385772705, Acc: 0.6539624929428101): 87%|███████████████████▏ | 217830/250000 [18:53:05<16:31:09, 1.85s/it]

Step... (215000/250000 | Loss: 1.7257192134857178, Acc: 0.6526839137077332): 86%|██████████████████▉ | 215865/250000 [17:52:25<17:22:49, 1.83s/it]

Step... (213000/250000 | Loss: 1.7249395847320557, Acc: 0.6525405049324036): 86%|██████████████████▊ | 213895/250000 [16:51:46<18:13:28, 1.82s/it]

Step... (211000/250000 | Loss: 1.7207177877426147, Acc: 0.6533975601196289): 85%|██████████████████▋ | 211920/250000 [15:51:10<20:07:10, 1.90s/it]

Step... (209000/250000 | Loss: 1.7272114753723145, Acc: 0.6517964005470276): 84%|██████████████████▍ | 209954/250000 [14:50:34<22:17:30, 2.00s/it]

Step... (207000/250000 | Loss: 1.7318421602249146, Acc: 0.651650071144104): 83%|███████████████████▏ | 207980/250000 [13:49:59<19:31:21, 1.67s/it]

Step... (204000/250000 | Loss: 1.7288177013397217, Acc: 0.652102530002594): 82%|██████████████████▊ | 204028/250000 [11:49:01<24:37:57, 1.93s/it]

Step... (202000/250000 | Loss: 1.7276959419250488, Acc: 0.6522585153579712): 81%|█████████████████▊ | 202056/250000 [10:48:26<24:11:21, 1.82s/it]

Step... (200000/250000 | Loss: 1.7357631921768188, Acc: 0.6514398455619812): 80%|██████████████████▍ | 200090/250000 [9:47:49<26:24:09, 1.90s/it]

Step... (198000/250000 | Loss: 1.7336537837982178, Acc: 0.6512141227722168): 79%|██████████████████▏ | 198122/250000 [8:47:14<26:31:47, 1.84s/it]

Step... (196000/250000 | Loss: 1.7322393655776978, Acc: 0.6510968208312988): 78%|██████████████████ | 196143/250000 [7:46:37<26:35:29, 1.78s/it]

Step... (194000/250000 | Loss: 1.7338842153549194, Acc: 0.6511355042457581): 78%|█████████████████▊ | 194166/250000 [6:46:03<30:39:02, 1.98s/it]

Step... (192000/250000 | Loss: 1.7405705451965332, Acc: 0.6498751044273376): 77%|█████████████████▋ | 192193/250000 [5:45:27<29:58:25, 1.87s/it]

Step... (190000/250000 | Loss: 1.7414145469665527, Acc: 0.6501311659812927): 76%|█████████████████▍ | 190210/250000 [4:44:51<29:20:59, 1.77s/it]

Step... (188000/250000 | Loss: 1.7402708530426025, Acc: 0.6501697897911072): 75%|█████████████████▎ | 188213/250000 [3:43:59<31:25:35, 1.83s/it]

Step... (186000/250000 | Loss: 1.7381113767623901, Acc: 0.6502522826194763): 74%|█████████████████ | 186090/250000 [2:39:06<32:58:04, 1.86s/it]

Update README.md

Update README.md

Create README.md

Dataset stats

tfevents

PyTorch version 180k steps acc 0.6487

Training dump