Upload log_ts_d4.txt with huggingface_hub
Browse files- log_ts_d4.txt +47 -23
log_ts_d4.txt
CHANGED
|
@@ -794,26 +794,50 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 794 |
|
| 795 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 796 |
|
| 797 |
|
| 798 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 799 |
-
|
| 800 |
-
|
| 801 |
-
|
| 802 |
-
|
| 803 |
-
01:28:06 step 63300 loss=2.7911 tok=1037.1M dt=8224
|
| 804 |
-
01:28:20 step 63400 loss=2.7706 tok=1038.7M dt=8239
|
| 805 |
-
01:28:35 step 63500 loss=2.8239 tok=1040.4M dt=8253
|
| 806 |
-
01:28:49 step 63600 loss=2.8323 tok=1042.0M dt=8267
|
| 807 |
-
01:29:04 step 63700 loss=2.8402 tok=1043.7M dt=8282
|
| 808 |
-
01:29:18 step 63800 loss=2.8004 tok=1045.3M dt=8296
|
| 809 |
-
01:29:33 step 63900 loss=2.7950 tok=1046.9M dt=8311
|
| 810 |
-
01:29:47 step 64000 loss=2.8262 tok=1048.6M dt=8325
|
| 811 |
-
01:29:48 pushed log_ts_d4.txt
|
| 812 |
-
01:30:02 step 64100 loss=2.7767 tok=1050.2M dt=8341
|
| 813 |
-
01:30:17 step 64200 loss=2.8513 tok=1051.9M dt=8355
|
| 814 |
-
01:30:31 step 64300 loss=2.8074 tok=1053.5M dt=8370
|
| 815 |
-
01:30:46 step 64400 loss=2.8179 tok=1055.1M dt=8384
|
| 816 |
-
01:31:00 step 64500 loss=2.8342 tok=1056.8M dt=8398
|
| 817 |
-
01:31:14 step 64600 loss=2.7969 tok=1058.4M dt=8412
|
| 818 |
-
01:31:29 step 64700 loss=2.8430 tok=1060.0M dt=8427
|
| 819 |
-
01:31:44 step 64800 loss=2.7906 tok=1061.7M dt=8442
|
| 820 |
-
01:31:58 step 64900 loss=2.8402 tok=1063.3M dt=8456
|
| 821 |
-
01:32:12 step 65000 loss=2.8033 tok=1065.0M dt=8470
|
| 822 |
/tmp/ts_d4_m.pt : 25%|βββ | 19.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 823 |
/tmp/ts_d4_m.pt : 25%|βββ | 19.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 824 |
/tmp/ts_d4_m.pt : 76%|ββββββββ | 57.9MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 825 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 826 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 827 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 828 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 829 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 830 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 831 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 832 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 833 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 834 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 794 |
|
| 795 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 796 |
|
| 797 |
|
| 798 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 799 |
+
|
| 800 |
+
|
| 801 |
+
|
| 802 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 803 |
/tmp/ts_d4_m.pt : 25%|βββ | 19.2MB / 75.8MB [A[A
|
| 804 |
+
|
| 805 |
+
|
| 806 |
/tmp/ts_d4_m.pt : 25%|βββ | 19.2MB / 75.8MB [A[A
|
| 807 |
+
|
| 808 |
+
|
| 809 |
+
|
| 810 |
/tmp/ts_d4_m.pt : 76%|ββββββββ | 57.9MB / 75.8MB [A[A
|
| 811 |
+
|
| 812 |
+
|
| 813 |
+
|
| 814 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 815 |
+
|
| 816 |
+
|
| 817 |
+
|
| 818 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 819 |
+
|
| 820 |
+
|
| 821 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 822 |
+
|
| 823 |
+
|
| 824 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 825 |
+
|
| 826 |
+
|
| 827 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 828 |
+
|
| 829 |
+
|
| 830 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 831 |
+
|
| 832 |
+
|
| 833 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 834 |
+
|
| 835 |
+
|
| 836 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 837 |
+
|
| 838 |
+
|
| 839 |
+
|
| 840 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 841 |
+
|
| 842 |
+
|
| 843 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 844 |
+
01:34:51 pushed ts_d4.pt
|
| 845 |
+
01:34:53 pulled global r=10 3.031 -> 3.054
|
| 846 |
+
01:34:54 push fail (Request ID: Root=1-6aa2093e-118170742a4fb3772d26cb0f;bde908d8-853b-437e-b649-9cb00994d11f)
|
| 847 |
+
|
| 848 |
+
429 Too Many Requests for u
|
| 849 |
+
01:35:08 step 66100 loss=2.7837 tok=1083.0M dt=8646
|
| 850 |
+
01:35:23 step 66200 loss=2.8340 tok=1084.6M dt=8661
|
| 851 |
+
01:35:37 step 66300 loss=2.8282 tok=1086.3M dt=8675
|
| 852 |
+
01:35:52 step 66400 loss=2.8095 tok=1087.9M dt=8690
|
| 853 |
+
01:36:06 step 66500 loss=2.8097 tok=1089.5M dt=8704
|
| 854 |
+
01:36:20 step 66600 loss=2.7979 tok=1091.2M dt=8719
|
| 855 |
+
01:36:35 step 66700 loss=2.8399 tok=1092.8M dt=8733
|
| 856 |
+
01:36:49 step 66800 loss=2.8727 tok=1094.5M dt=8747
|
| 857 |
+
01:37:03 step 66900 loss=2.8401 tok=1096.1M dt=8762
|
| 858 |
+
01:37:17 step 67000 loss=2.7748 tok=1097.7M dt=8775
|