Upload log_ts_f_both.txt with huggingface_hub
Browse files- log_ts_f_both.txt +34 -23
log_ts_f_both.txt
CHANGED
|
@@ -1,26 +1,37 @@
|
|
| 1 |
/tmp/tiny_train.py:237: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior.
|
| 2 |
Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:836.)
|
| 3 |
total += float(l) * w
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
10:25:57 step 78300 loss=2.4356 tok=1282.9M dt=32
|
| 9 |
-
10:26:04 step 78400 loss=2.4045 tok=1284.5M dt=39
|
| 10 |
-
10:26:11 step 78500 loss=2.2719 tok=1286.1M dt=46
|
| 11 |
-
10:26:19 step 78600 loss=2.2379 tok=1287.8M dt=54
|
| 12 |
-
10:26:26 step 78700 loss=2.3549 tok=1289.4M dt=61
|
| 13 |
-
10:26:33 step 78800 loss=2.3268 tok=1291.1M dt=68
|
| 14 |
-
10:26:40 step 78900 loss=2.4014 tok=1292.7M dt=75
|
| 15 |
-
10:26:47 step 79000 loss=2.3770 tok=1294.3M dt=82
|
| 16 |
-
10:26:49 pushed log_ts_f_both.txt
|
| 17 |
-
10:26:57 step 79100 loss=2.2771 tok=1296.0M dt=92
|
| 18 |
-
10:27:04 step 79200 loss=2.3697 tok=1297.6M dt=99
|
| 19 |
-
10:27:11 step 79300 loss=2.3155 tok=1299.3M dt=106
|
| 20 |
-
10:27:18 step 79400 loss=2.3917 tok=1300.9M dt=113
|
| 21 |
-
10:27:26 step 79500 loss=2.3605 tok=1302.5M dt=121
|
| 22 |
-
10:27:33 step 79600 loss=2.2733 tok=1304.2M dt=129
|
| 23 |
-
10:27:41 step 79700 loss=2.2557 tok=1305.8M dt=136
|
| 24 |
-
10:27:48 step 79800 loss=2.3351 tok=1307.4M dt=143
|
| 25 |
-
10:27:55 step 79900 loss=2.2232 tok=1309.1M dt=150
|
| 26 |
-
10:28:02 step 80000 loss=2.2553 tok=1310.7M dt=157
|
| 27 |
/tmp/ts_f_both_m.pt : 24%|βββ | 18.5MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 28 |
/tmp/ts_f_both_m.pt : 24%|βββ | 18.5MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 29 |
/tmp/ts_f_both_m.pt : 72%|ββββββββ | 54.7MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 30 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 31 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 32 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 33 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 34 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 35 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 36 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 37 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 38 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 39 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
|
|
|
|
|
|
|
|
| 1 |
/tmp/tiny_train.py:237: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior.
|
| 2 |
Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:836.)
|
| 3 |
total += float(l) * w
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
/tmp/ts_f_both_m.pt : 24%|βββ | 18.5MB / 75.8MB [A[A
|
| 9 |
+
|
| 10 |
+
|
| 11 |
/tmp/ts_f_both_m.pt : 24%|βββ | 18.5MB / 75.8MB [A[A
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
/tmp/ts_f_both_m.pt : 72%|ββββββββ | 54.7MB / 75.8MB [A[A
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 24 |
+
|
| 25 |
+
|
| 26 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 27 |
+
|
| 28 |
+
|
| 29 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 30 |
+
|
| 31 |
+
|
| 32 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 33 |
+
|
| 34 |
+
|
| 35 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 36 |
+
|
| 37 |
+
|
| 38 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 39 |
+
|
| 40 |
+
|
| 41 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 46 |
+
|
| 47 |
+
|
| 48 |
/tmp/ts_f_both_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 49 |
+
10:29:18 pushed ts_f_both.pt
|
| 50 |
+
10:29:23 pulled global r=10 2.790 -> 2.892
|