Upload log_ts_e2.txt with huggingface_hub
Browse files- log_ts_e2.txt +43 -23
log_ts_e2.txt
CHANGED
|
@@ -1,26 +1,46 @@
|
|
| 1 |
/tmp/tiny_train.py:234: 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 |
-
02:02:34 step 78300 loss=3.2418 tok=1282.9M dt=52
|
| 9 |
-
02:02:48 step 78400 loss=3.1992 tok=1284.5M dt=66
|
| 10 |
-
02:03:02 step 78500 loss=3.4728 tok=1286.1M dt=81
|
| 11 |
-
02:03:17 step 78600 loss=3.4394 tok=1287.8M dt=96
|
| 12 |
-
02:03:31 step 78700 loss=3.2085 tok=1289.4M dt=110
|
| 13 |
-
02:03:46 step 78800 loss=3.2910 tok=1291.1M dt=124
|
| 14 |
-
02:04:00 step 78900 loss=3.1681 tok=1292.7M dt=139
|
| 15 |
-
02:04:14 step 79000 loss=3.2512 tok=1294.3M dt=153
|
| 16 |
-
02:04:15 pushed log_ts_e2.txt
|
| 17 |
-
02:04:30 step 79100 loss=3.3347 tok=1296.0M dt=169
|
| 18 |
-
02:04:44 step 79200 loss=3.2014 tok=1297.6M dt=183
|
| 19 |
-
02:04:58 step 79300 loss=3.1897 tok=1299.3M dt=197
|
| 20 |
-
02:05:12 step 79400 loss=3.1600 tok=1300.9M dt=211
|
| 21 |
-
02:05:27 step 79500 loss=3.2748 tok=1302.5M dt=225
|
| 22 |
-
02:05:41 step 79600 loss=3.3005 tok=1304.2M dt=240
|
| 23 |
-
02:05:55 step 79700 loss=3.3673 tok=1305.8M dt=254
|
| 24 |
-
02:06:09 step 79800 loss=3.2836 tok=1307.4M dt=268
|
| 25 |
-
02:06:23 step 79900 loss=3.2903 tok=1309.1M dt=282
|
| 26 |
-
02:06:38 step 80000 loss=3.3288 tok=1310.7M dt=296
|
| 27 |
/tmp/ts_e2_m.pt : 1%| | 646kB / 75.8MB [A[A
|
|
|
|
|
|
|
| 28 |
/tmp/ts_e2_m.pt : 1%| | 646kB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 29 |
/tmp/ts_e2_m.pt : 15%|ββ | 11.6MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 30 |
/tmp/ts_e2_m.pt : 48%|βββββ | 36.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 31 |
/tmp/ts_e2_m.pt : 72%|ββββββββ | 54.7MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 32 |
/tmp/ts_e2_m.pt : 96%|ββββββββββ| 72.6MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 33 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 34 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 35 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 36 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 37 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 38 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 39 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 40 |
/tmp/ts_e2_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 41 |
/tmp/ts_e2_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 42 |
/tmp/ts_e2_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
|
|
|
|
|
|
|
|
| 1 |
/tmp/tiny_train.py:234: 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_e2_m.pt : 1%| | 646kB / 75.8MB [A[A
|
| 9 |
+
|
| 10 |
+
|
| 11 |
/tmp/ts_e2_m.pt : 1%| | 646kB / 75.8MB [A[A
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
/tmp/ts_e2_m.pt : 15%|ββ | 11.6MB / 75.8MB [A[A
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
/tmp/ts_e2_m.pt : 48%|βββββ | 36.2MB / 75.8MB [A[A
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
/tmp/ts_e2_m.pt : 72%|ββββββββ | 54.7MB / 75.8MB [A[A
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
/tmp/ts_e2_m.pt : 96%|ββββββββββ| 72.6MB / 75.8MB [A[A
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 36 |
+
|
| 37 |
+
|
| 38 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 39 |
+
|
| 40 |
+
|
| 41 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 42 |
+
|
| 43 |
+
|
| 44 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 45 |
+
|
| 46 |
+
|
| 47 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 48 |
+
|
| 49 |
+
|
| 50 |
/tmp/ts_e2_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 51 |
+
|
| 52 |
+
|
| 53 |
/tmp/ts_e2_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
/tmp/ts_e2_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 58 |
+
|
| 59 |
+
|
| 60 |
/tmp/ts_e2_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 61 |
+
02:09:04 pushed ts_e2.pt
|
| 62 |
+
02:09:06 pulled global r=10 2.766 -> 2.858
|