Upload log_ts_f_span.txt with huggingface_hub
Browse files- log_ts_f_span.txt +45 -23
log_ts_f_span.txt
CHANGED
|
@@ -1,26 +1,48 @@
|
|
| 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 |
-
10:25:58 step 78300 loss=2.7037 tok=1282.9M dt=31
|
| 9 |
-
10:26:05 step 78400 loss=2.6348 tok=1284.5M dt=39
|
| 10 |
-
10:26:12 step 78500 loss=2.6299 tok=1286.1M dt=46
|
| 11 |
-
10:26:19 step 78600 loss=2.5841 tok=1287.8M dt=53
|
| 12 |
-
10:26:27 step 78700 loss=2.6414 tok=1289.4M dt=60
|
| 13 |
-
10:26:34 step 78800 loss=2.6474 tok=1291.1M dt=67
|
| 14 |
-
10:26:41 step 78900 loss=2.6496 tok=1292.7M dt=74
|
| 15 |
-
10:26:48 step 79000 loss=2.6420 tok=1294.3M dt=81
|
| 16 |
-
10:26:49 pushed log_ts_f_span.txt
|
| 17 |
-
10:26:56 step 79100 loss=2.6169 tok=1296.0M dt=89
|
| 18 |
-
10:27:03 step 79200 loss=2.6711 tok=1297.6M dt=96
|
| 19 |
-
10:27:10 step 79300 loss=2.5754 tok=1299.3M dt=103
|
| 20 |
-
10:27:17 step 79400 loss=2.6232 tok=1300.9M dt=111
|
| 21 |
-
10:27:25 step 79500 loss=2.6928 tok=1302.5M dt=118
|
| 22 |
-
10:27:32 step 79600 loss=2.6117 tok=1304.2M dt=126
|
| 23 |
-
10:27:40 step 79700 loss=2.6112 tok=1305.8M dt=134
|
| 24 |
-
10:27:48 step 79800 loss=2.6100 tok=1307.4M dt=141
|
| 25 |
-
10:27:55 step 79900 loss=2.6102 tok=1309.1M dt=148
|
| 26 |
-
10:28:02 step 80000 loss=2.6073 tok=1310.7M dt=155
|
| 27 |
/tmp/ts_f_span_m.pt : 1%| | 646kB / 75.8MB [A[A
|
|
|
|
|
|
|
| 28 |
/tmp/ts_f_span_m.pt : 1%| | 646kB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 29 |
/tmp/ts_f_span_m.pt : 22%|βββ | 16.7MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 30 |
/tmp/ts_f_span_m.pt : 36%|ββββ | 27.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 31 |
/tmp/ts_f_span_m.pt : 36%|ββββ | 27.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 32 |
/tmp/ts_f_span_m.pt : 58%|ββββββ | 43.9MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 33 |
/tmp/ts_f_span_m.pt : 81%|ββββββββ | 61.1MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 34 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 35 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 36 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 37 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 38 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 39 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 40 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 41 |
/tmp/ts_f_span_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 42 |
/tmp/ts_f_span_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 43 |
/tmp/ts_f_span_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_span_m.pt : 1%| | 646kB / 75.8MB [A[A
|
| 9 |
+
|
| 10 |
+
|
| 11 |
/tmp/ts_f_span_m.pt : 1%| | 646kB / 75.8MB [A[A
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
/tmp/ts_f_span_m.pt : 22%|βββ | 16.7MB / 75.8MB [A[A
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
/tmp/ts_f_span_m.pt : 36%|ββββ | 27.3MB / 75.8MB [A[A
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
/tmp/ts_f_span_m.pt : 36%|ββββ | 27.3MB / 75.8MB [A[A
|
| 24 |
+
|
| 25 |
+
|
| 26 |
/tmp/ts_f_span_m.pt : 58%|ββββββ | 43.9MB / 75.8MB [A[A
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
/tmp/ts_f_span_m.pt : 81%|ββββββββ | 61.1MB / 75.8MB [A[A
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 39 |
+
|
| 40 |
+
|
| 41 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 42 |
+
|
| 43 |
+
|
| 44 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 45 |
+
|
| 46 |
+
|
| 47 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 48 |
+
|
| 49 |
+
|
| 50 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 51 |
+
|
| 52 |
+
|
| 53 |
/tmp/ts_f_span_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 54 |
+
|
| 55 |
+
|
| 56 |
/tmp/ts_f_span_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
|
| 60 |
/tmp/ts_f_span_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 61 |
+
|
| 62 |
+
|
| 63 |
/tmp/ts_f_span_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 64 |
+
10:29:18 pushed ts_f_span.pt
|
| 65 |
+
10:29:20 pulled global r=10 2.791 -> 2.892
|