Upload log_ts_e5.txt with huggingface_hub
Browse files- log_ts_e5.txt +41 -23
log_ts_e5.txt
CHANGED
|
@@ -1,26 +1,44 @@
|
|
| 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=3.2519 tok=1282.9M dt=53
|
| 9 |
-
02:02:49 step 78400 loss=3.2181 tok=1284.5M dt=68
|
| 10 |
-
02:03:03 step 78500 loss=3.4631 tok=1286.1M dt=82
|
| 11 |
-
02:03:18 step 78600 loss=3.4332 tok=1287.8M dt=97
|
| 12 |
-
02:03:33 step 78700 loss=3.1962 tok=1289.4M dt=112
|
| 13 |
-
02:03:48 step 78800 loss=3.2953 tok=1291.1M dt=127
|
| 14 |
-
02:04:02 step 78900 loss=3.1548 tok=1292.7M dt=141
|
| 15 |
-
02:04:17 step 79000 loss=3.2490 tok=1294.3M dt=156
|
| 16 |
-
02:04:18 pushed log_ts_e5.txt
|
| 17 |
-
02:04:33 step 79100 loss=3.3447 tok=1296.0M dt=172
|
| 18 |
-
02:04:47 step 79200 loss=3.2075 tok=1297.6M dt=186
|
| 19 |
-
02:05:02 step 79300 loss=3.1878 tok=1299.3M dt=201
|
| 20 |
-
02:05:16 step 79400 loss=3.1595 tok=1300.9M dt=215
|
| 21 |
-
02:05:31 step 79500 loss=3.2666 tok=1302.5M dt=230
|
| 22 |
-
02:05:45 step 79600 loss=3.3175 tok=1304.2M dt=244
|
| 23 |
-
02:06:00 step 79700 loss=3.3653 tok=1305.8M dt=259
|
| 24 |
-
02:06:14 step 79800 loss=3.2628 tok=1307.4M dt=273
|
| 25 |
-
02:06:28 step 79900 loss=3.2896 tok=1309.1M dt=287
|
| 26 |
-
02:06:43 step 80000 loss=3.3204 tok=1310.7M dt=302
|
| 27 |
/tmp/ts_e5_m.pt : 13%|ββ | 9.61MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 28 |
/tmp/ts_e5_m.pt : 13%|ββ | 9.61MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 29 |
/tmp/ts_e5_m.pt : 56%|ββββββ | 42.6MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 30 |
/tmp/ts_e5_m.pt : 66%|βββββββ | 49.7MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 31 |
/tmp/ts_e5_m.pt : 80%|ββββββββ | 60.5MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 32 |
/tmp/ts_e5_m.pt : 98%|ββββββββββ| 74.0MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 33 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 34 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 35 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 36 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 37 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 38 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 39 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 40 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 41 |
/tmp/ts_e5_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_e5_m.pt : 13%|ββ | 9.61MB / 75.8MB [A[A
|
| 9 |
+
|
| 10 |
+
|
| 11 |
/tmp/ts_e5_m.pt : 13%|ββ | 9.61MB / 75.8MB [A[A
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
/tmp/ts_e5_m.pt : 56%|ββββββ | 42.6MB / 75.8MB [A[A
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
/tmp/ts_e5_m.pt : 66%|βββββββ | 49.7MB / 75.8MB [A[A
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
/tmp/ts_e5_m.pt : 80%|ββββββββ | 60.5MB / 75.8MB [A[A
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
/tmp/ts_e5_m.pt : 98%|ββββββββββ| 74.0MB / 75.8MB [A[A
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 36 |
+
|
| 37 |
+
|
| 38 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 39 |
+
|
| 40 |
+
|
| 41 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 42 |
+
|
| 43 |
+
|
| 44 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 45 |
+
|
| 46 |
+
|
| 47 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 48 |
+
|
| 49 |
+
|
| 50 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 55 |
+
|
| 56 |
+
|
| 57 |
/tmp/ts_e5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 58 |
+
02:09:11 pushed ts_e5.pt
|
| 59 |
+
02:09:12 pulled global r=10 2.851 -> 2.936
|