Upload log_ts_e4.txt with huggingface_hub
Browse files- log_ts_e4.txt +43 -23
log_ts_e4.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 |
-
02:02:32 step 78300 loss=3.2437 tok=1282.9M dt=50
|
| 9 |
-
02:02:46 step 78400 loss=3.2071 tok=1284.5M dt=63
|
| 10 |
-
02:02:59 step 78500 loss=3.4786 tok=1286.1M dt=77
|
| 11 |
-
02:03:13 step 78600 loss=3.4313 tok=1287.8M dt=91
|
| 12 |
-
02:03:27 step 78700 loss=3.2091 tok=1289.4M dt=104
|
| 13 |
-
02:03:40 step 78800 loss=3.3013 tok=1291.1M dt=118
|
| 14 |
-
02:03:54 step 78900 loss=3.1614 tok=1292.7M dt=132
|
| 15 |
-
02:04:08 step 79000 loss=3.2536 tok=1294.3M dt=146
|
| 16 |
-
02:04:09 pushed log_ts_e4.txt
|
| 17 |
-
02:04:22 step 79100 loss=3.3400 tok=1296.0M dt=160
|
| 18 |
-
02:04:36 step 79200 loss=3.2032 tok=1297.6M dt=174
|
| 19 |
-
02:04:49 step 79300 loss=3.1819 tok=1299.3M dt=187
|
| 20 |
-
02:05:04 step 79400 loss=3.1554 tok=1300.9M dt=201
|
| 21 |
-
02:05:18 step 79500 loss=3.2742 tok=1302.5M dt=215
|
| 22 |
-
02:05:31 step 79600 loss=3.3149 tok=1304.2M dt=229
|
| 23 |
-
02:05:45 step 79700 loss=3.3810 tok=1305.8M dt=243
|
| 24 |
-
02:05:58 step 79800 loss=3.2682 tok=1307.4M dt=256
|
| 25 |
-
02:06:12 step 79900 loss=3.2823 tok=1309.1M dt=269
|
| 26 |
-
02:06:25 step 80000 loss=3.3228 tok=1310.7M dt=283
|
| 27 |
/tmp/ts_e4_m.pt : 1%| | 645kB / 75.8MB [A[A
|
|
|
|
|
|
|
| 28 |
/tmp/ts_e4_m.pt : 1%| | 645kB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 29 |
/tmp/ts_e4_m.pt : 25%|βββ | 19.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 30 |
/tmp/ts_e4_m.pt : 78%|ββββββββ | 58.9MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 31 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 32 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 33 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 34 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 35 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 36 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 37 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 38 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 39 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 40 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 41 |
/tmp/ts_e4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 42 |
/tmp/ts_e4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 43 |
/tmp/ts_e4_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_e4_m.pt : 1%| | 645kB / 75.8MB [A[A
|
| 9 |
+
|
| 10 |
+
|
| 11 |
/tmp/ts_e4_m.pt : 1%| | 645kB / 75.8MB [A[A
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
/tmp/ts_e4_m.pt : 25%|βββ | 19.3MB / 75.8MB [A[A
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
/tmp/ts_e4_m.pt : 78%|ββββββββ | 58.9MB / 75.8MB [A[A
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 28 |
+
|
| 29 |
+
|
| 30 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 31 |
+
|
| 32 |
+
|
| 33 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 34 |
+
|
| 35 |
+
|
| 36 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 37 |
+
|
| 38 |
+
|
| 39 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 40 |
+
|
| 41 |
+
|
| 42 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 43 |
+
|
| 44 |
+
|
| 45 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 46 |
+
|
| 47 |
+
|
| 48 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 49 |
+
|
| 50 |
+
|
| 51 |
/tmp/ts_e4_m.pt : 99%|ββββββββββ| 75.2MB / 75.8MB [A[A
|
| 52 |
+
|
| 53 |
+
|
| 54 |
/tmp/ts_e4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
|
| 58 |
/tmp/ts_e4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 59 |
+
|
| 60 |
+
|
| 61 |
/tmp/ts_e4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 62 |
+
02:08:46 pushed ts_e4.pt
|
| 63 |
+
02:08:49 pulled global r=10 2.991 -> 3.054
|