Upload log_ts_e1.txt with huggingface_hub
Browse files- log_ts_e1.txt +40 -23
log_ts_e1.txt
CHANGED
|
@@ -1,26 +1,43 @@
|
|
| 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 |
-
02:02:37 step 78300 loss=3.2512 tok=1282.9M dt=55
|
| 9 |
-
02:02:52 step 78400 loss=3.2114 tok=1284.5M dt=69
|
| 10 |
-
02:03:07 step 78500 loss=3.4774 tok=1286.1M dt=85
|
| 11 |
-
02:03:23 step 78600 loss=3.4400 tok=1287.8M dt=100
|
| 12 |
-
02:03:37 step 78700 loss=3.1952 tok=1289.4M dt=115
|
| 13 |
-
02:03:52 step 78800 loss=3.2841 tok=1291.1M dt=130
|
| 14 |
-
02:04:07 step 78900 loss=3.1681 tok=1292.7M dt=145
|
| 15 |
-
02:04:22 step 79000 loss=3.2480 tok=1294.3M dt=159
|
| 16 |
-
02:04:23 pushed log_ts_e1.txt
|
| 17 |
-
02:04:37 step 79100 loss=3.3462 tok=1296.0M dt=175
|
| 18 |
-
02:04:52 step 79200 loss=3.2001 tok=1297.6M dt=189
|
| 19 |
-
02:05:06 step 79300 loss=3.2078 tok=1299.3M dt=204
|
| 20 |
-
02:05:21 step 79400 loss=3.1641 tok=1300.9M dt=218
|
| 21 |
-
02:05:35 step 79500 loss=3.2677 tok=1302.5M dt=233
|
| 22 |
-
02:05:50 step 79600 loss=3.3151 tok=1304.2M dt=247
|
| 23 |
-
02:06:05 step 79700 loss=3.3720 tok=1305.8M dt=262
|
| 24 |
-
02:06:19 step 79800 loss=3.2738 tok=1307.4M dt=276
|
| 25 |
-
02:06:33 step 79900 loss=3.2880 tok=1309.1M dt=291
|
| 26 |
-
02:06:49 step 80000 loss=3.3326 tok=1310.7M dt=307
|
| 27 |
/tmp/ts_e1_m.pt : 1%| | 648kB / 75.8MB [A[A
|
|
|
|
|
|
|
| 28 |
/tmp/ts_e1_m.pt : 1%| | 648kB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 29 |
/tmp/ts_e1_m.pt : 20%|ββ | 14.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 30 |
/tmp/ts_e1_m.pt : 55%|ββββββ | 41.7MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 31 |
/tmp/ts_e1_m.pt : 87%|βββββββββ | 65.7MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 32 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 33 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 34 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 35 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 36 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 37 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 38 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
|
|
|
| 39 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 40 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
|
|
|
|
|
|
| 41 |
/tmp/ts_e1_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_e1_m.pt : 1%| | 648kB / 75.8MB [A[A
|
| 9 |
+
|
| 10 |
+
|
| 11 |
/tmp/ts_e1_m.pt : 1%| | 648kB / 75.8MB [A[A
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
/tmp/ts_e1_m.pt : 20%|ββ | 14.8MB / 75.8MB [A[A
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
/tmp/ts_e1_m.pt : 55%|ββββββ | 41.7MB / 75.8MB [A[A
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
/tmp/ts_e1_m.pt : 87%|βββββββββ | 65.7MB / 75.8MB [A[A
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
| 32 |
+
|
| 33 |
+
|
| 34 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
| 35 |
+
|
| 36 |
+
|
| 37 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
| 38 |
+
|
| 39 |
+
|
| 40 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
| 41 |
+
|
| 42 |
+
|
| 43 |
/tmp/ts_e1_m.pt : 99%|ββββββββββ| 75.3MB / 75.8MB [A[A
|
| 44 |
+
|
| 45 |
+
|
| 46 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 51 |
+
|
| 52 |
+
|
| 53 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB [A[A
|
| 54 |
+
|
| 55 |
+
|
| 56 |
/tmp/ts_e1_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 57 |
+
02:09:21 pushed ts_e1.pt
|
| 58 |
+
02:09:24 pulled global r=10 2.764 -> 2.838
|