Upload log_ts_d4.txt with huggingface_hub
Browse files- log_ts_d4.txt +11 -0
log_ts_d4.txt
CHANGED
|
@@ -860,3 +860,14 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 860 |
|
| 861 |
|
| 862 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 863 |
01:42:09 pushed ts_d4.pt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 860 |
|
| 861 |
|
| 862 |
/tmp/ts_d4_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 863 |
01:42:09 pushed ts_d4.pt
|
| 864 |
+
01:42:09 pushed log_ts_d4.txt
|
| 865 |
+
01:42:24 step 69100 loss=2.7806 tok=1132.1M dt=9082
|
| 866 |
+
01:42:38 step 69200 loss=2.7482 tok=1133.8M dt=9096
|
| 867 |
+
01:42:52 step 69300 loss=2.7811 tok=1135.4M dt=9110
|
| 868 |
+
01:43:07 step 69400 loss=2.7792 tok=1137.0M dt=9125
|
| 869 |
+
01:43:21 step 69500 loss=2.8115 tok=1138.7M dt=9139
|
| 870 |
+
01:43:35 step 69600 loss=2.8472 tok=1140.3M dt=9153
|
| 871 |
+
01:43:50 step 69700 loss=2.8365 tok=1142.0M dt=9168
|
| 872 |
+
01:44:04 step 69800 loss=2.7985 tok=1143.6M dt=9183
|
| 873 |
+
01:44:19 step 69900 loss=2.7940 tok=1145.2M dt=9197
|
| 874 |
+
01:44:33 step 70000 loss=2.7817 tok=1146.9M dt=9211
|