Upload log_ts_d5.txt with huggingface_hub
Browse files- log_ts_d5.txt +11 -0
log_ts_d5.txt
CHANGED
|
@@ -791,3 +791,14 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 791 |
|
| 792 |
/tmp/ts_d5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 793 |
01:39:04 pushed ts_d5.pt
|
| 794 |
01:39:08 pulled global r=10 2.868 -> 2.936
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 791 |
|
| 792 |
/tmp/ts_d5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 793 |
01:39:04 pushed ts_d5.pt
|
| 794 |
01:39:08 pulled global r=10 2.868 -> 2.936
|
| 795 |
+
01:39:08 pushed log_ts_d5.txt
|
| 796 |
+
01:39:23 step 69100 loss=2.7872 tok=1132.1M dt=8902
|
| 797 |
+
01:39:39 step 69200 loss=2.8210 tok=1133.8M dt=8917
|
| 798 |
+
01:39:54 step 69300 loss=2.8461 tok=1135.4M dt=8932
|
| 799 |
+
01:40:09 step 69400 loss=2.7969 tok=1137.0M dt=8947
|
| 800 |
+
01:40:24 step 69500 loss=2.8214 tok=1138.7M dt=8963
|
| 801 |
+
01:40:40 step 69600 loss=2.7904 tok=1140.3M dt=8978
|
| 802 |
+
01:40:56 step 69700 loss=2.8315 tok=1142.0M dt=8994
|
| 803 |
+
01:41:12 step 69800 loss=2.8762 tok=1143.6M dt=9010
|
| 804 |
+
01:41:27 step 69900 loss=2.8600 tok=1145.2M dt=9026
|
| 805 |
+
01:41:44 step 70000 loss=2.7996 tok=1146.9M dt=9042
|