Upload log_ts_d5.txt with huggingface_hub
Browse files- log_ts_d5.txt +11 -0
log_ts_d5.txt
CHANGED
|
@@ -765,3 +765,14 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 765 |
01:33:20 step 66800 loss=2.8412 tok=1094.5M dt=8539
|
| 766 |
01:33:35 step 66900 loss=2.8004 tok=1096.1M dt=8554
|
| 767 |
01:33:50 step 67000 loss=2.7985 tok=1097.7M dt=8569
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 765 |
01:33:20 step 66800 loss=2.8412 tok=1094.5M dt=8539
|
| 766 |
01:33:35 step 66900 loss=2.8004 tok=1096.1M dt=8554
|
| 767 |
01:33:50 step 67000 loss=2.7985 tok=1097.7M dt=8569
|
| 768 |
+
01:33:51 pushed log_ts_d5.txt
|
| 769 |
+
01:34:07 step 67100 loss=2.7796 tok=1099.4M dt=8585
|
| 770 |
+
01:34:23 step 67200 loss=2.8394 tok=1101.0M dt=8601
|
| 771 |
+
01:34:38 step 67300 loss=2.8196 tok=1102.6M dt=8616
|
| 772 |
+
01:34:54 step 67400 loss=2.8041 tok=1104.3M dt=8632
|
| 773 |
+
01:35:09 step 67500 loss=2.8315 tok=1105.9M dt=8647
|
| 774 |
+
01:35:24 step 67600 loss=2.7911 tok=1107.6M dt=8663
|
| 775 |
+
01:35:39 step 67700 loss=2.8651 tok=1109.2M dt=8678
|
| 776 |
+
01:35:55 step 67800 loss=2.7831 tok=1110.8M dt=8693
|
| 777 |
+
01:36:10 step 67900 loss=2.8230 tok=1112.5M dt=8708
|
| 778 |
+
01:36:25 step 68000 loss=2.7989 tok=1114.1M dt=8723
|