Upload log_ts_d4.txt with huggingface_hub
Browse files- log_ts_d4.txt +11 -0
log_ts_d4.txt
CHANGED
|
@@ -841,3 +841,14 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 841 |
01:36:49 step 66800 loss=2.8727 tok=1094.5M dt=8747
|
| 842 |
01:37:03 step 66900 loss=2.8401 tok=1096.1M dt=8762
|
| 843 |
01:37:17 step 67000 loss=2.7748 tok=1097.7M dt=8775
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 841 |
01:36:49 step 66800 loss=2.8727 tok=1094.5M dt=8747
|
| 842 |
01:37:03 step 66900 loss=2.8401 tok=1096.1M dt=8762
|
| 843 |
01:37:17 step 67000 loss=2.7748 tok=1097.7M dt=8775
|
| 844 |
+
01:37:18 pushed log_ts_d4.txt
|
| 845 |
+
01:37:32 step 67100 loss=2.7683 tok=1099.4M dt=8790
|
| 846 |
+
01:37:47 step 67200 loss=2.8195 tok=1101.0M dt=8805
|
| 847 |
+
01:38:01 step 67300 loss=2.7694 tok=1102.6M dt=8819
|
| 848 |
+
01:38:15 step 67400 loss=2.7314 tok=1104.3M dt=8833
|
| 849 |
+
01:38:29 step 67500 loss=2.8000 tok=1105.9M dt=8847
|
| 850 |
+
01:38:44 step 67600 loss=2.7829 tok=1107.6M dt=8862
|
| 851 |
+
01:38:58 step 67700 loss=2.7947 tok=1109.2M dt=8876
|
| 852 |
+
01:39:12 step 67800 loss=2.7687 tok=1110.8M dt=8890
|
| 853 |
+
01:39:26 step 67900 loss=2.7409 tok=1112.5M dt=8904
|
| 854 |
+
01:39:41 step 68000 loss=2.7955 tok=1114.1M dt=8919
|