Upload log_ts_d3.txt with huggingface_hub
Browse files- log_ts_d3.txt +12 -0
log_ts_d3.txt
CHANGED
|
@@ -849,3 +849,15 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 849 |
01:42:31 step 75800 loss=2.8101 tok=1241.9M dt=9088
|
| 850 |
01:42:46 step 75900 loss=2.7982 tok=1243.5M dt=9102
|
| 851 |
01:43:00 step 76000 loss=2.7799 tok=1245.2M dt=9117
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 849 |
01:42:31 step 75800 loss=2.8101 tok=1241.9M dt=9088
|
| 850 |
01:42:46 step 75900 loss=2.7982 tok=1243.5M dt=9102
|
| 851 |
01:43:00 step 76000 loss=2.7799 tok=1245.2M dt=9117
|
| 852 |
+
01:43:01 pushed log_ts_d3.txt
|
| 853 |
+
01:43:15 step 76100 loss=2.7554 tok=1246.8M dt=9132
|
| 854 |
+
01:43:29 step 76200 loss=2.8128 tok=1248.5M dt=9146
|
| 855 |
+
01:43:44 step 76300 loss=2.8352 tok=1250.1M dt=9161
|
| 856 |
+
01:43:58 step 76400 loss=2.8059 tok=1251.7M dt=9175
|
| 857 |
+
01:44:12 step 76500 loss=2.8225 tok=1253.4M dt=9189
|
| 858 |
+
01:44:27 step 76600 loss=2.8050 tok=1255.0M dt=9204
|
| 859 |
+
01:44:41 step 76700 loss=2.8397 tok=1256.7M dt=9218
|
| 860 |
+
01:44:55 step 76800 loss=2.7705 tok=1258.3M dt=9232
|
| 861 |
+
01:45:09 step 76900 loss=2.7775 tok=1259.9M dt=9246
|
| 862 |
+
01:45:20 epoch 11 start
|
| 863 |
+
01:45:35 step 77000 loss=2.7872 tok=1261.6M dt=9272
|