Upload log_ts_d5.txt with huggingface_hub
Browse files- log_ts_d5.txt +12 -0
log_ts_d5.txt
CHANGED
|
@@ -753,3 +753,15 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 753 |
|
| 754 |
|
| 755 |
/tmp/ts_d5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 756 |
01:31:00 pushed ts_d5.pt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 753 |
|
| 754 |
|
| 755 |
/tmp/ts_d5_m.pt : 100%|ββββββββββ| 75.8MB / 75.8MB
|
| 756 |
01:31:00 pushed ts_d5.pt
|
| 757 |
+
01:31:03 pushed log_ts_d5.txt
|
| 758 |
+
01:31:19 step 66100 loss=2.7957 tok=1083.0M dt=8417
|
| 759 |
+
01:31:37 step 66200 loss=2.7434 tok=1084.6M dt=8435
|
| 760 |
+
01:31:37 epoch 10 start
|
| 761 |
+
01:32:01 step 66300 loss=2.8174 tok=1086.3M dt=8459
|
| 762 |
+
01:32:17 step 66400 loss=2.7682 tok=1087.9M dt=8475
|
| 763 |
+
01:32:33 step 66500 loss=2.8210 tok=1089.5M dt=8491
|
| 764 |
+
01:32:49 step 66600 loss=2.8217 tok=1091.2M dt=8507
|
| 765 |
+
01:33:05 step 66700 loss=2.8526 tok=1092.8M dt=8523
|
| 766 |
+
01:33:20 step 66800 loss=2.8412 tok=1094.5M dt=8539
|
| 767 |
+
01:33:35 step 66900 loss=2.8004 tok=1096.1M dt=8554
|
| 768 |
+
01:33:50 step 67000 loss=2.7985 tok=1097.7M dt=8569
|