Upload log_ts_f_both.txt with huggingface_hub
Browse files- log_ts_f_both.txt +11 -0
log_ts_f_both.txt
CHANGED
|
@@ -281,3 +281,14 @@ Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/cs
|
|
| 281 |
10:52:25 step 99800 loss=2.3079 tok=1635.1M dt=1620
|
| 282 |
10:52:32 step 99900 loss=2.3483 tok=1636.8M dt=1627
|
| 283 |
10:52:39 step 100000 loss=2.3760 tok=1638.4M dt=1634
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 281 |
10:52:25 step 99800 loss=2.3079 tok=1635.1M dt=1620
|
| 282 |
10:52:32 step 99900 loss=2.3483 tok=1636.8M dt=1627
|
| 283 |
10:52:39 step 100000 loss=2.3760 tok=1638.4M dt=1634
|
| 284 |
+
10:52:39 pushed log_ts_f_both.txt
|
| 285 |
+
10:52:47 step 100100 loss=2.2502 tok=1640.0M dt=1642
|
| 286 |
+
10:52:54 step 100200 loss=2.3165 tok=1641.7M dt=1649
|
| 287 |
+
10:53:01 step 100300 loss=2.3797 tok=1643.3M dt=1657
|
| 288 |
+
10:53:09 step 100400 loss=2.4324 tok=1645.0M dt=1664
|
| 289 |
+
10:53:16 step 100500 loss=2.3327 tok=1646.6M dt=1671
|
| 290 |
+
10:53:23 step 100600 loss=2.3263 tok=1648.2M dt=1678
|
| 291 |
+
10:53:30 step 100700 loss=2.3784 tok=1649.9M dt=1686
|
| 292 |
+
10:53:37 step 100800 loss=2.3919 tok=1651.5M dt=1693
|
| 293 |
+
10:53:45 step 100900 loss=2.2525 tok=1653.1M dt=1700
|
| 294 |
+
10:53:52 step 101000 loss=2.3265 tok=1654.8M dt=1707
|