Upload logs.txt with huggingface_hub
Browse files
logs.txt
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Epoch 1/60 161.3s lr=3.33e-06 loss=3.4129 tag_loss=1.5993 antecedent_loss=1.8136
|
| 2 |
+
Epoch 2/60 159.3s lr=6.67e-06 loss=3.3298 tag_loss=1.5197 antecedent_loss=1.8101
|
| 3 |
+
Epoch 3/60 159.1s lr=1.00e-05 loss=3.2759 tag_loss=1.4843 antecedent_loss=1.7916
|
| 4 |
+
Epoch 4/60 160.5s lr=1.33e-05 loss=3.2532 tag_loss=1.4668 antecedent_loss=1.7864
|
| 5 |
+
Epoch 5/60 160.1s lr=1.67e-05 loss=3.2291 tag_loss=1.4533 antecedent_loss=1.7758
|
| 6 |
+
Epoch 6/60 159.1s lr=2.00e-05 loss=3.1842 tag_loss=1.4483 antecedent_loss=1.7359
|
| 7 |
+
Epoch 7/60 159.1s lr=2.00e-05 loss=3.1694 tag_loss=1.4372 antecedent_loss=1.7322
|
| 8 |
+
Epoch 8/60 160.9s lr=1.99e-05 loss=3.1683 tag_loss=1.4382 antecedent_loss=1.7301
|
| 9 |
+
Epoch 9/60 159.5s lr=1.98e-05 loss=3.1494 tag_loss=1.4286 antecedent_loss=1.7208
|
| 10 |
+
Epoch 10/60 159.5s lr=1.97e-05 loss=3.1634 tag_loss=1.4288 antecedent_loss=1.7346
|
| 11 |
+
Epoch 11/60 161.2s lr=1.96e-05 loss=3.1118 tag_loss=1.4236 antecedent_loss=1.6882
|
| 12 |
+
Epoch 12/60 160.7s lr=1.94e-05 loss=3.1555 tag_loss=1.4191 antecedent_loss=1.7364
|
| 13 |
+
Epoch 13/60 159.4s lr=1.92e-05 loss=3.1221 tag_loss=1.4226 antecedent_loss=1.6995
|
| 14 |
+
Epoch 14/60 159.5s lr=1.89e-05 loss=3.1179 tag_loss=1.4187 antecedent_loss=1.6992
|
| 15 |
+
Epoch 15/60 160.6s lr=1.87e-05 loss=3.1021 tag_loss=1.4149 antecedent_loss=1.6872
|
| 16 |
+
Epoch 16/60 159.5s lr=1.84e-05 loss=3.1155 tag_loss=1.4121 antecedent_loss=1.7034
|
| 17 |
+
Epoch 17/60 159.5s lr=1.80e-05 loss=3.1116 tag_loss=1.4134 antecedent_loss=1.6983
|
| 18 |
+
Epoch 18/60 160.6s lr=1.77e-05 loss=3.0626 tag_loss=1.4105 antecedent_loss=1.6522
|
| 19 |
+
Epoch 19/60 159.5s lr=1.73e-05 loss=3.1047 tag_loss=1.4081 antecedent_loss=1.6966
|
| 20 |
+
Epoch 20/60 161.6s lr=1.69e-05 loss=3.0952 tag_loss=1.4107 antecedent_loss=1.6845
|
| 21 |
+
Epoch 21/60 161.1s lr=1.64e-05 loss=3.0870 tag_loss=1.4089 antecedent_loss=1.6781
|
| 22 |
+
Epoch 22/60 159.8s lr=1.60e-05 loss=3.0811 tag_loss=1.4055 antecedent_loss=1.6756
|
| 23 |
+
Epoch 23/60 161.3s lr=1.55e-05 loss=3.0674 tag_loss=1.4067 antecedent_loss=1.6606
|
| 24 |
+
Epoch 24/60 159.4s lr=1.50e-05 loss=3.0572 tag_loss=1.4077 antecedent_loss=1.6496
|
| 25 |
+
Epoch 25/60 160.0s lr=1.45e-05 loss=3.0807 tag_loss=1.3998 antecedent_loss=1.6809
|
| 26 |
+
Epoch 26/60 161.3s lr=1.40e-05 loss=3.0613 tag_loss=1.4020 antecedent_loss=1.6593
|
| 27 |
+
Epoch 27/60 159.3s lr=1.34e-05 loss=3.0771 tag_loss=1.4031 antecedent_loss=1.6740
|
| 28 |
+
Epoch 28/60 159.1s lr=1.29e-05 loss=3.0682 tag_loss=1.4030 antecedent_loss=1.6652
|
| 29 |
+
Epoch 29/60 159.2s lr=1.23e-05 loss=3.0680 tag_loss=1.4007 antecedent_loss=1.6673
|
| 30 |
+
Epoch 30/60 161.8s lr=1.17e-05 loss=3.0520 tag_loss=1.4025 antecedent_loss=1.6494
|
| 31 |
+
Epoch 31/60 159.6s lr=1.12e-05 loss=3.0681 tag_loss=1.3945 antecedent_loss=1.6736
|
| 32 |
+
Epoch 32/60 161.2s lr=1.06e-05 loss=3.0257 tag_loss=1.4032 antecedent_loss=1.6224
|
| 33 |
+
Epoch 33/60 159.9s lr=1.00e-05 loss=3.0548 tag_loss=1.3960 antecedent_loss=1.6588
|
| 34 |
+
Epoch 34/60 159.4s lr=9.42e-06 loss=3.0754 tag_loss=1.3968 antecedent_loss=1.6786
|
| 35 |
+
Epoch 35/60 161.8s lr=8.84e-06 loss=3.0340 tag_loss=1.3990 antecedent_loss=1.6350
|
| 36 |
+
Epoch 36/60 159.5s lr=8.26e-06 loss=3.0364 tag_loss=1.3969 antecedent_loss=1.6395
|
| 37 |
+
Epoch 37/60 159.5s lr=7.69e-06 loss=3.0518 tag_loss=1.3947 antecedent_loss=1.6571
|
| 38 |
+
Epoch 38/60 159.8s lr=7.13e-06 loss=3.0256 tag_loss=1.3975 antecedent_loss=1.6281
|
| 39 |
+
Epoch 39/60 159.5s lr=6.58e-06 loss=3.0375 tag_loss=1.3925 antecedent_loss=1.6450
|
| 40 |
+
Epoch 40/60 161.7s lr=6.04e-06 loss=3.0374 tag_loss=1.3925 antecedent_loss=1.6448
|
| 41 |
+
Epoch 41/60 159.5s lr=5.51e-06 loss=3.0337 tag_loss=1.3928 antecedent_loss=1.6409
|
| 42 |
+
Epoch 42/60 161.7s lr=5.00e-06 loss=3.0503 tag_loss=1.3927 antecedent_loss=1.6576
|
| 43 |
+
Epoch 43/60 159.5s lr=4.50e-06 loss=3.0314 tag_loss=1.3999 antecedent_loss=1.6315
|
| 44 |
+
Epoch 44/60 161.5s lr=4.03e-06 loss=3.0410 tag_loss=1.3957 antecedent_loss=1.6454
|
| 45 |
+
Epoch 45/60 161.4s lr=3.57e-06 loss=3.0335 tag_loss=1.3940 antecedent_loss=1.6395
|
| 46 |
+
Epoch 46/60 159.9s lr=3.14e-06 loss=3.0085 tag_loss=1.3966 antecedent_loss=1.6119
|
| 47 |
+
Epoch 47/60 161.5s lr=2.73e-06 loss=3.0462 tag_loss=1.3916 antecedent_loss=1.6545
|
| 48 |
+
Epoch 48/60 159.8s lr=2.34e-06 loss=3.0474 tag_loss=1.3933 antecedent_loss=1.6541
|
| 49 |
+
Epoch 49/60 161.8s lr=1.98e-06 loss=3.0265 tag_loss=1.3940 antecedent_loss=1.6325
|
| 50 |
+
Epoch 50/60 159.1s lr=1.65e-06 loss=3.0454 tag_loss=1.3931 antecedent_loss=1.6523
|
| 51 |
+
Epoch 51/60 161.9s lr=1.34e-06 loss=3.0260 tag_loss=1.3941 antecedent_loss=1.6318
|
| 52 |
+
Epoch 52/60 159.0s lr=1.06e-06 loss=3.0571 tag_loss=1.3945 antecedent_loss=1.6626
|
| 53 |
+
Epoch 53/60 159.3s lr=8.18e-07 loss=3.0352 tag_loss=1.3934 antecedent_loss=1.6418
|
| 54 |
+
Epoch 54/60 159.0s lr=6.03e-07 loss=3.0181 tag_loss=1.3917 antecedent_loss=1.6263
|
| 55 |
+
Epoch 55/60 159.5s lr=4.20e-07 loss=3.0560 tag_loss=1.3889 antecedent_loss=1.6671
|
| 56 |
+
Epoch 56/60 159.0s lr=2.70e-07 loss=3.0323 tag_loss=1.3962 antecedent_loss=1.6362
|
| 57 |
+
Epoch 57/60 161.2s lr=1.52e-07 loss=3.0433 tag_loss=1.3951 antecedent_loss=1.6482
|
| 58 |
+
Epoch 58/60 159.6s lr=6.76e-08 loss=3.0519 tag_loss=1.3940 antecedent_loss=1.6579
|
| 59 |
+
Epoch 59/60 159.7s lr=1.69e-08 loss=3.0236 tag_loss=1.3939 antecedent_loss=1.6297
|
| 60 |
+
Epoch 60/60 161.4s lr=0.0000 loss=3.0489 tag_loss=1.3915 antecedent_loss=1.6574
|