Update README.md
Browse files
README.md
CHANGED
|
@@ -97,48 +97,50 @@ training_args = Seq2SeqTrainingArguments(
|
|
| 97 |
|
| 98 |
## Training and Validation Metrics
|
| 99 |
|
| 100 |
-
Step Training Loss
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
|
|
|
|
|
|
|
|
| 97 |
|
| 98 |
## Training and Validation Metrics
|
| 99 |
|
| 100 |
+
Step | Training Loss | Validation Loss | Gen Len
|
| 101 |
+
--------|---------------|-----------------|---------
|
| 102 |
+
500 | 21.636200 | 9.776628 | 2.001900
|
| 103 |
+
1000 | 10.103400 | 6.105016 | 2.077900
|
| 104 |
+
1500 | 6.830800 | 5.081259 | 3.811600
|
| 105 |
+
2000 | 6.003100 | 4.702793 | 4.237300
|
| 106 |
+
2500 | 5.690200 | 4.469123 | 4.700000
|
| 107 |
+
3000 | 5.443100 | 4.274406 | 4.808300
|
| 108 |
+
3500 | 5.265300 | 4.121417 | 4.749400
|
| 109 |
+
4000 | 5.128500 | 3.989708 | 4.782300
|
| 110 |
+
4500 | 5.007200 | 3.885391 | 4.805100
|
| 111 |
+
5000 | 4.909600 | 3.787640 | 4.874800
|
| 112 |
+
5500 | 4.836000 | 3.715750 | 4.855500
|
| 113 |
+
6000 | 4.733000 | 3.640963 | 4.962000
|
| 114 |
+
6500 | 4.673500 | 3.587330 | 5.011600
|
| 115 |
+
7000 | 4.623800 | 3.531883 | 5.068300
|
| 116 |
+
7500 | 4.567400 | 3.481622 | 5.108500
|
| 117 |
+
8000 | 4.523200 | 3.445404 | 5.092700
|
| 118 |
+
8500 | 4.464000 | 3.413630 | 5.132700
|
| 119 |
+
9000 | 4.423100 | 3.326201 | 5.211700
|
| 120 |
+
9500 | 4.315700 | 3.238422 | 5.200600
|
| 121 |
+
10000 | 4.218200 | 3.143774 | 5.288100
|
| 122 |
+
10500 | 4.133600 | 3.080613 | 5.202300
|
| 123 |
+
11000 | 4.087700 | 3.011713 | 5.271800
|
| 124 |
+
11500 | 4.004300 | 2.957386 | 5.178700
|
| 125 |
+
12000 | 3.956700 | 2.898953 | 5.209600
|
| 126 |
+
12500 | 3.922800 | 2.850440 | 5.210100
|
| 127 |
+
13000 | 3.853400 | 2.796974 | 5.171700
|
| 128 |
+
13500 | 3.807900 | 2.745325 | 5.281200
|
| 129 |
+
14000 | 3.755700 | 2.708517 | 5.223000
|
| 130 |
+
14500 | 3.729300 | 2.678200 | 5.210700
|
| 131 |
+
15000 | 3.673600 | 2.637842 | 5.230200
|
| 132 |
+
15500 | 3.625400 | 2.607649 | 5.264100
|
| 133 |
+
16000 | 3.601100 | 2.592188 | 5.129800
|
| 134 |
+
16500 | 3.608200 | 2.556329 | 5.215800
|
| 135 |
+
17000 | 3.557900 | 2.536781 | 5.162900
|
| 136 |
+
17500 | 3.533500 | 2.504695 | 5.206000
|
| 137 |
+
18000 | 3.500000 | 2.477887 | 5.211600
|
| 138 |
+
18500 | 3.463600 | 2.456758 | 5.201000
|
| 139 |
+
19000 | 3.457100 | 2.433362 | 5.210000
|
| 140 |
+
19500 | 3.435400 | 2.411479 | 5.197600
|
| 141 |
+
20000 | 3.413300 | 2.392534 | 5.221100
|
| 142 |
+
20500 | 3.366100 | 2.378421 | 5.165200
|
| 143 |
+
21000 | 3.363500 | 2.357117 | 5.187300
|
| 144 |
+
21500 | 3.346500 | 2.343485 | 5.193600
|
| 145 |
+
22000 | 3.328300 | 2.331021 | 5.183300
|
| 146 |
+
|