loss 0.6
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- trainer_state.json +20 -20
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1376950965
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f026eda995519627803ace49004b3bc7ea09e4718d606ea2a985c1aa49bec92
|
| 3 |
size 1376950965
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 688496379
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4af008a4fb55ce22292b6d47f4f921949c51109b77f9094d3ec89f3c9810fcac
|
| 3 |
size 688496379
|
trainer_state.json
CHANGED
|
@@ -10,121 +10,121 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
"learning_rate": 0.0006992397089171283,
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
"learning_rate": 0.0006984794178342565,
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 200
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.03,
|
| 24 |
"learning_rate": 0.0006977191267513849,
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 300
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.04,
|
| 30 |
"learning_rate": 0.0006969588356685131,
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.05,
|
| 36 |
"learning_rate": 0.0006961985445856413,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.07,
|
| 42 |
"learning_rate": 0.0006954382535027696,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.08,
|
| 48 |
"learning_rate": 0.0006946779624198979,
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 700
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.09,
|
| 54 |
"learning_rate": 0.0006939176713370262,
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 800
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.1,
|
| 60 |
"learning_rate": 0.0006931573802541545,
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 900
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.11,
|
| 66 |
"learning_rate": 0.0006923970891712827,
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 1000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.12,
|
| 72 |
"learning_rate": 0.0006916367980884109,
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 1100
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.13,
|
| 78 |
"learning_rate": 0.0006908765070055393,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 1200
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.14,
|
| 84 |
"learning_rate": 0.0006901162159226675,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 1300
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.15,
|
| 90 |
"learning_rate": 0.0006893559248397958,
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 1400
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.16,
|
| 96 |
"learning_rate": 0.0006885956337569241,
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 1500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.17,
|
| 102 |
"learning_rate": 0.0006878353426740524,
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 1600
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.18,
|
| 108 |
"learning_rate": 0.0006870750515911806,
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 1700
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.2,
|
| 114 |
"learning_rate": 0.0006863147605083089,
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 1800
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.21,
|
| 120 |
"learning_rate": 0.0006855544694254371,
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 1900
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.22,
|
| 126 |
"learning_rate": 0.0006847941783425654,
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 2000
|
| 129 |
}
|
| 130 |
],
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
"learning_rate": 0.0006992397089171283,
|
| 13 |
+
"loss": 0.5664,
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
"learning_rate": 0.0006984794178342565,
|
| 19 |
+
"loss": 0.5958,
|
| 20 |
"step": 200
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.03,
|
| 24 |
"learning_rate": 0.0006977191267513849,
|
| 25 |
+
"loss": 0.599,
|
| 26 |
"step": 300
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.04,
|
| 30 |
"learning_rate": 0.0006969588356685131,
|
| 31 |
+
"loss": 0.6111,
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.05,
|
| 36 |
"learning_rate": 0.0006961985445856413,
|
| 37 |
+
"loss": 0.5763,
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.07,
|
| 42 |
"learning_rate": 0.0006954382535027696,
|
| 43 |
+
"loss": 0.6012,
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.08,
|
| 48 |
"learning_rate": 0.0006946779624198979,
|
| 49 |
+
"loss": 0.6054,
|
| 50 |
"step": 700
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.09,
|
| 54 |
"learning_rate": 0.0006939176713370262,
|
| 55 |
+
"loss": 0.5922,
|
| 56 |
"step": 800
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.1,
|
| 60 |
"learning_rate": 0.0006931573802541545,
|
| 61 |
+
"loss": 0.5865,
|
| 62 |
"step": 900
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.11,
|
| 66 |
"learning_rate": 0.0006923970891712827,
|
| 67 |
+
"loss": 0.6263,
|
| 68 |
"step": 1000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.12,
|
| 72 |
"learning_rate": 0.0006916367980884109,
|
| 73 |
+
"loss": 0.6332,
|
| 74 |
"step": 1100
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.13,
|
| 78 |
"learning_rate": 0.0006908765070055393,
|
| 79 |
+
"loss": 0.618,
|
| 80 |
"step": 1200
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.14,
|
| 84 |
"learning_rate": 0.0006901162159226675,
|
| 85 |
+
"loss": 0.6272,
|
| 86 |
"step": 1300
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.15,
|
| 90 |
"learning_rate": 0.0006893559248397958,
|
| 91 |
+
"loss": 0.6505,
|
| 92 |
"step": 1400
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.16,
|
| 96 |
"learning_rate": 0.0006885956337569241,
|
| 97 |
+
"loss": 0.6179,
|
| 98 |
"step": 1500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.17,
|
| 102 |
"learning_rate": 0.0006878353426740524,
|
| 103 |
+
"loss": 0.6509,
|
| 104 |
"step": 1600
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.18,
|
| 108 |
"learning_rate": 0.0006870750515911806,
|
| 109 |
+
"loss": 0.6487,
|
| 110 |
"step": 1700
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.2,
|
| 114 |
"learning_rate": 0.0006863147605083089,
|
| 115 |
+
"loss": 0.6341,
|
| 116 |
"step": 1800
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.21,
|
| 120 |
"learning_rate": 0.0006855544694254371,
|
| 121 |
+
"loss": 0.6408,
|
| 122 |
"step": 1900
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.22,
|
| 126 |
"learning_rate": 0.0006847941783425654,
|
| 127 |
+
"loss": 0.6413,
|
| 128 |
"step": 2000
|
| 129 |
}
|
| 130 |
],
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2607
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cde6ae4d30903dd742743295e31cc8a8412a32ae7919684e13e6a12099005672
|
| 3 |
size 2607
|