Push MLM model
Browse files
bert_embeddings_finetune/checkpoint-4662/trainer_state.json
CHANGED
|
@@ -11,9 +11,9 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_loss": 2.5209195613861084,
|
| 14 |
-
"eval_runtime": 7.
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second": 46.
|
| 17 |
"step": 333
|
| 18 |
},
|
| 19 |
{
|
|
@@ -26,17 +26,17 @@
|
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
"eval_loss": 2.278496742248535,
|
| 29 |
-
"eval_runtime": 7.
|
| 30 |
-
"eval_samples_per_second":
|
| 31 |
-
"eval_steps_per_second": 45.
|
| 32 |
"step": 666
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
"eval_loss": NaN,
|
| 37 |
-
"eval_runtime": 7.
|
| 38 |
-
"eval_samples_per_second":
|
| 39 |
-
"eval_steps_per_second":
|
| 40 |
"step": 999
|
| 41 |
},
|
| 42 |
{
|
|
@@ -49,9 +49,9 @@
|
|
| 49 |
{
|
| 50 |
"epoch": 4.0,
|
| 51 |
"eval_loss": NaN,
|
| 52 |
-
"eval_runtime": 7.
|
| 53 |
-
"eval_samples_per_second":
|
| 54 |
-
"eval_steps_per_second": 44.
|
| 55 |
"step": 1332
|
| 56 |
},
|
| 57 |
{
|
|
@@ -64,17 +64,17 @@
|
|
| 64 |
{
|
| 65 |
"epoch": 5.0,
|
| 66 |
"eval_loss": 1.7883461713790894,
|
| 67 |
-
"eval_runtime": 7.
|
| 68 |
-
"eval_samples_per_second":
|
| 69 |
-
"eval_steps_per_second":
|
| 70 |
"step": 1665
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 6.0,
|
| 74 |
"eval_loss": 1.617417573928833,
|
| 75 |
-
"eval_runtime": 7.
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second":
|
| 78 |
"step": 1998
|
| 79 |
},
|
| 80 |
{
|
|
@@ -87,9 +87,9 @@
|
|
| 87 |
{
|
| 88 |
"epoch": 7.0,
|
| 89 |
"eval_loss": 1.5227739810943604,
|
| 90 |
-
"eval_runtime": 7.
|
| 91 |
-
"eval_samples_per_second":
|
| 92 |
-
"eval_steps_per_second":
|
| 93 |
"step": 2331
|
| 94 |
},
|
| 95 |
{
|
|
@@ -102,17 +102,17 @@
|
|
| 102 |
{
|
| 103 |
"epoch": 8.0,
|
| 104 |
"eval_loss": 1.448709487915039,
|
| 105 |
-
"eval_runtime": 7.
|
| 106 |
-
"eval_samples_per_second":
|
| 107 |
-
"eval_steps_per_second":
|
| 108 |
"step": 2664
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 9.0,
|
| 112 |
"eval_loss": NaN,
|
| 113 |
-
"eval_runtime": 7.
|
| 114 |
-
"eval_samples_per_second":
|
| 115 |
-
"eval_steps_per_second":
|
| 116 |
"step": 2997
|
| 117 |
},
|
| 118 |
{
|
|
@@ -125,9 +125,9 @@
|
|
| 125 |
{
|
| 126 |
"epoch": 10.0,
|
| 127 |
"eval_loss": NaN,
|
| 128 |
-
"eval_runtime": 7.
|
| 129 |
-
"eval_samples_per_second":
|
| 130 |
-
"eval_steps_per_second": 44.
|
| 131 |
"step": 3330
|
| 132 |
},
|
| 133 |
{
|
|
@@ -140,17 +140,17 @@
|
|
| 140 |
{
|
| 141 |
"epoch": 11.0,
|
| 142 |
"eval_loss": 1.2851027250289917,
|
| 143 |
-
"eval_runtime": 7.
|
| 144 |
-
"eval_samples_per_second":
|
| 145 |
-
"eval_steps_per_second":
|
| 146 |
"step": 3663
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 12.0,
|
| 150 |
"eval_loss": 1.2175213098526,
|
| 151 |
-
"eval_runtime": 7.
|
| 152 |
-
"eval_samples_per_second":
|
| 153 |
-
"eval_steps_per_second":
|
| 154 |
"step": 3996
|
| 155 |
},
|
| 156 |
{
|
|
@@ -163,9 +163,9 @@
|
|
| 163 |
{
|
| 164 |
"epoch": 13.0,
|
| 165 |
"eval_loss": NaN,
|
| 166 |
-
"eval_runtime": 7.
|
| 167 |
-
"eval_samples_per_second":
|
| 168 |
-
"eval_steps_per_second": 44.
|
| 169 |
"step": 4329
|
| 170 |
},
|
| 171 |
{
|
|
@@ -178,9 +178,9 @@
|
|
| 178 |
{
|
| 179 |
"epoch": 14.0,
|
| 180 |
"eval_loss": 1.1719356775283813,
|
| 181 |
-
"eval_runtime": 7.
|
| 182 |
-
"eval_samples_per_second":
|
| 183 |
-
"eval_steps_per_second":
|
| 184 |
"step": 4662
|
| 185 |
}
|
| 186 |
],
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_loss": 2.5209195613861084,
|
| 14 |
+
"eval_runtime": 7.2095,
|
| 15 |
+
"eval_samples_per_second": 738.75,
|
| 16 |
+
"eval_steps_per_second": 46.189,
|
| 17 |
"step": 333
|
| 18 |
},
|
| 19 |
{
|
|
|
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
"eval_loss": 2.278496742248535,
|
| 29 |
+
"eval_runtime": 7.3416,
|
| 30 |
+
"eval_samples_per_second": 725.453,
|
| 31 |
+
"eval_steps_per_second": 45.358,
|
| 32 |
"step": 666
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
"eval_loss": NaN,
|
| 37 |
+
"eval_runtime": 7.386,
|
| 38 |
+
"eval_samples_per_second": 721.09,
|
| 39 |
+
"eval_steps_per_second": 45.085,
|
| 40 |
"step": 999
|
| 41 |
},
|
| 42 |
{
|
|
|
|
| 49 |
{
|
| 50 |
"epoch": 4.0,
|
| 51 |
"eval_loss": NaN,
|
| 52 |
+
"eval_runtime": 7.5366,
|
| 53 |
+
"eval_samples_per_second": 706.68,
|
| 54 |
+
"eval_steps_per_second": 44.184,
|
| 55 |
"step": 1332
|
| 56 |
},
|
| 57 |
{
|
|
|
|
| 64 |
{
|
| 65 |
"epoch": 5.0,
|
| 66 |
"eval_loss": 1.7883461713790894,
|
| 67 |
+
"eval_runtime": 7.5591,
|
| 68 |
+
"eval_samples_per_second": 704.577,
|
| 69 |
+
"eval_steps_per_second": 44.053,
|
| 70 |
"step": 1665
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 6.0,
|
| 74 |
"eval_loss": 1.617417573928833,
|
| 75 |
+
"eval_runtime": 7.5921,
|
| 76 |
+
"eval_samples_per_second": 701.518,
|
| 77 |
+
"eval_steps_per_second": 43.861,
|
| 78 |
"step": 1998
|
| 79 |
},
|
| 80 |
{
|
|
|
|
| 87 |
{
|
| 88 |
"epoch": 7.0,
|
| 89 |
"eval_loss": 1.5227739810943604,
|
| 90 |
+
"eval_runtime": 7.4262,
|
| 91 |
+
"eval_samples_per_second": 717.188,
|
| 92 |
+
"eval_steps_per_second": 44.841,
|
| 93 |
"step": 2331
|
| 94 |
},
|
| 95 |
{
|
|
|
|
| 102 |
{
|
| 103 |
"epoch": 8.0,
|
| 104 |
"eval_loss": 1.448709487915039,
|
| 105 |
+
"eval_runtime": 7.4455,
|
| 106 |
+
"eval_samples_per_second": 715.331,
|
| 107 |
+
"eval_steps_per_second": 44.725,
|
| 108 |
"step": 2664
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 9.0,
|
| 112 |
"eval_loss": NaN,
|
| 113 |
+
"eval_runtime": 7.5963,
|
| 114 |
+
"eval_samples_per_second": 701.13,
|
| 115 |
+
"eval_steps_per_second": 43.837,
|
| 116 |
"step": 2997
|
| 117 |
},
|
| 118 |
{
|
|
|
|
| 125 |
{
|
| 126 |
"epoch": 10.0,
|
| 127 |
"eval_loss": NaN,
|
| 128 |
+
"eval_runtime": 7.4766,
|
| 129 |
+
"eval_samples_per_second": 712.357,
|
| 130 |
+
"eval_steps_per_second": 44.539,
|
| 131 |
"step": 3330
|
| 132 |
},
|
| 133 |
{
|
|
|
|
| 140 |
{
|
| 141 |
"epoch": 11.0,
|
| 142 |
"eval_loss": 1.2851027250289917,
|
| 143 |
+
"eval_runtime": 7.5315,
|
| 144 |
+
"eval_samples_per_second": 707.164,
|
| 145 |
+
"eval_steps_per_second": 44.214,
|
| 146 |
"step": 3663
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 12.0,
|
| 150 |
"eval_loss": 1.2175213098526,
|
| 151 |
+
"eval_runtime": 7.5286,
|
| 152 |
+
"eval_samples_per_second": 707.433,
|
| 153 |
+
"eval_steps_per_second": 44.231,
|
| 154 |
"step": 3996
|
| 155 |
},
|
| 156 |
{
|
|
|
|
| 163 |
{
|
| 164 |
"epoch": 13.0,
|
| 165 |
"eval_loss": NaN,
|
| 166 |
+
"eval_runtime": 7.4167,
|
| 167 |
+
"eval_samples_per_second": 718.113,
|
| 168 |
+
"eval_steps_per_second": 44.899,
|
| 169 |
"step": 4329
|
| 170 |
},
|
| 171 |
{
|
|
|
|
| 178 |
{
|
| 179 |
"epoch": 14.0,
|
| 180 |
"eval_loss": 1.1719356775283813,
|
| 181 |
+
"eval_runtime": 7.391,
|
| 182 |
+
"eval_samples_per_second": 720.609,
|
| 183 |
+
"eval_steps_per_second": 45.055,
|
| 184 |
"step": 4662
|
| 185 |
}
|
| 186 |
],
|
bert_embeddings_finetune/checkpoint-4995/trainer_state.json
CHANGED
|
@@ -11,9 +11,9 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_loss": 2.5209195613861084,
|
| 14 |
-
"eval_runtime": 7.
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second": 46.
|
| 17 |
"step": 333
|
| 18 |
},
|
| 19 |
{
|
|
@@ -26,17 +26,17 @@
|
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
"eval_loss": 2.278496742248535,
|
| 29 |
-
"eval_runtime": 7.
|
| 30 |
-
"eval_samples_per_second":
|
| 31 |
-
"eval_steps_per_second": 45.
|
| 32 |
"step": 666
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
"eval_loss": NaN,
|
| 37 |
-
"eval_runtime": 7.
|
| 38 |
-
"eval_samples_per_second":
|
| 39 |
-
"eval_steps_per_second":
|
| 40 |
"step": 999
|
| 41 |
},
|
| 42 |
{
|
|
@@ -49,9 +49,9 @@
|
|
| 49 |
{
|
| 50 |
"epoch": 4.0,
|
| 51 |
"eval_loss": NaN,
|
| 52 |
-
"eval_runtime": 7.
|
| 53 |
-
"eval_samples_per_second":
|
| 54 |
-
"eval_steps_per_second": 44.
|
| 55 |
"step": 1332
|
| 56 |
},
|
| 57 |
{
|
|
@@ -64,17 +64,17 @@
|
|
| 64 |
{
|
| 65 |
"epoch": 5.0,
|
| 66 |
"eval_loss": 1.7883461713790894,
|
| 67 |
-
"eval_runtime": 7.
|
| 68 |
-
"eval_samples_per_second":
|
| 69 |
-
"eval_steps_per_second":
|
| 70 |
"step": 1665
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 6.0,
|
| 74 |
"eval_loss": 1.617417573928833,
|
| 75 |
-
"eval_runtime": 7.
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second":
|
| 78 |
"step": 1998
|
| 79 |
},
|
| 80 |
{
|
|
@@ -87,9 +87,9 @@
|
|
| 87 |
{
|
| 88 |
"epoch": 7.0,
|
| 89 |
"eval_loss": 1.5227739810943604,
|
| 90 |
-
"eval_runtime": 7.
|
| 91 |
-
"eval_samples_per_second":
|
| 92 |
-
"eval_steps_per_second":
|
| 93 |
"step": 2331
|
| 94 |
},
|
| 95 |
{
|
|
@@ -102,17 +102,17 @@
|
|
| 102 |
{
|
| 103 |
"epoch": 8.0,
|
| 104 |
"eval_loss": 1.448709487915039,
|
| 105 |
-
"eval_runtime": 7.
|
| 106 |
-
"eval_samples_per_second":
|
| 107 |
-
"eval_steps_per_second":
|
| 108 |
"step": 2664
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 9.0,
|
| 112 |
"eval_loss": NaN,
|
| 113 |
-
"eval_runtime": 7.
|
| 114 |
-
"eval_samples_per_second":
|
| 115 |
-
"eval_steps_per_second":
|
| 116 |
"step": 2997
|
| 117 |
},
|
| 118 |
{
|
|
@@ -125,9 +125,9 @@
|
|
| 125 |
{
|
| 126 |
"epoch": 10.0,
|
| 127 |
"eval_loss": NaN,
|
| 128 |
-
"eval_runtime": 7.
|
| 129 |
-
"eval_samples_per_second":
|
| 130 |
-
"eval_steps_per_second": 44.
|
| 131 |
"step": 3330
|
| 132 |
},
|
| 133 |
{
|
|
@@ -140,17 +140,17 @@
|
|
| 140 |
{
|
| 141 |
"epoch": 11.0,
|
| 142 |
"eval_loss": 1.2851027250289917,
|
| 143 |
-
"eval_runtime": 7.
|
| 144 |
-
"eval_samples_per_second":
|
| 145 |
-
"eval_steps_per_second":
|
| 146 |
"step": 3663
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 12.0,
|
| 150 |
"eval_loss": 1.2175213098526,
|
| 151 |
-
"eval_runtime": 7.
|
| 152 |
-
"eval_samples_per_second":
|
| 153 |
-
"eval_steps_per_second":
|
| 154 |
"step": 3996
|
| 155 |
},
|
| 156 |
{
|
|
@@ -163,9 +163,9 @@
|
|
| 163 |
{
|
| 164 |
"epoch": 13.0,
|
| 165 |
"eval_loss": NaN,
|
| 166 |
-
"eval_runtime": 7.
|
| 167 |
-
"eval_samples_per_second":
|
| 168 |
-
"eval_steps_per_second": 44.
|
| 169 |
"step": 4329
|
| 170 |
},
|
| 171 |
{
|
|
@@ -178,17 +178,17 @@
|
|
| 178 |
{
|
| 179 |
"epoch": 14.0,
|
| 180 |
"eval_loss": 1.1719356775283813,
|
| 181 |
-
"eval_runtime": 7.
|
| 182 |
-
"eval_samples_per_second":
|
| 183 |
-
"eval_steps_per_second":
|
| 184 |
"step": 4662
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 15.0,
|
| 188 |
"eval_loss": 1.2066022157669067,
|
| 189 |
-
"eval_runtime": 7.
|
| 190 |
-
"eval_samples_per_second":
|
| 191 |
-
"eval_steps_per_second":
|
| 192 |
"step": 4995
|
| 193 |
}
|
| 194 |
],
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_loss": 2.5209195613861084,
|
| 14 |
+
"eval_runtime": 7.2095,
|
| 15 |
+
"eval_samples_per_second": 738.75,
|
| 16 |
+
"eval_steps_per_second": 46.189,
|
| 17 |
"step": 333
|
| 18 |
},
|
| 19 |
{
|
|
|
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
"eval_loss": 2.278496742248535,
|
| 29 |
+
"eval_runtime": 7.3416,
|
| 30 |
+
"eval_samples_per_second": 725.453,
|
| 31 |
+
"eval_steps_per_second": 45.358,
|
| 32 |
"step": 666
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
"eval_loss": NaN,
|
| 37 |
+
"eval_runtime": 7.386,
|
| 38 |
+
"eval_samples_per_second": 721.09,
|
| 39 |
+
"eval_steps_per_second": 45.085,
|
| 40 |
"step": 999
|
| 41 |
},
|
| 42 |
{
|
|
|
|
| 49 |
{
|
| 50 |
"epoch": 4.0,
|
| 51 |
"eval_loss": NaN,
|
| 52 |
+
"eval_runtime": 7.5366,
|
| 53 |
+
"eval_samples_per_second": 706.68,
|
| 54 |
+
"eval_steps_per_second": 44.184,
|
| 55 |
"step": 1332
|
| 56 |
},
|
| 57 |
{
|
|
|
|
| 64 |
{
|
| 65 |
"epoch": 5.0,
|
| 66 |
"eval_loss": 1.7883461713790894,
|
| 67 |
+
"eval_runtime": 7.5591,
|
| 68 |
+
"eval_samples_per_second": 704.577,
|
| 69 |
+
"eval_steps_per_second": 44.053,
|
| 70 |
"step": 1665
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 6.0,
|
| 74 |
"eval_loss": 1.617417573928833,
|
| 75 |
+
"eval_runtime": 7.5921,
|
| 76 |
+
"eval_samples_per_second": 701.518,
|
| 77 |
+
"eval_steps_per_second": 43.861,
|
| 78 |
"step": 1998
|
| 79 |
},
|
| 80 |
{
|
|
|
|
| 87 |
{
|
| 88 |
"epoch": 7.0,
|
| 89 |
"eval_loss": 1.5227739810943604,
|
| 90 |
+
"eval_runtime": 7.4262,
|
| 91 |
+
"eval_samples_per_second": 717.188,
|
| 92 |
+
"eval_steps_per_second": 44.841,
|
| 93 |
"step": 2331
|
| 94 |
},
|
| 95 |
{
|
|
|
|
| 102 |
{
|
| 103 |
"epoch": 8.0,
|
| 104 |
"eval_loss": 1.448709487915039,
|
| 105 |
+
"eval_runtime": 7.4455,
|
| 106 |
+
"eval_samples_per_second": 715.331,
|
| 107 |
+
"eval_steps_per_second": 44.725,
|
| 108 |
"step": 2664
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 9.0,
|
| 112 |
"eval_loss": NaN,
|
| 113 |
+
"eval_runtime": 7.5963,
|
| 114 |
+
"eval_samples_per_second": 701.13,
|
| 115 |
+
"eval_steps_per_second": 43.837,
|
| 116 |
"step": 2997
|
| 117 |
},
|
| 118 |
{
|
|
|
|
| 125 |
{
|
| 126 |
"epoch": 10.0,
|
| 127 |
"eval_loss": NaN,
|
| 128 |
+
"eval_runtime": 7.4766,
|
| 129 |
+
"eval_samples_per_second": 712.357,
|
| 130 |
+
"eval_steps_per_second": 44.539,
|
| 131 |
"step": 3330
|
| 132 |
},
|
| 133 |
{
|
|
|
|
| 140 |
{
|
| 141 |
"epoch": 11.0,
|
| 142 |
"eval_loss": 1.2851027250289917,
|
| 143 |
+
"eval_runtime": 7.5315,
|
| 144 |
+
"eval_samples_per_second": 707.164,
|
| 145 |
+
"eval_steps_per_second": 44.214,
|
| 146 |
"step": 3663
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 12.0,
|
| 150 |
"eval_loss": 1.2175213098526,
|
| 151 |
+
"eval_runtime": 7.5286,
|
| 152 |
+
"eval_samples_per_second": 707.433,
|
| 153 |
+
"eval_steps_per_second": 44.231,
|
| 154 |
"step": 3996
|
| 155 |
},
|
| 156 |
{
|
|
|
|
| 163 |
{
|
| 164 |
"epoch": 13.0,
|
| 165 |
"eval_loss": NaN,
|
| 166 |
+
"eval_runtime": 7.4167,
|
| 167 |
+
"eval_samples_per_second": 718.113,
|
| 168 |
+
"eval_steps_per_second": 44.899,
|
| 169 |
"step": 4329
|
| 170 |
},
|
| 171 |
{
|
|
|
|
| 178 |
{
|
| 179 |
"epoch": 14.0,
|
| 180 |
"eval_loss": 1.1719356775283813,
|
| 181 |
+
"eval_runtime": 7.391,
|
| 182 |
+
"eval_samples_per_second": 720.609,
|
| 183 |
+
"eval_steps_per_second": 45.055,
|
| 184 |
"step": 4662
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 15.0,
|
| 188 |
"eval_loss": 1.2066022157669067,
|
| 189 |
+
"eval_runtime": 7.4171,
|
| 190 |
+
"eval_samples_per_second": 718.067,
|
| 191 |
+
"eval_steps_per_second": 44.896,
|
| 192 |
"step": 4995
|
| 193 |
}
|
| 194 |
],
|