Training in progress, step 100
Browse files- all_results.json +9 -9
- config.json +6 -6
- eval_results.json +5 -5
- pytorch_model.bin +1 -1
- runs/Aug24_12-31-14_surveily-ag-02/events.out.tfevents.1692873360.surveily-ag-02.7570.1 +3 -0
- runs/Aug24_12-57-54_surveily-ag-02/events.out.tfevents.1692874678.surveily-ag-02.7570.2 +3 -0
- train_results.json +4 -4
- trainer_state.json +135 -114
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 1.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9444444444444444,
|
| 4 |
+
"eval_loss": 0.29236936569213867,
|
| 5 |
+
"eval_runtime": 1.9546,
|
| 6 |
+
"eval_samples_per_second": 18.418,
|
| 7 |
+
"eval_steps_per_second": 2.558,
|
| 8 |
+
"train_loss": 0.13472866227229435,
|
| 9 |
+
"train_runtime": 231.7859,
|
| 10 |
+
"train_samples_per_second": 5.177,
|
| 11 |
+
"train_steps_per_second": 1.294
|
| 12 |
}
|
config.json
CHANGED
|
@@ -17,9 +17,9 @@
|
|
| 17 |
"3": "building_site",
|
| 18 |
"4": "factory",
|
| 19 |
"5": "food",
|
| 20 |
-
"6": "
|
| 21 |
-
"7": "
|
| 22 |
-
"8": "
|
| 23 |
"9": "skatepart"
|
| 24 |
},
|
| 25 |
"image_size": 224,
|
|
@@ -32,9 +32,9 @@
|
|
| 32 |
"building_site": "3",
|
| 33 |
"factory": "4",
|
| 34 |
"food": "5",
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
"skatepart": "9",
|
| 39 |
"warehouse": "10",
|
| 40 |
"zoo": "11"
|
|
|
|
| 17 |
"3": "building_site",
|
| 18 |
"4": "factory",
|
| 19 |
"5": "food",
|
| 20 |
+
"6": "office",
|
| 21 |
+
"7": "road",
|
| 22 |
+
"8": "skatepark",
|
| 23 |
"9": "skatepart"
|
| 24 |
},
|
| 25 |
"image_size": 224,
|
|
|
|
| 32 |
"building_site": "3",
|
| 33 |
"factory": "4",
|
| 34 |
"food": "5",
|
| 35 |
+
"office": "6",
|
| 36 |
+
"road": "7",
|
| 37 |
+
"skatepark": "8",
|
| 38 |
"skatepart": "9",
|
| 39 |
"warehouse": "10",
|
| 40 |
"zoo": "11"
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9444444444444444,
|
| 4 |
+
"eval_loss": 0.29236936569213867,
|
| 5 |
+
"eval_runtime": 1.9546,
|
| 6 |
+
"eval_samples_per_second": 18.418,
|
| 7 |
+
"eval_steps_per_second": 2.558
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343299437
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dd98cc78c1a563980f48c5611699ed17798f72747c76fc7360a45ac23d62092
|
| 3 |
size 343299437
|
runs/Aug24_12-31-14_surveily-ag-02/events.out.tfevents.1692873360.surveily-ag-02.7570.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:525c6b5796d2cb1620a57db96771fd2705b36583a507393b7fa007a0c35a0494
|
| 3 |
+
size 411
|
runs/Aug24_12-57-54_surveily-ag-02/events.out.tfevents.1692874678.surveily-ag-02.7570.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb9f8dc3c58c856bb4fb3db142bc05d10e36b21e334a96b10f316df0458295a
|
| 3 |
+
size 6610
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 1.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.13472866227229435,
|
| 4 |
+
"train_runtime": 231.7859,
|
| 5 |
+
"train_samples_per_second": 5.177,
|
| 6 |
+
"train_steps_per_second": 1.294
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,238 +1,259 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./vit-base/checkpoint-
|
| 4 |
"epoch": 20.0,
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 1.
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss":
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 2.
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 2.
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 3.
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 3.
|
| 42 |
-
"eval_accuracy": 0.
|
| 43 |
-
"eval_loss": 0.
|
| 44 |
-
"eval_runtime": 1.
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second": 2.
|
| 47 |
"step": 50
|
| 48 |
},
|
| 49 |
{
|
| 50 |
-
"epoch": 4.
|
| 51 |
-
"learning_rate": 0.
|
| 52 |
-
"loss": 0.
|
| 53 |
"step": 60
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch":
|
| 57 |
-
"learning_rate": 0.
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 5.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 6.
|
| 69 |
-
"learning_rate": 0.
|
| 70 |
-
"loss": 0.
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch":
|
| 75 |
-
"learning_rate": 0.
|
| 76 |
-
"loss": 0.
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch":
|
| 81 |
-
"eval_accuracy": 0.
|
| 82 |
-
"eval_loss": 0.
|
| 83 |
-
"eval_runtime": 1.
|
| 84 |
-
"eval_samples_per_second":
|
| 85 |
-
"eval_steps_per_second":
|
| 86 |
"step": 100
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 7.
|
| 90 |
-
"learning_rate": 0.
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 110
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 8.
|
| 96 |
-
"learning_rate": 0.
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 120
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate": 0.
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 130
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate": 0.
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 140
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 10.
|
| 114 |
-
"learning_rate":
|
| 115 |
"loss": 0.0004,
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 10.
|
| 120 |
-
"eval_accuracy": 0.
|
| 121 |
-
"eval_loss": 0.
|
| 122 |
-
"eval_runtime":
|
| 123 |
-
"eval_samples_per_second":
|
| 124 |
-
"eval_steps_per_second":
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
-
"epoch":
|
| 129 |
-
"learning_rate":
|
| 130 |
"loss": 0.0004,
|
| 131 |
"step": 160
|
| 132 |
},
|
| 133 |
{
|
| 134 |
-
"epoch":
|
| 135 |
-
"learning_rate":
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch": 12.
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss": 0.
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"learning_rate":
|
| 148 |
"loss": 0.0003,
|
| 149 |
"step": 190
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"learning_rate":
|
| 154 |
-
"loss": 0.
|
| 155 |
"step": 200
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch":
|
| 159 |
-
"eval_accuracy": 0.
|
| 160 |
-
"eval_loss": 0.
|
| 161 |
-
"eval_runtime":
|
| 162 |
-
"eval_samples_per_second":
|
| 163 |
-
"eval_steps_per_second":
|
| 164 |
"step": 200
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"learning_rate":
|
| 169 |
"loss": 0.0003,
|
| 170 |
"step": 210
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"learning_rate":
|
| 175 |
"loss": 0.0003,
|
| 176 |
"step": 220
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
-
"learning_rate":
|
| 181 |
"loss": 0.0003,
|
| 182 |
"step": 230
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"learning_rate":
|
| 187 |
"loss": 0.0003,
|
| 188 |
"step": 240
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"learning_rate":
|
| 193 |
"loss": 0.0003,
|
| 194 |
"step": 250
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"eval_accuracy": 0.
|
| 199 |
-
"eval_loss": 0.
|
| 200 |
-
"eval_runtime": 1.
|
| 201 |
-
"eval_samples_per_second":
|
| 202 |
-
"eval_steps_per_second":
|
| 203 |
"step": 250
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
-
"learning_rate":
|
| 208 |
"loss": 0.0003,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"learning_rate":
|
| 214 |
"loss": 0.0003,
|
| 215 |
"step": 270
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch":
|
| 219 |
-
"learning_rate":
|
| 220 |
"loss": 0.0003,
|
| 221 |
"step": 280
|
| 222 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 223 |
{
|
| 224 |
"epoch": 20.0,
|
| 225 |
-
"step":
|
| 226 |
-
"total_flos":
|
| 227 |
-
"train_loss": 0.
|
| 228 |
-
"train_runtime":
|
| 229 |
-
"train_samples_per_second":
|
| 230 |
-
"train_steps_per_second": 1.
|
| 231 |
}
|
| 232 |
],
|
| 233 |
-
"max_steps":
|
| 234 |
"num_train_epochs": 20,
|
| 235 |
-
"total_flos":
|
| 236 |
"trial_name": null,
|
| 237 |
"trial_params": null
|
| 238 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.29236936569213867,
|
| 3 |
+
"best_model_checkpoint": "./vit-base/checkpoint-300",
|
| 4 |
"epoch": 20.0,
|
| 5 |
+
"global_step": 300,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.67,
|
| 12 |
+
"learning_rate": 0.000194,
|
| 13 |
+
"loss": 2.2893,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 1.33,
|
| 18 |
+
"learning_rate": 0.000188,
|
| 19 |
+
"loss": 1.2128,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"learning_rate": 0.00018133333333333334,
|
| 25 |
+
"loss": 0.3941,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 2.67,
|
| 30 |
+
"learning_rate": 0.00017466666666666667,
|
| 31 |
+
"loss": 0.1061,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 3.33,
|
| 36 |
+
"learning_rate": 0.000168,
|
| 37 |
+
"loss": 0.0169,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 3.33,
|
| 42 |
+
"eval_accuracy": 0.8055555555555556,
|
| 43 |
+
"eval_loss": 0.5319890975952148,
|
| 44 |
+
"eval_runtime": 1.9752,
|
| 45 |
+
"eval_samples_per_second": 18.226,
|
| 46 |
+
"eval_steps_per_second": 2.531,
|
| 47 |
"step": 50
|
| 48 |
},
|
| 49 |
{
|
| 50 |
+
"epoch": 4.0,
|
| 51 |
+
"learning_rate": 0.00016133333333333334,
|
| 52 |
+
"loss": 0.009,
|
| 53 |
"step": 60
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 4.67,
|
| 57 |
+
"learning_rate": 0.00015466666666666667,
|
| 58 |
+
"loss": 0.0032,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 5.33,
|
| 63 |
+
"learning_rate": 0.000148,
|
| 64 |
+
"loss": 0.0012,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 6.0,
|
| 69 |
+
"learning_rate": 0.00014133333333333334,
|
| 70 |
+
"loss": 0.0009,
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 6.67,
|
| 75 |
+
"learning_rate": 0.00013466666666666667,
|
| 76 |
+
"loss": 0.0008,
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 6.67,
|
| 81 |
+
"eval_accuracy": 0.9166666666666666,
|
| 82 |
+
"eval_loss": 0.34849807620048523,
|
| 83 |
+
"eval_runtime": 1.9712,
|
| 84 |
+
"eval_samples_per_second": 18.263,
|
| 85 |
+
"eval_steps_per_second": 2.536,
|
| 86 |
"step": 100
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 7.33,
|
| 90 |
+
"learning_rate": 0.00012800000000000002,
|
| 91 |
+
"loss": 0.0007,
|
| 92 |
"step": 110
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 8.0,
|
| 96 |
+
"learning_rate": 0.00012133333333333335,
|
| 97 |
+
"loss": 0.0006,
|
| 98 |
"step": 120
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 8.67,
|
| 102 |
+
"learning_rate": 0.00011466666666666667,
|
| 103 |
+
"loss": 0.0005,
|
| 104 |
"step": 130
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 9.33,
|
| 108 |
+
"learning_rate": 0.00010800000000000001,
|
| 109 |
+
"loss": 0.0005,
|
| 110 |
"step": 140
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 10.0,
|
| 114 |
+
"learning_rate": 0.00010133333333333335,
|
| 115 |
"loss": 0.0004,
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 10.0,
|
| 120 |
+
"eval_accuracy": 0.9444444444444444,
|
| 121 |
+
"eval_loss": 0.29886576533317566,
|
| 122 |
+
"eval_runtime": 2.245,
|
| 123 |
+
"eval_samples_per_second": 16.035,
|
| 124 |
+
"eval_steps_per_second": 2.227,
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 10.67,
|
| 129 |
+
"learning_rate": 9.466666666666667e-05,
|
| 130 |
"loss": 0.0004,
|
| 131 |
"step": 160
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 11.33,
|
| 135 |
+
"learning_rate": 8.800000000000001e-05,
|
| 136 |
+
"loss": 0.0004,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 12.0,
|
| 141 |
+
"learning_rate": 8.133333333333334e-05,
|
| 142 |
+
"loss": 0.0004,
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 12.67,
|
| 147 |
+
"learning_rate": 7.466666666666667e-05,
|
| 148 |
"loss": 0.0003,
|
| 149 |
"step": 190
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 13.33,
|
| 153 |
+
"learning_rate": 6.800000000000001e-05,
|
| 154 |
+
"loss": 0.0004,
|
| 155 |
"step": 200
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 13.33,
|
| 159 |
+
"eval_accuracy": 0.9444444444444444,
|
| 160 |
+
"eval_loss": 0.29390671849250793,
|
| 161 |
+
"eval_runtime": 2.0759,
|
| 162 |
+
"eval_samples_per_second": 17.342,
|
| 163 |
+
"eval_steps_per_second": 2.409,
|
| 164 |
"step": 200
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 14.0,
|
| 168 |
+
"learning_rate": 6.133333333333334e-05,
|
| 169 |
"loss": 0.0003,
|
| 170 |
"step": 210
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 14.67,
|
| 174 |
+
"learning_rate": 5.466666666666666e-05,
|
| 175 |
"loss": 0.0003,
|
| 176 |
"step": 220
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 15.33,
|
| 180 |
+
"learning_rate": 4.8e-05,
|
| 181 |
"loss": 0.0003,
|
| 182 |
"step": 230
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 16.0,
|
| 186 |
+
"learning_rate": 4.133333333333333e-05,
|
| 187 |
"loss": 0.0003,
|
| 188 |
"step": 240
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 16.67,
|
| 192 |
+
"learning_rate": 3.466666666666667e-05,
|
| 193 |
"loss": 0.0003,
|
| 194 |
"step": 250
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 16.67,
|
| 198 |
+
"eval_accuracy": 0.9444444444444444,
|
| 199 |
+
"eval_loss": 0.29294198751449585,
|
| 200 |
+
"eval_runtime": 1.9452,
|
| 201 |
+
"eval_samples_per_second": 18.507,
|
| 202 |
+
"eval_steps_per_second": 2.57,
|
| 203 |
"step": 250
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 17.33,
|
| 207 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 208 |
"loss": 0.0003,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 18.0,
|
| 213 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 214 |
"loss": 0.0003,
|
| 215 |
"step": 270
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 18.67,
|
| 219 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 220 |
"loss": 0.0003,
|
| 221 |
"step": 280
|
| 222 |
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 19.33,
|
| 225 |
+
"learning_rate": 8.000000000000001e-06,
|
| 226 |
+
"loss": 0.0003,
|
| 227 |
+
"step": 290
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 20.0,
|
| 231 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 232 |
+
"loss": 0.0003,
|
| 233 |
+
"step": 300
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 20.0,
|
| 237 |
+
"eval_accuracy": 0.9444444444444444,
|
| 238 |
+
"eval_loss": 0.29236936569213867,
|
| 239 |
+
"eval_runtime": 1.9351,
|
| 240 |
+
"eval_samples_per_second": 18.604,
|
| 241 |
+
"eval_steps_per_second": 2.584,
|
| 242 |
+
"step": 300
|
| 243 |
+
},
|
| 244 |
{
|
| 245 |
"epoch": 20.0,
|
| 246 |
+
"step": 300,
|
| 247 |
+
"total_flos": 9.29987219718144e+16,
|
| 248 |
+
"train_loss": 0.13472866227229435,
|
| 249 |
+
"train_runtime": 231.7859,
|
| 250 |
+
"train_samples_per_second": 5.177,
|
| 251 |
+
"train_steps_per_second": 1.294
|
| 252 |
}
|
| 253 |
],
|
| 254 |
+
"max_steps": 300,
|
| 255 |
"num_train_epochs": 20,
|
| 256 |
+
"total_flos": 9.29987219718144e+16,
|
| 257 |
"trial_name": null,
|
| 258 |
"trial_params": null
|
| 259 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:505351b249d79638ccd34717b52da9b6f37bbfecf576c89da5d02fadb59a2bc6
|
| 3 |
size 3963
|