Training in progress, step 100
Browse files- all_results.json +9 -9
- eval_results.json +5 -5
- pytorch_model.bin +1 -1
- runs/Aug16_12-12-49_surveily-ag-02/events.out.tfevents.1692180872.surveily-ag-02.5572.3 +3 -0
- runs/Aug16_13-00-22_surveily-ag-02/events.out.tfevents.1692183626.surveily-ag-02.3986.0 +3 -0
- runs/Aug16_13-01-44_surveily-ag-02/events.out.tfevents.1692183706.surveily-ag-02.3986.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +152 -83
- 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": 0.
|
| 6 |
-
"eval_samples_per_second": 60.
|
| 7 |
-
"eval_steps_per_second": 7.
|
| 8 |
-
"train_loss":
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.9943184852600098,
|
| 5 |
+
"eval_runtime": 0.265,
|
| 6 |
+
"eval_samples_per_second": 60.385,
|
| 7 |
+
"eval_steps_per_second": 7.548,
|
| 8 |
+
"train_loss": 0.07943551431099574,
|
| 9 |
+
"train_runtime": 62.6784,
|
| 10 |
+
"train_samples_per_second": 18.188,
|
| 11 |
+
"train_steps_per_second": 4.786
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second": 60.
|
| 7 |
-
"eval_steps_per_second": 7.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.9943184852600098,
|
| 5 |
+
"eval_runtime": 0.265,
|
| 6 |
+
"eval_samples_per_second": 60.385,
|
| 7 |
+
"eval_steps_per_second": 7.548
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343277933
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c69e9c58dfb8b93fc76d6b1fab019fcc9c2dcbc39d445e570afefd4a1620d6f
|
| 3 |
size 343277933
|
runs/Aug16_12-12-49_surveily-ag-02/events.out.tfevents.1692180872.surveily-ag-02.5572.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5cba1197a29f9f38e7abad8063fc366cec05e2c4390eebc4733aa3a53d09cb0
|
| 3 |
+
size 411
|
runs/Aug16_13-00-22_surveily-ag-02/events.out.tfevents.1692183626.surveily-ag-02.3986.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8052356d689d6acb182d6ea1c91624554d66d667adcde26a82a5ba6480f6b653
|
| 3 |
+
size 4779
|
runs/Aug16_13-01-44_surveily-ag-02/events.out.tfevents.1692183706.surveily-ag-02.3986.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e8c2151ea3d5a47962e48e92faaff5673674b0d87f64d7283dc1a4338b69382
|
| 3 |
+
size 6020
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.07943551431099574,
|
| 4 |
+
"train_runtime": 62.6784,
|
| 5 |
+
"train_samples_per_second": 18.188,
|
| 6 |
+
"train_steps_per_second": 4.786
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,163 +1,232 @@
|
|
| 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":
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss":
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch":
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch":
|
| 24 |
-
"learning_rate": 0.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"learning_rate": 0.
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate": 0.
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate": 0.
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate": 0.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"eval_accuracy": 0.
|
| 73 |
-
"eval_loss": 0.
|
| 74 |
-
"eval_runtime": 0.
|
| 75 |
-
"eval_samples_per_second":
|
| 76 |
-
"eval_steps_per_second": 7.
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch":
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch":
|
| 93 |
-
"learning_rate":
|
| 94 |
-
"loss": 0.
|
| 95 |
"step": 130
|
| 96 |
},
|
| 97 |
{
|
| 98 |
-
"epoch":
|
| 99 |
-
"learning_rate":
|
| 100 |
-
"loss": 0.
|
| 101 |
"step": 140
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"loss": 0.
|
| 113 |
"step": 160
|
| 114 |
},
|
| 115 |
{
|
| 116 |
-
"epoch":
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 170
|
| 120 |
},
|
| 121 |
{
|
| 122 |
-
"epoch":
|
| 123 |
-
"learning_rate":
|
| 124 |
-
"loss": 0.
|
| 125 |
"step": 180
|
| 126 |
},
|
| 127 |
{
|
| 128 |
-
"epoch":
|
| 129 |
-
"learning_rate":
|
| 130 |
-
"loss": 0.
|
| 131 |
"step": 190
|
| 132 |
},
|
| 133 |
{
|
| 134 |
-
"epoch":
|
| 135 |
-
"learning_rate":
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 200
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch":
|
| 141 |
-
"eval_accuracy": 0.
|
| 142 |
-
"eval_loss":
|
| 143 |
-
"eval_runtime": 0.
|
| 144 |
-
"eval_samples_per_second":
|
| 145 |
-
"eval_steps_per_second":
|
| 146 |
"step": 200
|
| 147 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
{
|
| 149 |
"epoch": 20.0,
|
| 150 |
-
"step":
|
| 151 |
-
"total_flos":
|
| 152 |
-
"train_loss":
|
| 153 |
-
"train_runtime":
|
| 154 |
-
"train_samples_per_second":
|
| 155 |
-
"train_steps_per_second":
|
| 156 |
}
|
| 157 |
],
|
| 158 |
-
"max_steps":
|
| 159 |
"num_train_epochs": 20,
|
| 160 |
-
"total_flos":
|
| 161 |
"trial_name": null,
|
| 162 |
"trial_params": null
|
| 163 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9943184852600098,
|
| 3 |
+
"best_model_checkpoint": "./vit-base/checkpoint-100",
|
| 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": 1.4506,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 1.33,
|
| 18 |
+
"learning_rate": 0.000188,
|
| 19 |
+
"loss": 0.7681,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"learning_rate": 0.00018133333333333334,
|
| 25 |
+
"loss": 0.1499,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 2.67,
|
| 30 |
+
"learning_rate": 0.00017466666666666667,
|
| 31 |
+
"loss": 0.0079,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 3.33,
|
| 36 |
+
"learning_rate": 0.000168,
|
| 37 |
+
"loss": 0.0022,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 4.0,
|
| 42 |
+
"learning_rate": 0.00016133333333333334,
|
| 43 |
+
"loss": 0.0006,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 4.67,
|
| 48 |
+
"learning_rate": 0.00015466666666666667,
|
| 49 |
+
"loss": 0.0004,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 5.33,
|
| 54 |
+
"learning_rate": 0.000148,
|
| 55 |
+
"loss": 0.0003,
|
| 56 |
"step": 80
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 6.0,
|
| 60 |
+
"learning_rate": 0.00014133333333333334,
|
| 61 |
+
"loss": 0.0002,
|
| 62 |
"step": 90
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 6.67,
|
| 66 |
+
"learning_rate": 0.00013466666666666667,
|
| 67 |
+
"loss": 0.0002,
|
| 68 |
"step": 100
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 6.67,
|
| 72 |
+
"eval_accuracy": 0.75,
|
| 73 |
+
"eval_loss": 0.9943184852600098,
|
| 74 |
+
"eval_runtime": 0.2625,
|
| 75 |
+
"eval_samples_per_second": 60.953,
|
| 76 |
+
"eval_steps_per_second": 7.619,
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 7.33,
|
| 81 |
+
"learning_rate": 0.00012800000000000002,
|
| 82 |
+
"loss": 0.0002,
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 8.0,
|
| 87 |
+
"learning_rate": 0.00012133333333333335,
|
| 88 |
+
"loss": 0.0002,
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 8.67,
|
| 93 |
+
"learning_rate": 0.00011466666666666667,
|
| 94 |
+
"loss": 0.0002,
|
| 95 |
"step": 130
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 9.33,
|
| 99 |
+
"learning_rate": 0.00010800000000000001,
|
| 100 |
+
"loss": 0.0001,
|
| 101 |
"step": 140
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 10.0,
|
| 105 |
+
"learning_rate": 0.00010133333333333335,
|
| 106 |
+
"loss": 0.0002,
|
| 107 |
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 10.67,
|
| 111 |
+
"learning_rate": 9.466666666666667e-05,
|
| 112 |
+
"loss": 0.0001,
|
| 113 |
"step": 160
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 11.33,
|
| 117 |
+
"learning_rate": 8.800000000000001e-05,
|
| 118 |
+
"loss": 0.0001,
|
| 119 |
"step": 170
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 12.0,
|
| 123 |
+
"learning_rate": 8.133333333333334e-05,
|
| 124 |
+
"loss": 0.0001,
|
| 125 |
"step": 180
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 12.67,
|
| 129 |
+
"learning_rate": 7.466666666666667e-05,
|
| 130 |
+
"loss": 0.0001,
|
| 131 |
"step": 190
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 13.33,
|
| 135 |
+
"learning_rate": 6.800000000000001e-05,
|
| 136 |
+
"loss": 0.0001,
|
| 137 |
"step": 200
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 13.33,
|
| 141 |
+
"eval_accuracy": 0.75,
|
| 142 |
+
"eval_loss": 1.0497348308563232,
|
| 143 |
+
"eval_runtime": 0.2471,
|
| 144 |
+
"eval_samples_per_second": 64.739,
|
| 145 |
+
"eval_steps_per_second": 8.092,
|
| 146 |
"step": 200
|
| 147 |
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 14.0,
|
| 150 |
+
"learning_rate": 6.133333333333334e-05,
|
| 151 |
+
"loss": 0.0001,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 14.67,
|
| 156 |
+
"learning_rate": 5.466666666666666e-05,
|
| 157 |
+
"loss": 0.0001,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 15.33,
|
| 162 |
+
"learning_rate": 4.8e-05,
|
| 163 |
+
"loss": 0.0001,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 16.0,
|
| 168 |
+
"learning_rate": 4.133333333333333e-05,
|
| 169 |
+
"loss": 0.0001,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 16.67,
|
| 174 |
+
"learning_rate": 3.466666666666667e-05,
|
| 175 |
+
"loss": 0.0001,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 17.33,
|
| 180 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 181 |
+
"loss": 0.0001,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 18.0,
|
| 186 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 187 |
+
"loss": 0.0001,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 18.67,
|
| 192 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 193 |
+
"loss": 0.0001,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 19.33,
|
| 198 |
+
"learning_rate": 8.000000000000001e-06,
|
| 199 |
+
"loss": 0.0001,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 20.0,
|
| 204 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 205 |
+
"loss": 0.0001,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 20.0,
|
| 210 |
+
"eval_accuracy": 0.75,
|
| 211 |
+
"eval_loss": 1.0663217306137085,
|
| 212 |
+
"eval_runtime": 0.2864,
|
| 213 |
+
"eval_samples_per_second": 55.866,
|
| 214 |
+
"eval_steps_per_second": 6.983,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
{
|
| 218 |
"epoch": 20.0,
|
| 219 |
+
"step": 300,
|
| 220 |
+
"total_flos": 8.834324347441152e+16,
|
| 221 |
+
"train_loss": 0.07943551431099574,
|
| 222 |
+
"train_runtime": 62.6784,
|
| 223 |
+
"train_samples_per_second": 18.188,
|
| 224 |
+
"train_steps_per_second": 4.786
|
| 225 |
}
|
| 226 |
],
|
| 227 |
+
"max_steps": 300,
|
| 228 |
"num_train_epochs": 20,
|
| 229 |
+
"total_flos": 8.834324347441152e+16,
|
| 230 |
"trial_name": null,
|
| 231 |
"trial_params": null
|
| 232 |
}
|
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:f08db5d5770c27835141cccd2f1441c44bd2448ac70fe81d4da3d218a51fb3f0
|
| 3 |
size 3963
|