Model save
Browse files- all_results.json +9 -9
- config.json +4 -6
- eval_results.json +5 -5
- pytorch_model.bin +2 -2
- runs/Aug24_13-03-12_surveily-ag-02/events.out.tfevents.1692875166.surveily-ag-02.7570.4 +3 -0
- runs/Aug24_13-10-32_surveily-ag-02/events.out.tfevents.1692875436.surveily-ag-02.7570.5 +3 -0
- train_results.json +4 -4
- trainer_state.json +110 -131
- 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":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.8181818181818182,
|
| 4 |
+
"eval_loss": 0.6734122037887573,
|
| 5 |
+
"eval_runtime": 1.4864,
|
| 6 |
+
"eval_samples_per_second": 22.202,
|
| 7 |
+
"eval_steps_per_second": 3.364,
|
| 8 |
+
"train_loss": 0.13838704336334817,
|
| 9 |
+
"train_runtime": 109.7367,
|
| 10 |
+
"train_samples_per_second": 10.024,
|
| 11 |
+
"train_steps_per_second": 2.552
|
| 12 |
}
|
config.json
CHANGED
|
@@ -11,8 +11,7 @@
|
|
| 11 |
"id2label": {
|
| 12 |
"0": "airport",
|
| 13 |
"1": "bathroom",
|
| 14 |
-
"10": "
|
| 15 |
-
"11": "zoo",
|
| 16 |
"2": "beach",
|
| 17 |
"3": "building_site",
|
| 18 |
"4": "factory",
|
|
@@ -20,7 +19,7 @@
|
|
| 20 |
"6": "office",
|
| 21 |
"7": "road",
|
| 22 |
"8": "skatepark",
|
| 23 |
-
"9": "
|
| 24 |
},
|
| 25 |
"image_size": 224,
|
| 26 |
"initializer_range": 0.02,
|
|
@@ -35,9 +34,8 @@
|
|
| 35 |
"office": "6",
|
| 36 |
"road": "7",
|
| 37 |
"skatepark": "8",
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"zoo": "11"
|
| 41 |
},
|
| 42 |
"layer_norm_eps": 1e-12,
|
| 43 |
"model_type": "vit",
|
|
|
|
| 11 |
"id2label": {
|
| 12 |
"0": "airport",
|
| 13 |
"1": "bathroom",
|
| 14 |
+
"10": "zoo",
|
|
|
|
| 15 |
"2": "beach",
|
| 16 |
"3": "building_site",
|
| 17 |
"4": "factory",
|
|
|
|
| 19 |
"6": "office",
|
| 20 |
"7": "road",
|
| 21 |
"8": "skatepark",
|
| 22 |
+
"9": "warehouse"
|
| 23 |
},
|
| 24 |
"image_size": 224,
|
| 25 |
"initializer_range": 0.02,
|
|
|
|
| 34 |
"office": "6",
|
| 35 |
"road": "7",
|
| 36 |
"skatepark": "8",
|
| 37 |
+
"warehouse": "9",
|
| 38 |
+
"zoo": "10"
|
|
|
|
| 39 |
},
|
| 40 |
"layer_norm_eps": 1e-12,
|
| 41 |
"model_type": "vit",
|
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":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.8181818181818182,
|
| 4 |
+
"eval_loss": 0.6734122037887573,
|
| 5 |
+
"eval_runtime": 1.4864,
|
| 6 |
+
"eval_samples_per_second": 22.202,
|
| 7 |
+
"eval_steps_per_second": 3.364
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6c7f522f68588cf269ae201d49f828239335dfdf028d9288aa02d7be49ecb0c
|
| 3 |
+
size 343296365
|
runs/Aug24_13-03-12_surveily-ag-02/events.out.tfevents.1692875166.surveily-ag-02.7570.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2437b4f2a4702cc272a89027ea23ad6b3438ee7a80bf5604a92d1f909863c797
|
| 3 |
+
size 411
|
runs/Aug24_13-10-32_surveily-ag-02/events.out.tfevents.1692875436.surveily-ag-02.7570.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:115806065f8772798edf10f2b09e96ac34020aa063f4b7899cf0fe781db4d97a
|
| 3 |
+
size 10707
|
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":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.13838704336334817,
|
| 4 |
+
"train_runtime": 109.7367,
|
| 5 |
+
"train_samples_per_second": 10.024,
|
| 6 |
+
"train_steps_per_second": 2.552
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,259 +1,238 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_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": 1.
|
| 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":
|
| 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": 0.0009,
|
| 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": 0.0005,
|
| 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": 0.0004,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch": 12.
|
| 141 |
-
"learning_rate":
|
| 142 |
"loss": 0.0004,
|
| 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": 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.
|
| 232 |
"loss": 0.0003,
|
| 233 |
-
"step":
|
| 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":
|
| 247 |
-
"total_flos":
|
| 248 |
-
"train_loss": 0.
|
| 249 |
-
"train_runtime":
|
| 250 |
-
"train_samples_per_second":
|
| 251 |
-
"train_steps_per_second":
|
| 252 |
}
|
| 253 |
],
|
| 254 |
-
"max_steps":
|
| 255 |
"num_train_epochs": 20,
|
| 256 |
-
"total_flos":
|
| 257 |
"trial_name": null,
|
| 258 |
"trial_params": null
|
| 259 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
"epoch": 20.0,
|
| 5 |
+
"global_step": 280,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.71,
|
| 12 |
+
"learning_rate": 0.0001942857142857143,
|
| 13 |
+
"loss": 2.4106,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 1.43,
|
| 18 |
+
"learning_rate": 0.00018714285714285716,
|
| 19 |
+
"loss": 1.1806,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 2.14,
|
| 24 |
+
"learning_rate": 0.00018,
|
| 25 |
+
"loss": 0.221,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 2.86,
|
| 30 |
+
"learning_rate": 0.00017285714285714287,
|
| 31 |
+
"loss": 0.0374,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 3.57,
|
| 36 |
+
"learning_rate": 0.00016571428571428575,
|
| 37 |
+
"loss": 0.0099,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 3.57,
|
| 42 |
+
"eval_accuracy": 0.8181818181818182,
|
| 43 |
+
"eval_loss": 0.6155198812484741,
|
| 44 |
+
"eval_runtime": 1.2934,
|
| 45 |
+
"eval_samples_per_second": 25.515,
|
| 46 |
+
"eval_steps_per_second": 3.866,
|
| 47 |
"step": 50
|
| 48 |
},
|
| 49 |
{
|
| 50 |
+
"epoch": 4.29,
|
| 51 |
+
"learning_rate": 0.00015857142857142857,
|
| 52 |
+
"loss": 0.0047,
|
| 53 |
"step": 60
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 5.0,
|
| 57 |
+
"learning_rate": 0.00015142857142857143,
|
| 58 |
+
"loss": 0.0013,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 5.71,
|
| 63 |
+
"learning_rate": 0.00014428571428571428,
|
| 64 |
+
"loss": 0.0011,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 6.43,
|
| 69 |
+
"learning_rate": 0.00013714285714285716,
|
| 70 |
"loss": 0.0009,
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 7.14,
|
| 75 |
+
"learning_rate": 0.00013000000000000002,
|
| 76 |
+
"loss": 0.0007,
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 7.14,
|
| 81 |
+
"eval_accuracy": 0.7575757575757576,
|
| 82 |
+
"eval_loss": 0.7440532445907593,
|
| 83 |
+
"eval_runtime": 1.2943,
|
| 84 |
+
"eval_samples_per_second": 25.497,
|
| 85 |
+
"eval_steps_per_second": 3.863,
|
| 86 |
"step": 100
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 7.86,
|
| 90 |
+
"learning_rate": 0.00012285714285714287,
|
| 91 |
+
"loss": 0.0005,
|
| 92 |
"step": 110
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 8.57,
|
| 96 |
+
"learning_rate": 0.00011571428571428574,
|
| 97 |
+
"loss": 0.0005,
|
| 98 |
"step": 120
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 9.29,
|
| 102 |
+
"learning_rate": 0.00010857142857142856,
|
| 103 |
"loss": 0.0005,
|
| 104 |
"step": 130
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 10.0,
|
| 108 |
+
"learning_rate": 0.00010142857142857143,
|
| 109 |
+
"loss": 0.0004,
|
| 110 |
"step": 140
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 10.71,
|
| 114 |
+
"learning_rate": 9.428571428571429e-05,
|
| 115 |
"loss": 0.0004,
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 10.71,
|
| 120 |
+
"eval_accuracy": 0.8181818181818182,
|
| 121 |
+
"eval_loss": 0.6925162076950073,
|
| 122 |
+
"eval_runtime": 1.4314,
|
| 123 |
+
"eval_samples_per_second": 23.054,
|
| 124 |
+
"eval_steps_per_second": 3.493,
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 11.43,
|
| 129 |
+
"learning_rate": 8.714285714285715e-05,
|
| 130 |
"loss": 0.0004,
|
| 131 |
"step": 160
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 12.14,
|
| 135 |
+
"learning_rate": 8e-05,
|
| 136 |
"loss": 0.0004,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 12.86,
|
| 141 |
+
"learning_rate": 7.285714285714286e-05,
|
| 142 |
"loss": 0.0004,
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 13.57,
|
| 147 |
+
"learning_rate": 6.571428571428571e-05,
|
| 148 |
"loss": 0.0003,
|
| 149 |
"step": 190
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 14.29,
|
| 153 |
+
"learning_rate": 5.8571428571428575e-05,
|
| 154 |
+
"loss": 0.0003,
|
| 155 |
"step": 200
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 14.29,
|
| 159 |
+
"eval_accuracy": 0.8181818181818182,
|
| 160 |
+
"eval_loss": 0.6792979836463928,
|
| 161 |
+
"eval_runtime": 1.395,
|
| 162 |
+
"eval_samples_per_second": 23.655,
|
| 163 |
+
"eval_steps_per_second": 3.584,
|
| 164 |
"step": 200
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 15.0,
|
| 168 |
+
"learning_rate": 5.142857142857143e-05,
|
| 169 |
"loss": 0.0003,
|
| 170 |
"step": 210
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 15.71,
|
| 174 |
+
"learning_rate": 4.428571428571428e-05,
|
| 175 |
"loss": 0.0003,
|
| 176 |
"step": 220
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 16.43,
|
| 180 |
+
"learning_rate": 3.7142857142857143e-05,
|
| 181 |
"loss": 0.0003,
|
| 182 |
"step": 230
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 17.14,
|
| 186 |
+
"learning_rate": 3e-05,
|
| 187 |
"loss": 0.0003,
|
| 188 |
"step": 240
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 17.86,
|
| 192 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 193 |
"loss": 0.0003,
|
| 194 |
"step": 250
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 17.86,
|
| 198 |
+
"eval_accuracy": 0.8181818181818182,
|
| 199 |
+
"eval_loss": 0.6743510365486145,
|
| 200 |
+
"eval_runtime": 1.4417,
|
| 201 |
+
"eval_samples_per_second": 22.889,
|
| 202 |
+
"eval_steps_per_second": 3.468,
|
| 203 |
"step": 250
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 18.57,
|
| 207 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 208 |
"loss": 0.0003,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 19.29,
|
| 213 |
+
"learning_rate": 8.571428571428573e-06,
|
| 214 |
"loss": 0.0003,
|
| 215 |
"step": 270
|
| 216 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 217 |
{
|
| 218 |
"epoch": 20.0,
|
| 219 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 220 |
"loss": 0.0003,
|
| 221 |
+
"step": 280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 20.0,
|
| 225 |
+
"step": 280,
|
| 226 |
+
"total_flos": 8.52488284741632e+16,
|
| 227 |
+
"train_loss": 0.13838704336334817,
|
| 228 |
+
"train_runtime": 109.7367,
|
| 229 |
+
"train_samples_per_second": 10.024,
|
| 230 |
+
"train_steps_per_second": 2.552
|
| 231 |
}
|
| 232 |
],
|
| 233 |
+
"max_steps": 280,
|
| 234 |
"num_train_epochs": 20,
|
| 235 |
+
"total_flos": 8.52488284741632e+16,
|
| 236 |
"trial_name": null,
|
| 237 |
"trial_params": null
|
| 238 |
}
|
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 sha256:661912173424dfdc3132cb755d1df219646068269bba2359fcbdf40187fe7da3
|
| 3 |
size 3963
|