End of training
Browse files- all_results.json +5 -5
- pytorch_model.bin +1 -1
- runs/Nov17_09-39-19_DESKTOP-FPB11SM/1637138516.9584877/events.out.tfevents.1637138516.DESKTOP-FPB11SM.20532.1 +3 -0
- runs/Nov17_09-39-19_DESKTOP-FPB11SM/events.out.tfevents.1637138516.DESKTOP-FPB11SM.20532.0 +3 -0
- train_results.json +5 -5
- trainer_state.json +107 -107
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 120.
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 8.903275526092911e-05,
|
| 4 |
+
"train_runtime": 1219.8966,
|
| 5 |
+
"train_samples": 147398,
|
| 6 |
+
"train_samples_per_second": 120.828,
|
| 7 |
+
"train_steps_per_second": 1.889
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891650871
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da9572ed85cbe2d90b1dc5d5957cb7842fee5159f78cb999a6b0ba94be16fe00
|
| 3 |
size 891650871
|
runs/Nov17_09-39-19_DESKTOP-FPB11SM/1637138516.9584877/events.out.tfevents.1637138516.DESKTOP-FPB11SM.20532.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ea8e080d7be125de73c2b72380a254a335b18bdc9230ec72738a9ef715c5767
|
| 3 |
+
size 4740
|
runs/Nov17_09-39-19_DESKTOP-FPB11SM/events.out.tfevents.1637138516.DESKTOP-FPB11SM.20532.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8425212a4f9ce9341f0fba4cfa1cf07a1ce4e1383fe3ee535a43bcecdfd6ecb
|
| 3 |
+
size 11606
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 120.
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 8.903275526092911e-05,
|
| 4 |
+
"train_runtime": 1219.8966,
|
| 5 |
+
"train_samples": 147398,
|
| 6 |
+
"train_samples_per_second": 120.828,
|
| 7 |
+
"train_steps_per_second": 1.889
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,300 +2,300 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 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": 0.02,
|
| 12 |
-
"learning_rate": 4.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 50
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.04,
|
| 18 |
-
"learning_rate": 4.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 100
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate": 4.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 150
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.09,
|
| 30 |
-
"learning_rate": 4.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 200
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.11,
|
| 36 |
-
"learning_rate": 4.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 250
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.13,
|
| 42 |
-
"learning_rate": 4.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.15,
|
| 48 |
-
"learning_rate": 4.
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 350
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.17,
|
| 54 |
-
"learning_rate": 4.
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 400
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate": 4.
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 450
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"learning_rate": 3.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.24,
|
| 72 |
-
"learning_rate": 3.
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 550
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.26,
|
| 78 |
-
"learning_rate": 3.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.28,
|
| 84 |
-
"learning_rate": 3.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 650
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3,
|
| 90 |
-
"learning_rate": 3.
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 700
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate": 3.
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 750
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate": 3.
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 800
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.37,
|
| 108 |
-
"learning_rate": 3.
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 850
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.39,
|
| 114 |
-
"learning_rate": 3.
|
| 115 |
"loss": 0.0001,
|
| 116 |
"step": 900
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.41,
|
| 120 |
-
"learning_rate": 2.
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 950
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.43,
|
| 126 |
-
"learning_rate": 2.
|
| 127 |
"loss": 0.0,
|
| 128 |
"step": 1000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"learning_rate": 2.
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 1050
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 0.
|
| 138 |
-
"learning_rate": 2.
|
| 139 |
"loss": 0.0,
|
| 140 |
"step": 1100
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 0.
|
| 144 |
-
"learning_rate": 2.
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 1150
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.52,
|
| 150 |
-
"learning_rate": 2.
|
| 151 |
"loss": 0.0,
|
| 152 |
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.54,
|
| 156 |
-
"learning_rate": 2.
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 1250
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.56,
|
| 162 |
-
"learning_rate": 2.
|
| 163 |
"loss": 0.0,
|
| 164 |
"step": 1300
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"learning_rate": 2.
|
| 169 |
"loss": 0.0,
|
| 170 |
"step": 1350
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"learning_rate": 1.
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 1400
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch": 0.
|
| 180 |
-
"learning_rate": 1.
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 1450
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch": 0.
|
| 186 |
-
"learning_rate": 1.
|
| 187 |
"loss": 0.0,
|
| 188 |
"step": 1500
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.67,
|
| 192 |
-
"learning_rate": 1.
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 1550
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.69,
|
| 198 |
-
"learning_rate": 1.
|
| 199 |
"loss": 0.0,
|
| 200 |
"step": 1600
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 0.
|
| 204 |
-
"learning_rate": 1.
|
| 205 |
"loss": 0.0,
|
| 206 |
"step": 1650
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 0.
|
| 210 |
-
"learning_rate": 1.
|
| 211 |
"loss": 0.0,
|
| 212 |
"step": 1700
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"learning_rate": 1.
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 1750
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 0.
|
| 222 |
-
"learning_rate": 1.
|
| 223 |
"loss": 0.0,
|
| 224 |
"step": 1800
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.8,
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 1850
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 0.82,
|
| 234 |
-
"learning_rate":
|
| 235 |
"loss": 0.0,
|
| 236 |
"step": 1900
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch": 0.
|
| 240 |
-
"learning_rate":
|
| 241 |
"loss": 0.0,
|
| 242 |
"step": 1950
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 0.
|
| 246 |
-
"learning_rate":
|
| 247 |
"loss": 0.0,
|
| 248 |
"step": 2000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 0.
|
| 252 |
-
"learning_rate": 5.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 2050
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"learning_rate": 4.
|
| 259 |
"loss": 0.0,
|
| 260 |
"step": 2100
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 0.
|
| 264 |
-
"learning_rate": 3.
|
| 265 |
"loss": 0.0,
|
| 266 |
"step": 2150
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.95,
|
| 270 |
-
"learning_rate": 2.
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 2200
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch": 0.
|
| 276 |
-
"learning_rate": 1.
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 2250
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 0
|
| 282 |
-
"learning_rate":
|
| 283 |
"loss": 0.0,
|
| 284 |
"step": 2300
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 1.0,
|
| 288 |
-
"step":
|
| 289 |
-
"total_flos": 1.
|
| 290 |
-
"train_loss":
|
| 291 |
-
"train_runtime":
|
| 292 |
-
"train_samples_per_second": 120.
|
| 293 |
-
"train_steps_per_second": 1.
|
| 294 |
}
|
| 295 |
],
|
| 296 |
-
"max_steps":
|
| 297 |
"num_train_epochs": 1,
|
| 298 |
-
"total_flos": 1.
|
| 299 |
"trial_name": null,
|
| 300 |
"trial_params": null
|
| 301 |
}
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
+
"global_step": 2304,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.891493055555556e-05,
|
| 13 |
+
"loss": 0.0,
|
| 14 |
"step": 50
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 4.782986111111111e-05,
|
| 19 |
+
"loss": 0.0006,
|
| 20 |
"step": 100
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 4.674479166666667e-05,
|
| 25 |
+
"loss": 0.0006,
|
| 26 |
"step": 150
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 4.5659722222222224e-05,
|
| 31 |
+
"loss": 0.0,
|
| 32 |
"step": 200
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.11,
|
| 36 |
+
"learning_rate": 4.457465277777778e-05,
|
| 37 |
+
"loss": 0.0,
|
| 38 |
"step": 250
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.13,
|
| 42 |
+
"learning_rate": 4.3489583333333334e-05,
|
| 43 |
+
"loss": 0.0001,
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.15,
|
| 48 |
+
"learning_rate": 4.240451388888889e-05,
|
| 49 |
+
"loss": 0.0,
|
| 50 |
"step": 350
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.17,
|
| 54 |
+
"learning_rate": 4.1319444444444445e-05,
|
| 55 |
+
"loss": 0.0,
|
| 56 |
"step": 400
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.2,
|
| 60 |
+
"learning_rate": 4.0234375e-05,
|
| 61 |
+
"loss": 0.0002,
|
| 62 |
"step": 450
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.22,
|
| 66 |
+
"learning_rate": 3.914930555555556e-05,
|
| 67 |
+
"loss": 0.0001,
|
| 68 |
"step": 500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.24,
|
| 72 |
+
"learning_rate": 3.806423611111111e-05,
|
| 73 |
+
"loss": 0.0,
|
| 74 |
"step": 550
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.26,
|
| 78 |
+
"learning_rate": 3.697916666666667e-05,
|
| 79 |
+
"loss": 0.0,
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.28,
|
| 84 |
+
"learning_rate": 3.589409722222222e-05,
|
| 85 |
+
"loss": 0.0002,
|
| 86 |
"step": 650
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3,
|
| 90 |
+
"learning_rate": 3.4809027777777784e-05,
|
| 91 |
+
"loss": 0.0,
|
| 92 |
"step": 700
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 3.372395833333333e-05,
|
| 97 |
+
"loss": 0.0,
|
| 98 |
"step": 750
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.35,
|
| 102 |
+
"learning_rate": 3.263888888888889e-05,
|
| 103 |
+
"loss": 0.0002,
|
| 104 |
"step": 800
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.37,
|
| 108 |
+
"learning_rate": 3.155381944444444e-05,
|
| 109 |
+
"loss": 0.0002,
|
| 110 |
"step": 850
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.39,
|
| 114 |
+
"learning_rate": 3.0468750000000002e-05,
|
| 115 |
"loss": 0.0001,
|
| 116 |
"step": 900
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.41,
|
| 120 |
+
"learning_rate": 2.938368055555556e-05,
|
| 121 |
+
"loss": 0.0002,
|
| 122 |
"step": 950
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.43,
|
| 126 |
+
"learning_rate": 2.8298611111111113e-05,
|
| 127 |
"loss": 0.0,
|
| 128 |
"step": 1000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.46,
|
| 132 |
+
"learning_rate": 2.721354166666667e-05,
|
| 133 |
+
"loss": 0.0001,
|
| 134 |
"step": 1050
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 0.48,
|
| 138 |
+
"learning_rate": 2.6128472222222223e-05,
|
| 139 |
"loss": 0.0,
|
| 140 |
"step": 1100
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 0.5,
|
| 144 |
+
"learning_rate": 2.504340277777778e-05,
|
| 145 |
+
"loss": 0.0,
|
| 146 |
"step": 1150
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.52,
|
| 150 |
+
"learning_rate": 2.3958333333333334e-05,
|
| 151 |
"loss": 0.0,
|
| 152 |
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.54,
|
| 156 |
+
"learning_rate": 2.287326388888889e-05,
|
| 157 |
+
"loss": 0.0,
|
| 158 |
"step": 1250
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.56,
|
| 162 |
+
"learning_rate": 2.1788194444444445e-05,
|
| 163 |
"loss": 0.0,
|
| 164 |
"step": 1300
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.59,
|
| 168 |
+
"learning_rate": 2.0703125e-05,
|
| 169 |
"loss": 0.0,
|
| 170 |
"step": 1350
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.61,
|
| 174 |
+
"learning_rate": 1.9618055555555555e-05,
|
| 175 |
+
"loss": 0.0002,
|
| 176 |
"step": 1400
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 0.63,
|
| 180 |
+
"learning_rate": 1.853298611111111e-05,
|
| 181 |
+
"loss": 0.0003,
|
| 182 |
"step": 1450
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 0.65,
|
| 186 |
+
"learning_rate": 1.7447916666666666e-05,
|
| 187 |
"loss": 0.0,
|
| 188 |
"step": 1500
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.67,
|
| 192 |
+
"learning_rate": 1.636284722222222e-05,
|
| 193 |
+
"loss": 0.0001,
|
| 194 |
"step": 1550
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.69,
|
| 198 |
+
"learning_rate": 1.527777777777778e-05,
|
| 199 |
"loss": 0.0,
|
| 200 |
"step": 1600
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 0.72,
|
| 204 |
+
"learning_rate": 1.4192708333333336e-05,
|
| 205 |
"loss": 0.0,
|
| 206 |
"step": 1650
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 0.74,
|
| 210 |
+
"learning_rate": 1.3107638888888891e-05,
|
| 211 |
"loss": 0.0,
|
| 212 |
"step": 1700
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.76,
|
| 216 |
+
"learning_rate": 1.2022569444444445e-05,
|
| 217 |
+
"loss": 0.0,
|
| 218 |
"step": 1750
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 0.78,
|
| 222 |
+
"learning_rate": 1.09375e-05,
|
| 223 |
"loss": 0.0,
|
| 224 |
"step": 1800
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.8,
|
| 228 |
+
"learning_rate": 9.852430555555555e-06,
|
| 229 |
+
"loss": 0.0,
|
| 230 |
"step": 1850
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 0.82,
|
| 234 |
+
"learning_rate": 8.76736111111111e-06,
|
| 235 |
"loss": 0.0,
|
| 236 |
"step": 1900
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 0.85,
|
| 240 |
+
"learning_rate": 7.682291666666668e-06,
|
| 241 |
"loss": 0.0,
|
| 242 |
"step": 1950
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.87,
|
| 246 |
+
"learning_rate": 6.597222222222223e-06,
|
| 247 |
"loss": 0.0,
|
| 248 |
"step": 2000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 0.89,
|
| 252 |
+
"learning_rate": 5.512152777777778e-06,
|
| 253 |
+
"loss": 0.0,
|
| 254 |
"step": 2050
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.91,
|
| 258 |
+
"learning_rate": 4.427083333333334e-06,
|
| 259 |
"loss": 0.0,
|
| 260 |
"step": 2100
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 0.93,
|
| 264 |
+
"learning_rate": 3.342013888888889e-06,
|
| 265 |
"loss": 0.0,
|
| 266 |
"step": 2150
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.95,
|
| 270 |
+
"learning_rate": 2.2569444444444443e-06,
|
| 271 |
+
"loss": 0.0003,
|
| 272 |
"step": 2200
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 0.98,
|
| 276 |
+
"learning_rate": 1.1718750000000001e-06,
|
| 277 |
+
"loss": 0.0,
|
| 278 |
"step": 2250
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 1.0,
|
| 282 |
+
"learning_rate": 8.680555555555556e-08,
|
| 283 |
"loss": 0.0,
|
| 284 |
"step": 2300
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 1.0,
|
| 288 |
+
"step": 2304,
|
| 289 |
+
"total_flos": 1.824601497550848e+16,
|
| 290 |
+
"train_loss": 8.903275526092911e-05,
|
| 291 |
+
"train_runtime": 1219.8966,
|
| 292 |
+
"train_samples_per_second": 120.828,
|
| 293 |
+
"train_steps_per_second": 1.889
|
| 294 |
}
|
| 295 |
],
|
| 296 |
+
"max_steps": 2304,
|
| 297 |
"num_train_epochs": 1,
|
| 298 |
+
"total_flos": 1.824601497550848e+16,
|
| 299 |
"trial_name": null,
|
| 300 |
"trial_params": null
|
| 301 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2991
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37965f20e4224692e9ce75eebe5b5077a2ec83505220564aa7c847843215e9e0
|
| 3 |
size 2991
|