Commit ·
2b1d8be
1
Parent(s): 4617467
Training in progress, epoch 1
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- runs/Jan15_14-25-45_node3/events.out.tfevents.1642227962.node3 +2 -2
- runs/Jan15_14-25-45_node3/events.out.tfevents.1642228023.node3 +3 -0
- runs/Jan15_14-45-51_node3/1642229168.4472055/events.out.tfevents.1642229168.node3 +3 -0
- runs/Jan15_14-45-51_node3/events.out.tfevents.1642229168.node3 +3 -0
- tokenizer.json +0 -0
- train_results.json +5 -5
- trainer_state.json +65 -761
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
"eval_samples": 277,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 2490,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7472924187725631,
|
| 4 |
+
"eval_loss": 0.5988962054252625,
|
| 5 |
+
"eval_runtime": 0.3009,
|
| 6 |
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 920.67,
|
| 8 |
+
"eval_steps_per_second": 9.971,
|
| 9 |
+
"train_loss": 0.49518577380058093,
|
| 10 |
+
"train_runtime": 60.2408,
|
| 11 |
"train_samples": 2490,
|
| 12 |
+
"train_samples_per_second": 413.341,
|
| 13 |
+
"train_steps_per_second": 12.948
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
"eval_samples": 277,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7472924187725631,
|
| 4 |
+
"eval_loss": 0.5988962054252625,
|
| 5 |
+
"eval_runtime": 0.3009,
|
| 6 |
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 920.67,
|
| 8 |
+
"eval_steps_per_second": 9.971
|
| 9 |
}
|
runs/Jan15_14-25-45_node3/events.out.tfevents.1642227962.node3
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 sha256:86ec7a2500b6f80fe87d847cac323f7130a3b730e48ada599a2f9910622e4b9c
|
| 3 |
+
size 7251
|
runs/Jan15_14-25-45_node3/events.out.tfevents.1642228023.node3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15611aaa3f81743fc33924ae0afe13a8d36e79351c1a1dbe127cd16c92b40f95
|
| 3 |
+
size 363
|
runs/Jan15_14-45-51_node3/1642229168.4472055/events.out.tfevents.1642229168.node3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30d75d791374ffedd3a37ac7babefce0461663bb02452e13316e0c2270b70724
|
| 3 |
+
size 4585
|
runs/Jan15_14-45-51_node3/events.out.tfevents.1642229168.node3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ccabbb2c70db197b63cbdce1e1ed6de1e4e28d706aaed1028c4ffd55b584048
|
| 3 |
+
size 3516
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 2490,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.49518577380058093,
|
| 4 |
+
"train_runtime": 60.2408,
|
| 5 |
"train_samples": 2490,
|
| 6 |
+
"train_samples_per_second": 413.341,
|
| 7 |
+
"train_steps_per_second": 12.948
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -10,808 +10,112 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
"eval_accuracy": 0.4729241877256318,
|
| 13 |
-
"eval_loss": 0.
|
| 14 |
-
"eval_runtime": 0.
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second":
|
| 17 |
"step": 78
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 2.0,
|
| 21 |
-
"eval_accuracy": 0.
|
| 22 |
-
"eval_loss": 0.
|
| 23 |
-
"eval_runtime": 0.
|
| 24 |
-
"eval_samples_per_second":
|
| 25 |
-
"eval_steps_per_second":
|
| 26 |
"step": 156
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 3.0,
|
| 30 |
-
"eval_accuracy": 0.
|
| 31 |
-
"eval_loss": 0.
|
| 32 |
-
"eval_runtime": 0.
|
| 33 |
-
"eval_samples_per_second":
|
| 34 |
-
"eval_steps_per_second":
|
| 35 |
"step": 234
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 4.0,
|
| 39 |
-
"eval_accuracy": 0.
|
| 40 |
-
"eval_loss": 0.
|
| 41 |
-
"eval_runtime": 0.
|
| 42 |
-
"eval_samples_per_second": 1214.
|
| 43 |
-
"eval_steps_per_second": 13.
|
| 44 |
"step": 312
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 5.0,
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss": 0.
|
| 50 |
-
"eval_runtime": 0.
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second":
|
| 53 |
"step": 390
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 6.0,
|
| 57 |
-
"eval_accuracy": 0.
|
| 58 |
-
"eval_loss": 0.
|
| 59 |
-
"eval_runtime": 0.
|
| 60 |
-
"eval_samples_per_second":
|
| 61 |
-
"eval_steps_per_second":
|
| 62 |
"step": 468
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 6.41,
|
| 66 |
-
"learning_rate": 0.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 7.0,
|
| 72 |
-
"eval_accuracy": 0.
|
| 73 |
-
"eval_loss": 0.
|
| 74 |
-
"eval_runtime": 0.
|
| 75 |
-
"eval_samples_per_second":
|
| 76 |
-
"eval_steps_per_second":
|
| 77 |
"step": 546
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 8.0,
|
| 81 |
-
"eval_accuracy": 0.
|
| 82 |
-
"eval_loss": 0.
|
| 83 |
-
"eval_runtime": 0.
|
| 84 |
-
"eval_samples_per_second":
|
| 85 |
-
"eval_steps_per_second":
|
| 86 |
"step": 624
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 9.0,
|
| 90 |
-
"eval_accuracy": 0.
|
| 91 |
-
"eval_loss": 0.
|
| 92 |
-
"eval_runtime": 0.
|
| 93 |
-
"eval_samples_per_second":
|
| 94 |
-
"eval_steps_per_second":
|
| 95 |
"step": 702
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 10.0,
|
| 99 |
-
"eval_accuracy": 0.
|
| 100 |
-
"eval_loss": 0.
|
| 101 |
-
"eval_runtime": 0.
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
"step": 780
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 12.0,
|
| 117 |
-
"eval_accuracy": 0.7545126353790613,
|
| 118 |
-
"eval_loss": 0.7537366151809692,
|
| 119 |
-
"eval_runtime": 0.2349,
|
| 120 |
-
"eval_samples_per_second": 1179.15,
|
| 121 |
-
"eval_steps_per_second": 12.771,
|
| 122 |
-
"step": 936
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 12.82,
|
| 126 |
-
"learning_rate": 0.00044671781756180733,
|
| 127 |
-
"loss": 0.3007,
|
| 128 |
-
"step": 1000
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 13.0,
|
| 132 |
-
"eval_accuracy": 0.7653429602888087,
|
| 133 |
-
"eval_loss": 0.8136062622070312,
|
| 134 |
-
"eval_runtime": 0.2324,
|
| 135 |
-
"eval_samples_per_second": 1191.907,
|
| 136 |
-
"eval_steps_per_second": 12.909,
|
| 137 |
-
"step": 1014
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 14.0,
|
| 141 |
-
"eval_accuracy": 0.7003610108303249,
|
| 142 |
-
"eval_loss": 1.2378367185592651,
|
| 143 |
-
"eval_runtime": 0.2301,
|
| 144 |
-
"eval_samples_per_second": 1203.951,
|
| 145 |
-
"eval_steps_per_second": 13.039,
|
| 146 |
-
"step": 1092
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 15.0,
|
| 150 |
-
"eval_accuracy": 0.7689530685920578,
|
| 151 |
-
"eval_loss": 0.787124514579773,
|
| 152 |
-
"eval_runtime": 0.2444,
|
| 153 |
-
"eval_samples_per_second": 1133.544,
|
| 154 |
-
"eval_steps_per_second": 12.277,
|
| 155 |
-
"step": 1170
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 16.0,
|
| 159 |
-
"eval_accuracy": 0.7545126353790613,
|
| 160 |
-
"eval_loss": 1.070081114768982,
|
| 161 |
-
"eval_runtime": 0.2359,
|
| 162 |
-
"eval_samples_per_second": 1174.133,
|
| 163 |
-
"eval_steps_per_second": 12.716,
|
| 164 |
-
"step": 1248
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 17.0,
|
| 168 |
-
"eval_accuracy": 0.776173285198556,
|
| 169 |
-
"eval_loss": 0.840284526348114,
|
| 170 |
-
"eval_runtime": 0.3239,
|
| 171 |
-
"eval_samples_per_second": 855.277,
|
| 172 |
-
"eval_steps_per_second": 9.263,
|
| 173 |
-
"step": 1326
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 18.0,
|
| 177 |
-
"eval_accuracy": 0.7364620938628159,
|
| 178 |
-
"eval_loss": 1.004836082458496,
|
| 179 |
-
"eval_runtime": 0.2349,
|
| 180 |
-
"eval_samples_per_second": 1179.426,
|
| 181 |
-
"eval_steps_per_second": 12.774,
|
| 182 |
-
"step": 1404
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 19.0,
|
| 186 |
-
"eval_accuracy": 0.7725631768953068,
|
| 187 |
-
"eval_loss": 1.151750087738037,
|
| 188 |
-
"eval_runtime": 0.2448,
|
| 189 |
-
"eval_samples_per_second": 1131.443,
|
| 190 |
-
"eval_steps_per_second": 12.254,
|
| 191 |
-
"step": 1482
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 19.23,
|
| 195 |
-
"learning_rate": 0.0004040920716112532,
|
| 196 |
-
"loss": 0.1396,
|
| 197 |
-
"step": 1500
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 20.0,
|
| 201 |
-
"eval_accuracy": 0.7509025270758123,
|
| 202 |
-
"eval_loss": 1.3428694009780884,
|
| 203 |
-
"eval_runtime": 0.2276,
|
| 204 |
-
"eval_samples_per_second": 1217.064,
|
| 205 |
-
"eval_steps_per_second": 13.181,
|
| 206 |
-
"step": 1560
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 21.0,
|
| 210 |
-
"eval_accuracy": 0.7617328519855595,
|
| 211 |
-
"eval_loss": 1.3712104558944702,
|
| 212 |
-
"eval_runtime": 0.3329,
|
| 213 |
-
"eval_samples_per_second": 832.029,
|
| 214 |
-
"eval_steps_per_second": 9.011,
|
| 215 |
-
"step": 1638
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 22.0,
|
| 219 |
-
"eval_accuracy": 0.740072202166065,
|
| 220 |
-
"eval_loss": 1.764930009841919,
|
| 221 |
-
"eval_runtime": 0.2783,
|
| 222 |
-
"eval_samples_per_second": 995.158,
|
| 223 |
-
"eval_steps_per_second": 10.778,
|
| 224 |
-
"step": 1716
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 23.0,
|
| 228 |
-
"eval_accuracy": 0.7436823104693141,
|
| 229 |
-
"eval_loss": 1.5562723875045776,
|
| 230 |
-
"eval_runtime": 0.2305,
|
| 231 |
-
"eval_samples_per_second": 1201.943,
|
| 232 |
-
"eval_steps_per_second": 13.017,
|
| 233 |
-
"step": 1794
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 24.0,
|
| 237 |
-
"eval_accuracy": 0.7653429602888087,
|
| 238 |
-
"eval_loss": 1.4325311183929443,
|
| 239 |
-
"eval_runtime": 0.2723,
|
| 240 |
-
"eval_samples_per_second": 1017.092,
|
| 241 |
-
"eval_steps_per_second": 11.015,
|
| 242 |
-
"step": 1872
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 25.0,
|
| 246 |
-
"eval_accuracy": 0.7509025270758123,
|
| 247 |
-
"eval_loss": 1.7198717594146729,
|
| 248 |
-
"eval_runtime": 0.3389,
|
| 249 |
-
"eval_samples_per_second": 817.452,
|
| 250 |
-
"eval_steps_per_second": 8.853,
|
| 251 |
-
"step": 1950
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 25.64,
|
| 255 |
-
"learning_rate": 0.0003614663256606991,
|
| 256 |
-
"loss": 0.0875,
|
| 257 |
-
"step": 2000
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 26.0,
|
| 261 |
-
"eval_accuracy": 0.7545126353790613,
|
| 262 |
-
"eval_loss": 1.5090142488479614,
|
| 263 |
-
"eval_runtime": 0.2361,
|
| 264 |
-
"eval_samples_per_second": 1173.253,
|
| 265 |
-
"eval_steps_per_second": 12.707,
|
| 266 |
-
"step": 2028
|
| 267 |
-
},
|
| 268 |
-
{
|
| 269 |
-
"epoch": 27.0,
|
| 270 |
-
"eval_accuracy": 0.7436823104693141,
|
| 271 |
-
"eval_loss": 1.8515905141830444,
|
| 272 |
-
"eval_runtime": 0.2487,
|
| 273 |
-
"eval_samples_per_second": 1113.898,
|
| 274 |
-
"eval_steps_per_second": 12.064,
|
| 275 |
-
"step": 2106
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 28.0,
|
| 279 |
-
"eval_accuracy": 0.7509025270758123,
|
| 280 |
-
"eval_loss": 1.5827966928482056,
|
| 281 |
-
"eval_runtime": 0.3236,
|
| 282 |
-
"eval_samples_per_second": 856.029,
|
| 283 |
-
"eval_steps_per_second": 9.271,
|
| 284 |
-
"step": 2184
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 29.0,
|
| 288 |
-
"eval_accuracy": 0.7509025270758123,
|
| 289 |
-
"eval_loss": 1.9509788751602173,
|
| 290 |
-
"eval_runtime": 0.2848,
|
| 291 |
-
"eval_samples_per_second": 972.601,
|
| 292 |
-
"eval_steps_per_second": 10.534,
|
| 293 |
-
"step": 2262
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 30.0,
|
| 297 |
-
"eval_accuracy": 0.7617328519855595,
|
| 298 |
-
"eval_loss": 1.903420329093933,
|
| 299 |
-
"eval_runtime": 0.3114,
|
| 300 |
-
"eval_samples_per_second": 889.649,
|
| 301 |
-
"eval_steps_per_second": 9.635,
|
| 302 |
-
"step": 2340
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 31.0,
|
| 306 |
-
"eval_accuracy": 0.7364620938628159,
|
| 307 |
-
"eval_loss": 2.065227508544922,
|
| 308 |
-
"eval_runtime": 0.2318,
|
| 309 |
-
"eval_samples_per_second": 1195.129,
|
| 310 |
-
"eval_steps_per_second": 12.944,
|
| 311 |
-
"step": 2418
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 32.0,
|
| 315 |
-
"eval_accuracy": 0.7617328519855595,
|
| 316 |
-
"eval_loss": 1.5601612329483032,
|
| 317 |
-
"eval_runtime": 0.2455,
|
| 318 |
-
"eval_samples_per_second": 1128.485,
|
| 319 |
-
"eval_steps_per_second": 12.222,
|
| 320 |
-
"step": 2496
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 32.05,
|
| 324 |
-
"learning_rate": 0.0003188405797101449,
|
| 325 |
-
"loss": 0.0561,
|
| 326 |
-
"step": 2500
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 33.0,
|
| 330 |
-
"eval_accuracy": 0.7653429602888087,
|
| 331 |
-
"eval_loss": 1.9638988971710205,
|
| 332 |
-
"eval_runtime": 0.3284,
|
| 333 |
-
"eval_samples_per_second": 843.409,
|
| 334 |
-
"eval_steps_per_second": 9.134,
|
| 335 |
-
"step": 2574
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 34.0,
|
| 339 |
-
"eval_accuracy": 0.7653429602888087,
|
| 340 |
-
"eval_loss": 2.137803792953491,
|
| 341 |
-
"eval_runtime": 0.2261,
|
| 342 |
-
"eval_samples_per_second": 1225.21,
|
| 343 |
-
"eval_steps_per_second": 13.269,
|
| 344 |
-
"step": 2652
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 35.0,
|
| 348 |
-
"eval_accuracy": 0.7509025270758123,
|
| 349 |
-
"eval_loss": 1.8859294652938843,
|
| 350 |
-
"eval_runtime": 0.2755,
|
| 351 |
-
"eval_samples_per_second": 1005.403,
|
| 352 |
-
"eval_steps_per_second": 10.889,
|
| 353 |
-
"step": 2730
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 36.0,
|
| 357 |
-
"eval_accuracy": 0.7653429602888087,
|
| 358 |
-
"eval_loss": 1.9513648748397827,
|
| 359 |
-
"eval_runtime": 0.3253,
|
| 360 |
-
"eval_samples_per_second": 851.469,
|
| 361 |
-
"eval_steps_per_second": 9.222,
|
| 362 |
-
"step": 2808
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 37.0,
|
| 366 |
-
"eval_accuracy": 0.7725631768953068,
|
| 367 |
-
"eval_loss": 1.9519377946853638,
|
| 368 |
-
"eval_runtime": 0.2278,
|
| 369 |
-
"eval_samples_per_second": 1215.717,
|
| 370 |
-
"eval_steps_per_second": 13.167,
|
| 371 |
-
"step": 2886
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 38.0,
|
| 375 |
-
"eval_accuracy": 0.7617328519855595,
|
| 376 |
-
"eval_loss": 2.181129217147827,
|
| 377 |
-
"eval_runtime": 0.2412,
|
| 378 |
-
"eval_samples_per_second": 1148.242,
|
| 379 |
-
"eval_steps_per_second": 12.436,
|
| 380 |
-
"step": 2964
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 38.46,
|
| 384 |
-
"learning_rate": 0.00027621483375959077,
|
| 385 |
-
"loss": 0.0423,
|
| 386 |
-
"step": 3000
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 39.0,
|
| 390 |
-
"eval_accuracy": 0.7581227436823105,
|
| 391 |
-
"eval_loss": 2.104398250579834,
|
| 392 |
-
"eval_runtime": 0.3032,
|
| 393 |
-
"eval_samples_per_second": 913.545,
|
| 394 |
-
"eval_steps_per_second": 9.894,
|
| 395 |
-
"step": 3042
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 40.0,
|
| 399 |
-
"eval_accuracy": 0.7689530685920578,
|
| 400 |
-
"eval_loss": 2.0705928802490234,
|
| 401 |
-
"eval_runtime": 0.2647,
|
| 402 |
-
"eval_samples_per_second": 1046.589,
|
| 403 |
-
"eval_steps_per_second": 11.335,
|
| 404 |
-
"step": 3120
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 41.0,
|
| 408 |
-
"eval_accuracy": 0.7870036101083032,
|
| 409 |
-
"eval_loss": 1.89673912525177,
|
| 410 |
-
"eval_runtime": 0.2316,
|
| 411 |
-
"eval_samples_per_second": 1195.807,
|
| 412 |
-
"eval_steps_per_second": 12.951,
|
| 413 |
-
"step": 3198
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 42.0,
|
| 417 |
-
"eval_accuracy": 0.7906137184115524,
|
| 418 |
-
"eval_loss": 2.081404209136963,
|
| 419 |
-
"eval_runtime": 0.3113,
|
| 420 |
-
"eval_samples_per_second": 889.737,
|
| 421 |
-
"eval_steps_per_second": 9.636,
|
| 422 |
-
"step": 3276
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 43.0,
|
| 426 |
-
"eval_accuracy": 0.779783393501805,
|
| 427 |
-
"eval_loss": 2.200363874435425,
|
| 428 |
-
"eval_runtime": 0.3027,
|
| 429 |
-
"eval_samples_per_second": 914.986,
|
| 430 |
-
"eval_steps_per_second": 9.91,
|
| 431 |
-
"step": 3354
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 44.0,
|
| 435 |
-
"eval_accuracy": 0.7689530685920578,
|
| 436 |
-
"eval_loss": 2.4501726627349854,
|
| 437 |
-
"eval_runtime": 0.3032,
|
| 438 |
-
"eval_samples_per_second": 913.655,
|
| 439 |
-
"eval_steps_per_second": 9.895,
|
| 440 |
-
"step": 3432
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 44.87,
|
| 444 |
-
"learning_rate": 0.00023358908780903668,
|
| 445 |
-
"loss": 0.0294,
|
| 446 |
-
"step": 3500
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 45.0,
|
| 450 |
-
"eval_accuracy": 0.7725631768953068,
|
| 451 |
-
"eval_loss": 2.2387545108795166,
|
| 452 |
-
"eval_runtime": 0.308,
|
| 453 |
-
"eval_samples_per_second": 899.428,
|
| 454 |
-
"eval_steps_per_second": 9.741,
|
| 455 |
-
"step": 3510
|
| 456 |
-
},
|
| 457 |
-
{
|
| 458 |
-
"epoch": 46.0,
|
| 459 |
-
"eval_accuracy": 0.7978339350180506,
|
| 460 |
-
"eval_loss": 2.1785941123962402,
|
| 461 |
-
"eval_runtime": 0.2416,
|
| 462 |
-
"eval_samples_per_second": 1146.514,
|
| 463 |
-
"eval_steps_per_second": 12.417,
|
| 464 |
-
"step": 3588
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 47.0,
|
| 468 |
-
"eval_accuracy": 0.7653429602888087,
|
| 469 |
-
"eval_loss": 2.5040040016174316,
|
| 470 |
-
"eval_runtime": 0.2296,
|
| 471 |
-
"eval_samples_per_second": 1206.456,
|
| 472 |
-
"eval_steps_per_second": 13.066,
|
| 473 |
-
"step": 3666
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 48.0,
|
| 477 |
-
"eval_accuracy": 0.779783393501805,
|
| 478 |
-
"eval_loss": 2.4230690002441406,
|
| 479 |
-
"eval_runtime": 0.3106,
|
| 480 |
-
"eval_samples_per_second": 891.893,
|
| 481 |
-
"eval_steps_per_second": 9.659,
|
| 482 |
-
"step": 3744
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 49.0,
|
| 486 |
-
"eval_accuracy": 0.776173285198556,
|
| 487 |
-
"eval_loss": 2.3979299068450928,
|
| 488 |
-
"eval_runtime": 0.2331,
|
| 489 |
-
"eval_samples_per_second": 1188.417,
|
| 490 |
-
"eval_steps_per_second": 12.871,
|
| 491 |
-
"step": 3822
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 50.0,
|
| 495 |
-
"eval_accuracy": 0.8050541516245487,
|
| 496 |
-
"eval_loss": 2.2128214836120605,
|
| 497 |
-
"eval_runtime": 0.2857,
|
| 498 |
-
"eval_samples_per_second": 969.393,
|
| 499 |
-
"eval_steps_per_second": 10.499,
|
| 500 |
-
"step": 3900
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 51.0,
|
| 504 |
-
"eval_accuracy": 0.7870036101083032,
|
| 505 |
-
"eval_loss": 2.4434621334075928,
|
| 506 |
-
"eval_runtime": 0.232,
|
| 507 |
-
"eval_samples_per_second": 1193.915,
|
| 508 |
-
"eval_steps_per_second": 12.93,
|
| 509 |
-
"step": 3978
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 51.28,
|
| 513 |
-
"learning_rate": 0.00019096334185848252,
|
| 514 |
-
"loss": 0.0247,
|
| 515 |
-
"step": 4000
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 52.0,
|
| 519 |
-
"eval_accuracy": 0.8050541516245487,
|
| 520 |
-
"eval_loss": 2.1702017784118652,
|
| 521 |
-
"eval_runtime": 0.2785,
|
| 522 |
-
"eval_samples_per_second": 994.698,
|
| 523 |
-
"eval_steps_per_second": 10.773,
|
| 524 |
-
"step": 4056
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 53.0,
|
| 528 |
-
"eval_accuracy": 0.7942238267148014,
|
| 529 |
-
"eval_loss": 2.052528142929077,
|
| 530 |
-
"eval_runtime": 0.2278,
|
| 531 |
-
"eval_samples_per_second": 1216.111,
|
| 532 |
-
"eval_steps_per_second": 13.171,
|
| 533 |
-
"step": 4134
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 54.0,
|
| 537 |
-
"eval_accuracy": 0.7978339350180506,
|
| 538 |
-
"eval_loss": 2.259878396987915,
|
| 539 |
-
"eval_runtime": 0.2332,
|
| 540 |
-
"eval_samples_per_second": 1187.792,
|
| 541 |
-
"eval_steps_per_second": 12.864,
|
| 542 |
-
"step": 4212
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 55.0,
|
| 546 |
-
"eval_accuracy": 0.7870036101083032,
|
| 547 |
-
"eval_loss": 2.3375229835510254,
|
| 548 |
-
"eval_runtime": 0.2354,
|
| 549 |
-
"eval_samples_per_second": 1176.728,
|
| 550 |
-
"eval_steps_per_second": 12.744,
|
| 551 |
-
"step": 4290
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 56.0,
|
| 555 |
-
"eval_accuracy": 0.776173285198556,
|
| 556 |
-
"eval_loss": 2.3791956901550293,
|
| 557 |
-
"eval_runtime": 0.2303,
|
| 558 |
-
"eval_samples_per_second": 1202.553,
|
| 559 |
-
"eval_steps_per_second": 13.024,
|
| 560 |
-
"step": 4368
|
| 561 |
-
},
|
| 562 |
-
{
|
| 563 |
-
"epoch": 57.0,
|
| 564 |
-
"eval_accuracy": 0.7617328519855595,
|
| 565 |
-
"eval_loss": 2.6323866844177246,
|
| 566 |
-
"eval_runtime": 0.2788,
|
| 567 |
-
"eval_samples_per_second": 993.528,
|
| 568 |
-
"eval_steps_per_second": 10.76,
|
| 569 |
-
"step": 4446
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 57.69,
|
| 573 |
-
"learning_rate": 0.0001483375959079284,
|
| 574 |
-
"loss": 0.0262,
|
| 575 |
-
"step": 4500
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 58.0,
|
| 579 |
-
"eval_accuracy": 0.7725631768953068,
|
| 580 |
-
"eval_loss": 2.386228561401367,
|
| 581 |
-
"eval_runtime": 0.2333,
|
| 582 |
-
"eval_samples_per_second": 1187.256,
|
| 583 |
-
"eval_steps_per_second": 12.858,
|
| 584 |
-
"step": 4524
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 59.0,
|
| 588 |
-
"eval_accuracy": 0.7653429602888087,
|
| 589 |
-
"eval_loss": 2.629952907562256,
|
| 590 |
-
"eval_runtime": 0.2289,
|
| 591 |
-
"eval_samples_per_second": 1210.168,
|
| 592 |
-
"eval_steps_per_second": 13.107,
|
| 593 |
-
"step": 4602
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 60.0,
|
| 597 |
-
"eval_accuracy": 0.7689530685920578,
|
| 598 |
-
"eval_loss": 2.5751161575317383,
|
| 599 |
-
"eval_runtime": 0.2343,
|
| 600 |
-
"eval_samples_per_second": 1182.419,
|
| 601 |
-
"eval_steps_per_second": 12.806,
|
| 602 |
-
"step": 4680
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 61.0,
|
| 606 |
-
"eval_accuracy": 0.776173285198556,
|
| 607 |
-
"eval_loss": 2.4631881713867188,
|
| 608 |
-
"eval_runtime": 0.3299,
|
| 609 |
-
"eval_samples_per_second": 839.738,
|
| 610 |
-
"eval_steps_per_second": 9.095,
|
| 611 |
-
"step": 4758
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 62.0,
|
| 615 |
-
"eval_accuracy": 0.779783393501805,
|
| 616 |
-
"eval_loss": 2.332425117492676,
|
| 617 |
-
"eval_runtime": 0.2338,
|
| 618 |
-
"eval_samples_per_second": 1184.805,
|
| 619 |
-
"eval_steps_per_second": 12.832,
|
| 620 |
-
"step": 4836
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 63.0,
|
| 624 |
-
"eval_accuracy": 0.7942238267148014,
|
| 625 |
-
"eval_loss": 2.282438039779663,
|
| 626 |
-
"eval_runtime": 0.3154,
|
| 627 |
-
"eval_samples_per_second": 878.349,
|
| 628 |
-
"eval_steps_per_second": 9.513,
|
| 629 |
-
"step": 4914
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 64.0,
|
| 633 |
-
"eval_accuracy": 0.7725631768953068,
|
| 634 |
-
"eval_loss": 2.5226333141326904,
|
| 635 |
-
"eval_runtime": 0.2747,
|
| 636 |
-
"eval_samples_per_second": 1008.395,
|
| 637 |
-
"eval_steps_per_second": 10.921,
|
| 638 |
-
"step": 4992
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 64.1,
|
| 642 |
-
"learning_rate": 0.00010571184995737426,
|
| 643 |
-
"loss": 0.0163,
|
| 644 |
-
"step": 5000
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 65.0,
|
| 648 |
-
"eval_accuracy": 0.7833935018050542,
|
| 649 |
-
"eval_loss": 2.5482494831085205,
|
| 650 |
-
"eval_runtime": 0.2312,
|
| 651 |
-
"eval_samples_per_second": 1198.154,
|
| 652 |
-
"eval_steps_per_second": 12.976,
|
| 653 |
-
"step": 5070
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 66.0,
|
| 657 |
-
"eval_accuracy": 0.7906137184115524,
|
| 658 |
-
"eval_loss": 2.5009658336639404,
|
| 659 |
-
"eval_runtime": 0.2315,
|
| 660 |
-
"eval_samples_per_second": 1196.726,
|
| 661 |
-
"eval_steps_per_second": 12.961,
|
| 662 |
-
"step": 5148
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 67.0,
|
| 666 |
-
"eval_accuracy": 0.7653429602888087,
|
| 667 |
-
"eval_loss": 2.863718032836914,
|
| 668 |
-
"eval_runtime": 0.2338,
|
| 669 |
-
"eval_samples_per_second": 1184.556,
|
| 670 |
-
"eval_steps_per_second": 12.829,
|
| 671 |
-
"step": 5226
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 68.0,
|
| 675 |
-
"eval_accuracy": 0.7833935018050542,
|
| 676 |
-
"eval_loss": 2.638036012649536,
|
| 677 |
-
"eval_runtime": 0.3062,
|
| 678 |
-
"eval_samples_per_second": 904.565,
|
| 679 |
-
"eval_steps_per_second": 9.797,
|
| 680 |
-
"step": 5304
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"epoch": 69.0,
|
| 684 |
-
"eval_accuracy": 0.779783393501805,
|
| 685 |
-
"eval_loss": 2.676180839538574,
|
| 686 |
-
"eval_runtime": 0.2797,
|
| 687 |
-
"eval_samples_per_second": 990.196,
|
| 688 |
-
"eval_steps_per_second": 10.724,
|
| 689 |
-
"step": 5382
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 70.0,
|
| 693 |
-
"eval_accuracy": 0.779783393501805,
|
| 694 |
-
"eval_loss": 2.7992238998413086,
|
| 695 |
-
"eval_runtime": 0.2332,
|
| 696 |
-
"eval_samples_per_second": 1187.793,
|
| 697 |
-
"eval_steps_per_second": 12.864,
|
| 698 |
-
"step": 5460
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 70.51,
|
| 702 |
-
"learning_rate": 6.308610400682012e-05,
|
| 703 |
-
"loss": 0.0133,
|
| 704 |
-
"step": 5500
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 71.0,
|
| 708 |
-
"eval_accuracy": 0.7870036101083032,
|
| 709 |
-
"eval_loss": 2.691901445388794,
|
| 710 |
-
"eval_runtime": 0.2313,
|
| 711 |
-
"eval_samples_per_second": 1197.649,
|
| 712 |
-
"eval_steps_per_second": 12.971,
|
| 713 |
-
"step": 5538
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 72.0,
|
| 717 |
-
"eval_accuracy": 0.7833935018050542,
|
| 718 |
-
"eval_loss": 2.6941630840301514,
|
| 719 |
-
"eval_runtime": 0.3108,
|
| 720 |
-
"eval_samples_per_second": 891.377,
|
| 721 |
-
"eval_steps_per_second": 9.654,
|
| 722 |
-
"step": 5616
|
| 723 |
-
},
|
| 724 |
-
{
|
| 725 |
-
"epoch": 73.0,
|
| 726 |
-
"eval_accuracy": 0.7942238267148014,
|
| 727 |
-
"eval_loss": 2.6317222118377686,
|
| 728 |
-
"eval_runtime": 0.2308,
|
| 729 |
-
"eval_samples_per_second": 1200.365,
|
| 730 |
-
"eval_steps_per_second": 13.0,
|
| 731 |
-
"step": 5694
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 74.0,
|
| 735 |
-
"eval_accuracy": 0.7870036101083032,
|
| 736 |
-
"eval_loss": 2.635883331298828,
|
| 737 |
-
"eval_runtime": 0.2325,
|
| 738 |
-
"eval_samples_per_second": 1191.569,
|
| 739 |
-
"eval_steps_per_second": 12.905,
|
| 740 |
-
"step": 5772
|
| 741 |
-
},
|
| 742 |
-
{
|
| 743 |
-
"epoch": 75.0,
|
| 744 |
-
"eval_accuracy": 0.7870036101083032,
|
| 745 |
-
"eval_loss": 2.631652593612671,
|
| 746 |
-
"eval_runtime": 0.2307,
|
| 747 |
-
"eval_samples_per_second": 1200.479,
|
| 748 |
-
"eval_steps_per_second": 13.002,
|
| 749 |
-
"step": 5850
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 76.0,
|
| 753 |
-
"eval_accuracy": 0.7833935018050542,
|
| 754 |
-
"eval_loss": 2.68886661529541,
|
| 755 |
-
"eval_runtime": 0.2322,
|
| 756 |
-
"eval_samples_per_second": 1193.142,
|
| 757 |
-
"eval_steps_per_second": 12.922,
|
| 758 |
-
"step": 5928
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 76.92,
|
| 762 |
-
"learning_rate": 2.0460358056265986e-05,
|
| 763 |
-
"loss": 0.0085,
|
| 764 |
-
"step": 6000
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 77.0,
|
| 768 |
-
"eval_accuracy": 0.7833935018050542,
|
| 769 |
-
"eval_loss": 2.730724811553955,
|
| 770 |
-
"eval_runtime": 0.2718,
|
| 771 |
-
"eval_samples_per_second": 1019.194,
|
| 772 |
-
"eval_steps_per_second": 11.038,
|
| 773 |
-
"step": 6006
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 78.0,
|
| 777 |
-
"eval_accuracy": 0.779783393501805,
|
| 778 |
-
"eval_loss": 2.7645108699798584,
|
| 779 |
-
"eval_runtime": 0.232,
|
| 780 |
-
"eval_samples_per_second": 1193.866,
|
| 781 |
-
"eval_steps_per_second": 12.93,
|
| 782 |
-
"step": 6084
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 79.0,
|
| 786 |
-
"eval_accuracy": 0.7833935018050542,
|
| 787 |
-
"eval_loss": 2.7476391792297363,
|
| 788 |
-
"eval_runtime": 0.3197,
|
| 789 |
-
"eval_samples_per_second": 866.393,
|
| 790 |
-
"eval_steps_per_second": 9.383,
|
| 791 |
-
"step": 6162
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 80.0,
|
| 795 |
-
"eval_accuracy": 0.7833935018050542,
|
| 796 |
-
"eval_loss": 2.7370429039001465,
|
| 797 |
-
"eval_runtime": 0.2352,
|
| 798 |
-
"eval_samples_per_second": 1177.509,
|
| 799 |
-
"eval_steps_per_second": 12.753,
|
| 800 |
-
"step": 6240
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 80.0,
|
| 804 |
-
"step": 6240,
|
| 805 |
-
"total_flos": 1.31480478461952e+16,
|
| 806 |
-
"train_loss": 0.10918387793577634,
|
| 807 |
-
"train_runtime": 662.0132,
|
| 808 |
-
"train_samples_per_second": 300.9,
|
| 809 |
-
"train_steps_per_second": 9.426
|
| 810 |
}
|
| 811 |
],
|
| 812 |
-
"max_steps":
|
| 813 |
-
"num_train_epochs":
|
| 814 |
-
"total_flos":
|
| 815 |
"trial_name": null,
|
| 816 |
"trial_params": null
|
| 817 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7472924187725631,
|
| 3 |
+
"best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-702",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 780,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
"eval_accuracy": 0.4729241877256318,
|
| 13 |
+
"eval_loss": 0.700201690196991,
|
| 14 |
+
"eval_runtime": 0.2542,
|
| 15 |
+
"eval_samples_per_second": 1089.901,
|
| 16 |
+
"eval_steps_per_second": 11.804,
|
| 17 |
"step": 78
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 2.0,
|
| 21 |
+
"eval_accuracy": 0.6389891696750902,
|
| 22 |
+
"eval_loss": 0.6369197964668274,
|
| 23 |
+
"eval_runtime": 0.3571,
|
| 24 |
+
"eval_samples_per_second": 775.771,
|
| 25 |
+
"eval_steps_per_second": 8.402,
|
| 26 |
"step": 156
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 3.0,
|
| 30 |
+
"eval_accuracy": 0.6606498194945848,
|
| 31 |
+
"eval_loss": 0.6243730783462524,
|
| 32 |
+
"eval_runtime": 0.2436,
|
| 33 |
+
"eval_samples_per_second": 1137.183,
|
| 34 |
+
"eval_steps_per_second": 12.316,
|
| 35 |
"step": 234
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 4.0,
|
| 39 |
+
"eval_accuracy": 0.7184115523465704,
|
| 40 |
+
"eval_loss": 0.572300136089325,
|
| 41 |
+
"eval_runtime": 0.228,
|
| 42 |
+
"eval_samples_per_second": 1214.712,
|
| 43 |
+
"eval_steps_per_second": 13.156,
|
| 44 |
"step": 312
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 5.0,
|
| 48 |
+
"eval_accuracy": 0.7220216606498195,
|
| 49 |
+
"eval_loss": 0.5677592754364014,
|
| 50 |
+
"eval_runtime": 0.2299,
|
| 51 |
+
"eval_samples_per_second": 1204.73,
|
| 52 |
+
"eval_steps_per_second": 13.048,
|
| 53 |
"step": 390
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 6.0,
|
| 57 |
+
"eval_accuracy": 0.7220216606498195,
|
| 58 |
+
"eval_loss": 0.6392128467559814,
|
| 59 |
+
"eval_runtime": 0.2306,
|
| 60 |
+
"eval_samples_per_second": 1201.256,
|
| 61 |
+
"eval_steps_per_second": 13.01,
|
| 62 |
"step": 468
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 6.41,
|
| 66 |
+
"learning_rate": 0.00019099590723055935,
|
| 67 |
+
"loss": 0.5649,
|
| 68 |
"step": 500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 7.0,
|
| 72 |
+
"eval_accuracy": 0.7364620938628159,
|
| 73 |
+
"eval_loss": 0.5661243200302124,
|
| 74 |
+
"eval_runtime": 0.3267,
|
| 75 |
+
"eval_samples_per_second": 847.854,
|
| 76 |
+
"eval_steps_per_second": 9.183,
|
| 77 |
"step": 546
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 8.0,
|
| 81 |
+
"eval_accuracy": 0.7328519855595668,
|
| 82 |
+
"eval_loss": 0.6633248329162598,
|
| 83 |
+
"eval_runtime": 0.228,
|
| 84 |
+
"eval_samples_per_second": 1214.709,
|
| 85 |
+
"eval_steps_per_second": 13.156,
|
| 86 |
"step": 624
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 9.0,
|
| 90 |
+
"eval_accuracy": 0.7472924187725631,
|
| 91 |
+
"eval_loss": 0.5988962054252625,
|
| 92 |
+
"eval_runtime": 0.2338,
|
| 93 |
+
"eval_samples_per_second": 1184.722,
|
| 94 |
+
"eval_steps_per_second": 12.831,
|
| 95 |
"step": 702
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 10.0,
|
| 99 |
+
"eval_accuracy": 0.7292418772563177,
|
| 100 |
+
"eval_loss": 0.6346577405929565,
|
| 101 |
+
"eval_runtime": 0.2362,
|
| 102 |
+
"eval_samples_per_second": 1172.727,
|
| 103 |
+
"eval_steps_per_second": 12.701,
|
| 104 |
"step": 780
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 10.0,
|
| 108 |
+
"step": 780,
|
| 109 |
+
"total_flos": 1643505980774400.0,
|
| 110 |
+
"train_loss": 0.49518577380058093,
|
| 111 |
+
"train_runtime": 60.2408,
|
| 112 |
+
"train_samples_per_second": 413.341,
|
| 113 |
+
"train_steps_per_second": 12.948
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
}
|
| 115 |
],
|
| 116 |
+
"max_steps": 780,
|
| 117 |
+
"num_train_epochs": 10,
|
| 118 |
+
"total_flos": 1643505980774400.0,
|
| 119 |
"trial_name": null,
|
| 120 |
"trial_params": null
|
| 121 |
}
|
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:db3be2cac0cb77090e11e0d4f57a25a90219062e587aa740922cc72ee94791b6
|
| 3 |
size 2991
|