Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +18 -402
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun19_20-59-16_8ec774155421/1687209890.901812/events.out.tfevents.1687209890.8ec774155421.1587.1 +3 -0
- runs/Jun19_20-59-16_8ec774155421/events.out.tfevents.1687209890.8ec774155421.1587.0 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3871543575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1ca558fe245d313604fd389a6004b1c65ad37c609677df360c569cb3b937d7e
|
| 3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1944201353
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82874203cde91954f63917da0013a6bc226b135e310668e99c7dfbec08ec6ad6
|
| 3 |
size 1944201353
|
last-checkpoint/rng_state.pth
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:bac3b6dc509b813a21c5c4e60320aebcaa22059bbd1c6bb3758047e872d2df17
|
| 3 |
+
size 14575
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c04e37b233032e89e5ef09f15ff0eaec4401524b548396f1324fb84e2737b4c
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9938aa06f1913042d5d26005724eb6b5208f63c1c353e69f30be6617d10a34a0
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -10,439 +10,55 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
"learning_rate": 4.9978809321803e-05,
|
| 13 |
-
"loss":
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.03,
|
| 18 |
-
"learning_rate": 4.
|
| 19 |
-
"loss":
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.04,
|
| 24 |
-
"learning_rate": 4.
|
| 25 |
-
"loss":
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.05,
|
| 30 |
-
"learning_rate": 4.
|
| 31 |
-
"loss":
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.07,
|
| 36 |
-
"learning_rate": 4.
|
| 37 |
-
"loss":
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.08,
|
| 42 |
-
"learning_rate": 4.
|
| 43 |
-
"loss":
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.09,
|
| 48 |
-
"learning_rate": 4.
|
| 49 |
-
"loss":
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.1,
|
| 54 |
-
"learning_rate": 4.
|
| 55 |
-
"loss":
|
| 56 |
"step": 4000
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.12,
|
| 60 |
-
"learning_rate": 4.830436051991575e-05,
|
| 61 |
-
"loss": 1.471,
|
| 62 |
-
"step": 4500
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.13,
|
| 66 |
-
"learning_rate": 4.791205648303775e-05,
|
| 67 |
-
"loss": 1.4848,
|
| 68 |
-
"step": 5000
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.14,
|
| 72 |
-
"learning_rate": 4.7480910684898666e-05,
|
| 73 |
-
"loss": 1.4828,
|
| 74 |
-
"step": 5500
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.16,
|
| 78 |
-
"learning_rate": 4.7011654027247644e-05,
|
| 79 |
-
"loss": 1.4773,
|
| 80 |
-
"step": 6000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.17,
|
| 84 |
-
"learning_rate": 4.650508201943061e-05,
|
| 85 |
-
"loss": 1.4821,
|
| 86 |
-
"step": 6500
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.18,
|
| 90 |
-
"learning_rate": 4.5962053429799665e-05,
|
| 91 |
-
"loss": 1.5051,
|
| 92 |
-
"step": 7000
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.2,
|
| 96 |
-
"learning_rate": 4.5383488829882384e-05,
|
| 97 |
-
"loss": 1.4952,
|
| 98 |
-
"step": 7500
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.21,
|
| 102 |
-
"learning_rate": 4.477036903377901e-05,
|
| 103 |
-
"loss": 1.4986,
|
| 104 |
-
"step": 8000
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 0.22,
|
| 108 |
-
"learning_rate": 4.412373343543317e-05,
|
| 109 |
-
"loss": 1.4854,
|
| 110 |
-
"step": 8500
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 0.24,
|
| 114 |
-
"learning_rate": 4.3446067955536154e-05,
|
| 115 |
-
"loss": 1.4922,
|
| 116 |
-
"step": 9000
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.25,
|
| 120 |
-
"learning_rate": 4.273580569980726e-05,
|
| 121 |
-
"loss": 1.5026,
|
| 122 |
-
"step": 9500
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.26,
|
| 126 |
-
"learning_rate": 4.199547674398644e-05,
|
| 127 |
-
"loss": 1.5012,
|
| 128 |
-
"step": 10000
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.28,
|
| 132 |
-
"learning_rate": 4.1226336133886704e-05,
|
| 133 |
-
"loss": 1.492,
|
| 134 |
-
"step": 10500
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 0.29,
|
| 138 |
-
"learning_rate": 4.04296877584006e-05,
|
| 139 |
-
"loss": 1.4902,
|
| 140 |
-
"step": 11000
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 0.3,
|
| 144 |
-
"learning_rate": 3.9606882139077016e-05,
|
| 145 |
-
"loss": 1.4784,
|
| 146 |
-
"step": 11500
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.31,
|
| 150 |
-
"learning_rate": 3.876275184846879e-05,
|
| 151 |
-
"loss": 1.4809,
|
| 152 |
-
"step": 12000
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 0.33,
|
| 156 |
-
"learning_rate": 3.78919487009023e-05,
|
| 157 |
-
"loss": 1.4744,
|
| 158 |
-
"step": 12500
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 0.34,
|
| 162 |
-
"learning_rate": 3.6999290422435554e-05,
|
| 163 |
-
"loss": 1.4659,
|
| 164 |
-
"step": 13000
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.35,
|
| 168 |
-
"learning_rate": 3.608629029581408e-05,
|
| 169 |
-
"loss": 1.4679,
|
| 170 |
-
"step": 13500
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.37,
|
| 174 |
-
"learning_rate": 3.5154496088388036e-05,
|
| 175 |
-
"loss": 1.4721,
|
| 176 |
-
"step": 14000
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.38,
|
| 180 |
-
"learning_rate": 3.420548742825304e-05,
|
| 181 |
-
"loss": 1.4471,
|
| 182 |
-
"step": 14500
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 0.39,
|
| 186 |
-
"learning_rate": 3.3240873126378964e-05,
|
| 187 |
-
"loss": 1.4757,
|
| 188 |
-
"step": 15000
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 0.41,
|
| 192 |
-
"learning_rate": 3.226228844926621e-05,
|
| 193 |
-
"loss": 1.4617,
|
| 194 |
-
"step": 15500
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 0.42,
|
| 198 |
-
"learning_rate": 3.1271392346753284e-05,
|
| 199 |
-
"loss": 1.4551,
|
| 200 |
-
"step": 16000
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 0.43,
|
| 204 |
-
"learning_rate": 3.0269864639674983e-05,
|
| 205 |
-
"loss": 1.4527,
|
| 206 |
-
"step": 16500
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.45,
|
| 210 |
-
"learning_rate": 2.9259403172138987e-05,
|
| 211 |
-
"loss": 1.4356,
|
| 212 |
-
"step": 17000
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 0.46,
|
| 216 |
-
"learning_rate": 2.82437623590975e-05,
|
| 217 |
-
"loss": 1.4362,
|
| 218 |
-
"step": 17500
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 0.47,
|
| 222 |
-
"learning_rate": 2.7220593841620623e-05,
|
| 223 |
-
"loss": 1.432,
|
| 224 |
-
"step": 18000
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 0.48,
|
| 228 |
-
"learning_rate": 2.6193660852983415e-05,
|
| 229 |
-
"loss": 1.4234,
|
| 230 |
-
"step": 18500
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 0.5,
|
| 234 |
-
"learning_rate": 2.516676307917844e-05,
|
| 235 |
-
"loss": 1.436,
|
| 236 |
-
"step": 19000
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 0.51,
|
| 240 |
-
"learning_rate": 2.4137526132994945e-05,
|
| 241 |
-
"loss": 1.4238,
|
| 242 |
-
"step": 19500
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.52,
|
| 246 |
-
"learning_rate": 2.3109751299304977e-05,
|
| 247 |
-
"loss": 1.41,
|
| 248 |
-
"step": 20000
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 0.54,
|
| 252 |
-
"learning_rate": 2.208518091776931e-05,
|
| 253 |
-
"loss": 1.3994,
|
| 254 |
-
"step": 20500
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 0.55,
|
| 258 |
-
"learning_rate": 2.1065551895687553e-05,
|
| 259 |
-
"loss": 1.402,
|
| 260 |
-
"step": 21000
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 0.56,
|
| 264 |
-
"learning_rate": 2.0054610881655616e-05,
|
| 265 |
-
"loss": 1.3803,
|
| 266 |
-
"step": 21500
|
| 267 |
-
},
|
| 268 |
-
{
|
| 269 |
-
"epoch": 0.58,
|
| 270 |
-
"learning_rate": 1.9050020383592233e-05,
|
| 271 |
-
"loss": 1.396,
|
| 272 |
-
"step": 22000
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 0.59,
|
| 276 |
-
"learning_rate": 1.8055516613795243e-05,
|
| 277 |
-
"loss": 1.3896,
|
| 278 |
-
"step": 22500
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 0.6,
|
| 282 |
-
"learning_rate": 1.707278550901278e-05,
|
| 283 |
-
"loss": 1.3721,
|
| 284 |
-
"step": 23000
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.62,
|
| 288 |
-
"learning_rate": 1.610349304833249e-05,
|
| 289 |
-
"loss": 1.3559,
|
| 290 |
-
"step": 23500
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.63,
|
| 294 |
-
"learning_rate": 1.5149282428923398e-05,
|
| 295 |
-
"loss": 1.3745,
|
| 296 |
-
"step": 24000
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 0.64,
|
| 300 |
-
"learning_rate": 1.4211771280398977e-05,
|
| 301 |
-
"loss": 1.3667,
|
| 302 |
-
"step": 24500
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 0.66,
|
| 306 |
-
"learning_rate": 1.3292548922523571e-05,
|
| 307 |
-
"loss": 1.3644,
|
| 308 |
-
"step": 25000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.67,
|
| 312 |
-
"learning_rate": 1.2393173670911351e-05,
|
| 313 |
-
"loss": 1.338,
|
| 314 |
-
"step": 25500
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.68,
|
| 318 |
-
"learning_rate": 1.1515170195285154e-05,
|
| 319 |
-
"loss": 1.3728,
|
| 320 |
-
"step": 26000
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.69,
|
| 324 |
-
"learning_rate": 1.0660026934773603e-05,
|
| 325 |
-
"loss": 1.3354,
|
| 326 |
-
"step": 26500
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.71,
|
| 330 |
-
"learning_rate": 9.82919357462835e-06,
|
| 331 |
-
"loss": 1.342,
|
| 332 |
-
"step": 27000
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.72,
|
| 336 |
-
"learning_rate": 9.024078588639035e-06,
|
| 337 |
-
"loss": 1.3398,
|
| 338 |
-
"step": 27500
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.73,
|
| 342 |
-
"learning_rate": 8.246046851412012e-06,
|
| 343 |
-
"loss": 1.3244,
|
| 344 |
-
"step": 28000
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 0.75,
|
| 348 |
-
"learning_rate": 7.49641732456094e-06,
|
| 349 |
-
"loss": 1.3254,
|
| 350 |
-
"step": 28500
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 0.76,
|
| 354 |
-
"learning_rate": 6.776460820731448e-06,
|
| 355 |
-
"loss": 1.3128,
|
| 356 |
-
"step": 29000
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 0.77,
|
| 360 |
-
"learning_rate": 6.088744358104376e-06,
|
| 361 |
-
"loss": 1.3184,
|
| 362 |
-
"step": 29500
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 0.79,
|
| 366 |
-
"learning_rate": 5.432959190805995e-06,
|
| 367 |
-
"loss": 1.3254,
|
| 368 |
-
"step": 30000
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 0.8,
|
| 372 |
-
"learning_rate": 4.808998495602621e-06,
|
| 373 |
-
"loss": 1.3187,
|
| 374 |
-
"step": 30500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.81,
|
| 378 |
-
"learning_rate": 4.219266681627635e-06,
|
| 379 |
-
"loss": 1.3044,
|
| 380 |
-
"step": 31000
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 0.83,
|
| 384 |
-
"learning_rate": 3.6647634942484356e-06,
|
| 385 |
-
"loss": 1.3002,
|
| 386 |
-
"step": 31500
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 0.84,
|
| 390 |
-
"learning_rate": 3.1474289357030756e-06,
|
| 391 |
-
"loss": 1.3125,
|
| 392 |
-
"step": 32000
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 0.85,
|
| 396 |
-
"learning_rate": 2.666066827958255e-06,
|
| 397 |
-
"loss": 1.2965,
|
| 398 |
-
"step": 32500
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 0.87,
|
| 402 |
-
"learning_rate": 2.2225664154712e-06,
|
| 403 |
-
"loss": 1.3045,
|
| 404 |
-
"step": 33000
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.88,
|
| 408 |
-
"learning_rate": 1.8176795442036071e-06,
|
| 409 |
-
"loss": 1.2954,
|
| 410 |
-
"step": 33500
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.89,
|
| 414 |
-
"learning_rate": 1.4520926003470992e-06,
|
| 415 |
-
"loss": 1.2965,
|
| 416 |
-
"step": 34000
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 0.9,
|
| 420 |
-
"learning_rate": 1.126425346724097e-06,
|
| 421 |
-
"loss": 1.2995,
|
| 422 |
-
"step": 34500
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.92,
|
| 426 |
-
"learning_rate": 8.417595393838212e-07,
|
| 427 |
-
"loss": 1.2603,
|
| 428 |
-
"step": 35000
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 0.93,
|
| 432 |
-
"learning_rate": 5.974369756604148e-07,
|
| 433 |
-
"loss": 1.2969,
|
| 434 |
-
"step": 35500
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 0.94,
|
| 438 |
-
"learning_rate": 3.94482960755474e-07,
|
| 439 |
-
"loss": 1.2839,
|
| 440 |
-
"step": 36000
|
| 441 |
}
|
| 442 |
],
|
| 443 |
"max_steps": 38148,
|
| 444 |
"num_train_epochs": 1,
|
| 445 |
-
"total_flos":
|
| 446 |
"trial_name": null,
|
| 447 |
"trial_params": null
|
| 448 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.10485367669417328,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
"learning_rate": 4.9978809321803e-05,
|
| 13 |
+
"loss": 0.8279,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 4.9915273210799395e-05,
|
| 19 |
+
"loss": 0.8793,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 4.980949937685176e-05,
|
| 25 |
+
"loss": 0.8954,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 4.9661667133502234e-05,
|
| 31 |
+
"loss": 0.9086,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.07,
|
| 36 |
+
"learning_rate": 4.94720270939905e-05,
|
| 37 |
+
"loss": 0.9014,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.08,
|
| 42 |
+
"learning_rate": 4.9240900746400607e-05,
|
| 43 |
+
"loss": 0.9305,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.09,
|
| 48 |
+
"learning_rate": 4.896926506742532e-05,
|
| 49 |
+
"loss": 0.9258,
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.1,
|
| 54 |
+
"learning_rate": 4.8656491982587736e-05,
|
| 55 |
+
"loss": 0.9271,
|
| 56 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
}
|
| 58 |
],
|
| 59 |
"max_steps": 38148,
|
| 60 |
"num_train_epochs": 1,
|
| 61 |
+
"total_flos": 4460244113866752.0,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
| 64 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863c1db60fca2d02e0c6137161b1e81bb2b0da7c524e6279ae9b11b2b522325f
|
| 3 |
size 3771
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1944201353
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82874203cde91954f63917da0013a6bc226b135e310668e99c7dfbec08ec6ad6
|
| 3 |
size 1944201353
|
runs/Jun19_20-59-16_8ec774155421/1687209890.901812/events.out.tfevents.1687209890.8ec774155421.1587.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b335dffc2b097907cf5a9b4bd399aebad1387397f959237fb7b06a3097b8979
|
| 3 |
+
size 6184
|
runs/Jun19_20-59-16_8ec774155421/events.out.tfevents.1687209890.8ec774155421.1587.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9840b9f991af90b7de19de63dfa67697bbf5fa0c43d0e9b84d70693970c4fdc1
|
| 3 |
+
size 5716
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863c1db60fca2d02e0c6137161b1e81bb2b0da7c524e6279ae9b11b2b522325f
|
| 3 |
size 3771
|