Training in progress, step 2000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +16 -560
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- stderr-2e-05.slurm +0 -0
- stderr.slurm +0 -0
- stdout-2e-05.slurm +89 -0
- stdout.slurm +4 -89
- 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 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1edf4f86c6269a79267fb4ce7d98eb3f9f313b813ec70cc44a8efe5c7a9bdf8
|
| 3 |
size 995604017
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510396521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3be2cdd04b6fd3a2b0e3d3da36df5b1fc4508e842028d912c36c98523fa24cdd
|
| 3 |
size 510396521
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7d28830c94d92b6d19326a0184936f2862087877e8af1a427622e66aefb96fa
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef7fd4940c48846b401f583408aac64a7d546cbc01ca65e30e622a1b591fafa7
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,592 +1,48 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
"best_model_checkpoint": "./ES_corlec/checkpoint-2000",
|
| 4 |
-
"epoch":
|
| 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": 0.1,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 4.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.2,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss":
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.3,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss":
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.4,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss":
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.4,
|
| 36 |
-
"eval_loss":
|
| 37 |
-
"eval_runtime": 958.
|
| 38 |
-
"eval_samples_per_second": 42.
|
| 39 |
-
"eval_steps_per_second": 2.641,
|
| 40 |
-
"step": 2000
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"epoch": 0.5,
|
| 44 |
-
"learning_rate": 1.90843949044586e-05,
|
| 45 |
-
"loss": 3.3359,
|
| 46 |
-
"step": 2500
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"epoch": 0.59,
|
| 50 |
-
"learning_rate": 1.8885350318471337e-05,
|
| 51 |
-
"loss": 3.2161,
|
| 52 |
-
"step": 3000
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.69,
|
| 56 |
-
"learning_rate": 1.868630573248408e-05,
|
| 57 |
-
"loss": 3.122,
|
| 58 |
-
"step": 3500
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.79,
|
| 62 |
-
"learning_rate": 1.8487261146496816e-05,
|
| 63 |
-
"loss": 3.0293,
|
| 64 |
-
"step": 4000
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"epoch": 0.79,
|
| 68 |
-
"eval_loss": 4.006344795227051,
|
| 69 |
-
"eval_runtime": 958.9036,
|
| 70 |
-
"eval_samples_per_second": 42.216,
|
| 71 |
-
"eval_steps_per_second": 2.639,
|
| 72 |
-
"step": 4000
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.89,
|
| 76 |
-
"learning_rate": 1.8288216560509554e-05,
|
| 77 |
-
"loss": 2.9397,
|
| 78 |
-
"step": 4500
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"epoch": 0.99,
|
| 82 |
-
"learning_rate": 1.8089171974522295e-05,
|
| 83 |
-
"loss": 2.8495,
|
| 84 |
-
"step": 5000
|
| 85 |
-
},
|
| 86 |
-
{
|
| 87 |
-
"epoch": 1.09,
|
| 88 |
-
"learning_rate": 1.7890127388535033e-05,
|
| 89 |
-
"loss": 2.7033,
|
| 90 |
-
"step": 5500
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 1.19,
|
| 94 |
-
"learning_rate": 1.769108280254777e-05,
|
| 95 |
-
"loss": 2.6331,
|
| 96 |
-
"step": 6000
|
| 97 |
-
},
|
| 98 |
-
{
|
| 99 |
-
"epoch": 1.19,
|
| 100 |
-
"eval_loss": 4.1308207511901855,
|
| 101 |
-
"eval_runtime": 958.6456,
|
| 102 |
-
"eval_samples_per_second": 42.227,
|
| 103 |
"eval_steps_per_second": 2.64,
|
| 104 |
-
"step":
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 1.29,
|
| 108 |
-
"learning_rate": 1.7492038216560512e-05,
|
| 109 |
-
"loss": 2.5481,
|
| 110 |
-
"step": 6500
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 1.39,
|
| 114 |
-
"learning_rate": 1.729299363057325e-05,
|
| 115 |
-
"loss": 2.4854,
|
| 116 |
-
"step": 7000
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 1.49,
|
| 120 |
-
"learning_rate": 1.7093949044585988e-05,
|
| 121 |
-
"loss": 2.4066,
|
| 122 |
-
"step": 7500
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 1.59,
|
| 126 |
-
"learning_rate": 1.6894904458598726e-05,
|
| 127 |
-
"loss": 2.3432,
|
| 128 |
-
"step": 8000
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 1.59,
|
| 132 |
-
"eval_loss": 4.2555365562438965,
|
| 133 |
-
"eval_runtime": 959.2942,
|
| 134 |
-
"eval_samples_per_second": 42.199,
|
| 135 |
-
"eval_steps_per_second": 2.638,
|
| 136 |
-
"step": 8000
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 1.69,
|
| 140 |
-
"learning_rate": 1.6695859872611467e-05,
|
| 141 |
-
"loss": 2.2699,
|
| 142 |
-
"step": 8500
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 1.78,
|
| 146 |
-
"learning_rate": 1.6496815286624205e-05,
|
| 147 |
-
"loss": 2.1978,
|
| 148 |
-
"step": 9000
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"epoch": 1.88,
|
| 152 |
-
"learning_rate": 1.6297770700636943e-05,
|
| 153 |
-
"loss": 2.1452,
|
| 154 |
-
"step": 9500
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 1.98,
|
| 158 |
-
"learning_rate": 1.6098726114649684e-05,
|
| 159 |
-
"loss": 2.0791,
|
| 160 |
-
"step": 10000
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 1.98,
|
| 164 |
-
"eval_loss": 4.388513088226318,
|
| 165 |
-
"eval_runtime": 958.7919,
|
| 166 |
-
"eval_samples_per_second": 42.221,
|
| 167 |
-
"eval_steps_per_second": 2.64,
|
| 168 |
-
"step": 10000
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 2.08,
|
| 172 |
-
"learning_rate": 1.589968152866242e-05,
|
| 173 |
-
"loss": 1.9673,
|
| 174 |
-
"step": 10500
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 2.18,
|
| 178 |
-
"learning_rate": 1.570063694267516e-05,
|
| 179 |
-
"loss": 1.9147,
|
| 180 |
-
"step": 11000
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 2.28,
|
| 184 |
-
"learning_rate": 1.55015923566879e-05,
|
| 185 |
-
"loss": 1.8628,
|
| 186 |
-
"step": 11500
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 2.38,
|
| 190 |
-
"learning_rate": 1.530254777070064e-05,
|
| 191 |
-
"loss": 1.7991,
|
| 192 |
-
"step": 12000
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 2.38,
|
| 196 |
-
"eval_loss": 4.536414623260498,
|
| 197 |
-
"eval_runtime": 958.7918,
|
| 198 |
-
"eval_samples_per_second": 42.221,
|
| 199 |
-
"eval_steps_per_second": 2.64,
|
| 200 |
-
"step": 12000
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 2.48,
|
| 204 |
-
"learning_rate": 1.5103503184713378e-05,
|
| 205 |
-
"loss": 1.755,
|
| 206 |
-
"step": 12500
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 2.58,
|
| 210 |
-
"learning_rate": 1.4904458598726114e-05,
|
| 211 |
-
"loss": 1.699,
|
| 212 |
-
"step": 13000
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 2.68,
|
| 216 |
-
"learning_rate": 1.4705414012738855e-05,
|
| 217 |
-
"loss": 1.6565,
|
| 218 |
-
"step": 13500
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 2.78,
|
| 222 |
-
"learning_rate": 1.4506369426751595e-05,
|
| 223 |
-
"loss": 1.6005,
|
| 224 |
-
"step": 14000
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 2.78,
|
| 228 |
-
"eval_loss": 4.665872097015381,
|
| 229 |
-
"eval_runtime": 958.5203,
|
| 230 |
-
"eval_samples_per_second": 42.233,
|
| 231 |
-
"eval_steps_per_second": 2.641,
|
| 232 |
-
"step": 14000
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 2.87,
|
| 236 |
-
"learning_rate": 1.4307324840764331e-05,
|
| 237 |
-
"loss": 1.5739,
|
| 238 |
-
"step": 14500
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"epoch": 2.97,
|
| 242 |
-
"learning_rate": 1.4108280254777072e-05,
|
| 243 |
-
"loss": 1.5312,
|
| 244 |
-
"step": 15000
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 3.07,
|
| 248 |
-
"learning_rate": 1.3909235668789812e-05,
|
| 249 |
-
"loss": 1.4352,
|
| 250 |
-
"step": 15500
|
| 251 |
-
},
|
| 252 |
-
{
|
| 253 |
-
"epoch": 3.17,
|
| 254 |
-
"learning_rate": 1.371019108280255e-05,
|
| 255 |
-
"loss": 1.4018,
|
| 256 |
-
"step": 16000
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 3.17,
|
| 260 |
-
"eval_loss": 4.807626724243164,
|
| 261 |
-
"eval_runtime": 959.3471,
|
| 262 |
-
"eval_samples_per_second": 42.196,
|
| 263 |
-
"eval_steps_per_second": 2.638,
|
| 264 |
-
"step": 16000
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 3.27,
|
| 268 |
-
"learning_rate": 1.3511146496815289e-05,
|
| 269 |
-
"loss": 1.362,
|
| 270 |
-
"step": 16500
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 3.37,
|
| 274 |
-
"learning_rate": 1.3312101910828025e-05,
|
| 275 |
-
"loss": 1.3312,
|
| 276 |
-
"step": 17000
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 3.47,
|
| 280 |
-
"learning_rate": 1.3113057324840766e-05,
|
| 281 |
-
"loss": 1.2996,
|
| 282 |
-
"step": 17500
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 3.57,
|
| 286 |
-
"learning_rate": 1.2914012738853506e-05,
|
| 287 |
-
"loss": 1.2584,
|
| 288 |
-
"step": 18000
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 3.57,
|
| 292 |
-
"eval_loss": 4.938758373260498,
|
| 293 |
-
"eval_runtime": 959.0042,
|
| 294 |
-
"eval_samples_per_second": 42.211,
|
| 295 |
-
"eval_steps_per_second": 2.639,
|
| 296 |
-
"step": 18000
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 3.67,
|
| 300 |
-
"learning_rate": 1.2714968152866244e-05,
|
| 301 |
-
"loss": 1.2251,
|
| 302 |
-
"step": 18500
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 3.77,
|
| 306 |
-
"learning_rate": 1.2515923566878983e-05,
|
| 307 |
-
"loss": 1.1985,
|
| 308 |
-
"step": 19000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 3.87,
|
| 312 |
-
"learning_rate": 1.231687898089172e-05,
|
| 313 |
-
"loss": 1.1689,
|
| 314 |
-
"step": 19500
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 3.97,
|
| 318 |
-
"learning_rate": 1.211783439490446e-05,
|
| 319 |
-
"loss": 1.1476,
|
| 320 |
-
"step": 20000
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 3.97,
|
| 324 |
-
"eval_loss": 5.052674293518066,
|
| 325 |
-
"eval_runtime": 959.1305,
|
| 326 |
-
"eval_samples_per_second": 42.206,
|
| 327 |
-
"eval_steps_per_second": 2.639,
|
| 328 |
-
"step": 20000
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 4.06,
|
| 332 |
-
"learning_rate": 1.19187898089172e-05,
|
| 333 |
-
"loss": 1.0804,
|
| 334 |
-
"step": 20500
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 4.16,
|
| 338 |
-
"learning_rate": 1.1719745222929938e-05,
|
| 339 |
-
"loss": 1.0489,
|
| 340 |
-
"step": 21000
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 4.26,
|
| 344 |
-
"learning_rate": 1.1520700636942677e-05,
|
| 345 |
-
"loss": 1.0267,
|
| 346 |
-
"step": 21500
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 4.36,
|
| 350 |
-
"learning_rate": 1.1321656050955413e-05,
|
| 351 |
-
"loss": 1.0043,
|
| 352 |
-
"step": 22000
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 4.36,
|
| 356 |
-
"eval_loss": 5.172101974487305,
|
| 357 |
-
"eval_runtime": 958.8916,
|
| 358 |
-
"eval_samples_per_second": 42.216,
|
| 359 |
-
"eval_steps_per_second": 2.64,
|
| 360 |
-
"step": 22000
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 4.46,
|
| 364 |
-
"learning_rate": 1.1122611464968155e-05,
|
| 365 |
-
"loss": 0.989,
|
| 366 |
-
"step": 22500
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 4.56,
|
| 370 |
-
"learning_rate": 1.0923566878980894e-05,
|
| 371 |
-
"loss": 0.9617,
|
| 372 |
-
"step": 23000
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 4.66,
|
| 376 |
-
"learning_rate": 1.0724522292993632e-05,
|
| 377 |
-
"loss": 0.9621,
|
| 378 |
-
"step": 23500
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 4.76,
|
| 382 |
-
"learning_rate": 1.0525477707006371e-05,
|
| 383 |
-
"loss": 0.9271,
|
| 384 |
-
"step": 24000
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 4.76,
|
| 388 |
-
"eval_loss": 5.2821364402771,
|
| 389 |
-
"eval_runtime": 959.4888,
|
| 390 |
-
"eval_samples_per_second": 42.19,
|
| 391 |
-
"eval_steps_per_second": 2.638,
|
| 392 |
-
"step": 24000
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 4.86,
|
| 396 |
-
"learning_rate": 1.0326433121019107e-05,
|
| 397 |
-
"loss": 0.8991,
|
| 398 |
-
"step": 24500
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 4.96,
|
| 402 |
-
"learning_rate": 1.0127388535031849e-05,
|
| 403 |
-
"loss": 0.8971,
|
| 404 |
-
"step": 25000
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 5.06,
|
| 408 |
-
"learning_rate": 9.928343949044586e-06,
|
| 409 |
-
"loss": 0.8486,
|
| 410 |
-
"step": 25500
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 5.15,
|
| 414 |
-
"learning_rate": 9.729299363057324e-06,
|
| 415 |
-
"loss": 0.8291,
|
| 416 |
-
"step": 26000
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 5.15,
|
| 420 |
-
"eval_loss": 5.384232521057129,
|
| 421 |
-
"eval_runtime": 958.7754,
|
| 422 |
-
"eval_samples_per_second": 42.222,
|
| 423 |
-
"eval_steps_per_second": 2.64,
|
| 424 |
-
"step": 26000
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 5.25,
|
| 428 |
-
"learning_rate": 9.530254777070066e-06,
|
| 429 |
-
"loss": 0.8108,
|
| 430 |
-
"step": 26500
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 5.35,
|
| 434 |
-
"learning_rate": 9.331210191082803e-06,
|
| 435 |
-
"loss": 0.7972,
|
| 436 |
-
"step": 27000
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 5.45,
|
| 440 |
-
"learning_rate": 9.132165605095543e-06,
|
| 441 |
-
"loss": 0.7845,
|
| 442 |
-
"step": 27500
|
| 443 |
-
},
|
| 444 |
-
{
|
| 445 |
-
"epoch": 5.55,
|
| 446 |
-
"learning_rate": 8.93312101910828e-06,
|
| 447 |
-
"loss": 0.776,
|
| 448 |
-
"step": 28000
|
| 449 |
-
},
|
| 450 |
-
{
|
| 451 |
-
"epoch": 5.55,
|
| 452 |
-
"eval_loss": 5.476274490356445,
|
| 453 |
-
"eval_runtime": 959.1462,
|
| 454 |
-
"eval_samples_per_second": 42.205,
|
| 455 |
-
"eval_steps_per_second": 2.639,
|
| 456 |
-
"step": 28000
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 5.65,
|
| 460 |
-
"learning_rate": 8.734076433121018e-06,
|
| 461 |
-
"loss": 0.76,
|
| 462 |
-
"step": 28500
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 5.75,
|
| 466 |
-
"learning_rate": 8.53503184713376e-06,
|
| 467 |
-
"loss": 0.7445,
|
| 468 |
-
"step": 29000
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 5.85,
|
| 472 |
-
"learning_rate": 8.335987261146497e-06,
|
| 473 |
-
"loss": 0.731,
|
| 474 |
-
"step": 29500
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 5.95,
|
| 478 |
-
"learning_rate": 8.136942675159237e-06,
|
| 479 |
-
"loss": 0.7241,
|
| 480 |
-
"step": 30000
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 5.95,
|
| 484 |
-
"eval_loss": 5.554164886474609,
|
| 485 |
-
"eval_runtime": 958.7676,
|
| 486 |
-
"eval_samples_per_second": 42.222,
|
| 487 |
-
"eval_steps_per_second": 2.64,
|
| 488 |
-
"step": 30000
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 6.05,
|
| 492 |
-
"learning_rate": 7.937898089171975e-06,
|
| 493 |
-
"loss": 0.7027,
|
| 494 |
-
"step": 30500
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 6.15,
|
| 498 |
-
"learning_rate": 7.738853503184714e-06,
|
| 499 |
-
"loss": 0.6773,
|
| 500 |
-
"step": 31000
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 6.25,
|
| 504 |
-
"learning_rate": 7.539808917197453e-06,
|
| 505 |
-
"loss": 0.6782,
|
| 506 |
-
"step": 31500
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 6.34,
|
| 510 |
-
"learning_rate": 7.340764331210192e-06,
|
| 511 |
-
"loss": 0.6602,
|
| 512 |
-
"step": 32000
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 6.34,
|
| 516 |
-
"eval_loss": 5.626761436462402,
|
| 517 |
-
"eval_runtime": 959.3904,
|
| 518 |
-
"eval_samples_per_second": 42.195,
|
| 519 |
-
"eval_steps_per_second": 2.638,
|
| 520 |
-
"step": 32000
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 6.44,
|
| 524 |
-
"learning_rate": 7.14171974522293e-06,
|
| 525 |
-
"loss": 0.6511,
|
| 526 |
-
"step": 32500
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 6.54,
|
| 530 |
-
"learning_rate": 6.942675159235669e-06,
|
| 531 |
-
"loss": 0.6436,
|
| 532 |
-
"step": 33000
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 6.64,
|
| 536 |
-
"learning_rate": 6.7436305732484085e-06,
|
| 537 |
-
"loss": 0.6435,
|
| 538 |
-
"step": 33500
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 6.74,
|
| 542 |
-
"learning_rate": 6.544585987261147e-06,
|
| 543 |
-
"loss": 0.635,
|
| 544 |
-
"step": 34000
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 6.74,
|
| 548 |
-
"eval_loss": 5.690598011016846,
|
| 549 |
-
"eval_runtime": 958.9891,
|
| 550 |
-
"eval_samples_per_second": 42.212,
|
| 551 |
-
"eval_steps_per_second": 2.639,
|
| 552 |
-
"step": 34000
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 6.84,
|
| 556 |
-
"learning_rate": 6.345541401273886e-06,
|
| 557 |
-
"loss": 0.6306,
|
| 558 |
-
"step": 34500
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 6.94,
|
| 562 |
-
"learning_rate": 6.1464968152866244e-06,
|
| 563 |
-
"loss": 0.6146,
|
| 564 |
-
"step": 35000
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 7.04,
|
| 568 |
-
"learning_rate": 5.947452229299363e-06,
|
| 569 |
-
"loss": 0.5998,
|
| 570 |
-
"step": 35500
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 7.14,
|
| 574 |
-
"learning_rate": 5.748407643312103e-06,
|
| 575 |
-
"loss": 0.5837,
|
| 576 |
-
"step": 36000
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 7.14,
|
| 580 |
-
"eval_loss": 5.752773761749268,
|
| 581 |
-
"eval_runtime": 959.2742,
|
| 582 |
-
"eval_samples_per_second": 42.2,
|
| 583 |
-
"eval_steps_per_second": 2.638,
|
| 584 |
-
"step": 36000
|
| 585 |
}
|
| 586 |
],
|
| 587 |
"max_steps": 50440,
|
| 588 |
"num_train_epochs": 10,
|
| 589 |
-
"total_flos":
|
| 590 |
"trial_name": null,
|
| 591 |
"trial_params": null
|
| 592 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 4.065090656280518,
|
| 3 |
"best_model_checkpoint": "./ES_corlec/checkpoint-2000",
|
| 4 |
+
"epoch": 0.3965107057890563,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 9.940286624203822e-07,
|
| 13 |
+
"loss": 4.6573,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 9.84076433121019e-07,
|
| 19 |
+
"loss": 4.1908,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 9.74124203821656e-07,
|
| 25 |
+
"loss": 4.1363,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 9.64171974522293e-07,
|
| 31 |
+
"loss": 4.0949,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.4,
|
| 36 |
+
"eval_loss": 4.065090656280518,
|
| 37 |
+
"eval_runtime": 958.7496,
|
| 38 |
+
"eval_samples_per_second": 42.223,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
"eval_steps_per_second": 2.64,
|
| 40 |
+
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"max_steps": 50440,
|
| 44 |
"num_train_epochs": 10,
|
| 45 |
+
"total_flos": 2449612800000000.0,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
| 48 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00a5bfc0fa6a3aa2ab924b9d0fd18640137651b4b65a92e04e2fc725dbd4f332
|
| 3 |
size 3055
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510396521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3be2cdd04b6fd3a2b0e3d3da36df5b1fc4508e842028d912c36c98523fa24cdd
|
| 3 |
size 510396521
|
stderr-2e-05.slurm
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
stderr.slurm
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
stdout-2e-05.slurm
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{'loss': 4.1429, 'learning_rate': 1.9880573248407645e-05, 'epoch': 0.1}
|
| 2 |
+
{'loss': 3.7366, 'learning_rate': 1.9681528662420383e-05, 'epoch': 0.2}
|
| 3 |
+
{'loss': 3.5836, 'learning_rate': 1.9482484076433124e-05, 'epoch': 0.3}
|
| 4 |
+
{'loss': 3.4588, 'learning_rate': 1.9283439490445862e-05, 'epoch': 0.4}
|
| 5 |
+
{'eval_loss': 3.926462411880493, 'eval_runtime': 958.5106, 'eval_samples_per_second': 42.233, 'eval_steps_per_second': 2.641, 'epoch': 0.4}
|
| 6 |
+
{'loss': 3.3359, 'learning_rate': 1.90843949044586e-05, 'epoch': 0.5}
|
| 7 |
+
{'loss': 3.2161, 'learning_rate': 1.8885350318471337e-05, 'epoch': 0.59}
|
| 8 |
+
{'loss': 3.122, 'learning_rate': 1.868630573248408e-05, 'epoch': 0.69}
|
| 9 |
+
{'loss': 3.0293, 'learning_rate': 1.8487261146496816e-05, 'epoch': 0.79}
|
| 10 |
+
{'eval_loss': 4.006344795227051, 'eval_runtime': 958.9036, 'eval_samples_per_second': 42.216, 'eval_steps_per_second': 2.639, 'epoch': 0.79}
|
| 11 |
+
{'loss': 2.9397, 'learning_rate': 1.8288216560509554e-05, 'epoch': 0.89}
|
| 12 |
+
{'loss': 2.8495, 'learning_rate': 1.8089171974522295e-05, 'epoch': 0.99}
|
| 13 |
+
{'loss': 2.7033, 'learning_rate': 1.7890127388535033e-05, 'epoch': 1.09}
|
| 14 |
+
{'loss': 2.6331, 'learning_rate': 1.769108280254777e-05, 'epoch': 1.19}
|
| 15 |
+
{'eval_loss': 4.1308207511901855, 'eval_runtime': 958.6456, 'eval_samples_per_second': 42.227, 'eval_steps_per_second': 2.64, 'epoch': 1.19}
|
| 16 |
+
{'loss': 2.5481, 'learning_rate': 1.7492038216560512e-05, 'epoch': 1.29}
|
| 17 |
+
{'loss': 2.4854, 'learning_rate': 1.729299363057325e-05, 'epoch': 1.39}
|
| 18 |
+
{'loss': 2.4066, 'learning_rate': 1.7093949044585988e-05, 'epoch': 1.49}
|
| 19 |
+
{'loss': 2.3432, 'learning_rate': 1.6894904458598726e-05, 'epoch': 1.59}
|
| 20 |
+
{'eval_loss': 4.2555365562438965, 'eval_runtime': 959.2942, 'eval_samples_per_second': 42.199, 'eval_steps_per_second': 2.638, 'epoch': 1.59}
|
| 21 |
+
{'loss': 2.2699, 'learning_rate': 1.6695859872611467e-05, 'epoch': 1.69}
|
| 22 |
+
{'loss': 2.1978, 'learning_rate': 1.6496815286624205e-05, 'epoch': 1.78}
|
| 23 |
+
{'loss': 2.1452, 'learning_rate': 1.6297770700636943e-05, 'epoch': 1.88}
|
| 24 |
+
{'loss': 2.0791, 'learning_rate': 1.6098726114649684e-05, 'epoch': 1.98}
|
| 25 |
+
{'eval_loss': 4.388513088226318, 'eval_runtime': 958.7919, 'eval_samples_per_second': 42.221, 'eval_steps_per_second': 2.64, 'epoch': 1.98}
|
| 26 |
+
{'loss': 1.9673, 'learning_rate': 1.589968152866242e-05, 'epoch': 2.08}
|
| 27 |
+
{'loss': 1.9147, 'learning_rate': 1.570063694267516e-05, 'epoch': 2.18}
|
| 28 |
+
{'loss': 1.8628, 'learning_rate': 1.55015923566879e-05, 'epoch': 2.28}
|
| 29 |
+
{'loss': 1.7991, 'learning_rate': 1.530254777070064e-05, 'epoch': 2.38}
|
| 30 |
+
{'eval_loss': 4.536414623260498, 'eval_runtime': 958.7918, 'eval_samples_per_second': 42.221, 'eval_steps_per_second': 2.64, 'epoch': 2.38}
|
| 31 |
+
{'loss': 1.755, 'learning_rate': 1.5103503184713378e-05, 'epoch': 2.48}
|
| 32 |
+
{'loss': 1.699, 'learning_rate': 1.4904458598726114e-05, 'epoch': 2.58}
|
| 33 |
+
{'loss': 1.6565, 'learning_rate': 1.4705414012738855e-05, 'epoch': 2.68}
|
| 34 |
+
{'loss': 1.6005, 'learning_rate': 1.4506369426751595e-05, 'epoch': 2.78}
|
| 35 |
+
{'eval_loss': 4.665872097015381, 'eval_runtime': 958.5203, 'eval_samples_per_second': 42.233, 'eval_steps_per_second': 2.641, 'epoch': 2.78}
|
| 36 |
+
{'loss': 1.5739, 'learning_rate': 1.4307324840764331e-05, 'epoch': 2.87}
|
| 37 |
+
{'loss': 1.5312, 'learning_rate': 1.4108280254777072e-05, 'epoch': 2.97}
|
| 38 |
+
{'loss': 1.4352, 'learning_rate': 1.3909235668789812e-05, 'epoch': 3.07}
|
| 39 |
+
{'loss': 1.4018, 'learning_rate': 1.371019108280255e-05, 'epoch': 3.17}
|
| 40 |
+
{'eval_loss': 4.807626724243164, 'eval_runtime': 959.3471, 'eval_samples_per_second': 42.196, 'eval_steps_per_second': 2.638, 'epoch': 3.17}
|
| 41 |
+
{'loss': 1.362, 'learning_rate': 1.3511146496815289e-05, 'epoch': 3.27}
|
| 42 |
+
{'loss': 1.3312, 'learning_rate': 1.3312101910828025e-05, 'epoch': 3.37}
|
| 43 |
+
{'loss': 1.2996, 'learning_rate': 1.3113057324840766e-05, 'epoch': 3.47}
|
| 44 |
+
{'loss': 1.2584, 'learning_rate': 1.2914012738853506e-05, 'epoch': 3.57}
|
| 45 |
+
{'eval_loss': 4.938758373260498, 'eval_runtime': 959.0042, 'eval_samples_per_second': 42.211, 'eval_steps_per_second': 2.639, 'epoch': 3.57}
|
| 46 |
+
{'loss': 1.2251, 'learning_rate': 1.2714968152866244e-05, 'epoch': 3.67}
|
| 47 |
+
{'loss': 1.1985, 'learning_rate': 1.2515923566878983e-05, 'epoch': 3.77}
|
| 48 |
+
{'loss': 1.1689, 'learning_rate': 1.231687898089172e-05, 'epoch': 3.87}
|
| 49 |
+
{'loss': 1.1476, 'learning_rate': 1.211783439490446e-05, 'epoch': 3.97}
|
| 50 |
+
{'eval_loss': 5.052674293518066, 'eval_runtime': 959.1305, 'eval_samples_per_second': 42.206, 'eval_steps_per_second': 2.639, 'epoch': 3.97}
|
| 51 |
+
{'loss': 1.0804, 'learning_rate': 1.19187898089172e-05, 'epoch': 4.06}
|
| 52 |
+
{'loss': 1.0489, 'learning_rate': 1.1719745222929938e-05, 'epoch': 4.16}
|
| 53 |
+
{'loss': 1.0267, 'learning_rate': 1.1520700636942677e-05, 'epoch': 4.26}
|
| 54 |
+
{'loss': 1.0043, 'learning_rate': 1.1321656050955413e-05, 'epoch': 4.36}
|
| 55 |
+
{'eval_loss': 5.172101974487305, 'eval_runtime': 958.8916, 'eval_samples_per_second': 42.216, 'eval_steps_per_second': 2.64, 'epoch': 4.36}
|
| 56 |
+
{'loss': 0.989, 'learning_rate': 1.1122611464968155e-05, 'epoch': 4.46}
|
| 57 |
+
{'loss': 0.9617, 'learning_rate': 1.0923566878980894e-05, 'epoch': 4.56}
|
| 58 |
+
{'loss': 0.9621, 'learning_rate': 1.0724522292993632e-05, 'epoch': 4.66}
|
| 59 |
+
{'loss': 0.9271, 'learning_rate': 1.0525477707006371e-05, 'epoch': 4.76}
|
| 60 |
+
{'eval_loss': 5.2821364402771, 'eval_runtime': 959.4888, 'eval_samples_per_second': 42.19, 'eval_steps_per_second': 2.638, 'epoch': 4.76}
|
| 61 |
+
{'loss': 0.8991, 'learning_rate': 1.0326433121019107e-05, 'epoch': 4.86}
|
| 62 |
+
{'loss': 0.8971, 'learning_rate': 1.0127388535031849e-05, 'epoch': 4.96}
|
| 63 |
+
{'loss': 0.8486, 'learning_rate': 9.928343949044586e-06, 'epoch': 5.06}
|
| 64 |
+
{'loss': 0.8291, 'learning_rate': 9.729299363057324e-06, 'epoch': 5.15}
|
| 65 |
+
{'eval_loss': 5.384232521057129, 'eval_runtime': 958.7754, 'eval_samples_per_second': 42.222, 'eval_steps_per_second': 2.64, 'epoch': 5.15}
|
| 66 |
+
{'loss': 0.8108, 'learning_rate': 9.530254777070066e-06, 'epoch': 5.25}
|
| 67 |
+
{'loss': 0.7972, 'learning_rate': 9.331210191082803e-06, 'epoch': 5.35}
|
| 68 |
+
{'loss': 0.7845, 'learning_rate': 9.132165605095543e-06, 'epoch': 5.45}
|
| 69 |
+
{'loss': 0.776, 'learning_rate': 8.93312101910828e-06, 'epoch': 5.55}
|
| 70 |
+
{'eval_loss': 5.476274490356445, 'eval_runtime': 959.1462, 'eval_samples_per_second': 42.205, 'eval_steps_per_second': 2.639, 'epoch': 5.55}
|
| 71 |
+
{'loss': 0.76, 'learning_rate': 8.734076433121018e-06, 'epoch': 5.65}
|
| 72 |
+
{'loss': 0.7445, 'learning_rate': 8.53503184713376e-06, 'epoch': 5.75}
|
| 73 |
+
{'loss': 0.731, 'learning_rate': 8.335987261146497e-06, 'epoch': 5.85}
|
| 74 |
+
{'loss': 0.7241, 'learning_rate': 8.136942675159237e-06, 'epoch': 5.95}
|
| 75 |
+
{'eval_loss': 5.554164886474609, 'eval_runtime': 958.7676, 'eval_samples_per_second': 42.222, 'eval_steps_per_second': 2.64, 'epoch': 5.95}
|
| 76 |
+
{'loss': 0.7027, 'learning_rate': 7.937898089171975e-06, 'epoch': 6.05}
|
| 77 |
+
{'loss': 0.6773, 'learning_rate': 7.738853503184714e-06, 'epoch': 6.15}
|
| 78 |
+
{'loss': 0.6782, 'learning_rate': 7.539808917197453e-06, 'epoch': 6.25}
|
| 79 |
+
{'loss': 0.6602, 'learning_rate': 7.340764331210192e-06, 'epoch': 6.34}
|
| 80 |
+
{'eval_loss': 5.626761436462402, 'eval_runtime': 959.3904, 'eval_samples_per_second': 42.195, 'eval_steps_per_second': 2.638, 'epoch': 6.34}
|
| 81 |
+
{'loss': 0.6511, 'learning_rate': 7.14171974522293e-06, 'epoch': 6.44}
|
| 82 |
+
{'loss': 0.6436, 'learning_rate': 6.942675159235669e-06, 'epoch': 6.54}
|
| 83 |
+
{'loss': 0.6435, 'learning_rate': 6.7436305732484085e-06, 'epoch': 6.64}
|
| 84 |
+
{'loss': 0.635, 'learning_rate': 6.544585987261147e-06, 'epoch': 6.74}
|
| 85 |
+
{'eval_loss': 5.690598011016846, 'eval_runtime': 958.9891, 'eval_samples_per_second': 42.212, 'eval_steps_per_second': 2.639, 'epoch': 6.74}
|
| 86 |
+
{'loss': 0.6306, 'learning_rate': 6.345541401273886e-06, 'epoch': 6.84}
|
| 87 |
+
{'loss': 0.6146, 'learning_rate': 6.1464968152866244e-06, 'epoch': 6.94}
|
| 88 |
+
{'loss': 0.5998, 'learning_rate': 5.947452229299363e-06, 'epoch': 7.04}
|
| 89 |
+
{'loss': 0.5837, 'learning_rate': 5.748407643312103e-06, 'epoch': 7.14}
|
stdout.slurm
CHANGED
|
@@ -1,89 +1,4 @@
|
|
| 1 |
-
{'loss': 4.
|
| 2 |
-
{'loss':
|
| 3 |
-
{'loss':
|
| 4 |
-
{'loss':
|
| 5 |
-
{'eval_loss': 3.926462411880493, 'eval_runtime': 958.5106, 'eval_samples_per_second': 42.233, 'eval_steps_per_second': 2.641, 'epoch': 0.4}
|
| 6 |
-
{'loss': 3.3359, 'learning_rate': 1.90843949044586e-05, 'epoch': 0.5}
|
| 7 |
-
{'loss': 3.2161, 'learning_rate': 1.8885350318471337e-05, 'epoch': 0.59}
|
| 8 |
-
{'loss': 3.122, 'learning_rate': 1.868630573248408e-05, 'epoch': 0.69}
|
| 9 |
-
{'loss': 3.0293, 'learning_rate': 1.8487261146496816e-05, 'epoch': 0.79}
|
| 10 |
-
{'eval_loss': 4.006344795227051, 'eval_runtime': 958.9036, 'eval_samples_per_second': 42.216, 'eval_steps_per_second': 2.639, 'epoch': 0.79}
|
| 11 |
-
{'loss': 2.9397, 'learning_rate': 1.8288216560509554e-05, 'epoch': 0.89}
|
| 12 |
-
{'loss': 2.8495, 'learning_rate': 1.8089171974522295e-05, 'epoch': 0.99}
|
| 13 |
-
{'loss': 2.7033, 'learning_rate': 1.7890127388535033e-05, 'epoch': 1.09}
|
| 14 |
-
{'loss': 2.6331, 'learning_rate': 1.769108280254777e-05, 'epoch': 1.19}
|
| 15 |
-
{'eval_loss': 4.1308207511901855, 'eval_runtime': 958.6456, 'eval_samples_per_second': 42.227, 'eval_steps_per_second': 2.64, 'epoch': 1.19}
|
| 16 |
-
{'loss': 2.5481, 'learning_rate': 1.7492038216560512e-05, 'epoch': 1.29}
|
| 17 |
-
{'loss': 2.4854, 'learning_rate': 1.729299363057325e-05, 'epoch': 1.39}
|
| 18 |
-
{'loss': 2.4066, 'learning_rate': 1.7093949044585988e-05, 'epoch': 1.49}
|
| 19 |
-
{'loss': 2.3432, 'learning_rate': 1.6894904458598726e-05, 'epoch': 1.59}
|
| 20 |
-
{'eval_loss': 4.2555365562438965, 'eval_runtime': 959.2942, 'eval_samples_per_second': 42.199, 'eval_steps_per_second': 2.638, 'epoch': 1.59}
|
| 21 |
-
{'loss': 2.2699, 'learning_rate': 1.6695859872611467e-05, 'epoch': 1.69}
|
| 22 |
-
{'loss': 2.1978, 'learning_rate': 1.6496815286624205e-05, 'epoch': 1.78}
|
| 23 |
-
{'loss': 2.1452, 'learning_rate': 1.6297770700636943e-05, 'epoch': 1.88}
|
| 24 |
-
{'loss': 2.0791, 'learning_rate': 1.6098726114649684e-05, 'epoch': 1.98}
|
| 25 |
-
{'eval_loss': 4.388513088226318, 'eval_runtime': 958.7919, 'eval_samples_per_second': 42.221, 'eval_steps_per_second': 2.64, 'epoch': 1.98}
|
| 26 |
-
{'loss': 1.9673, 'learning_rate': 1.589968152866242e-05, 'epoch': 2.08}
|
| 27 |
-
{'loss': 1.9147, 'learning_rate': 1.570063694267516e-05, 'epoch': 2.18}
|
| 28 |
-
{'loss': 1.8628, 'learning_rate': 1.55015923566879e-05, 'epoch': 2.28}
|
| 29 |
-
{'loss': 1.7991, 'learning_rate': 1.530254777070064e-05, 'epoch': 2.38}
|
| 30 |
-
{'eval_loss': 4.536414623260498, 'eval_runtime': 958.7918, 'eval_samples_per_second': 42.221, 'eval_steps_per_second': 2.64, 'epoch': 2.38}
|
| 31 |
-
{'loss': 1.755, 'learning_rate': 1.5103503184713378e-05, 'epoch': 2.48}
|
| 32 |
-
{'loss': 1.699, 'learning_rate': 1.4904458598726114e-05, 'epoch': 2.58}
|
| 33 |
-
{'loss': 1.6565, 'learning_rate': 1.4705414012738855e-05, 'epoch': 2.68}
|
| 34 |
-
{'loss': 1.6005, 'learning_rate': 1.4506369426751595e-05, 'epoch': 2.78}
|
| 35 |
-
{'eval_loss': 4.665872097015381, 'eval_runtime': 958.5203, 'eval_samples_per_second': 42.233, 'eval_steps_per_second': 2.641, 'epoch': 2.78}
|
| 36 |
-
{'loss': 1.5739, 'learning_rate': 1.4307324840764331e-05, 'epoch': 2.87}
|
| 37 |
-
{'loss': 1.5312, 'learning_rate': 1.4108280254777072e-05, 'epoch': 2.97}
|
| 38 |
-
{'loss': 1.4352, 'learning_rate': 1.3909235668789812e-05, 'epoch': 3.07}
|
| 39 |
-
{'loss': 1.4018, 'learning_rate': 1.371019108280255e-05, 'epoch': 3.17}
|
| 40 |
-
{'eval_loss': 4.807626724243164, 'eval_runtime': 959.3471, 'eval_samples_per_second': 42.196, 'eval_steps_per_second': 2.638, 'epoch': 3.17}
|
| 41 |
-
{'loss': 1.362, 'learning_rate': 1.3511146496815289e-05, 'epoch': 3.27}
|
| 42 |
-
{'loss': 1.3312, 'learning_rate': 1.3312101910828025e-05, 'epoch': 3.37}
|
| 43 |
-
{'loss': 1.2996, 'learning_rate': 1.3113057324840766e-05, 'epoch': 3.47}
|
| 44 |
-
{'loss': 1.2584, 'learning_rate': 1.2914012738853506e-05, 'epoch': 3.57}
|
| 45 |
-
{'eval_loss': 4.938758373260498, 'eval_runtime': 959.0042, 'eval_samples_per_second': 42.211, 'eval_steps_per_second': 2.639, 'epoch': 3.57}
|
| 46 |
-
{'loss': 1.2251, 'learning_rate': 1.2714968152866244e-05, 'epoch': 3.67}
|
| 47 |
-
{'loss': 1.1985, 'learning_rate': 1.2515923566878983e-05, 'epoch': 3.77}
|
| 48 |
-
{'loss': 1.1689, 'learning_rate': 1.231687898089172e-05, 'epoch': 3.87}
|
| 49 |
-
{'loss': 1.1476, 'learning_rate': 1.211783439490446e-05, 'epoch': 3.97}
|
| 50 |
-
{'eval_loss': 5.052674293518066, 'eval_runtime': 959.1305, 'eval_samples_per_second': 42.206, 'eval_steps_per_second': 2.639, 'epoch': 3.97}
|
| 51 |
-
{'loss': 1.0804, 'learning_rate': 1.19187898089172e-05, 'epoch': 4.06}
|
| 52 |
-
{'loss': 1.0489, 'learning_rate': 1.1719745222929938e-05, 'epoch': 4.16}
|
| 53 |
-
{'loss': 1.0267, 'learning_rate': 1.1520700636942677e-05, 'epoch': 4.26}
|
| 54 |
-
{'loss': 1.0043, 'learning_rate': 1.1321656050955413e-05, 'epoch': 4.36}
|
| 55 |
-
{'eval_loss': 5.172101974487305, 'eval_runtime': 958.8916, 'eval_samples_per_second': 42.216, 'eval_steps_per_second': 2.64, 'epoch': 4.36}
|
| 56 |
-
{'loss': 0.989, 'learning_rate': 1.1122611464968155e-05, 'epoch': 4.46}
|
| 57 |
-
{'loss': 0.9617, 'learning_rate': 1.0923566878980894e-05, 'epoch': 4.56}
|
| 58 |
-
{'loss': 0.9621, 'learning_rate': 1.0724522292993632e-05, 'epoch': 4.66}
|
| 59 |
-
{'loss': 0.9271, 'learning_rate': 1.0525477707006371e-05, 'epoch': 4.76}
|
| 60 |
-
{'eval_loss': 5.2821364402771, 'eval_runtime': 959.4888, 'eval_samples_per_second': 42.19, 'eval_steps_per_second': 2.638, 'epoch': 4.76}
|
| 61 |
-
{'loss': 0.8991, 'learning_rate': 1.0326433121019107e-05, 'epoch': 4.86}
|
| 62 |
-
{'loss': 0.8971, 'learning_rate': 1.0127388535031849e-05, 'epoch': 4.96}
|
| 63 |
-
{'loss': 0.8486, 'learning_rate': 9.928343949044586e-06, 'epoch': 5.06}
|
| 64 |
-
{'loss': 0.8291, 'learning_rate': 9.729299363057324e-06, 'epoch': 5.15}
|
| 65 |
-
{'eval_loss': 5.384232521057129, 'eval_runtime': 958.7754, 'eval_samples_per_second': 42.222, 'eval_steps_per_second': 2.64, 'epoch': 5.15}
|
| 66 |
-
{'loss': 0.8108, 'learning_rate': 9.530254777070066e-06, 'epoch': 5.25}
|
| 67 |
-
{'loss': 0.7972, 'learning_rate': 9.331210191082803e-06, 'epoch': 5.35}
|
| 68 |
-
{'loss': 0.7845, 'learning_rate': 9.132165605095543e-06, 'epoch': 5.45}
|
| 69 |
-
{'loss': 0.776, 'learning_rate': 8.93312101910828e-06, 'epoch': 5.55}
|
| 70 |
-
{'eval_loss': 5.476274490356445, 'eval_runtime': 959.1462, 'eval_samples_per_second': 42.205, 'eval_steps_per_second': 2.639, 'epoch': 5.55}
|
| 71 |
-
{'loss': 0.76, 'learning_rate': 8.734076433121018e-06, 'epoch': 5.65}
|
| 72 |
-
{'loss': 0.7445, 'learning_rate': 8.53503184713376e-06, 'epoch': 5.75}
|
| 73 |
-
{'loss': 0.731, 'learning_rate': 8.335987261146497e-06, 'epoch': 5.85}
|
| 74 |
-
{'loss': 0.7241, 'learning_rate': 8.136942675159237e-06, 'epoch': 5.95}
|
| 75 |
-
{'eval_loss': 5.554164886474609, 'eval_runtime': 958.7676, 'eval_samples_per_second': 42.222, 'eval_steps_per_second': 2.64, 'epoch': 5.95}
|
| 76 |
-
{'loss': 0.7027, 'learning_rate': 7.937898089171975e-06, 'epoch': 6.05}
|
| 77 |
-
{'loss': 0.6773, 'learning_rate': 7.738853503184714e-06, 'epoch': 6.15}
|
| 78 |
-
{'loss': 0.6782, 'learning_rate': 7.539808917197453e-06, 'epoch': 6.25}
|
| 79 |
-
{'loss': 0.6602, 'learning_rate': 7.340764331210192e-06, 'epoch': 6.34}
|
| 80 |
-
{'eval_loss': 5.626761436462402, 'eval_runtime': 959.3904, 'eval_samples_per_second': 42.195, 'eval_steps_per_second': 2.638, 'epoch': 6.34}
|
| 81 |
-
{'loss': 0.6511, 'learning_rate': 7.14171974522293e-06, 'epoch': 6.44}
|
| 82 |
-
{'loss': 0.6436, 'learning_rate': 6.942675159235669e-06, 'epoch': 6.54}
|
| 83 |
-
{'loss': 0.6435, 'learning_rate': 6.7436305732484085e-06, 'epoch': 6.64}
|
| 84 |
-
{'loss': 0.635, 'learning_rate': 6.544585987261147e-06, 'epoch': 6.74}
|
| 85 |
-
{'eval_loss': 5.690598011016846, 'eval_runtime': 958.9891, 'eval_samples_per_second': 42.212, 'eval_steps_per_second': 2.639, 'epoch': 6.74}
|
| 86 |
-
{'loss': 0.6306, 'learning_rate': 6.345541401273886e-06, 'epoch': 6.84}
|
| 87 |
-
{'loss': 0.6146, 'learning_rate': 6.1464968152866244e-06, 'epoch': 6.94}
|
| 88 |
-
{'loss': 0.5998, 'learning_rate': 5.947452229299363e-06, 'epoch': 7.04}
|
| 89 |
-
{'loss': 0.5837, 'learning_rate': 5.748407643312103e-06, 'epoch': 7.14}
|
|
|
|
| 1 |
+
{'loss': 4.6573, 'learning_rate': 9.940286624203822e-07, 'epoch': 0.1}
|
| 2 |
+
{'loss': 4.1908, 'learning_rate': 9.84076433121019e-07, 'epoch': 0.2}
|
| 3 |
+
{'loss': 4.1363, 'learning_rate': 9.74124203821656e-07, 'epoch': 0.3}
|
| 4 |
+
{'loss': 4.0949, 'learning_rate': 9.64171974522293e-07, 'epoch': 0.4}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00a5bfc0fa6a3aa2ab924b9d0fd18640137651b4b65a92e04e2fc725dbd4f332
|
| 3 |
size 3055
|