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 +18 -754
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- stderr-1e-06-err.slurm +0 -0
- stderr.slurm +0 -0
- stdout-1e-06-err.slurm +119 -0
- stdout.slurm +4 -119
- 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 sha256:047d719f73cd36ac9f58a2203fa5e0c98b8b1d4370508542a1a633fb075d3753
|
| 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 sha256:9d90bbdc010d82ccf4c49b054ebb3c8c9600f1f85cdd8548e8b1cf667068e70a
|
| 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 sha256:360bfe5d7b0b6d589270f3932ba49712e88c4c1d12dc82eb69c2d144a105fa45
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,784 +1,48 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./ES_corlec/checkpoint-
|
| 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": 9.
|
| 13 |
"loss": 4.6573,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.2,
|
| 18 |
-
"learning_rate": 9.
|
| 19 |
-
"loss": 4.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.3,
|
| 24 |
-
"learning_rate": 9.
|
| 25 |
-
"loss": 4.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.4,
|
| 30 |
-
"learning_rate": 9.
|
| 31 |
-
"loss": 4.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.4,
|
| 36 |
-
"eval_loss": 4.
|
| 37 |
-
"eval_runtime":
|
| 38 |
-
"eval_samples_per_second": 42.
|
| 39 |
-
"eval_steps_per_second": 2.
|
| 40 |
"step": 2000
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"epoch": 0.5,
|
| 44 |
-
"learning_rate": 9.542197452229298e-07,
|
| 45 |
-
"loss": 4.0574,
|
| 46 |
-
"step": 2500
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"epoch": 0.59,
|
| 50 |
-
"learning_rate": 9.442675159235668e-07,
|
| 51 |
-
"loss": 4.0203,
|
| 52 |
-
"step": 3000
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.69,
|
| 56 |
-
"learning_rate": 9.343152866242037e-07,
|
| 57 |
-
"loss": 4.0018,
|
| 58 |
-
"step": 3500
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.79,
|
| 62 |
-
"learning_rate": 9.243630573248408e-07,
|
| 63 |
-
"loss": 3.9827,
|
| 64 |
-
"step": 4000
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"epoch": 0.79,
|
| 68 |
-
"eval_loss": 3.9990909099578857,
|
| 69 |
-
"eval_runtime": 956.511,
|
| 70 |
-
"eval_samples_per_second": 42.322,
|
| 71 |
-
"eval_steps_per_second": 2.646,
|
| 72 |
-
"step": 4000
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.89,
|
| 76 |
-
"learning_rate": 9.144108280254777e-07,
|
| 77 |
-
"loss": 3.9639,
|
| 78 |
-
"step": 4500
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"epoch": 0.99,
|
| 82 |
-
"learning_rate": 9.044585987261146e-07,
|
| 83 |
-
"loss": 3.9332,
|
| 84 |
-
"step": 5000
|
| 85 |
-
},
|
| 86 |
-
{
|
| 87 |
-
"epoch": 1.09,
|
| 88 |
-
"learning_rate": 8.945063694267515e-07,
|
| 89 |
-
"loss": 3.9176,
|
| 90 |
-
"step": 5500
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 1.19,
|
| 94 |
-
"learning_rate": 8.845541401273885e-07,
|
| 95 |
-
"loss": 3.9053,
|
| 96 |
-
"step": 6000
|
| 97 |
-
},
|
| 98 |
-
{
|
| 99 |
-
"epoch": 1.19,
|
| 100 |
-
"eval_loss": 3.9662063121795654,
|
| 101 |
-
"eval_runtime": 956.3954,
|
| 102 |
-
"eval_samples_per_second": 42.327,
|
| 103 |
-
"eval_steps_per_second": 2.646,
|
| 104 |
-
"step": 6000
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 1.29,
|
| 108 |
-
"learning_rate": 8.746019108280255e-07,
|
| 109 |
-
"loss": 3.8901,
|
| 110 |
-
"step": 6500
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 1.39,
|
| 114 |
-
"learning_rate": 8.646496815286623e-07,
|
| 115 |
-
"loss": 3.8773,
|
| 116 |
-
"step": 7000
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 1.49,
|
| 120 |
-
"learning_rate": 8.546974522292994e-07,
|
| 121 |
-
"loss": 3.8635,
|
| 122 |
-
"step": 7500
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 1.59,
|
| 126 |
-
"learning_rate": 8.447452229299363e-07,
|
| 127 |
-
"loss": 3.8504,
|
| 128 |
-
"step": 8000
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 1.59,
|
| 132 |
-
"eval_loss": 3.947122097015381,
|
| 133 |
-
"eval_runtime": 958.2407,
|
| 134 |
-
"eval_samples_per_second": 42.245,
|
| 135 |
-
"eval_steps_per_second": 2.641,
|
| 136 |
-
"step": 8000
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 1.69,
|
| 140 |
-
"learning_rate": 8.347929936305732e-07,
|
| 141 |
-
"loss": 3.8412,
|
| 142 |
-
"step": 8500
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 1.78,
|
| 146 |
-
"learning_rate": 8.248407643312102e-07,
|
| 147 |
-
"loss": 3.8197,
|
| 148 |
-
"step": 9000
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"epoch": 1.88,
|
| 152 |
-
"learning_rate": 8.148885350318471e-07,
|
| 153 |
-
"loss": 3.8104,
|
| 154 |
-
"step": 9500
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 1.98,
|
| 158 |
-
"learning_rate": 8.04936305732484e-07,
|
| 159 |
-
"loss": 3.8018,
|
| 160 |
-
"step": 10000
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 1.98,
|
| 164 |
-
"eval_loss": 3.934990406036377,
|
| 165 |
-
"eval_runtime": 958.0564,
|
| 166 |
-
"eval_samples_per_second": 42.253,
|
| 167 |
-
"eval_steps_per_second": 2.642,
|
| 168 |
-
"step": 10000
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 2.08,
|
| 172 |
-
"learning_rate": 7.949840764331209e-07,
|
| 173 |
-
"loss": 3.7856,
|
| 174 |
-
"step": 10500
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 2.18,
|
| 178 |
-
"learning_rate": 7.85031847133758e-07,
|
| 179 |
-
"loss": 3.7865,
|
| 180 |
-
"step": 11000
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 2.28,
|
| 184 |
-
"learning_rate": 7.750796178343949e-07,
|
| 185 |
-
"loss": 3.7726,
|
| 186 |
-
"step": 11500
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 2.38,
|
| 190 |
-
"learning_rate": 7.651273885350318e-07,
|
| 191 |
-
"loss": 3.7621,
|
| 192 |
-
"step": 12000
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 2.38,
|
| 196 |
-
"eval_loss": 3.9279017448425293,
|
| 197 |
-
"eval_runtime": 958.1895,
|
| 198 |
-
"eval_samples_per_second": 42.247,
|
| 199 |
-
"eval_steps_per_second": 2.641,
|
| 200 |
-
"step": 12000
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 2.48,
|
| 204 |
-
"learning_rate": 7.551751592356688e-07,
|
| 205 |
-
"loss": 3.7631,
|
| 206 |
-
"step": 12500
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 2.58,
|
| 210 |
-
"learning_rate": 7.452229299363056e-07,
|
| 211 |
-
"loss": 3.7393,
|
| 212 |
-
"step": 13000
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 2.68,
|
| 216 |
-
"learning_rate": 7.352707006369426e-07,
|
| 217 |
-
"loss": 3.7422,
|
| 218 |
-
"step": 13500
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 2.78,
|
| 222 |
-
"learning_rate": 7.253184713375796e-07,
|
| 223 |
-
"loss": 3.7288,
|
| 224 |
-
"step": 14000
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 2.78,
|
| 228 |
-
"eval_loss": 3.923462152481079,
|
| 229 |
-
"eval_runtime": 957.9842,
|
| 230 |
-
"eval_samples_per_second": 42.256,
|
| 231 |
-
"eval_steps_per_second": 2.642,
|
| 232 |
-
"step": 14000
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 2.87,
|
| 236 |
-
"learning_rate": 7.153662420382165e-07,
|
| 237 |
-
"loss": 3.7287,
|
| 238 |
-
"step": 14500
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"epoch": 2.97,
|
| 242 |
-
"learning_rate": 7.054140127388535e-07,
|
| 243 |
-
"loss": 3.7216,
|
| 244 |
-
"step": 15000
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 3.07,
|
| 248 |
-
"learning_rate": 6.954617834394905e-07,
|
| 249 |
-
"loss": 3.7013,
|
| 250 |
-
"step": 15500
|
| 251 |
-
},
|
| 252 |
-
{
|
| 253 |
-
"epoch": 3.17,
|
| 254 |
-
"learning_rate": 6.855095541401274e-07,
|
| 255 |
-
"loss": 3.7045,
|
| 256 |
-
"step": 16000
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 3.17,
|
| 260 |
-
"eval_loss": 3.9206576347351074,
|
| 261 |
-
"eval_runtime": 958.4728,
|
| 262 |
-
"eval_samples_per_second": 42.235,
|
| 263 |
-
"eval_steps_per_second": 2.641,
|
| 264 |
-
"step": 16000
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 3.27,
|
| 268 |
-
"learning_rate": 6.755573248407643e-07,
|
| 269 |
-
"loss": 3.6973,
|
| 270 |
-
"step": 16500
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 3.37,
|
| 274 |
-
"learning_rate": 6.656050955414012e-07,
|
| 275 |
-
"loss": 3.6875,
|
| 276 |
-
"step": 17000
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 3.47,
|
| 280 |
-
"learning_rate": 6.556528662420382e-07,
|
| 281 |
-
"loss": 3.6816,
|
| 282 |
-
"step": 17500
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 3.57,
|
| 286 |
-
"learning_rate": 6.457006369426751e-07,
|
| 287 |
-
"loss": 3.6757,
|
| 288 |
-
"step": 18000
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 3.57,
|
| 292 |
-
"eval_loss": 3.9188361167907715,
|
| 293 |
-
"eval_runtime": 958.2286,
|
| 294 |
-
"eval_samples_per_second": 42.246,
|
| 295 |
-
"eval_steps_per_second": 2.641,
|
| 296 |
-
"step": 18000
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 3.67,
|
| 300 |
-
"learning_rate": 6.35748407643312e-07,
|
| 301 |
-
"loss": 3.6654,
|
| 302 |
-
"step": 18500
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 3.77,
|
| 306 |
-
"learning_rate": 6.257961783439491e-07,
|
| 307 |
-
"loss": 3.6676,
|
| 308 |
-
"step": 19000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 3.87,
|
| 312 |
-
"learning_rate": 6.158439490445859e-07,
|
| 313 |
-
"loss": 3.6625,
|
| 314 |
-
"step": 19500
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 3.97,
|
| 318 |
-
"learning_rate": 6.058917197452229e-07,
|
| 319 |
-
"loss": 3.6562,
|
| 320 |
-
"step": 20000
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 3.97,
|
| 324 |
-
"eval_loss": 3.9182815551757812,
|
| 325 |
-
"eval_runtime": 958.585,
|
| 326 |
-
"eval_samples_per_second": 42.23,
|
| 327 |
-
"eval_steps_per_second": 2.64,
|
| 328 |
-
"step": 20000
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 4.06,
|
| 332 |
-
"learning_rate": 5.959394904458599e-07,
|
| 333 |
-
"loss": 3.645,
|
| 334 |
-
"step": 20500
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 4.16,
|
| 338 |
-
"learning_rate": 5.859872611464968e-07,
|
| 339 |
-
"loss": 3.6396,
|
| 340 |
-
"step": 21000
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 4.26,
|
| 344 |
-
"learning_rate": 5.760350318471337e-07,
|
| 345 |
-
"loss": 3.6316,
|
| 346 |
-
"step": 21500
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 4.36,
|
| 350 |
-
"learning_rate": 5.660828025477706e-07,
|
| 351 |
-
"loss": 3.6261,
|
| 352 |
-
"step": 22000
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 4.36,
|
| 356 |
-
"eval_loss": 3.917975902557373,
|
| 357 |
-
"eval_runtime": 958.056,
|
| 358 |
-
"eval_samples_per_second": 42.253,
|
| 359 |
-
"eval_steps_per_second": 2.642,
|
| 360 |
-
"step": 22000
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 4.46,
|
| 364 |
-
"learning_rate": 5.561305732484077e-07,
|
| 365 |
-
"loss": 3.628,
|
| 366 |
-
"step": 22500
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 4.56,
|
| 370 |
-
"learning_rate": 5.461783439490446e-07,
|
| 371 |
-
"loss": 3.6237,
|
| 372 |
-
"step": 23000
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 4.66,
|
| 376 |
-
"learning_rate": 5.362261146496815e-07,
|
| 377 |
-
"loss": 3.6239,
|
| 378 |
-
"step": 23500
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 4.76,
|
| 382 |
-
"learning_rate": 5.262738853503185e-07,
|
| 383 |
-
"loss": 3.6161,
|
| 384 |
-
"step": 24000
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 4.76,
|
| 388 |
-
"eval_loss": 3.9181969165802,
|
| 389 |
-
"eval_runtime": 958.635,
|
| 390 |
-
"eval_samples_per_second": 42.228,
|
| 391 |
-
"eval_steps_per_second": 2.64,
|
| 392 |
-
"step": 24000
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 4.86,
|
| 396 |
-
"learning_rate": 5.163216560509553e-07,
|
| 397 |
-
"loss": 3.612,
|
| 398 |
-
"step": 24500
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 4.96,
|
| 402 |
-
"learning_rate": 5.063694267515923e-07,
|
| 403 |
-
"loss": 3.6078,
|
| 404 |
-
"step": 25000
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 5.06,
|
| 408 |
-
"learning_rate": 4.964171974522292e-07,
|
| 409 |
-
"loss": 3.6014,
|
| 410 |
-
"step": 25500
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 5.15,
|
| 414 |
-
"learning_rate": 4.864649681528662e-07,
|
| 415 |
-
"loss": 3.5983,
|
| 416 |
-
"step": 26000
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 5.15,
|
| 420 |
-
"eval_loss": 3.9187488555908203,
|
| 421 |
-
"eval_runtime": 960.0986,
|
| 422 |
-
"eval_samples_per_second": 42.163,
|
| 423 |
-
"eval_steps_per_second": 2.636,
|
| 424 |
-
"step": 26000
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 5.25,
|
| 428 |
-
"learning_rate": 4.7651273885350317e-07,
|
| 429 |
-
"loss": 3.5933,
|
| 430 |
-
"step": 26500
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 5.35,
|
| 434 |
-
"learning_rate": 4.6656050955414013e-07,
|
| 435 |
-
"loss": 3.5858,
|
| 436 |
-
"step": 27000
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 5.45,
|
| 440 |
-
"learning_rate": 4.5660828025477705e-07,
|
| 441 |
-
"loss": 3.5839,
|
| 442 |
-
"step": 27500
|
| 443 |
-
},
|
| 444 |
-
{
|
| 445 |
-
"epoch": 5.55,
|
| 446 |
-
"learning_rate": 4.4665605095541396e-07,
|
| 447 |
-
"loss": 3.5827,
|
| 448 |
-
"step": 28000
|
| 449 |
-
},
|
| 450 |
-
{
|
| 451 |
-
"epoch": 5.55,
|
| 452 |
-
"eval_loss": 3.919233798980713,
|
| 453 |
-
"eval_runtime": 958.3254,
|
| 454 |
-
"eval_samples_per_second": 42.241,
|
| 455 |
-
"eval_steps_per_second": 2.641,
|
| 456 |
-
"step": 28000
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 5.65,
|
| 460 |
-
"learning_rate": 4.367038216560509e-07,
|
| 461 |
-
"loss": 3.5799,
|
| 462 |
-
"step": 28500
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 5.75,
|
| 466 |
-
"learning_rate": 4.267515923566879e-07,
|
| 467 |
-
"loss": 3.5683,
|
| 468 |
-
"step": 29000
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 5.85,
|
| 472 |
-
"learning_rate": 4.1679936305732485e-07,
|
| 473 |
-
"loss": 3.567,
|
| 474 |
-
"step": 29500
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 5.95,
|
| 478 |
-
"learning_rate": 4.0684713375796176e-07,
|
| 479 |
-
"loss": 3.5641,
|
| 480 |
-
"step": 30000
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 5.95,
|
| 484 |
-
"eval_loss": 3.919787883758545,
|
| 485 |
-
"eval_runtime": 958.2729,
|
| 486 |
-
"eval_samples_per_second": 42.244,
|
| 487 |
-
"eval_steps_per_second": 2.641,
|
| 488 |
-
"step": 30000
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 6.05,
|
| 492 |
-
"learning_rate": 3.968949044585987e-07,
|
| 493 |
-
"loss": 3.5636,
|
| 494 |
-
"step": 30500
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 6.15,
|
| 498 |
-
"learning_rate": 3.869426751592357e-07,
|
| 499 |
-
"loss": 3.5607,
|
| 500 |
-
"step": 31000
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 6.25,
|
| 504 |
-
"learning_rate": 3.769904458598726e-07,
|
| 505 |
-
"loss": 3.5583,
|
| 506 |
-
"step": 31500
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 6.34,
|
| 510 |
-
"learning_rate": 3.670382165605095e-07,
|
| 511 |
-
"loss": 3.558,
|
| 512 |
-
"step": 32000
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 6.34,
|
| 516 |
-
"eval_loss": 3.92071270942688,
|
| 517 |
-
"eval_runtime": 958.5576,
|
| 518 |
-
"eval_samples_per_second": 42.231,
|
| 519 |
-
"eval_steps_per_second": 2.64,
|
| 520 |
-
"step": 32000
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 6.44,
|
| 524 |
-
"learning_rate": 3.570859872611465e-07,
|
| 525 |
-
"loss": 3.5481,
|
| 526 |
-
"step": 32500
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 6.54,
|
| 530 |
-
"learning_rate": 3.471337579617834e-07,
|
| 531 |
-
"loss": 3.5491,
|
| 532 |
-
"step": 33000
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 6.64,
|
| 536 |
-
"learning_rate": 3.371815286624204e-07,
|
| 537 |
-
"loss": 3.5458,
|
| 538 |
-
"step": 33500
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 6.74,
|
| 542 |
-
"learning_rate": 3.272292993630573e-07,
|
| 543 |
-
"loss": 3.544,
|
| 544 |
-
"step": 34000
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 6.74,
|
| 548 |
-
"eval_loss": 3.9213366508483887,
|
| 549 |
-
"eval_runtime": 958.1408,
|
| 550 |
-
"eval_samples_per_second": 42.25,
|
| 551 |
-
"eval_steps_per_second": 2.642,
|
| 552 |
-
"step": 34000
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 6.84,
|
| 556 |
-
"learning_rate": 3.1727707006369424e-07,
|
| 557 |
-
"loss": 3.5444,
|
| 558 |
-
"step": 34500
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 6.94,
|
| 562 |
-
"learning_rate": 3.073248407643312e-07,
|
| 563 |
-
"loss": 3.5384,
|
| 564 |
-
"step": 35000
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 7.04,
|
| 568 |
-
"learning_rate": 2.973726114649681e-07,
|
| 569 |
-
"loss": 3.5322,
|
| 570 |
-
"step": 35500
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 7.14,
|
| 574 |
-
"learning_rate": 2.874203821656051e-07,
|
| 575 |
-
"loss": 3.5243,
|
| 576 |
-
"step": 36000
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 7.14,
|
| 580 |
-
"eval_loss": 3.9221251010894775,
|
| 581 |
-
"eval_runtime": 958.7155,
|
| 582 |
-
"eval_samples_per_second": 42.224,
|
| 583 |
-
"eval_steps_per_second": 2.64,
|
| 584 |
-
"step": 36000
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 7.24,
|
| 588 |
-
"learning_rate": 2.7746815286624204e-07,
|
| 589 |
-
"loss": 3.5364,
|
| 590 |
-
"step": 36500
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 7.34,
|
| 594 |
-
"learning_rate": 2.6751592356687895e-07,
|
| 595 |
-
"loss": 3.5269,
|
| 596 |
-
"step": 37000
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 7.43,
|
| 600 |
-
"learning_rate": 2.575636942675159e-07,
|
| 601 |
-
"loss": 3.5259,
|
| 602 |
-
"step": 37500
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 7.53,
|
| 606 |
-
"learning_rate": 2.4761146496815283e-07,
|
| 607 |
-
"loss": 3.5246,
|
| 608 |
-
"step": 38000
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 7.53,
|
| 612 |
-
"eval_loss": 3.9223663806915283,
|
| 613 |
-
"eval_runtime": 958.3632,
|
| 614 |
-
"eval_samples_per_second": 42.24,
|
| 615 |
-
"eval_steps_per_second": 2.641,
|
| 616 |
-
"step": 38000
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 7.63,
|
| 620 |
-
"learning_rate": 2.376592356687898e-07,
|
| 621 |
-
"loss": 3.5249,
|
| 622 |
-
"step": 38500
|
| 623 |
-
},
|
| 624 |
-
{
|
| 625 |
-
"epoch": 7.73,
|
| 626 |
-
"learning_rate": 2.2770700636942673e-07,
|
| 627 |
-
"loss": 3.5216,
|
| 628 |
-
"step": 39000
|
| 629 |
-
},
|
| 630 |
-
{
|
| 631 |
-
"epoch": 7.83,
|
| 632 |
-
"learning_rate": 2.1775477707006367e-07,
|
| 633 |
-
"loss": 3.5242,
|
| 634 |
-
"step": 39500
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 7.93,
|
| 638 |
-
"learning_rate": 2.0780254777070064e-07,
|
| 639 |
-
"loss": 3.5265,
|
| 640 |
-
"step": 40000
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 7.93,
|
| 644 |
-
"eval_loss": 3.922888994216919,
|
| 645 |
-
"eval_runtime": 956.7286,
|
| 646 |
-
"eval_samples_per_second": 42.312,
|
| 647 |
-
"eval_steps_per_second": 2.645,
|
| 648 |
-
"step": 40000
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 8.03,
|
| 652 |
-
"learning_rate": 1.9785031847133758e-07,
|
| 653 |
-
"loss": 3.514,
|
| 654 |
-
"step": 40500
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 8.13,
|
| 658 |
-
"learning_rate": 1.8789808917197454e-07,
|
| 659 |
-
"loss": 3.5125,
|
| 660 |
-
"step": 41000
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"epoch": 8.23,
|
| 664 |
-
"learning_rate": 1.7794585987261145e-07,
|
| 665 |
-
"loss": 3.5122,
|
| 666 |
-
"step": 41500
|
| 667 |
-
},
|
| 668 |
-
{
|
| 669 |
-
"epoch": 8.33,
|
| 670 |
-
"learning_rate": 1.679936305732484e-07,
|
| 671 |
-
"loss": 3.5147,
|
| 672 |
-
"step": 42000
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 8.33,
|
| 676 |
-
"eval_loss": 3.923583745956421,
|
| 677 |
-
"eval_runtime": 956.6212,
|
| 678 |
-
"eval_samples_per_second": 42.317,
|
| 679 |
-
"eval_steps_per_second": 2.646,
|
| 680 |
-
"step": 42000
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"epoch": 8.43,
|
| 684 |
-
"learning_rate": 1.5804140127388535e-07,
|
| 685 |
-
"loss": 3.5081,
|
| 686 |
-
"step": 42500
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"epoch": 8.52,
|
| 690 |
-
"learning_rate": 1.480891719745223e-07,
|
| 691 |
-
"loss": 3.5144,
|
| 692 |
-
"step": 43000
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 8.62,
|
| 696 |
-
"learning_rate": 1.3813694267515923e-07,
|
| 697 |
-
"loss": 3.516,
|
| 698 |
-
"step": 43500
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 8.72,
|
| 702 |
-
"learning_rate": 1.2818471337579617e-07,
|
| 703 |
-
"loss": 3.5094,
|
| 704 |
-
"step": 44000
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 8.72,
|
| 708 |
-
"eval_loss": 3.923804521560669,
|
| 709 |
-
"eval_runtime": 956.9079,
|
| 710 |
-
"eval_samples_per_second": 42.304,
|
| 711 |
-
"eval_steps_per_second": 2.645,
|
| 712 |
-
"step": 44000
|
| 713 |
-
},
|
| 714 |
-
{
|
| 715 |
-
"epoch": 8.82,
|
| 716 |
-
"learning_rate": 1.1823248407643312e-07,
|
| 717 |
-
"loss": 3.5069,
|
| 718 |
-
"step": 44500
|
| 719 |
-
},
|
| 720 |
-
{
|
| 721 |
-
"epoch": 8.92,
|
| 722 |
-
"learning_rate": 1.0828025477707006e-07,
|
| 723 |
-
"loss": 3.4921,
|
| 724 |
-
"step": 45000
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 9.02,
|
| 728 |
-
"learning_rate": 9.832802547770701e-08,
|
| 729 |
-
"loss": 3.5038,
|
| 730 |
-
"step": 45500
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 9.12,
|
| 734 |
-
"learning_rate": 8.837579617834394e-08,
|
| 735 |
-
"loss": 3.5071,
|
| 736 |
-
"step": 46000
|
| 737 |
-
},
|
| 738 |
-
{
|
| 739 |
-
"epoch": 9.12,
|
| 740 |
-
"eval_loss": 3.924133062362671,
|
| 741 |
-
"eval_runtime": 956.9513,
|
| 742 |
-
"eval_samples_per_second": 42.302,
|
| 743 |
-
"eval_steps_per_second": 2.645,
|
| 744 |
-
"step": 46000
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 9.22,
|
| 748 |
-
"learning_rate": 7.842356687898089e-08,
|
| 749 |
-
"loss": 3.4962,
|
| 750 |
-
"step": 46500
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 9.32,
|
| 754 |
-
"learning_rate": 6.847133757961783e-08,
|
| 755 |
-
"loss": 3.5045,
|
| 756 |
-
"step": 47000
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 9.42,
|
| 760 |
-
"learning_rate": 5.851910828025478e-08,
|
| 761 |
-
"loss": 3.5056,
|
| 762 |
-
"step": 47500
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"epoch": 9.52,
|
| 766 |
-
"learning_rate": 4.856687898089172e-08,
|
| 767 |
-
"loss": 3.5073,
|
| 768 |
-
"step": 48000
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 9.52,
|
| 772 |
-
"eval_loss": 3.924396514892578,
|
| 773 |
-
"eval_runtime": 956.8381,
|
| 774 |
-
"eval_samples_per_second": 42.307,
|
| 775 |
-
"eval_steps_per_second": 2.645,
|
| 776 |
-
"step": 48000
|
| 777 |
}
|
| 778 |
],
|
| 779 |
-
"max_steps":
|
| 780 |
-
"num_train_epochs":
|
| 781 |
-
"total_flos":
|
| 782 |
"trial_name": null,
|
| 783 |
"trial_params": null
|
| 784 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 4.06580114364624,
|
| 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": 9.914549390452318e-07,
|
| 13 |
"loss": 4.6573,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 9.77213170787285e-07,
|
| 19 |
+
"loss": 4.1911,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 9.62971402529338e-07,
|
| 25 |
+
"loss": 4.1368,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 9.487296342713911e-07,
|
| 31 |
+
"loss": 4.0957,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.4,
|
| 36 |
+
"eval_loss": 4.06580114364624,
|
| 37 |
+
"eval_runtime": 962.1135,
|
| 38 |
+
"eval_samples_per_second": 42.075,
|
| 39 |
+
"eval_steps_per_second": 2.631,
|
| 40 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
],
|
| 43 |
+
"max_steps": 35308,
|
| 44 |
+
"num_train_epochs": 7,
|
| 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 sha256:18a92874b2068fdcc7d185fbc326fb1d602dc9a857bb7cdb7479752b527bc414
|
| 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 sha256:9d90bbdc010d82ccf4c49b054ebb3c8c9600f1f85cdd8548e8b1cf667068e70a
|
| 3 |
size 510396521
|
stderr-1e-06-err.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-1e-06-err.slurm
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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}
|
| 5 |
+
{'eval_loss': 4.065090656280518, 'eval_runtime': 956.8029, 'eval_samples_per_second': 42.309, 'eval_steps_per_second': 2.645, 'epoch': 0.4}
|
| 6 |
+
{'loss': 4.0574, 'learning_rate': 9.542197452229298e-07, 'epoch': 0.5}
|
| 7 |
+
{'loss': 4.0203, 'learning_rate': 9.442675159235668e-07, 'epoch': 0.59}
|
| 8 |
+
{'loss': 4.0018, 'learning_rate': 9.343152866242037e-07, 'epoch': 0.69}
|
| 9 |
+
{'loss': 3.9827, 'learning_rate': 9.243630573248408e-07, 'epoch': 0.79}
|
| 10 |
+
{'eval_loss': 3.9990909099578857, 'eval_runtime': 956.511, 'eval_samples_per_second': 42.322, 'eval_steps_per_second': 2.646, 'epoch': 0.79}
|
| 11 |
+
{'loss': 3.9639, 'learning_rate': 9.144108280254777e-07, 'epoch': 0.89}
|
| 12 |
+
{'loss': 3.9332, 'learning_rate': 9.044585987261146e-07, 'epoch': 0.99}
|
| 13 |
+
{'loss': 3.9176, 'learning_rate': 8.945063694267515e-07, 'epoch': 1.09}
|
| 14 |
+
{'loss': 3.9053, 'learning_rate': 8.845541401273885e-07, 'epoch': 1.19}
|
| 15 |
+
{'eval_loss': 3.9662063121795654, 'eval_runtime': 956.3954, 'eval_samples_per_second': 42.327, 'eval_steps_per_second': 2.646, 'epoch': 1.19}
|
| 16 |
+
{'loss': 3.8901, 'learning_rate': 8.746019108280255e-07, 'epoch': 1.29}
|
| 17 |
+
{'loss': 3.8773, 'learning_rate': 8.646496815286623e-07, 'epoch': 1.39}
|
| 18 |
+
{'loss': 3.8635, 'learning_rate': 8.546974522292994e-07, 'epoch': 1.49}
|
| 19 |
+
{'loss': 3.8504, 'learning_rate': 8.447452229299363e-07, 'epoch': 1.59}
|
| 20 |
+
{'eval_loss': 3.947122097015381, 'eval_runtime': 958.2407, 'eval_samples_per_second': 42.245, 'eval_steps_per_second': 2.641, 'epoch': 1.59}
|
| 21 |
+
{'loss': 3.8412, 'learning_rate': 8.347929936305732e-07, 'epoch': 1.69}
|
| 22 |
+
{'loss': 3.8197, 'learning_rate': 8.248407643312102e-07, 'epoch': 1.78}
|
| 23 |
+
{'loss': 3.8104, 'learning_rate': 8.148885350318471e-07, 'epoch': 1.88}
|
| 24 |
+
{'loss': 3.8018, 'learning_rate': 8.04936305732484e-07, 'epoch': 1.98}
|
| 25 |
+
{'eval_loss': 3.934990406036377, 'eval_runtime': 958.0564, 'eval_samples_per_second': 42.253, 'eval_steps_per_second': 2.642, 'epoch': 1.98}
|
| 26 |
+
{'loss': 3.7856, 'learning_rate': 7.949840764331209e-07, 'epoch': 2.08}
|
| 27 |
+
{'loss': 3.7865, 'learning_rate': 7.85031847133758e-07, 'epoch': 2.18}
|
| 28 |
+
{'loss': 3.7726, 'learning_rate': 7.750796178343949e-07, 'epoch': 2.28}
|
| 29 |
+
{'loss': 3.7621, 'learning_rate': 7.651273885350318e-07, 'epoch': 2.38}
|
| 30 |
+
{'eval_loss': 3.9279017448425293, 'eval_runtime': 958.1895, 'eval_samples_per_second': 42.247, 'eval_steps_per_second': 2.641, 'epoch': 2.38}
|
| 31 |
+
{'loss': 3.7631, 'learning_rate': 7.551751592356688e-07, 'epoch': 2.48}
|
| 32 |
+
{'loss': 3.7393, 'learning_rate': 7.452229299363056e-07, 'epoch': 2.58}
|
| 33 |
+
{'loss': 3.7422, 'learning_rate': 7.352707006369426e-07, 'epoch': 2.68}
|
| 34 |
+
{'loss': 3.7288, 'learning_rate': 7.253184713375796e-07, 'epoch': 2.78}
|
| 35 |
+
{'eval_loss': 3.923462152481079, 'eval_runtime': 957.9842, 'eval_samples_per_second': 42.256, 'eval_steps_per_second': 2.642, 'epoch': 2.78}
|
| 36 |
+
{'loss': 3.7287, 'learning_rate': 7.153662420382165e-07, 'epoch': 2.87}
|
| 37 |
+
{'loss': 3.7216, 'learning_rate': 7.054140127388535e-07, 'epoch': 2.97}
|
| 38 |
+
{'loss': 3.7013, 'learning_rate': 6.954617834394905e-07, 'epoch': 3.07}
|
| 39 |
+
{'loss': 3.7045, 'learning_rate': 6.855095541401274e-07, 'epoch': 3.17}
|
| 40 |
+
{'eval_loss': 3.9206576347351074, 'eval_runtime': 958.4728, 'eval_samples_per_second': 42.235, 'eval_steps_per_second': 2.641, 'epoch': 3.17}
|
| 41 |
+
{'loss': 3.6973, 'learning_rate': 6.755573248407643e-07, 'epoch': 3.27}
|
| 42 |
+
{'loss': 3.6875, 'learning_rate': 6.656050955414012e-07, 'epoch': 3.37}
|
| 43 |
+
{'loss': 3.6816, 'learning_rate': 6.556528662420382e-07, 'epoch': 3.47}
|
| 44 |
+
{'loss': 3.6757, 'learning_rate': 6.457006369426751e-07, 'epoch': 3.57}
|
| 45 |
+
{'eval_loss': 3.9188361167907715, 'eval_runtime': 958.2286, 'eval_samples_per_second': 42.246, 'eval_steps_per_second': 2.641, 'epoch': 3.57}
|
| 46 |
+
{'loss': 3.6654, 'learning_rate': 6.35748407643312e-07, 'epoch': 3.67}
|
| 47 |
+
{'loss': 3.6676, 'learning_rate': 6.257961783439491e-07, 'epoch': 3.77}
|
| 48 |
+
{'loss': 3.6625, 'learning_rate': 6.158439490445859e-07, 'epoch': 3.87}
|
| 49 |
+
{'loss': 3.6562, 'learning_rate': 6.058917197452229e-07, 'epoch': 3.97}
|
| 50 |
+
{'eval_loss': 3.9182815551757812, 'eval_runtime': 958.585, 'eval_samples_per_second': 42.23, 'eval_steps_per_second': 2.64, 'epoch': 3.97}
|
| 51 |
+
{'loss': 3.645, 'learning_rate': 5.959394904458599e-07, 'epoch': 4.06}
|
| 52 |
+
{'loss': 3.6396, 'learning_rate': 5.859872611464968e-07, 'epoch': 4.16}
|
| 53 |
+
{'loss': 3.6316, 'learning_rate': 5.760350318471337e-07, 'epoch': 4.26}
|
| 54 |
+
{'loss': 3.6261, 'learning_rate': 5.660828025477706e-07, 'epoch': 4.36}
|
| 55 |
+
{'eval_loss': 3.917975902557373, 'eval_runtime': 958.056, 'eval_samples_per_second': 42.253, 'eval_steps_per_second': 2.642, 'epoch': 4.36}
|
| 56 |
+
{'loss': 3.628, 'learning_rate': 5.561305732484077e-07, 'epoch': 4.46}
|
| 57 |
+
{'loss': 3.6237, 'learning_rate': 5.461783439490446e-07, 'epoch': 4.56}
|
| 58 |
+
{'loss': 3.6239, 'learning_rate': 5.362261146496815e-07, 'epoch': 4.66}
|
| 59 |
+
{'loss': 3.6161, 'learning_rate': 5.262738853503185e-07, 'epoch': 4.76}
|
| 60 |
+
{'eval_loss': 3.9181969165802, 'eval_runtime': 958.635, 'eval_samples_per_second': 42.228, 'eval_steps_per_second': 2.64, 'epoch': 4.76}
|
| 61 |
+
{'loss': 3.612, 'learning_rate': 5.163216560509553e-07, 'epoch': 4.86}
|
| 62 |
+
{'loss': 3.6078, 'learning_rate': 5.063694267515923e-07, 'epoch': 4.96}
|
| 63 |
+
{'loss': 3.6014, 'learning_rate': 4.964171974522292e-07, 'epoch': 5.06}
|
| 64 |
+
{'loss': 3.5983, 'learning_rate': 4.864649681528662e-07, 'epoch': 5.15}
|
| 65 |
+
{'eval_loss': 3.9187488555908203, 'eval_runtime': 960.0986, 'eval_samples_per_second': 42.163, 'eval_steps_per_second': 2.636, 'epoch': 5.15}
|
| 66 |
+
{'loss': 3.5933, 'learning_rate': 4.7651273885350317e-07, 'epoch': 5.25}
|
| 67 |
+
{'loss': 3.5858, 'learning_rate': 4.6656050955414013e-07, 'epoch': 5.35}
|
| 68 |
+
{'loss': 3.5839, 'learning_rate': 4.5660828025477705e-07, 'epoch': 5.45}
|
| 69 |
+
{'loss': 3.5827, 'learning_rate': 4.4665605095541396e-07, 'epoch': 5.55}
|
| 70 |
+
{'eval_loss': 3.919233798980713, 'eval_runtime': 958.3254, 'eval_samples_per_second': 42.241, 'eval_steps_per_second': 2.641, 'epoch': 5.55}
|
| 71 |
+
{'loss': 3.5799, 'learning_rate': 4.367038216560509e-07, 'epoch': 5.65}
|
| 72 |
+
{'loss': 3.5683, 'learning_rate': 4.267515923566879e-07, 'epoch': 5.75}
|
| 73 |
+
{'loss': 3.567, 'learning_rate': 4.1679936305732485e-07, 'epoch': 5.85}
|
| 74 |
+
{'loss': 3.5641, 'learning_rate': 4.0684713375796176e-07, 'epoch': 5.95}
|
| 75 |
+
{'eval_loss': 3.919787883758545, 'eval_runtime': 958.2729, 'eval_samples_per_second': 42.244, 'eval_steps_per_second': 2.641, 'epoch': 5.95}
|
| 76 |
+
{'loss': 3.5636, 'learning_rate': 3.968949044585987e-07, 'epoch': 6.05}
|
| 77 |
+
{'loss': 3.5607, 'learning_rate': 3.869426751592357e-07, 'epoch': 6.15}
|
| 78 |
+
{'loss': 3.5583, 'learning_rate': 3.769904458598726e-07, 'epoch': 6.25}
|
| 79 |
+
{'loss': 3.558, 'learning_rate': 3.670382165605095e-07, 'epoch': 6.34}
|
| 80 |
+
{'eval_loss': 3.92071270942688, 'eval_runtime': 958.5576, 'eval_samples_per_second': 42.231, 'eval_steps_per_second': 2.64, 'epoch': 6.34}
|
| 81 |
+
{'loss': 3.5481, 'learning_rate': 3.570859872611465e-07, 'epoch': 6.44}
|
| 82 |
+
{'loss': 3.5491, 'learning_rate': 3.471337579617834e-07, 'epoch': 6.54}
|
| 83 |
+
{'loss': 3.5458, 'learning_rate': 3.371815286624204e-07, 'epoch': 6.64}
|
| 84 |
+
{'loss': 3.544, 'learning_rate': 3.272292993630573e-07, 'epoch': 6.74}
|
| 85 |
+
{'eval_loss': 3.9213366508483887, 'eval_runtime': 958.1408, 'eval_samples_per_second': 42.25, 'eval_steps_per_second': 2.642, 'epoch': 6.74}
|
| 86 |
+
{'loss': 3.5444, 'learning_rate': 3.1727707006369424e-07, 'epoch': 6.84}
|
| 87 |
+
{'loss': 3.5384, 'learning_rate': 3.073248407643312e-07, 'epoch': 6.94}
|
| 88 |
+
{'loss': 3.5322, 'learning_rate': 2.973726114649681e-07, 'epoch': 7.04}
|
| 89 |
+
{'loss': 3.5243, 'learning_rate': 2.874203821656051e-07, 'epoch': 7.14}
|
| 90 |
+
{'eval_loss': 3.9221251010894775, 'eval_runtime': 958.7155, 'eval_samples_per_second': 42.224, 'eval_steps_per_second': 2.64, 'epoch': 7.14}
|
| 91 |
+
{'loss': 3.5364, 'learning_rate': 2.7746815286624204e-07, 'epoch': 7.24}
|
| 92 |
+
{'loss': 3.5269, 'learning_rate': 2.6751592356687895e-07, 'epoch': 7.34}
|
| 93 |
+
{'loss': 3.5259, 'learning_rate': 2.575636942675159e-07, 'epoch': 7.43}
|
| 94 |
+
{'loss': 3.5246, 'learning_rate': 2.4761146496815283e-07, 'epoch': 7.53}
|
| 95 |
+
{'eval_loss': 3.9223663806915283, 'eval_runtime': 958.3632, 'eval_samples_per_second': 42.24, 'eval_steps_per_second': 2.641, 'epoch': 7.53}
|
| 96 |
+
{'loss': 3.5249, 'learning_rate': 2.376592356687898e-07, 'epoch': 7.63}
|
| 97 |
+
{'loss': 3.5216, 'learning_rate': 2.2770700636942673e-07, 'epoch': 7.73}
|
| 98 |
+
{'loss': 3.5242, 'learning_rate': 2.1775477707006367e-07, 'epoch': 7.83}
|
| 99 |
+
{'loss': 3.5265, 'learning_rate': 2.0780254777070064e-07, 'epoch': 7.93}
|
| 100 |
+
{'eval_loss': 3.922888994216919, 'eval_runtime': 956.7286, 'eval_samples_per_second': 42.312, 'eval_steps_per_second': 2.645, 'epoch': 7.93}
|
| 101 |
+
{'loss': 3.514, 'learning_rate': 1.9785031847133758e-07, 'epoch': 8.03}
|
| 102 |
+
{'loss': 3.5125, 'learning_rate': 1.8789808917197454e-07, 'epoch': 8.13}
|
| 103 |
+
{'loss': 3.5122, 'learning_rate': 1.7794585987261145e-07, 'epoch': 8.23}
|
| 104 |
+
{'loss': 3.5147, 'learning_rate': 1.679936305732484e-07, 'epoch': 8.33}
|
| 105 |
+
{'eval_loss': 3.923583745956421, 'eval_runtime': 956.6212, 'eval_samples_per_second': 42.317, 'eval_steps_per_second': 2.646, 'epoch': 8.33}
|
| 106 |
+
{'loss': 3.5081, 'learning_rate': 1.5804140127388535e-07, 'epoch': 8.43}
|
| 107 |
+
{'loss': 3.5144, 'learning_rate': 1.480891719745223e-07, 'epoch': 8.52}
|
| 108 |
+
{'loss': 3.516, 'learning_rate': 1.3813694267515923e-07, 'epoch': 8.62}
|
| 109 |
+
{'loss': 3.5094, 'learning_rate': 1.2818471337579617e-07, 'epoch': 8.72}
|
| 110 |
+
{'eval_loss': 3.923804521560669, 'eval_runtime': 956.9079, 'eval_samples_per_second': 42.304, 'eval_steps_per_second': 2.645, 'epoch': 8.72}
|
| 111 |
+
{'loss': 3.5069, 'learning_rate': 1.1823248407643312e-07, 'epoch': 8.82}
|
| 112 |
+
{'loss': 3.4921, 'learning_rate': 1.0828025477707006e-07, 'epoch': 8.92}
|
| 113 |
+
{'loss': 3.5038, 'learning_rate': 9.832802547770701e-08, 'epoch': 9.02}
|
| 114 |
+
{'loss': 3.5071, 'learning_rate': 8.837579617834394e-08, 'epoch': 9.12}
|
| 115 |
+
{'eval_loss': 3.924133062362671, 'eval_runtime': 956.9513, 'eval_samples_per_second': 42.302, 'eval_steps_per_second': 2.645, 'epoch': 9.12}
|
| 116 |
+
{'loss': 3.4962, 'learning_rate': 7.842356687898089e-08, 'epoch': 9.22}
|
| 117 |
+
{'loss': 3.5045, 'learning_rate': 6.847133757961783e-08, 'epoch': 9.32}
|
| 118 |
+
{'loss': 3.5056, 'learning_rate': 5.851910828025478e-08, 'epoch': 9.42}
|
| 119 |
+
{'loss': 3.5073, 'learning_rate': 4.856687898089172e-08, 'epoch': 9.52}
|
stdout.slurm
CHANGED
|
@@ -1,119 +1,4 @@
|
|
| 1 |
-
{'loss': 4.6573, 'learning_rate': 9.
|
| 2 |
-
{'loss': 4.
|
| 3 |
-
{'loss': 4.
|
| 4 |
-
{'loss': 4.
|
| 5 |
-
{'eval_loss': 4.065090656280518, 'eval_runtime': 956.8029, 'eval_samples_per_second': 42.309, 'eval_steps_per_second': 2.645, 'epoch': 0.4}
|
| 6 |
-
{'loss': 4.0574, 'learning_rate': 9.542197452229298e-07, 'epoch': 0.5}
|
| 7 |
-
{'loss': 4.0203, 'learning_rate': 9.442675159235668e-07, 'epoch': 0.59}
|
| 8 |
-
{'loss': 4.0018, 'learning_rate': 9.343152866242037e-07, 'epoch': 0.69}
|
| 9 |
-
{'loss': 3.9827, 'learning_rate': 9.243630573248408e-07, 'epoch': 0.79}
|
| 10 |
-
{'eval_loss': 3.9990909099578857, 'eval_runtime': 956.511, 'eval_samples_per_second': 42.322, 'eval_steps_per_second': 2.646, 'epoch': 0.79}
|
| 11 |
-
{'loss': 3.9639, 'learning_rate': 9.144108280254777e-07, 'epoch': 0.89}
|
| 12 |
-
{'loss': 3.9332, 'learning_rate': 9.044585987261146e-07, 'epoch': 0.99}
|
| 13 |
-
{'loss': 3.9176, 'learning_rate': 8.945063694267515e-07, 'epoch': 1.09}
|
| 14 |
-
{'loss': 3.9053, 'learning_rate': 8.845541401273885e-07, 'epoch': 1.19}
|
| 15 |
-
{'eval_loss': 3.9662063121795654, 'eval_runtime': 956.3954, 'eval_samples_per_second': 42.327, 'eval_steps_per_second': 2.646, 'epoch': 1.19}
|
| 16 |
-
{'loss': 3.8901, 'learning_rate': 8.746019108280255e-07, 'epoch': 1.29}
|
| 17 |
-
{'loss': 3.8773, 'learning_rate': 8.646496815286623e-07, 'epoch': 1.39}
|
| 18 |
-
{'loss': 3.8635, 'learning_rate': 8.546974522292994e-07, 'epoch': 1.49}
|
| 19 |
-
{'loss': 3.8504, 'learning_rate': 8.447452229299363e-07, 'epoch': 1.59}
|
| 20 |
-
{'eval_loss': 3.947122097015381, 'eval_runtime': 958.2407, 'eval_samples_per_second': 42.245, 'eval_steps_per_second': 2.641, 'epoch': 1.59}
|
| 21 |
-
{'loss': 3.8412, 'learning_rate': 8.347929936305732e-07, 'epoch': 1.69}
|
| 22 |
-
{'loss': 3.8197, 'learning_rate': 8.248407643312102e-07, 'epoch': 1.78}
|
| 23 |
-
{'loss': 3.8104, 'learning_rate': 8.148885350318471e-07, 'epoch': 1.88}
|
| 24 |
-
{'loss': 3.8018, 'learning_rate': 8.04936305732484e-07, 'epoch': 1.98}
|
| 25 |
-
{'eval_loss': 3.934990406036377, 'eval_runtime': 958.0564, 'eval_samples_per_second': 42.253, 'eval_steps_per_second': 2.642, 'epoch': 1.98}
|
| 26 |
-
{'loss': 3.7856, 'learning_rate': 7.949840764331209e-07, 'epoch': 2.08}
|
| 27 |
-
{'loss': 3.7865, 'learning_rate': 7.85031847133758e-07, 'epoch': 2.18}
|
| 28 |
-
{'loss': 3.7726, 'learning_rate': 7.750796178343949e-07, 'epoch': 2.28}
|
| 29 |
-
{'loss': 3.7621, 'learning_rate': 7.651273885350318e-07, 'epoch': 2.38}
|
| 30 |
-
{'eval_loss': 3.9279017448425293, 'eval_runtime': 958.1895, 'eval_samples_per_second': 42.247, 'eval_steps_per_second': 2.641, 'epoch': 2.38}
|
| 31 |
-
{'loss': 3.7631, 'learning_rate': 7.551751592356688e-07, 'epoch': 2.48}
|
| 32 |
-
{'loss': 3.7393, 'learning_rate': 7.452229299363056e-07, 'epoch': 2.58}
|
| 33 |
-
{'loss': 3.7422, 'learning_rate': 7.352707006369426e-07, 'epoch': 2.68}
|
| 34 |
-
{'loss': 3.7288, 'learning_rate': 7.253184713375796e-07, 'epoch': 2.78}
|
| 35 |
-
{'eval_loss': 3.923462152481079, 'eval_runtime': 957.9842, 'eval_samples_per_second': 42.256, 'eval_steps_per_second': 2.642, 'epoch': 2.78}
|
| 36 |
-
{'loss': 3.7287, 'learning_rate': 7.153662420382165e-07, 'epoch': 2.87}
|
| 37 |
-
{'loss': 3.7216, 'learning_rate': 7.054140127388535e-07, 'epoch': 2.97}
|
| 38 |
-
{'loss': 3.7013, 'learning_rate': 6.954617834394905e-07, 'epoch': 3.07}
|
| 39 |
-
{'loss': 3.7045, 'learning_rate': 6.855095541401274e-07, 'epoch': 3.17}
|
| 40 |
-
{'eval_loss': 3.9206576347351074, 'eval_runtime': 958.4728, 'eval_samples_per_second': 42.235, 'eval_steps_per_second': 2.641, 'epoch': 3.17}
|
| 41 |
-
{'loss': 3.6973, 'learning_rate': 6.755573248407643e-07, 'epoch': 3.27}
|
| 42 |
-
{'loss': 3.6875, 'learning_rate': 6.656050955414012e-07, 'epoch': 3.37}
|
| 43 |
-
{'loss': 3.6816, 'learning_rate': 6.556528662420382e-07, 'epoch': 3.47}
|
| 44 |
-
{'loss': 3.6757, 'learning_rate': 6.457006369426751e-07, 'epoch': 3.57}
|
| 45 |
-
{'eval_loss': 3.9188361167907715, 'eval_runtime': 958.2286, 'eval_samples_per_second': 42.246, 'eval_steps_per_second': 2.641, 'epoch': 3.57}
|
| 46 |
-
{'loss': 3.6654, 'learning_rate': 6.35748407643312e-07, 'epoch': 3.67}
|
| 47 |
-
{'loss': 3.6676, 'learning_rate': 6.257961783439491e-07, 'epoch': 3.77}
|
| 48 |
-
{'loss': 3.6625, 'learning_rate': 6.158439490445859e-07, 'epoch': 3.87}
|
| 49 |
-
{'loss': 3.6562, 'learning_rate': 6.058917197452229e-07, 'epoch': 3.97}
|
| 50 |
-
{'eval_loss': 3.9182815551757812, 'eval_runtime': 958.585, 'eval_samples_per_second': 42.23, 'eval_steps_per_second': 2.64, 'epoch': 3.97}
|
| 51 |
-
{'loss': 3.645, 'learning_rate': 5.959394904458599e-07, 'epoch': 4.06}
|
| 52 |
-
{'loss': 3.6396, 'learning_rate': 5.859872611464968e-07, 'epoch': 4.16}
|
| 53 |
-
{'loss': 3.6316, 'learning_rate': 5.760350318471337e-07, 'epoch': 4.26}
|
| 54 |
-
{'loss': 3.6261, 'learning_rate': 5.660828025477706e-07, 'epoch': 4.36}
|
| 55 |
-
{'eval_loss': 3.917975902557373, 'eval_runtime': 958.056, 'eval_samples_per_second': 42.253, 'eval_steps_per_second': 2.642, 'epoch': 4.36}
|
| 56 |
-
{'loss': 3.628, 'learning_rate': 5.561305732484077e-07, 'epoch': 4.46}
|
| 57 |
-
{'loss': 3.6237, 'learning_rate': 5.461783439490446e-07, 'epoch': 4.56}
|
| 58 |
-
{'loss': 3.6239, 'learning_rate': 5.362261146496815e-07, 'epoch': 4.66}
|
| 59 |
-
{'loss': 3.6161, 'learning_rate': 5.262738853503185e-07, 'epoch': 4.76}
|
| 60 |
-
{'eval_loss': 3.9181969165802, 'eval_runtime': 958.635, 'eval_samples_per_second': 42.228, 'eval_steps_per_second': 2.64, 'epoch': 4.76}
|
| 61 |
-
{'loss': 3.612, 'learning_rate': 5.163216560509553e-07, 'epoch': 4.86}
|
| 62 |
-
{'loss': 3.6078, 'learning_rate': 5.063694267515923e-07, 'epoch': 4.96}
|
| 63 |
-
{'loss': 3.6014, 'learning_rate': 4.964171974522292e-07, 'epoch': 5.06}
|
| 64 |
-
{'loss': 3.5983, 'learning_rate': 4.864649681528662e-07, 'epoch': 5.15}
|
| 65 |
-
{'eval_loss': 3.9187488555908203, 'eval_runtime': 960.0986, 'eval_samples_per_second': 42.163, 'eval_steps_per_second': 2.636, 'epoch': 5.15}
|
| 66 |
-
{'loss': 3.5933, 'learning_rate': 4.7651273885350317e-07, 'epoch': 5.25}
|
| 67 |
-
{'loss': 3.5858, 'learning_rate': 4.6656050955414013e-07, 'epoch': 5.35}
|
| 68 |
-
{'loss': 3.5839, 'learning_rate': 4.5660828025477705e-07, 'epoch': 5.45}
|
| 69 |
-
{'loss': 3.5827, 'learning_rate': 4.4665605095541396e-07, 'epoch': 5.55}
|
| 70 |
-
{'eval_loss': 3.919233798980713, 'eval_runtime': 958.3254, 'eval_samples_per_second': 42.241, 'eval_steps_per_second': 2.641, 'epoch': 5.55}
|
| 71 |
-
{'loss': 3.5799, 'learning_rate': 4.367038216560509e-07, 'epoch': 5.65}
|
| 72 |
-
{'loss': 3.5683, 'learning_rate': 4.267515923566879e-07, 'epoch': 5.75}
|
| 73 |
-
{'loss': 3.567, 'learning_rate': 4.1679936305732485e-07, 'epoch': 5.85}
|
| 74 |
-
{'loss': 3.5641, 'learning_rate': 4.0684713375796176e-07, 'epoch': 5.95}
|
| 75 |
-
{'eval_loss': 3.919787883758545, 'eval_runtime': 958.2729, 'eval_samples_per_second': 42.244, 'eval_steps_per_second': 2.641, 'epoch': 5.95}
|
| 76 |
-
{'loss': 3.5636, 'learning_rate': 3.968949044585987e-07, 'epoch': 6.05}
|
| 77 |
-
{'loss': 3.5607, 'learning_rate': 3.869426751592357e-07, 'epoch': 6.15}
|
| 78 |
-
{'loss': 3.5583, 'learning_rate': 3.769904458598726e-07, 'epoch': 6.25}
|
| 79 |
-
{'loss': 3.558, 'learning_rate': 3.670382165605095e-07, 'epoch': 6.34}
|
| 80 |
-
{'eval_loss': 3.92071270942688, 'eval_runtime': 958.5576, 'eval_samples_per_second': 42.231, 'eval_steps_per_second': 2.64, 'epoch': 6.34}
|
| 81 |
-
{'loss': 3.5481, 'learning_rate': 3.570859872611465e-07, 'epoch': 6.44}
|
| 82 |
-
{'loss': 3.5491, 'learning_rate': 3.471337579617834e-07, 'epoch': 6.54}
|
| 83 |
-
{'loss': 3.5458, 'learning_rate': 3.371815286624204e-07, 'epoch': 6.64}
|
| 84 |
-
{'loss': 3.544, 'learning_rate': 3.272292993630573e-07, 'epoch': 6.74}
|
| 85 |
-
{'eval_loss': 3.9213366508483887, 'eval_runtime': 958.1408, 'eval_samples_per_second': 42.25, 'eval_steps_per_second': 2.642, 'epoch': 6.74}
|
| 86 |
-
{'loss': 3.5444, 'learning_rate': 3.1727707006369424e-07, 'epoch': 6.84}
|
| 87 |
-
{'loss': 3.5384, 'learning_rate': 3.073248407643312e-07, 'epoch': 6.94}
|
| 88 |
-
{'loss': 3.5322, 'learning_rate': 2.973726114649681e-07, 'epoch': 7.04}
|
| 89 |
-
{'loss': 3.5243, 'learning_rate': 2.874203821656051e-07, 'epoch': 7.14}
|
| 90 |
-
{'eval_loss': 3.9221251010894775, 'eval_runtime': 958.7155, 'eval_samples_per_second': 42.224, 'eval_steps_per_second': 2.64, 'epoch': 7.14}
|
| 91 |
-
{'loss': 3.5364, 'learning_rate': 2.7746815286624204e-07, 'epoch': 7.24}
|
| 92 |
-
{'loss': 3.5269, 'learning_rate': 2.6751592356687895e-07, 'epoch': 7.34}
|
| 93 |
-
{'loss': 3.5259, 'learning_rate': 2.575636942675159e-07, 'epoch': 7.43}
|
| 94 |
-
{'loss': 3.5246, 'learning_rate': 2.4761146496815283e-07, 'epoch': 7.53}
|
| 95 |
-
{'eval_loss': 3.9223663806915283, 'eval_runtime': 958.3632, 'eval_samples_per_second': 42.24, 'eval_steps_per_second': 2.641, 'epoch': 7.53}
|
| 96 |
-
{'loss': 3.5249, 'learning_rate': 2.376592356687898e-07, 'epoch': 7.63}
|
| 97 |
-
{'loss': 3.5216, 'learning_rate': 2.2770700636942673e-07, 'epoch': 7.73}
|
| 98 |
-
{'loss': 3.5242, 'learning_rate': 2.1775477707006367e-07, 'epoch': 7.83}
|
| 99 |
-
{'loss': 3.5265, 'learning_rate': 2.0780254777070064e-07, 'epoch': 7.93}
|
| 100 |
-
{'eval_loss': 3.922888994216919, 'eval_runtime': 956.7286, 'eval_samples_per_second': 42.312, 'eval_steps_per_second': 2.645, 'epoch': 7.93}
|
| 101 |
-
{'loss': 3.514, 'learning_rate': 1.9785031847133758e-07, 'epoch': 8.03}
|
| 102 |
-
{'loss': 3.5125, 'learning_rate': 1.8789808917197454e-07, 'epoch': 8.13}
|
| 103 |
-
{'loss': 3.5122, 'learning_rate': 1.7794585987261145e-07, 'epoch': 8.23}
|
| 104 |
-
{'loss': 3.5147, 'learning_rate': 1.679936305732484e-07, 'epoch': 8.33}
|
| 105 |
-
{'eval_loss': 3.923583745956421, 'eval_runtime': 956.6212, 'eval_samples_per_second': 42.317, 'eval_steps_per_second': 2.646, 'epoch': 8.33}
|
| 106 |
-
{'loss': 3.5081, 'learning_rate': 1.5804140127388535e-07, 'epoch': 8.43}
|
| 107 |
-
{'loss': 3.5144, 'learning_rate': 1.480891719745223e-07, 'epoch': 8.52}
|
| 108 |
-
{'loss': 3.516, 'learning_rate': 1.3813694267515923e-07, 'epoch': 8.62}
|
| 109 |
-
{'loss': 3.5094, 'learning_rate': 1.2818471337579617e-07, 'epoch': 8.72}
|
| 110 |
-
{'eval_loss': 3.923804521560669, 'eval_runtime': 956.9079, 'eval_samples_per_second': 42.304, 'eval_steps_per_second': 2.645, 'epoch': 8.72}
|
| 111 |
-
{'loss': 3.5069, 'learning_rate': 1.1823248407643312e-07, 'epoch': 8.82}
|
| 112 |
-
{'loss': 3.4921, 'learning_rate': 1.0828025477707006e-07, 'epoch': 8.92}
|
| 113 |
-
{'loss': 3.5038, 'learning_rate': 9.832802547770701e-08, 'epoch': 9.02}
|
| 114 |
-
{'loss': 3.5071, 'learning_rate': 8.837579617834394e-08, 'epoch': 9.12}
|
| 115 |
-
{'eval_loss': 3.924133062362671, 'eval_runtime': 956.9513, 'eval_samples_per_second': 42.302, 'eval_steps_per_second': 2.645, 'epoch': 9.12}
|
| 116 |
-
{'loss': 3.4962, 'learning_rate': 7.842356687898089e-08, 'epoch': 9.22}
|
| 117 |
-
{'loss': 3.5045, 'learning_rate': 6.847133757961783e-08, 'epoch': 9.32}
|
| 118 |
-
{'loss': 3.5056, 'learning_rate': 5.851910828025478e-08, 'epoch': 9.42}
|
| 119 |
-
{'loss': 3.5073, 'learning_rate': 4.856687898089172e-08, 'epoch': 9.52}
|
|
|
|
| 1 |
+
{'loss': 4.6573, 'learning_rate': 9.914549390452318e-07, 'epoch': 0.1}
|
| 2 |
+
{'loss': 4.1911, 'learning_rate': 9.77213170787285e-07, 'epoch': 0.2}
|
| 3 |
+
{'loss': 4.1368, 'learning_rate': 9.62971402529338e-07, 'epoch': 0.3}
|
| 4 |
+
{'loss': 4.0957, 'learning_rate': 9.487296342713911e-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 sha256:18a92874b2068fdcc7d185fbc326fb1d602dc9a857bb7cdb7479752b527bc414
|
| 3 |
size 3055
|