Upload 9 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +57 -807
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490594117
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fb9fa451e0fdfe61b20ff1a1ff5a502f2c4aed55f4bd2588a3818904242d2b7
|
| 3 |
size 2490594117
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262168365
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e87d88f08b88070c69b1f891d632fc2b2539758387567149ecdc8ea1fb5ea28c
|
| 3 |
size 1262168365
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff58ba996d368fe2e3614680ac55c25f343a30115fdd797d09cc9e5021f2ceb
|
| 3 |
size 14575
|
scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dc9eacfeb00bd0bfeb98934a2309be01be65b288e0d747bbfc423b32679169f
|
| 3 |
size 557
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c78769c18f0eab807e3f886758f225b7a6742b2333513c189962e3b430c92dd5
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,856 +1,106 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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": 1.
|
| 12 |
"learning_rate": 0.0001,
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 1.
|
| 18 |
-
"eval_loss": 0.
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second": 16.
|
| 21 |
-
"eval_steps_per_second": 2.
|
| 22 |
-
"eval_wer": 0.
|
| 23 |
"step": 100
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 2.
|
| 27 |
-
"learning_rate": 9.
|
| 28 |
-
"loss": 0.
|
| 29 |
"step": 200
|
| 30 |
},
|
| 31 |
{
|
| 32 |
-
"epoch": 2.
|
| 33 |
-
"eval_loss": 0.
|
| 34 |
-
"eval_runtime":
|
| 35 |
-
"eval_samples_per_second": 22.
|
| 36 |
-
"eval_steps_per_second": 2.
|
| 37 |
-
"eval_wer": 0.
|
| 38 |
"step": 200
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 3.
|
| 42 |
-
"learning_rate": 9.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 3.
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_runtime":
|
| 50 |
-
"eval_samples_per_second":
|
| 51 |
-
"eval_steps_per_second": 2.
|
| 52 |
-
"eval_wer": 0.
|
| 53 |
"step": 300
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch":
|
| 57 |
-
"learning_rate": 9.
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 400
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"eval_loss": 0.
|
| 64 |
-
"eval_runtime":
|
| 65 |
-
"eval_samples_per_second": 21.
|
| 66 |
-
"eval_steps_per_second": 2.
|
| 67 |
-
"eval_wer": 0.
|
| 68 |
"step": 400
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 6.
|
| 72 |
-
"learning_rate": 9.
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 6.
|
| 78 |
-
"eval_loss": 0.
|
| 79 |
-
"eval_runtime":
|
| 80 |
-
"eval_samples_per_second":
|
| 81 |
-
"eval_steps_per_second": 2.
|
| 82 |
-
"eval_wer": 0.
|
| 83 |
"step": 500
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch": 7.
|
| 87 |
-
"learning_rate": 9.
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 600
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch": 7.
|
| 93 |
-
"eval_loss": 0.
|
| 94 |
-
"eval_runtime":
|
| 95 |
-
"eval_samples_per_second":
|
| 96 |
-
"eval_steps_per_second": 2.
|
| 97 |
-
"eval_wer": 0.
|
| 98 |
"step": 600
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 9.09,
|
| 102 |
-
"learning_rate": 9.921976592977894e-05,
|
| 103 |
-
"loss": 0.0413,
|
| 104 |
-
"step": 700
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 9.09,
|
| 108 |
-
"eval_loss": 0.38365304470062256,
|
| 109 |
-
"eval_runtime": 157.1121,
|
| 110 |
-
"eval_samples_per_second": 19.839,
|
| 111 |
-
"eval_steps_per_second": 2.482,
|
| 112 |
-
"eval_wer": 0.24466410627715168,
|
| 113 |
-
"step": 700
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 10.39,
|
| 117 |
-
"learning_rate": 9.908972691807543e-05,
|
| 118 |
-
"loss": 0.0417,
|
| 119 |
-
"step": 800
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 10.39,
|
| 123 |
-
"eval_loss": 0.37991076707839966,
|
| 124 |
-
"eval_runtime": 160.431,
|
| 125 |
-
"eval_samples_per_second": 19.429,
|
| 126 |
-
"eval_steps_per_second": 2.431,
|
| 127 |
-
"eval_wer": 0.23786438330290247,
|
| 128 |
-
"step": 800
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 11.68,
|
| 132 |
-
"learning_rate": 9.89596879063719e-05,
|
| 133 |
-
"loss": 0.0423,
|
| 134 |
-
"step": 900
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 11.68,
|
| 138 |
-
"eval_loss": 0.41009148955345154,
|
| 139 |
-
"eval_runtime": 161.1546,
|
| 140 |
-
"eval_samples_per_second": 19.342,
|
| 141 |
-
"eval_steps_per_second": 2.42,
|
| 142 |
-
"eval_wer": 0.24485298747088083,
|
| 143 |
-
"step": 900
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 12.98,
|
| 147 |
-
"learning_rate": 9.88296488946684e-05,
|
| 148 |
-
"loss": 0.0425,
|
| 149 |
-
"step": 1000
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 12.98,
|
| 153 |
-
"eval_loss": 0.38417309522628784,
|
| 154 |
-
"eval_runtime": 162.4688,
|
| 155 |
-
"eval_samples_per_second": 19.185,
|
| 156 |
-
"eval_steps_per_second": 2.4,
|
| 157 |
-
"eval_wer": 0.23931247245482593,
|
| 158 |
-
"step": 1000
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 14.28,
|
| 162 |
-
"learning_rate": 9.869960988296489e-05,
|
| 163 |
-
"loss": 0.0413,
|
| 164 |
-
"step": 1100
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 14.28,
|
| 168 |
-
"eval_loss": 0.37902718782424927,
|
| 169 |
-
"eval_runtime": 164.4062,
|
| 170 |
-
"eval_samples_per_second": 18.959,
|
| 171 |
-
"eval_steps_per_second": 2.372,
|
| 172 |
-
"eval_wer": 0.24491594786879053,
|
| 173 |
-
"step": 1100
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 15.58,
|
| 177 |
-
"learning_rate": 9.856957087126138e-05,
|
| 178 |
-
"loss": 0.0416,
|
| 179 |
-
"step": 1200
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 15.58,
|
| 183 |
-
"eval_loss": 0.38784804940223694,
|
| 184 |
-
"eval_runtime": 163.9531,
|
| 185 |
-
"eval_samples_per_second": 19.012,
|
| 186 |
-
"eval_steps_per_second": 2.379,
|
| 187 |
-
"eval_wer": 0.23931247245482593,
|
| 188 |
-
"step": 1200
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 16.88,
|
| 192 |
-
"learning_rate": 9.844083224967491e-05,
|
| 193 |
-
"loss": 0.0436,
|
| 194 |
-
"step": 1300
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 16.88,
|
| 198 |
-
"eval_loss": 0.36406952142715454,
|
| 199 |
-
"eval_runtime": 162.4063,
|
| 200 |
-
"eval_samples_per_second": 19.193,
|
| 201 |
-
"eval_steps_per_second": 2.401,
|
| 202 |
-
"eval_wer": 0.23817918529245105,
|
| 203 |
-
"step": 1300
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 18.18,
|
| 207 |
-
"learning_rate": 9.83107932379714e-05,
|
| 208 |
-
"loss": 0.0424,
|
| 209 |
-
"step": 1400
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 18.18,
|
| 213 |
-
"eval_loss": 0.3773825764656067,
|
| 214 |
-
"eval_runtime": 161.8281,
|
| 215 |
-
"eval_samples_per_second": 19.261,
|
| 216 |
-
"eval_steps_per_second": 2.41,
|
| 217 |
-
"eval_wer": 0.2359126109677013,
|
| 218 |
-
"step": 1400
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 19.48,
|
| 222 |
-
"learning_rate": 9.818075422626789e-05,
|
| 223 |
-
"loss": 0.0379,
|
| 224 |
-
"step": 1500
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 19.48,
|
| 228 |
-
"eval_loss": 0.39104992151260376,
|
| 229 |
-
"eval_runtime": 153.8281,
|
| 230 |
-
"eval_samples_per_second": 20.263,
|
| 231 |
-
"eval_steps_per_second": 2.535,
|
| 232 |
-
"eval_wer": 0.23396083863250017,
|
| 233 |
-
"step": 1500
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 20.77,
|
| 237 |
-
"learning_rate": 9.805071521456437e-05,
|
| 238 |
-
"loss": 0.0401,
|
| 239 |
-
"step": 1600
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 20.77,
|
| 243 |
-
"eval_loss": 0.4012731611728668,
|
| 244 |
-
"eval_runtime": 166.1564,
|
| 245 |
-
"eval_samples_per_second": 18.759,
|
| 246 |
-
"eval_steps_per_second": 2.347,
|
| 247 |
-
"eval_wer": 0.23786438330290247,
|
| 248 |
-
"step": 1600
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 22.08,
|
| 252 |
-
"learning_rate": 9.792067620286086e-05,
|
| 253 |
-
"loss": 0.0397,
|
| 254 |
-
"step": 1700
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 22.08,
|
| 258 |
-
"eval_loss": 0.3917081952095032,
|
| 259 |
-
"eval_runtime": 151.5157,
|
| 260 |
-
"eval_samples_per_second": 20.572,
|
| 261 |
-
"eval_steps_per_second": 2.574,
|
| 262 |
-
"eval_wer": 0.23981615563810363,
|
| 263 |
-
"step": 1700
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 23.37,
|
| 267 |
-
"learning_rate": 9.779063719115735e-05,
|
| 268 |
-
"loss": 0.0399,
|
| 269 |
-
"step": 1800
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 23.37,
|
| 273 |
-
"eval_loss": 0.41352856159210205,
|
| 274 |
-
"eval_runtime": 169.9898,
|
| 275 |
-
"eval_samples_per_second": 18.336,
|
| 276 |
-
"eval_steps_per_second": 2.294,
|
| 277 |
-
"eval_wer": 0.24151608638166594,
|
| 278 |
-
"step": 1800
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 24.67,
|
| 282 |
-
"learning_rate": 9.766059817945384e-05,
|
| 283 |
-
"loss": 0.0407,
|
| 284 |
-
"step": 1900
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 24.67,
|
| 288 |
-
"eval_loss": 0.3818851113319397,
|
| 289 |
-
"eval_runtime": 176.1576,
|
| 290 |
-
"eval_samples_per_second": 17.694,
|
| 291 |
-
"eval_steps_per_second": 2.214,
|
| 292 |
-
"eval_wer": 0.23717181892589562,
|
| 293 |
-
"step": 1900
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 25.97,
|
| 297 |
-
"learning_rate": 9.753055916775033e-05,
|
| 298 |
-
"loss": 0.0392,
|
| 299 |
-
"step": 2000
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 25.97,
|
| 303 |
-
"eval_loss": 0.3882431983947754,
|
| 304 |
-
"eval_runtime": 167.0577,
|
| 305 |
-
"eval_samples_per_second": 18.658,
|
| 306 |
-
"eval_steps_per_second": 2.335,
|
| 307 |
-
"eval_wer": 0.23786438330290247,
|
| 308 |
-
"step": 2000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 27.27,
|
| 312 |
-
"learning_rate": 9.740052015604681e-05,
|
| 313 |
-
"loss": 0.0381,
|
| 314 |
-
"step": 2100
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 27.27,
|
| 318 |
-
"eval_loss": 0.3893887996673584,
|
| 319 |
-
"eval_runtime": 171.6954,
|
| 320 |
-
"eval_samples_per_second": 18.154,
|
| 321 |
-
"eval_steps_per_second": 2.271,
|
| 322 |
-
"eval_wer": 0.23943839325064534,
|
| 323 |
-
"step": 2100
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 28.57,
|
| 327 |
-
"learning_rate": 9.72704811443433e-05,
|
| 328 |
-
"loss": 0.0401,
|
| 329 |
-
"step": 2200
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 28.57,
|
| 333 |
-
"eval_loss": 0.3673301041126251,
|
| 334 |
-
"eval_runtime": 174.7303,
|
| 335 |
-
"eval_samples_per_second": 17.839,
|
| 336 |
-
"eval_steps_per_second": 2.232,
|
| 337 |
-
"eval_wer": 0.2357866901718819,
|
| 338 |
-
"step": 2200
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 29.86,
|
| 342 |
-
"learning_rate": 9.71404421326398e-05,
|
| 343 |
-
"loss": 0.0391,
|
| 344 |
-
"step": 2300
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 29.86,
|
| 348 |
-
"eval_loss": 0.3780101239681244,
|
| 349 |
-
"eval_runtime": 157.4375,
|
| 350 |
-
"eval_samples_per_second": 19.798,
|
| 351 |
-
"eval_steps_per_second": 2.477,
|
| 352 |
-
"eval_wer": 0.2354089277844236,
|
| 353 |
-
"step": 2300
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 31.17,
|
| 357 |
-
"learning_rate": 9.701040312093628e-05,
|
| 358 |
-
"loss": 0.0377,
|
| 359 |
-
"step": 2400
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 31.17,
|
| 363 |
-
"eval_loss": 0.3910522758960724,
|
| 364 |
-
"eval_runtime": 159.5625,
|
| 365 |
-
"eval_samples_per_second": 19.535,
|
| 366 |
-
"eval_steps_per_second": 2.444,
|
| 367 |
-
"eval_wer": 0.23654221494679847,
|
| 368 |
-
"step": 2400
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 32.46,
|
| 372 |
-
"learning_rate": 9.688036410923278e-05,
|
| 373 |
-
"loss": 0.0378,
|
| 374 |
-
"step": 2500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 32.46,
|
| 378 |
-
"eval_loss": 0.3806402087211609,
|
| 379 |
-
"eval_runtime": 170.7978,
|
| 380 |
-
"eval_samples_per_second": 18.25,
|
| 381 |
-
"eval_steps_per_second": 2.283,
|
| 382 |
-
"eval_wer": 0.23918655165900649,
|
| 383 |
-
"step": 2500
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 33.76,
|
| 387 |
-
"learning_rate": 9.675032509752925e-05,
|
| 388 |
-
"loss": 0.0347,
|
| 389 |
-
"step": 2600
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 33.76,
|
| 393 |
-
"eval_loss": 0.3844529390335083,
|
| 394 |
-
"eval_runtime": 160.3906,
|
| 395 |
-
"eval_samples_per_second": 19.434,
|
| 396 |
-
"eval_steps_per_second": 2.432,
|
| 397 |
-
"eval_wer": 0.23515708619278475,
|
| 398 |
-
"step": 2600
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 35.06,
|
| 402 |
-
"learning_rate": 9.662028608582574e-05,
|
| 403 |
-
"loss": 0.0369,
|
| 404 |
-
"step": 2700
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 35.06,
|
| 408 |
-
"eval_loss": 0.39440667629241943,
|
| 409 |
-
"eval_runtime": 167.7032,
|
| 410 |
-
"eval_samples_per_second": 18.586,
|
| 411 |
-
"eval_steps_per_second": 2.326,
|
| 412 |
-
"eval_wer": 0.23931247245482593,
|
| 413 |
-
"step": 2700
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 36.36,
|
| 417 |
-
"learning_rate": 9.649024707412224e-05,
|
| 418 |
-
"loss": 0.0375,
|
| 419 |
-
"step": 2800
|
| 420 |
-
},
|
| 421 |
-
{
|
| 422 |
-
"epoch": 36.36,
|
| 423 |
-
"eval_loss": 0.37219446897506714,
|
| 424 |
-
"eval_runtime": 165.2969,
|
| 425 |
-
"eval_samples_per_second": 18.857,
|
| 426 |
-
"eval_steps_per_second": 2.359,
|
| 427 |
-
"eval_wer": 0.23012025436000755,
|
| 428 |
-
"step": 2800
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 37.66,
|
| 432 |
-
"learning_rate": 9.636020806241873e-05,
|
| 433 |
-
"loss": 0.0363,
|
| 434 |
-
"step": 2900
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 37.66,
|
| 438 |
-
"eval_loss": 0.3664211332798004,
|
| 439 |
-
"eval_runtime": 167.8076,
|
| 440 |
-
"eval_samples_per_second": 18.575,
|
| 441 |
-
"eval_steps_per_second": 2.324,
|
| 442 |
-
"eval_wer": 0.23112762072656298,
|
| 443 |
-
"step": 2900
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 38.95,
|
| 447 |
-
"learning_rate": 9.623016905071522e-05,
|
| 448 |
-
"loss": 0.034,
|
| 449 |
-
"step": 3000
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 38.95,
|
| 453 |
-
"eval_loss": 0.392531156539917,
|
| 454 |
-
"eval_runtime": 173.8435,
|
| 455 |
-
"eval_samples_per_second": 17.93,
|
| 456 |
-
"eval_steps_per_second": 2.243,
|
| 457 |
-
"eval_wer": 0.23081281873701442,
|
| 458 |
-
"step": 3000
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 40.26,
|
| 462 |
-
"learning_rate": 9.610013003901171e-05,
|
| 463 |
-
"loss": 0.0331,
|
| 464 |
-
"step": 3100
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 40.26,
|
| 468 |
-
"eval_loss": 0.3893636465072632,
|
| 469 |
-
"eval_runtime": 167.8125,
|
| 470 |
-
"eval_samples_per_second": 18.574,
|
| 471 |
-
"eval_steps_per_second": 2.324,
|
| 472 |
-
"eval_wer": 0.2323868286847573,
|
| 473 |
-
"step": 3100
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 41.55,
|
| 477 |
-
"learning_rate": 9.59700910273082e-05,
|
| 478 |
-
"loss": 0.0339,
|
| 479 |
-
"step": 3200
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 41.55,
|
| 483 |
-
"eval_loss": 0.39426469802856445,
|
| 484 |
-
"eval_runtime": 168.7188,
|
| 485 |
-
"eval_samples_per_second": 18.475,
|
| 486 |
-
"eval_steps_per_second": 2.312,
|
| 487 |
-
"eval_wer": 0.233331234653403,
|
| 488 |
-
"step": 3200
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 42.85,
|
| 492 |
-
"learning_rate": 9.584005201560469e-05,
|
| 493 |
-
"loss": 0.033,
|
| 494 |
-
"step": 3300
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 42.85,
|
| 498 |
-
"eval_loss": 0.3865768313407898,
|
| 499 |
-
"eval_runtime": 161.5781,
|
| 500 |
-
"eval_samples_per_second": 19.291,
|
| 501 |
-
"eval_steps_per_second": 2.414,
|
| 502 |
-
"eval_wer": 0.2350311653969653,
|
| 503 |
-
"step": 3300
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 44.15,
|
| 507 |
-
"learning_rate": 9.571001300390118e-05,
|
| 508 |
-
"loss": 0.0334,
|
| 509 |
-
"step": 3400
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 44.15,
|
| 513 |
-
"eval_loss": 0.38849422335624695,
|
| 514 |
-
"eval_runtime": 166.5778,
|
| 515 |
-
"eval_samples_per_second": 18.712,
|
| 516 |
-
"eval_steps_per_second": 2.341,
|
| 517 |
-
"eval_wer": 0.2320720266952087,
|
| 518 |
-
"step": 3400
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 45.45,
|
| 522 |
-
"learning_rate": 9.557997399219767e-05,
|
| 523 |
-
"loss": 0.0331,
|
| 524 |
-
"step": 3500
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 45.45,
|
| 528 |
-
"eval_loss": 0.41077303886413574,
|
| 529 |
-
"eval_runtime": 165.0937,
|
| 530 |
-
"eval_samples_per_second": 18.88,
|
| 531 |
-
"eval_steps_per_second": 2.362,
|
| 532 |
-
"eval_wer": 0.232009066297299,
|
| 533 |
-
"step": 3500
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 46.75,
|
| 537 |
-
"learning_rate": 9.544993498049415e-05,
|
| 538 |
-
"loss": 0.0326,
|
| 539 |
-
"step": 3600
|
| 540 |
-
},
|
| 541 |
-
{
|
| 542 |
-
"epoch": 46.75,
|
| 543 |
-
"eval_loss": 0.3925323784351349,
|
| 544 |
-
"eval_runtime": 159.9375,
|
| 545 |
-
"eval_samples_per_second": 19.489,
|
| 546 |
-
"eval_steps_per_second": 2.438,
|
| 547 |
-
"eval_wer": 0.2414531259837562,
|
| 548 |
-
"step": 3600
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 48.05,
|
| 552 |
-
"learning_rate": 9.531989596879064e-05,
|
| 553 |
-
"loss": 0.036,
|
| 554 |
-
"step": 3700
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 48.05,
|
| 558 |
-
"eval_loss": 0.3832598030567169,
|
| 559 |
-
"eval_runtime": 171.125,
|
| 560 |
-
"eval_samples_per_second": 18.215,
|
| 561 |
-
"eval_steps_per_second": 2.279,
|
| 562 |
-
"eval_wer": 0.2387458288736385,
|
| 563 |
-
"step": 3700
|
| 564 |
-
},
|
| 565 |
-
{
|
| 566 |
-
"epoch": 49.35,
|
| 567 |
-
"learning_rate": 9.518985695708713e-05,
|
| 568 |
-
"loss": 0.0346,
|
| 569 |
-
"step": 3800
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 49.35,
|
| 573 |
-
"eval_loss": 0.3931749761104584,
|
| 574 |
-
"eval_runtime": 166.4063,
|
| 575 |
-
"eval_samples_per_second": 18.731,
|
| 576 |
-
"eval_steps_per_second": 2.344,
|
| 577 |
-
"eval_wer": 0.23263867027639615,
|
| 578 |
-
"step": 3800
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 50.64,
|
| 582 |
-
"learning_rate": 9.505981794538362e-05,
|
| 583 |
-
"loss": 0.0349,
|
| 584 |
-
"step": 3900
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 50.64,
|
| 588 |
-
"eval_loss": 0.3744593858718872,
|
| 589 |
-
"eval_runtime": 157.9687,
|
| 590 |
-
"eval_samples_per_second": 19.732,
|
| 591 |
-
"eval_steps_per_second": 2.469,
|
| 592 |
-
"eval_wer": 0.2354089277844236,
|
| 593 |
-
"step": 3900
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 51.94,
|
| 597 |
-
"learning_rate": 9.492977893368012e-05,
|
| 598 |
-
"loss": 0.034,
|
| 599 |
-
"step": 4000
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 51.94,
|
| 603 |
-
"eval_loss": 0.39862367510795593,
|
| 604 |
-
"eval_runtime": 155.8749,
|
| 605 |
-
"eval_samples_per_second": 19.997,
|
| 606 |
-
"eval_steps_per_second": 2.502,
|
| 607 |
-
"eval_wer": 0.2328275514701253,
|
| 608 |
-
"step": 4000
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 53.24,
|
| 612 |
-
"learning_rate": 9.479973992197659e-05,
|
| 613 |
-
"loss": 0.0334,
|
| 614 |
-
"step": 4100
|
| 615 |
-
},
|
| 616 |
-
{
|
| 617 |
-
"epoch": 53.24,
|
| 618 |
-
"eval_loss": 0.39466869831085205,
|
| 619 |
-
"eval_runtime": 162.0467,
|
| 620 |
-
"eval_samples_per_second": 19.235,
|
| 621 |
-
"eval_steps_per_second": 2.407,
|
| 622 |
-
"eval_wer": 0.23352011584713214,
|
| 623 |
-
"step": 4100
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 54.54,
|
| 627 |
-
"learning_rate": 9.466970091027308e-05,
|
| 628 |
-
"loss": 0.0325,
|
| 629 |
-
"step": 4200
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 54.54,
|
| 633 |
-
"eval_loss": 0.39441126585006714,
|
| 634 |
-
"eval_runtime": 162.4844,
|
| 635 |
-
"eval_samples_per_second": 19.183,
|
| 636 |
-
"eval_steps_per_second": 2.4,
|
| 637 |
-
"eval_wer": 0.23616445255934018,
|
| 638 |
-
"step": 4200
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 55.84,
|
| 642 |
-
"learning_rate": 9.453966189856957e-05,
|
| 643 |
-
"loss": 0.0308,
|
| 644 |
-
"step": 4300
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 55.84,
|
| 648 |
-
"eval_loss": 0.39918699860572815,
|
| 649 |
-
"eval_runtime": 155.5625,
|
| 650 |
-
"eval_samples_per_second": 20.037,
|
| 651 |
-
"eval_steps_per_second": 2.507,
|
| 652 |
-
"eval_wer": 0.23477932380532646,
|
| 653 |
-
"step": 4300
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 57.14,
|
| 657 |
-
"learning_rate": 9.440962288686607e-05,
|
| 658 |
-
"loss": 0.0316,
|
| 659 |
-
"step": 4400
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 57.14,
|
| 663 |
-
"eval_loss": 0.39010030031204224,
|
| 664 |
-
"eval_runtime": 163.0782,
|
| 665 |
-
"eval_samples_per_second": 19.114,
|
| 666 |
-
"eval_steps_per_second": 2.391,
|
| 667 |
-
"eval_wer": 0.229805452370459,
|
| 668 |
-
"step": 4400
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 58.44,
|
| 672 |
-
"learning_rate": 9.427958387516256e-05,
|
| 673 |
-
"loss": 0.0308,
|
| 674 |
-
"step": 4500
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 58.44,
|
| 678 |
-
"eval_loss": 0.404751718044281,
|
| 679 |
-
"eval_runtime": 161.3906,
|
| 680 |
-
"eval_samples_per_second": 19.313,
|
| 681 |
-
"eval_steps_per_second": 2.416,
|
| 682 |
-
"eval_wer": 0.23194610589938927,
|
| 683 |
-
"step": 4500
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 59.73,
|
| 687 |
-
"learning_rate": 9.414954486345903e-05,
|
| 688 |
-
"loss": 0.028,
|
| 689 |
-
"step": 4600
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 59.73,
|
| 693 |
-
"eval_loss": 0.41103655099868774,
|
| 694 |
-
"eval_runtime": 154.3905,
|
| 695 |
-
"eval_samples_per_second": 20.189,
|
| 696 |
-
"eval_steps_per_second": 2.526,
|
| 697 |
-
"eval_wer": 0.2277277592394384,
|
| 698 |
-
"step": 4600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 61.04,
|
| 702 |
-
"learning_rate": 9.401950585175553e-05,
|
| 703 |
-
"loss": 0.0299,
|
| 704 |
-
"step": 4700
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 61.04,
|
| 708 |
-
"eval_loss": 0.40084338188171387,
|
| 709 |
-
"eval_runtime": 168.5468,
|
| 710 |
-
"eval_samples_per_second": 18.493,
|
| 711 |
-
"eval_steps_per_second": 2.314,
|
| 712 |
-
"eval_wer": 0.23295347226594473,
|
| 713 |
-
"step": 4700
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 62.33,
|
| 717 |
-
"learning_rate": 9.388946684005202e-05,
|
| 718 |
-
"loss": 0.033,
|
| 719 |
-
"step": 4800
|
| 720 |
-
},
|
| 721 |
-
{
|
| 722 |
-
"epoch": 62.33,
|
| 723 |
-
"eval_loss": 0.3985605835914612,
|
| 724 |
-
"eval_runtime": 168.5159,
|
| 725 |
-
"eval_samples_per_second": 18.497,
|
| 726 |
-
"eval_steps_per_second": 2.314,
|
| 727 |
-
"eval_wer": 0.23490524460114587,
|
| 728 |
-
"step": 4800
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 63.63,
|
| 732 |
-
"learning_rate": 9.375942782834851e-05,
|
| 733 |
-
"loss": 0.0345,
|
| 734 |
-
"step": 4900
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 63.63,
|
| 738 |
-
"eval_loss": 0.3911936581134796,
|
| 739 |
-
"eval_runtime": 158.9531,
|
| 740 |
-
"eval_samples_per_second": 19.61,
|
| 741 |
-
"eval_steps_per_second": 2.454,
|
| 742 |
-
"eval_wer": 0.23559780897815275,
|
| 743 |
-
"step": 4900
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 64.93,
|
| 747 |
-
"learning_rate": 9.3629388816645e-05,
|
| 748 |
-
"loss": 0.0322,
|
| 749 |
-
"step": 5000
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 64.93,
|
| 753 |
-
"eval_loss": 0.3985706567764282,
|
| 754 |
-
"eval_runtime": 175.1875,
|
| 755 |
-
"eval_samples_per_second": 17.792,
|
| 756 |
-
"eval_steps_per_second": 2.226,
|
| 757 |
-
"eval_wer": 0.231568343511931,
|
| 758 |
-
"step": 5000
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 66.23,
|
| 762 |
-
"learning_rate": 9.349934980494148e-05,
|
| 763 |
-
"loss": 0.0313,
|
| 764 |
-
"step": 5100
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 66.23,
|
| 768 |
-
"eval_loss": 0.4163081645965576,
|
| 769 |
-
"eval_runtime": 179.4796,
|
| 770 |
-
"eval_samples_per_second": 17.367,
|
| 771 |
-
"eval_steps_per_second": 2.173,
|
| 772 |
-
"eval_wer": 0.23049801674746584,
|
| 773 |
-
"step": 5100
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 67.53,
|
| 777 |
-
"learning_rate": 9.336931079323797e-05,
|
| 778 |
-
"loss": 0.0315,
|
| 779 |
-
"step": 5200
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 67.53,
|
| 783 |
-
"eval_loss": 0.3985958993434906,
|
| 784 |
-
"eval_runtime": 170.0289,
|
| 785 |
-
"eval_samples_per_second": 18.332,
|
| 786 |
-
"eval_steps_per_second": 2.294,
|
| 787 |
-
"eval_wer": 0.23528300698860416,
|
| 788 |
-
"step": 5200
|
| 789 |
-
},
|
| 790 |
-
{
|
| 791 |
-
"epoch": 68.82,
|
| 792 |
-
"learning_rate": 9.323927178153446e-05,
|
| 793 |
-
"loss": 0.0294,
|
| 794 |
-
"step": 5300
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 68.82,
|
| 798 |
-
"eval_loss": 0.40526434779167175,
|
| 799 |
-
"eval_runtime": 177.9803,
|
| 800 |
-
"eval_samples_per_second": 17.513,
|
| 801 |
-
"eval_steps_per_second": 2.191,
|
| 802 |
-
"eval_wer": 0.2295536107788201,
|
| 803 |
-
"step": 5300
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 70.13,
|
| 807 |
-
"learning_rate": 9.310923276983095e-05,
|
| 808 |
-
"loss": 0.0302,
|
| 809 |
-
"step": 5400
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 70.13,
|
| 813 |
-
"eval_loss": 0.3818342089653015,
|
| 814 |
-
"eval_runtime": 177.545,
|
| 815 |
-
"eval_samples_per_second": 17.556,
|
| 816 |
-
"eval_steps_per_second": 2.197,
|
| 817 |
-
"eval_wer": 0.23131650192029213,
|
| 818 |
-
"step": 5400
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 71.42,
|
| 822 |
-
"learning_rate": 9.297919375812744e-05,
|
| 823 |
-
"loss": 0.0318,
|
| 824 |
-
"step": 5500
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 71.42,
|
| 828 |
-
"eval_loss": 0.3933159410953522,
|
| 829 |
-
"eval_runtime": 168.7969,
|
| 830 |
-
"eval_samples_per_second": 18.466,
|
| 831 |
-
"eval_steps_per_second": 2.31,
|
| 832 |
-
"eval_wer": 0.23301643266385444,
|
| 833 |
-
"step": 5500
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 72.72,
|
| 837 |
-
"learning_rate": 9.284915474642393e-05,
|
| 838 |
-
"loss": 0.0289,
|
| 839 |
-
"step": 5600
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 72.72,
|
| 843 |
-
"eval_loss": 0.38790163397789,
|
| 844 |
-
"eval_runtime": 167.7031,
|
| 845 |
-
"eval_samples_per_second": 18.586,
|
| 846 |
-
"eval_steps_per_second": 2.326,
|
| 847 |
-
"eval_wer": 0.23396083863250017,
|
| 848 |
-
"step": 5600
|
| 849 |
}
|
| 850 |
],
|
| 851 |
-
"max_steps":
|
| 852 |
"num_train_epochs": 1000,
|
| 853 |
-
"total_flos": 1.
|
| 854 |
"trial_name": null,
|
| 855 |
"trial_params": null
|
| 856 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.407407407407407,
|
| 5 |
+
"global_step": 600,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 1.23,
|
| 12 |
"learning_rate": 0.0001,
|
| 13 |
+
"loss": 0.0625,
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 1.23,
|
| 18 |
+
"eval_loss": 0.28051668405532837,
|
| 19 |
+
"eval_runtime": 198.6071,
|
| 20 |
+
"eval_samples_per_second": 16.374,
|
| 21 |
+
"eval_steps_per_second": 2.049,
|
| 22 |
+
"eval_wer": 0.2381097005406062,
|
| 23 |
"step": 100
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 2.47,
|
| 27 |
+
"learning_rate": 9.987639060568604e-05,
|
| 28 |
+
"loss": 0.047,
|
| 29 |
"step": 200
|
| 30 |
},
|
| 31 |
{
|
| 32 |
+
"epoch": 2.47,
|
| 33 |
+
"eval_loss": 0.34423157572746277,
|
| 34 |
+
"eval_runtime": 147.7154,
|
| 35 |
+
"eval_samples_per_second": 22.015,
|
| 36 |
+
"eval_steps_per_second": 2.755,
|
| 37 |
+
"eval_wer": 0.2334325457085586,
|
| 38 |
"step": 200
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 3.7,
|
| 42 |
+
"learning_rate": 9.975278121137207e-05,
|
| 43 |
+
"loss": 0.0409,
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 3.7,
|
| 48 |
+
"eval_loss": 0.3597787916660309,
|
| 49 |
+
"eval_runtime": 156.092,
|
| 50 |
+
"eval_samples_per_second": 20.834,
|
| 51 |
+
"eval_steps_per_second": 2.607,
|
| 52 |
+
"eval_wer": 0.23124582396889995,
|
| 53 |
"step": 300
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 4.94,
|
| 57 |
+
"learning_rate": 9.96291718170581e-05,
|
| 58 |
+
"loss": 0.0413,
|
| 59 |
"step": 400
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 4.94,
|
| 63 |
+
"eval_loss": 0.35860675573349,
|
| 64 |
+
"eval_runtime": 151.5312,
|
| 65 |
+
"eval_samples_per_second": 21.461,
|
| 66 |
+
"eval_steps_per_second": 2.686,
|
| 67 |
+
"eval_wer": 0.2421794326671931,
|
| 68 |
"step": 400
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 6.17,
|
| 72 |
+
"learning_rate": 9.950556242274414e-05,
|
| 73 |
+
"loss": 0.0388,
|
| 74 |
"step": 500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 6.17,
|
| 78 |
+
"eval_loss": 0.3748931586742401,
|
| 79 |
+
"eval_runtime": 154.1563,
|
| 80 |
+
"eval_samples_per_second": 21.095,
|
| 81 |
+
"eval_steps_per_second": 2.64,
|
| 82 |
+
"eval_wer": 0.23914231913988945,
|
| 83 |
"step": 500
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 7.41,
|
| 87 |
+
"learning_rate": 9.938195302843017e-05,
|
| 88 |
+
"loss": 0.0383,
|
| 89 |
"step": 600
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 7.41,
|
| 93 |
+
"eval_loss": 0.36109668016433716,
|
| 94 |
+
"eval_runtime": 163.2656,
|
| 95 |
+
"eval_samples_per_second": 19.918,
|
| 96 |
+
"eval_steps_per_second": 2.493,
|
| 97 |
+
"eval_wer": 0.2352548138249408,
|
| 98 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
}
|
| 100 |
],
|
| 101 |
+
"max_steps": 81000,
|
| 102 |
"num_train_epochs": 1000,
|
| 103 |
+
"total_flos": 1.9144703855961313e+19,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
| 106 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3323
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8601095f38d32bef09015c26566a62538d0cc825cfc7a586ccc7a2a2a4d0a2e
|
| 3 |
size 3323
|