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 +24 -864
- 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 sha256:49165c4ebf699f646d1ee8dd29b4f653a39fed3e54794548e77985e4ee0be462
|
| 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 sha256:680b1c63ef60208d52375170b4bca21c48bf4e869fba3d92686679e814810c15
|
| 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 14639
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35a38b2fb8837dad93900200eb443f5a115ca4b6d25b71a4f159eee52f1211c6
|
| 3 |
size 14639
|
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:efafd90182e3d39d1b7c4a686f86e5913f5abc094dc3e2f827a6d479c6cef247
|
| 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 sha256:1c76c6a7e6c643ec04de43f5e4cf627377d8989a6ae9dc6ff8a7d93215077cc3
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,901 +1,61 @@
|
|
| 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": 0.85,
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.85,
|
| 18 |
-
"eval_loss": 0.
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second": 15.
|
| 21 |
-
"eval_steps_per_second": 1.
|
| 22 |
-
"eval_wer": 0.
|
| 23 |
"step": 100
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.69,
|
| 27 |
-
"learning_rate":
|
| 28 |
-
"loss": 0.
|
| 29 |
"step": 200
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 1.69,
|
| 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": 2.54,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 2.54,
|
| 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": 3.39,
|
| 57 |
-
"learning_rate": 0.00029923664122137405,
|
| 58 |
-
"loss": 0.0968,
|
| 59 |
-
"step": 400
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 3.39,
|
| 63 |
-
"eval_loss": 0.34380972385406494,
|
| 64 |
-
"eval_runtime": 153.4688,
|
| 65 |
-
"eval_samples_per_second": 21.965,
|
| 66 |
-
"eval_steps_per_second": 2.75,
|
| 67 |
-
"eval_wer": 0.2737222028175573,
|
| 68 |
-
"step": 400
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 4.24,
|
| 72 |
-
"learning_rate": 0.00029898218829516537,
|
| 73 |
-
"loss": 0.0977,
|
| 74 |
-
"step": 500
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 4.24,
|
| 78 |
-
"eval_loss": 0.36153408885002136,
|
| 79 |
-
"eval_runtime": 166.8287,
|
| 80 |
-
"eval_samples_per_second": 20.206,
|
| 81 |
-
"eval_steps_per_second": 2.53,
|
| 82 |
-
"eval_wer": 0.2702875771335429,
|
| 83 |
-
"step": 500
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 5.08,
|
| 87 |
-
"learning_rate": 0.00029872773536895674,
|
| 88 |
-
"loss": 0.0916,
|
| 89 |
-
"step": 600
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 5.08,
|
| 93 |
-
"eval_loss": 0.3286847770214081,
|
| 94 |
-
"eval_runtime": 171.9341,
|
| 95 |
-
"eval_samples_per_second": 19.606,
|
| 96 |
-
"eval_steps_per_second": 2.454,
|
| 97 |
-
"eval_wer": 0.2669693794388171,
|
| 98 |
-
"step": 600
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 5.93,
|
| 102 |
-
"learning_rate": 0.00029847328244274806,
|
| 103 |
-
"loss": 0.0943,
|
| 104 |
-
"step": 700
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 5.93,
|
| 108 |
-
"eval_loss": 0.3330075442790985,
|
| 109 |
-
"eval_runtime": 152.0172,
|
| 110 |
-
"eval_samples_per_second": 22.175,
|
| 111 |
-
"eval_steps_per_second": 2.776,
|
| 112 |
-
"eval_wer": 0.2651647456048434,
|
| 113 |
-
"step": 700
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 6.78,
|
| 117 |
-
"learning_rate": 0.0002982213740458015,
|
| 118 |
-
"loss": 0.0959,
|
| 119 |
-
"step": 800
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 6.78,
|
| 123 |
-
"eval_loss": 0.3155308663845062,
|
| 124 |
-
"eval_runtime": 176.3551,
|
| 125 |
-
"eval_samples_per_second": 19.115,
|
| 126 |
-
"eval_steps_per_second": 2.393,
|
| 127 |
-
"eval_wer": 0.2723250669460938,
|
| 128 |
-
"step": 800
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 7.63,
|
| 132 |
-
"learning_rate": 0.00029796692111959286,
|
| 133 |
-
"loss": 0.0953,
|
| 134 |
-
"step": 900
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 7.63,
|
| 138 |
-
"eval_loss": 0.3184454143047333,
|
| 139 |
-
"eval_runtime": 179.411,
|
| 140 |
-
"eval_samples_per_second": 18.789,
|
| 141 |
-
"eval_steps_per_second": 2.352,
|
| 142 |
-
"eval_wer": 0.25940156013505644,
|
| 143 |
-
"step": 900
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 8.47,
|
| 147 |
-
"learning_rate": 0.0002977124681933842,
|
| 148 |
-
"loss": 0.0989,
|
| 149 |
-
"step": 1000
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 8.47,
|
| 153 |
-
"eval_loss": 0.3282919228076935,
|
| 154 |
-
"eval_runtime": 177.9041,
|
| 155 |
-
"eval_samples_per_second": 18.948,
|
| 156 |
-
"eval_steps_per_second": 2.372,
|
| 157 |
-
"eval_wer": 0.28070788217487486,
|
| 158 |
-
"step": 1000
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 9.32,
|
| 162 |
-
"learning_rate": 0.00029745801526717556,
|
| 163 |
-
"loss": 0.0962,
|
| 164 |
-
"step": 1100
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 9.32,
|
| 168 |
-
"eval_loss": 0.3113383948802948,
|
| 169 |
-
"eval_runtime": 183.182,
|
| 170 |
-
"eval_samples_per_second": 18.402,
|
| 171 |
-
"eval_steps_per_second": 2.304,
|
| 172 |
-
"eval_wer": 0.2656886715566422,
|
| 173 |
-
"step": 1100
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 10.17,
|
| 177 |
-
"learning_rate": 0.0002972035623409669,
|
| 178 |
-
"loss": 0.0911,
|
| 179 |
-
"step": 1200
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 10.17,
|
| 183 |
-
"eval_loss": 0.31265875697135925,
|
| 184 |
-
"eval_runtime": 178.4394,
|
| 185 |
-
"eval_samples_per_second": 18.892,
|
| 186 |
-
"eval_steps_per_second": 2.365,
|
| 187 |
-
"eval_wer": 0.2594597741297008,
|
| 188 |
-
"step": 1200
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 11.02,
|
| 192 |
-
"learning_rate": 0.00029694910941475825,
|
| 193 |
-
"loss": 0.093,
|
| 194 |
-
"step": 1300
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 11.02,
|
| 198 |
-
"eval_loss": 0.33750081062316895,
|
| 199 |
-
"eval_runtime": 185.9856,
|
| 200 |
-
"eval_samples_per_second": 18.125,
|
| 201 |
-
"eval_steps_per_second": 2.269,
|
| 202 |
-
"eval_wer": 0.2635347537548027,
|
| 203 |
-
"step": 1300
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 11.86,
|
| 207 |
-
"learning_rate": 0.0002966946564885496,
|
| 208 |
-
"loss": 0.0908,
|
| 209 |
-
"step": 1400
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 11.86,
|
| 213 |
-
"eval_loss": 0.31224948167800903,
|
| 214 |
-
"eval_runtime": 182.1874,
|
| 215 |
-
"eval_samples_per_second": 18.503,
|
| 216 |
-
"eval_steps_per_second": 2.316,
|
| 217 |
-
"eval_wer": 0.2616136919315403,
|
| 218 |
-
"step": 1400
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 12.71,
|
| 222 |
-
"learning_rate": 0.00029644020356234095,
|
| 223 |
-
"loss": 0.1039,
|
| 224 |
-
"step": 1500
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 12.71,
|
| 228 |
-
"eval_loss": 0.33441564440727234,
|
| 229 |
-
"eval_runtime": 187.7233,
|
| 230 |
-
"eval_samples_per_second": 17.957,
|
| 231 |
-
"eval_steps_per_second": 2.248,
|
| 232 |
-
"eval_wer": 0.2726161369193154,
|
| 233 |
-
"step": 1500
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 13.56,
|
| 237 |
-
"learning_rate": 0.00029618575063613227,
|
| 238 |
-
"loss": 0.0921,
|
| 239 |
-
"step": 1600
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 13.56,
|
| 243 |
-
"eval_loss": 0.3115340769290924,
|
| 244 |
-
"eval_runtime": 189.6708,
|
| 245 |
-
"eval_samples_per_second": 17.773,
|
| 246 |
-
"eval_steps_per_second": 2.225,
|
| 247 |
-
"eval_wer": 0.26859937128885786,
|
| 248 |
-
"step": 1600
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 14.41,
|
| 252 |
-
"learning_rate": 0.00029593129770992364,
|
| 253 |
-
"loss": 0.0995,
|
| 254 |
-
"step": 1700
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 14.41,
|
| 258 |
-
"eval_loss": 0.3103960156440735,
|
| 259 |
-
"eval_runtime": 183.1481,
|
| 260 |
-
"eval_samples_per_second": 18.406,
|
| 261 |
-
"eval_steps_per_second": 2.304,
|
| 262 |
-
"eval_wer": 0.2650483176155548,
|
| 263 |
-
"step": 1700
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 15.25,
|
| 267 |
-
"learning_rate": 0.00029567684478371497,
|
| 268 |
-
"loss": 0.1027,
|
| 269 |
-
"step": 1800
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 15.25,
|
| 273 |
-
"eval_loss": 0.33657944202423096,
|
| 274 |
-
"eval_runtime": 185.2922,
|
| 275 |
-
"eval_samples_per_second": 18.193,
|
| 276 |
-
"eval_steps_per_second": 2.277,
|
| 277 |
-
"eval_wer": 0.28891605541972293,
|
| 278 |
-
"step": 1800
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 16.1,
|
| 282 |
-
"learning_rate": 0.00029542239185750634,
|
| 283 |
-
"loss": 0.1001,
|
| 284 |
-
"step": 1900
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 16.1,
|
| 288 |
-
"eval_loss": 0.32664933800697327,
|
| 289 |
-
"eval_runtime": 182.6597,
|
| 290 |
-
"eval_samples_per_second": 18.455,
|
| 291 |
-
"eval_steps_per_second": 2.31,
|
| 292 |
-
"eval_wer": 0.2692979392245896,
|
| 293 |
-
"step": 1900
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 16.95,
|
| 297 |
-
"learning_rate": 0.0002951679389312977,
|
| 298 |
-
"loss": 0.0955,
|
| 299 |
-
"step": 2000
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 16.95,
|
| 303 |
-
"eval_loss": 0.32146599888801575,
|
| 304 |
-
"eval_runtime": 175.25,
|
| 305 |
-
"eval_samples_per_second": 19.235,
|
| 306 |
-
"eval_steps_per_second": 2.408,
|
| 307 |
-
"eval_wer": 0.25986727209221094,
|
| 308 |
-
"step": 2000
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 17.8,
|
| 312 |
-
"learning_rate": 0.00029491348600508904,
|
| 313 |
-
"loss": 0.0872,
|
| 314 |
-
"step": 2100
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 17.8,
|
| 318 |
-
"eval_loss": 0.31995928287506104,
|
| 319 |
-
"eval_runtime": 168.2812,
|
| 320 |
-
"eval_samples_per_second": 20.032,
|
| 321 |
-
"eval_steps_per_second": 2.508,
|
| 322 |
-
"eval_wer": 0.2623704738619164,
|
| 323 |
-
"step": 2100
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 18.64,
|
| 327 |
-
"learning_rate": 0.0002946590330788804,
|
| 328 |
-
"loss": 0.0919,
|
| 329 |
-
"step": 2200
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 18.64,
|
| 333 |
-
"eval_loss": 0.3285907208919525,
|
| 334 |
-
"eval_runtime": 176.4154,
|
| 335 |
-
"eval_samples_per_second": 19.108,
|
| 336 |
-
"eval_steps_per_second": 2.392,
|
| 337 |
-
"eval_wer": 0.26405867970660146,
|
| 338 |
-
"step": 2200
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 19.49,
|
| 342 |
-
"learning_rate": 0.00029440458015267173,
|
| 343 |
-
"loss": 0.0953,
|
| 344 |
-
"step": 2300
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 19.49,
|
| 348 |
-
"eval_loss": 0.35332390666007996,
|
| 349 |
-
"eval_runtime": 173.8594,
|
| 350 |
-
"eval_samples_per_second": 19.389,
|
| 351 |
-
"eval_steps_per_second": 2.427,
|
| 352 |
-
"eval_wer": 0.2674350913959716,
|
| 353 |
-
"step": 2300
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 20.34,
|
| 357 |
-
"learning_rate": 0.0002941501272264631,
|
| 358 |
-
"loss": 0.0923,
|
| 359 |
-
"step": 2400
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 20.34,
|
| 363 |
-
"eval_loss": 0.30950167775154114,
|
| 364 |
-
"eval_runtime": 173.4531,
|
| 365 |
-
"eval_samples_per_second": 19.435,
|
| 366 |
-
"eval_steps_per_second": 2.433,
|
| 367 |
-
"eval_wer": 0.2600419140761439,
|
| 368 |
-
"step": 2400
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 21.19,
|
| 372 |
-
"learning_rate": 0.00029389567430025443,
|
| 373 |
-
"loss": 0.0961,
|
| 374 |
-
"step": 2500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 21.19,
|
| 378 |
-
"eval_loss": 0.3377102315425873,
|
| 379 |
-
"eval_runtime": 183.4219,
|
| 380 |
-
"eval_samples_per_second": 18.378,
|
| 381 |
-
"eval_steps_per_second": 2.301,
|
| 382 |
-
"eval_wer": 0.255210152520666,
|
| 383 |
-
"step": 2500
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 22.03,
|
| 387 |
-
"learning_rate": 0.00029364122137404575,
|
| 388 |
-
"loss": 0.0919,
|
| 389 |
-
"step": 2600
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 22.03,
|
| 393 |
-
"eval_loss": 0.3226545751094818,
|
| 394 |
-
"eval_runtime": 183.0312,
|
| 395 |
-
"eval_samples_per_second": 18.418,
|
| 396 |
-
"eval_steps_per_second": 2.306,
|
| 397 |
-
"eval_wer": 0.2614390499476074,
|
| 398 |
-
"step": 2600
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 22.88,
|
| 402 |
-
"learning_rate": 0.00029338676844783713,
|
| 403 |
-
"loss": 0.0859,
|
| 404 |
-
"step": 2700
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 22.88,
|
| 408 |
-
"eval_loss": 0.30848973989486694,
|
| 409 |
-
"eval_runtime": 176.2969,
|
| 410 |
-
"eval_samples_per_second": 19.121,
|
| 411 |
-
"eval_steps_per_second": 2.394,
|
| 412 |
-
"eval_wer": 0.25416230061706835,
|
| 413 |
-
"step": 2700
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 23.73,
|
| 417 |
-
"learning_rate": 0.00029313231552162845,
|
| 418 |
-
"loss": 0.0915,
|
| 419 |
-
"step": 2800
|
| 420 |
-
},
|
| 421 |
-
{
|
| 422 |
-
"epoch": 23.73,
|
| 423 |
-
"eval_loss": 0.3403824269771576,
|
| 424 |
-
"eval_runtime": 172.6719,
|
| 425 |
-
"eval_samples_per_second": 19.523,
|
| 426 |
-
"eval_steps_per_second": 2.444,
|
| 427 |
-
"eval_wer": 0.2610315519850972,
|
| 428 |
-
"step": 2800
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 24.58,
|
| 432 |
-
"learning_rate": 0.00029288040712468187,
|
| 433 |
-
"loss": 0.0917,
|
| 434 |
-
"step": 2900
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 24.58,
|
| 438 |
-
"eval_loss": 0.2996799647808075,
|
| 439 |
-
"eval_runtime": 178.4531,
|
| 440 |
-
"eval_samples_per_second": 18.89,
|
| 441 |
-
"eval_steps_per_second": 2.365,
|
| 442 |
-
"eval_wer": 0.2529980207241821,
|
| 443 |
-
"step": 2900
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 25.42,
|
| 447 |
-
"learning_rate": 0.00029262595419847324,
|
| 448 |
-
"loss": 0.0967,
|
| 449 |
-
"step": 3000
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 25.42,
|
| 453 |
-
"eval_loss": 0.3144609332084656,
|
| 454 |
-
"eval_runtime": 177.4531,
|
| 455 |
-
"eval_samples_per_second": 18.997,
|
| 456 |
-
"eval_steps_per_second": 2.378,
|
| 457 |
-
"eval_wer": 0.25555943648853185,
|
| 458 |
-
"step": 3000
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 26.27,
|
| 462 |
-
"learning_rate": 0.0002923715012722646,
|
| 463 |
-
"loss": 0.0973,
|
| 464 |
-
"step": 3100
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 26.27,
|
| 468 |
-
"eval_loss": 0.3294685482978821,
|
| 469 |
-
"eval_runtime": 178.7969,
|
| 470 |
-
"eval_samples_per_second": 18.854,
|
| 471 |
-
"eval_steps_per_second": 2.36,
|
| 472 |
-
"eval_wer": 0.25940156013505644,
|
| 473 |
-
"step": 3100
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 27.12,
|
| 477 |
-
"learning_rate": 0.00029211704834605594,
|
| 478 |
-
"loss": 0.0932,
|
| 479 |
-
"step": 3200
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 27.12,
|
| 483 |
-
"eval_loss": 0.3125886023044586,
|
| 484 |
-
"eval_runtime": 168.7969,
|
| 485 |
-
"eval_samples_per_second": 19.971,
|
| 486 |
-
"eval_steps_per_second": 2.5,
|
| 487 |
-
"eval_wer": 0.25684014437070674,
|
| 488 |
-
"step": 3200
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 27.97,
|
| 492 |
-
"learning_rate": 0.0002918625954198473,
|
| 493 |
-
"loss": 0.0945,
|
| 494 |
-
"step": 3300
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 27.97,
|
| 498 |
-
"eval_loss": 0.3468785583972931,
|
| 499 |
-
"eval_runtime": 179.6094,
|
| 500 |
-
"eval_samples_per_second": 18.769,
|
| 501 |
-
"eval_steps_per_second": 2.35,
|
| 502 |
-
"eval_wer": 0.2523576667830947,
|
| 503 |
-
"step": 3300
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 28.81,
|
| 507 |
-
"learning_rate": 0.00029160814249363864,
|
| 508 |
-
"loss": 0.0852,
|
| 509 |
-
"step": 3400
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 28.81,
|
| 513 |
-
"eval_loss": 0.31798404455184937,
|
| 514 |
-
"eval_runtime": 173.2031,
|
| 515 |
-
"eval_samples_per_second": 19.463,
|
| 516 |
-
"eval_steps_per_second": 2.436,
|
| 517 |
-
"eval_wer": 0.254104086622424,
|
| 518 |
-
"step": 3400
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 29.66,
|
| 522 |
-
"learning_rate": 0.00029135368956743,
|
| 523 |
-
"loss": 0.0866,
|
| 524 |
-
"step": 3500
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 29.66,
|
| 528 |
-
"eval_loss": 0.31360727548599243,
|
| 529 |
-
"eval_runtime": 167.4063,
|
| 530 |
-
"eval_samples_per_second": 20.137,
|
| 531 |
-
"eval_steps_per_second": 2.521,
|
| 532 |
-
"eval_wer": 0.255210152520666,
|
| 533 |
-
"step": 3500
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"epoch": 30.51,
|
| 537 |
-
"learning_rate": 0.00029109923664122133,
|
| 538 |
-
"loss": 0.0844,
|
| 539 |
-
"step": 3600
|
| 540 |
-
},
|
| 541 |
-
{
|
| 542 |
-
"epoch": 30.51,
|
| 543 |
-
"eval_loss": 0.33361586928367615,
|
| 544 |
-
"eval_runtime": 166.3125,
|
| 545 |
-
"eval_samples_per_second": 20.269,
|
| 546 |
-
"eval_steps_per_second": 2.537,
|
| 547 |
-
"eval_wer": 0.2660379555245081,
|
| 548 |
-
"step": 3600
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 31.36,
|
| 552 |
-
"learning_rate": 0.0002908447837150127,
|
| 553 |
-
"loss": 0.0847,
|
| 554 |
-
"step": 3700
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 31.36,
|
| 558 |
-
"eval_loss": 0.31821873784065247,
|
| 559 |
-
"eval_runtime": 178.8437,
|
| 560 |
-
"eval_samples_per_second": 18.849,
|
| 561 |
-
"eval_steps_per_second": 2.36,
|
| 562 |
-
"eval_wer": 0.2507858889276982,
|
| 563 |
-
"step": 3700
|
| 564 |
-
},
|
| 565 |
-
{
|
| 566 |
-
"epoch": 32.2,
|
| 567 |
-
"learning_rate": 0.0002905903307888041,
|
| 568 |
-
"loss": 0.0885,
|
| 569 |
-
"step": 3800
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 32.2,
|
| 573 |
-
"eval_loss": 0.32577720284461975,
|
| 574 |
-
"eval_runtime": 175.0625,
|
| 575 |
-
"eval_samples_per_second": 19.256,
|
| 576 |
-
"eval_steps_per_second": 2.411,
|
| 577 |
-
"eval_wer": 0.2674933053906159,
|
| 578 |
-
"step": 3800
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 33.05,
|
| 582 |
-
"learning_rate": 0.0002903358778625954,
|
| 583 |
-
"loss": 0.0855,
|
| 584 |
-
"step": 3900
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 33.05,
|
| 588 |
-
"eval_loss": 0.31836631894111633,
|
| 589 |
-
"eval_runtime": 169.0469,
|
| 590 |
-
"eval_samples_per_second": 19.941,
|
| 591 |
-
"eval_steps_per_second": 2.496,
|
| 592 |
-
"eval_wer": 0.25375480265455813,
|
| 593 |
-
"step": 3900
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 33.9,
|
| 597 |
-
"learning_rate": 0.0002900814249363867,
|
| 598 |
-
"loss": 0.0813,
|
| 599 |
-
"step": 4000
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 33.9,
|
| 603 |
-
"eval_loss": 0.30345430970191956,
|
| 604 |
-
"eval_runtime": 175.0938,
|
| 605 |
-
"eval_samples_per_second": 19.253,
|
| 606 |
-
"eval_steps_per_second": 2.41,
|
| 607 |
-
"eval_wer": 0.2506112469437653,
|
| 608 |
-
"step": 4000
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 34.74,
|
| 612 |
-
"learning_rate": 0.0002898269720101781,
|
| 613 |
-
"loss": 0.0822,
|
| 614 |
-
"step": 4100
|
| 615 |
-
},
|
| 616 |
-
{
|
| 617 |
-
"epoch": 34.74,
|
| 618 |
-
"eval_loss": 0.3159136176109314,
|
| 619 |
-
"eval_runtime": 174.1406,
|
| 620 |
-
"eval_samples_per_second": 19.358,
|
| 621 |
-
"eval_steps_per_second": 2.423,
|
| 622 |
-
"eval_wer": 0.2572476423332169,
|
| 623 |
-
"step": 4100
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 35.59,
|
| 627 |
-
"learning_rate": 0.0002895725190839694,
|
| 628 |
-
"loss": 0.0849,
|
| 629 |
-
"step": 4200
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 35.59,
|
| 633 |
-
"eval_loss": 0.2940651774406433,
|
| 634 |
-
"eval_runtime": 173.233,
|
| 635 |
-
"eval_samples_per_second": 19.459,
|
| 636 |
-
"eval_steps_per_second": 2.436,
|
| 637 |
-
"eval_wer": 0.2512516008848527,
|
| 638 |
-
"step": 4200
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 36.44,
|
| 642 |
-
"learning_rate": 0.0002893180661577608,
|
| 643 |
-
"loss": 0.0885,
|
| 644 |
-
"step": 4300
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 36.44,
|
| 648 |
-
"eval_loss": 0.32734107971191406,
|
| 649 |
-
"eval_runtime": 193.9206,
|
| 650 |
-
"eval_samples_per_second": 17.383,
|
| 651 |
-
"eval_steps_per_second": 2.176,
|
| 652 |
-
"eval_wer": 0.26423332169053443,
|
| 653 |
-
"step": 4300
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 37.29,
|
| 657 |
-
"learning_rate": 0.0002890636132315521,
|
| 658 |
-
"loss": 0.0866,
|
| 659 |
-
"step": 4400
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 37.29,
|
| 663 |
-
"eval_loss": 0.33303678035736084,
|
| 664 |
-
"eval_runtime": 197.0429,
|
| 665 |
-
"eval_samples_per_second": 17.108,
|
| 666 |
-
"eval_steps_per_second": 2.142,
|
| 667 |
-
"eval_wer": 0.255966934451042,
|
| 668 |
-
"step": 4400
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 38.14,
|
| 672 |
-
"learning_rate": 0.0002888091603053435,
|
| 673 |
-
"loss": 0.0841,
|
| 674 |
-
"step": 4500
|
| 675 |
-
},
|
| 676 |
-
{
|
| 677 |
-
"epoch": 38.14,
|
| 678 |
-
"eval_loss": 0.32818496227264404,
|
| 679 |
-
"eval_runtime": 192.3874,
|
| 680 |
-
"eval_samples_per_second": 17.522,
|
| 681 |
-
"eval_steps_per_second": 2.193,
|
| 682 |
-
"eval_wer": 0.24997089300267786,
|
| 683 |
-
"step": 4500
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 38.98,
|
| 687 |
-
"learning_rate": 0.0002885547073791348,
|
| 688 |
-
"loss": 0.0848,
|
| 689 |
-
"step": 4600
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 38.98,
|
| 693 |
-
"eval_loss": 0.32277733087539673,
|
| 694 |
-
"eval_runtime": 188.7845,
|
| 695 |
-
"eval_samples_per_second": 17.856,
|
| 696 |
-
"eval_steps_per_second": 2.235,
|
| 697 |
-
"eval_wer": 0.2605658400279427,
|
| 698 |
-
"step": 4600
|
| 699 |
-
},
|
| 700 |
-
{
|
| 701 |
-
"epoch": 39.83,
|
| 702 |
-
"learning_rate": 0.0002883002544529262,
|
| 703 |
-
"loss": 0.0752,
|
| 704 |
-
"step": 4700
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 39.83,
|
| 708 |
-
"eval_loss": 0.3181003928184509,
|
| 709 |
-
"eval_runtime": 190.576,
|
| 710 |
-
"eval_samples_per_second": 17.688,
|
| 711 |
-
"eval_steps_per_second": 2.214,
|
| 712 |
-
"eval_wer": 0.2516008848527186,
|
| 713 |
-
"step": 4700
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 40.68,
|
| 717 |
-
"learning_rate": 0.0002880458015267175,
|
| 718 |
-
"loss": 0.0827,
|
| 719 |
-
"step": 4800
|
| 720 |
-
},
|
| 721 |
-
{
|
| 722 |
-
"epoch": 40.68,
|
| 723 |
-
"eval_loss": 0.3244548439979553,
|
| 724 |
-
"eval_runtime": 196.2976,
|
| 725 |
-
"eval_samples_per_second": 17.173,
|
| 726 |
-
"eval_steps_per_second": 2.15,
|
| 727 |
-
"eval_wer": 0.2487483991151473,
|
| 728 |
-
"step": 4800
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 41.52,
|
| 732 |
-
"learning_rate": 0.0002877913486005089,
|
| 733 |
-
"loss": 0.0765,
|
| 734 |
-
"step": 4900
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 41.52,
|
| 738 |
-
"eval_loss": 0.31394141912460327,
|
| 739 |
-
"eval_runtime": 194.1554,
|
| 740 |
-
"eval_samples_per_second": 17.362,
|
| 741 |
-
"eval_steps_per_second": 2.174,
|
| 742 |
-
"eval_wer": 0.24508091745255559,
|
| 743 |
-
"step": 4900
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 42.37,
|
| 747 |
-
"learning_rate": 0.0002875368956743002,
|
| 748 |
-
"loss": 0.0777,
|
| 749 |
-
"step": 5000
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 42.37,
|
| 753 |
-
"eval_loss": 0.3149695098400116,
|
| 754 |
-
"eval_runtime": 192.9814,
|
| 755 |
-
"eval_samples_per_second": 17.468,
|
| 756 |
-
"eval_steps_per_second": 2.187,
|
| 757 |
-
"eval_wer": 0.24508091745255559,
|
| 758 |
-
"step": 5000
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 43.22,
|
| 762 |
-
"learning_rate": 0.0002872824427480916,
|
| 763 |
-
"loss": 0.0804,
|
| 764 |
-
"step": 5100
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 43.22,
|
| 768 |
-
"eval_loss": 0.3207753598690033,
|
| 769 |
-
"eval_runtime": 190.3397,
|
| 770 |
-
"eval_samples_per_second": 17.71,
|
| 771 |
-
"eval_steps_per_second": 2.217,
|
| 772 |
-
"eval_wer": 0.25381301664920247,
|
| 773 |
-
"step": 5100
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 44.07,
|
| 777 |
-
"learning_rate": 0.000287030534351145,
|
| 778 |
-
"loss": 0.0838,
|
| 779 |
-
"step": 5200
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 44.07,
|
| 783 |
-
"eval_loss": 0.3102128505706787,
|
| 784 |
-
"eval_runtime": 175.1719,
|
| 785 |
-
"eval_samples_per_second": 19.244,
|
| 786 |
-
"eval_steps_per_second": 2.409,
|
| 787 |
-
"eval_wer": 0.24845732914192573,
|
| 788 |
-
"step": 5200
|
| 789 |
-
},
|
| 790 |
-
{
|
| 791 |
-
"epoch": 44.91,
|
| 792 |
-
"learning_rate": 0.0002867760814249364,
|
| 793 |
-
"loss": 0.0731,
|
| 794 |
-
"step": 5300
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 44.91,
|
| 798 |
-
"eval_loss": 0.29943132400512695,
|
| 799 |
-
"eval_runtime": 173.7343,
|
| 800 |
-
"eval_samples_per_second": 19.403,
|
| 801 |
-
"eval_steps_per_second": 2.429,
|
| 802 |
-
"eval_wer": 0.24449877750611246,
|
| 803 |
-
"step": 5300
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 45.76,
|
| 807 |
-
"learning_rate": 0.0002865216284987277,
|
| 808 |
-
"loss": 0.0736,
|
| 809 |
-
"step": 5400
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 45.76,
|
| 813 |
-
"eval_loss": 0.3185470998287201,
|
| 814 |
-
"eval_runtime": 174.5938,
|
| 815 |
-
"eval_samples_per_second": 19.308,
|
| 816 |
-
"eval_steps_per_second": 2.417,
|
| 817 |
-
"eval_wer": 0.2591687041564792,
|
| 818 |
-
"step": 5400
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 46.61,
|
| 822 |
-
"learning_rate": 0.0002862671755725191,
|
| 823 |
-
"loss": 0.0795,
|
| 824 |
-
"step": 5500
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 46.61,
|
| 828 |
-
"eval_loss": 0.3023243546485901,
|
| 829 |
-
"eval_runtime": 174.2188,
|
| 830 |
-
"eval_samples_per_second": 19.349,
|
| 831 |
-
"eval_steps_per_second": 2.422,
|
| 832 |
-
"eval_wer": 0.24583769938293165,
|
| 833 |
-
"step": 5500
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 47.46,
|
| 837 |
-
"learning_rate": 0.0002860127226463104,
|
| 838 |
-
"loss": 0.0753,
|
| 839 |
-
"step": 5600
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 47.46,
|
| 843 |
-
"eval_loss": 0.32648247480392456,
|
| 844 |
-
"eval_runtime": 179.8281,
|
| 845 |
-
"eval_samples_per_second": 18.746,
|
| 846 |
-
"eval_steps_per_second": 2.347,
|
| 847 |
-
"eval_wer": 0.2464780533240191,
|
| 848 |
-
"step": 5600
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 48.3,
|
| 852 |
-
"learning_rate": 0.0002857582697201018,
|
| 853 |
-
"loss": 0.0716,
|
| 854 |
-
"step": 5700
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 48.3,
|
| 858 |
-
"eval_loss": 0.3370068073272705,
|
| 859 |
-
"eval_runtime": 190.9301,
|
| 860 |
-
"eval_samples_per_second": 17.656,
|
| 861 |
-
"eval_steps_per_second": 2.21,
|
| 862 |
-
"eval_wer": 0.24903946908836885,
|
| 863 |
-
"step": 5700
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 49.15,
|
| 867 |
-
"learning_rate": 0.0002855038167938931,
|
| 868 |
-
"loss": 0.074,
|
| 869 |
-
"step": 5800
|
| 870 |
-
},
|
| 871 |
-
{
|
| 872 |
-
"epoch": 49.15,
|
| 873 |
-
"eval_loss": 0.299947589635849,
|
| 874 |
-
"eval_runtime": 192.7259,
|
| 875 |
-
"eval_samples_per_second": 17.491,
|
| 876 |
-
"eval_steps_per_second": 2.19,
|
| 877 |
-
"eval_wer": 0.2431598556292933,
|
| 878 |
-
"step": 5800
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 50.0,
|
| 882 |
-
"learning_rate": 0.00028524936386768447,
|
| 883 |
-
"loss": 0.0678,
|
| 884 |
-
"step": 5900
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 50.0,
|
| 888 |
-
"eval_loss": 0.32643795013427734,
|
| 889 |
-
"eval_runtime": 195.0205,
|
| 890 |
-
"eval_samples_per_second": 17.285,
|
| 891 |
-
"eval_steps_per_second": 2.164,
|
| 892 |
-
"eval_wer": 0.2549190825474444,
|
| 893 |
-
"step": 5900
|
| 894 |
}
|
| 895 |
],
|
| 896 |
"max_steps": 118000,
|
| 897 |
"num_train_epochs": 1000,
|
| 898 |
-
"total_flos":
|
| 899 |
"trial_name": null,
|
| 900 |
"trial_params": null
|
| 901 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.541798941798942,
|
| 5 |
+
"global_step": 300,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.85,
|
| 12 |
+
"learning_rate": 0.0001,
|
| 13 |
+
"loss": 0.0249,
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.85,
|
| 18 |
+
"eval_loss": 0.3500341773033142,
|
| 19 |
+
"eval_runtime": 218.9102,
|
| 20 |
+
"eval_samples_per_second": 15.399,
|
| 21 |
+
"eval_steps_per_second": 1.928,
|
| 22 |
+
"eval_wer": 0.2325649086040284,
|
| 23 |
"step": 100
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.69,
|
| 27 |
+
"learning_rate": 9.991518235793045e-05,
|
| 28 |
+
"loss": 0.0468,
|
| 29 |
"step": 200
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 1.69,
|
| 33 |
+
"eval_loss": 0.3051254153251648,
|
| 34 |
+
"eval_runtime": 153.0625,
|
| 35 |
+
"eval_samples_per_second": 22.024,
|
| 36 |
+
"eval_steps_per_second": 2.757,
|
| 37 |
+
"eval_wer": 0.22418209337524742,
|
| 38 |
"step": 200
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 2.54,
|
| 42 |
+
"learning_rate": 9.98303647158609e-05,
|
| 43 |
+
"loss": 0.0412,
|
| 44 |
"step": 300
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 2.54,
|
| 48 |
+
"eval_loss": 0.3074679672718048,
|
| 49 |
+
"eval_runtime": 155.3125,
|
| 50 |
+
"eval_samples_per_second": 21.705,
|
| 51 |
+
"eval_steps_per_second": 2.717,
|
| 52 |
+
"eval_wer": 0.22563744324135523,
|
| 53 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
}
|
| 55 |
],
|
| 56 |
"max_steps": 118000,
|
| 57 |
"num_train_epochs": 1000,
|
| 58 |
+
"total_flos": 6.832318928753621e+18,
|
| 59 |
"trial_name": null,
|
| 60 |
"trial_params": null
|
| 61 |
}
|
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:e1c9d7091f2595ad11d1aca691a21b9f02ef4199b26e120256c51f7316f0186d
|
| 3 |
size 3323
|