Training in progress, epoch 1, checkpoint
Browse files
checkpoint-555/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1629432864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:431d86bc92271d1ef5e64d393077b7e6cc36c837e77cc0dc2045c95b2a5b43a1
|
| 3 |
size 1629432864
|
checkpoint-555/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
-
"eval_steps":
|
| 6 |
"global_step": 555,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
|
@@ -10,405 +10,38 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0,
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_precision": 0.
|
| 16 |
-
"eval_recall": 0.
|
| 17 |
-
"eval_runtime":
|
| 18 |
-
"eval_samples_per_second":
|
| 19 |
-
"eval_steps_per_second":
|
| 20 |
"step": 0
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0
|
| 24 |
-
"grad_norm":
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 0.
|
| 27 |
-
"step":
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"learning_rate": 4.945848375451264e-05,
|
| 40 |
-
"loss": 0.1813,
|
| 41 |
-
"step": 30
|
| 42 |
-
},
|
| 43 |
-
{
|
| 44 |
-
"epoch": 0.07210455159981974,
|
| 45 |
-
"grad_norm": 15.57222843170166,
|
| 46 |
-
"learning_rate": 4.927797833935018e-05,
|
| 47 |
-
"loss": 0.2618,
|
| 48 |
-
"step": 40
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 0.09013068949977468,
|
| 52 |
-
"grad_norm": 11.892234802246094,
|
| 53 |
-
"learning_rate": 4.909747292418773e-05,
|
| 54 |
-
"loss": 0.1559,
|
| 55 |
-
"step": 50
|
| 56 |
-
},
|
| 57 |
-
{
|
| 58 |
-
"epoch": 0.10815682739972961,
|
| 59 |
-
"grad_norm": 6.340595722198486,
|
| 60 |
-
"learning_rate": 4.891696750902527e-05,
|
| 61 |
-
"loss": 0.1648,
|
| 62 |
-
"step": 60
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.12618296529968454,
|
| 66 |
-
"grad_norm": 10.196683883666992,
|
| 67 |
-
"learning_rate": 4.873646209386282e-05,
|
| 68 |
-
"loss": 0.1472,
|
| 69 |
-
"step": 70
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.14420910319963948,
|
| 73 |
-
"grad_norm": 11.511515617370605,
|
| 74 |
-
"learning_rate": 4.855595667870036e-05,
|
| 75 |
-
"loss": 0.2108,
|
| 76 |
-
"step": 80
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 0.16223524109959442,
|
| 80 |
-
"grad_norm": 8.681073188781738,
|
| 81 |
-
"learning_rate": 4.837545126353791e-05,
|
| 82 |
-
"loss": 0.1561,
|
| 83 |
-
"step": 90
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 0.18026137899954936,
|
| 87 |
-
"grad_norm": 41.062801361083984,
|
| 88 |
-
"learning_rate": 4.819494584837546e-05,
|
| 89 |
-
"loss": 0.1563,
|
| 90 |
-
"step": 100
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 0.19828751689950427,
|
| 94 |
-
"grad_norm": 19.93891716003418,
|
| 95 |
-
"learning_rate": 4.8014440433213e-05,
|
| 96 |
-
"loss": 0.1881,
|
| 97 |
-
"step": 110
|
| 98 |
-
},
|
| 99 |
-
{
|
| 100 |
-
"epoch": 0.21631365479945922,
|
| 101 |
-
"grad_norm": 21.90877914428711,
|
| 102 |
-
"learning_rate": 4.783393501805055e-05,
|
| 103 |
-
"loss": 0.1262,
|
| 104 |
-
"step": 120
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 0.23433979269941416,
|
| 108 |
-
"grad_norm": 14.123740196228027,
|
| 109 |
-
"learning_rate": 4.765342960288809e-05,
|
| 110 |
-
"loss": 0.1535,
|
| 111 |
-
"step": 130
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.25236593059936907,
|
| 115 |
-
"grad_norm": 30.671157836914062,
|
| 116 |
-
"learning_rate": 4.747292418772563e-05,
|
| 117 |
-
"loss": 0.1458,
|
| 118 |
-
"step": 140
|
| 119 |
-
},
|
| 120 |
-
{
|
| 121 |
-
"epoch": 0.270392068499324,
|
| 122 |
-
"grad_norm": 7.560745716094971,
|
| 123 |
-
"learning_rate": 4.7292418772563177e-05,
|
| 124 |
-
"loss": 0.1797,
|
| 125 |
-
"step": 150
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 0.28841820639927895,
|
| 129 |
-
"grad_norm": 12.448927879333496,
|
| 130 |
-
"learning_rate": 4.711191335740072e-05,
|
| 131 |
-
"loss": 0.1898,
|
| 132 |
-
"step": 160
|
| 133 |
-
},
|
| 134 |
-
{
|
| 135 |
-
"epoch": 0.3064443442992339,
|
| 136 |
-
"grad_norm": 20.040008544921875,
|
| 137 |
-
"learning_rate": 4.693140794223827e-05,
|
| 138 |
-
"loss": 0.1698,
|
| 139 |
-
"step": 170
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 0.32447048219918884,
|
| 143 |
-
"grad_norm": 7.592446804046631,
|
| 144 |
-
"learning_rate": 4.675090252707581e-05,
|
| 145 |
-
"loss": 0.156,
|
| 146 |
-
"step": 180
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.3424966200991438,
|
| 150 |
-
"grad_norm": 18.830904006958008,
|
| 151 |
-
"learning_rate": 4.657039711191336e-05,
|
| 152 |
-
"loss": 0.1536,
|
| 153 |
-
"step": 190
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 0.3605227579990987,
|
| 157 |
-
"grad_norm": 3.684938430786133,
|
| 158 |
-
"learning_rate": 4.63898916967509e-05,
|
| 159 |
-
"loss": 0.1152,
|
| 160 |
-
"step": 200
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 0.3785488958990536,
|
| 164 |
-
"grad_norm": 13.293309211730957,
|
| 165 |
-
"learning_rate": 4.620938628158845e-05,
|
| 166 |
-
"loss": 0.2116,
|
| 167 |
-
"step": 210
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 0.39657503379900855,
|
| 171 |
-
"grad_norm": 14.630786895751953,
|
| 172 |
-
"learning_rate": 4.602888086642599e-05,
|
| 173 |
-
"loss": 0.1549,
|
| 174 |
-
"step": 220
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 0.4146011716989635,
|
| 178 |
-
"grad_norm": 20.37642478942871,
|
| 179 |
-
"learning_rate": 4.584837545126354e-05,
|
| 180 |
-
"loss": 0.1679,
|
| 181 |
-
"step": 230
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 0.43262730959891843,
|
| 185 |
-
"grad_norm": 13.183340072631836,
|
| 186 |
-
"learning_rate": 4.566787003610109e-05,
|
| 187 |
-
"loss": 0.1581,
|
| 188 |
-
"step": 240
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 0.45065344749887337,
|
| 192 |
-
"grad_norm": 21.777263641357422,
|
| 193 |
-
"learning_rate": 4.548736462093863e-05,
|
| 194 |
-
"loss": 0.1618,
|
| 195 |
-
"step": 250
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.4686795853988283,
|
| 199 |
-
"grad_norm": 20.683944702148438,
|
| 200 |
-
"learning_rate": 4.530685920577618e-05,
|
| 201 |
-
"loss": 0.1606,
|
| 202 |
-
"step": 260
|
| 203 |
-
},
|
| 204 |
-
{
|
| 205 |
-
"epoch": 0.48670572329878325,
|
| 206 |
-
"grad_norm": 30.506752014160156,
|
| 207 |
-
"learning_rate": 4.5126353790613716e-05,
|
| 208 |
-
"loss": 0.1831,
|
| 209 |
-
"step": 270
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 0.5047318611987381,
|
| 213 |
-
"grad_norm": 22.953815460205078,
|
| 214 |
-
"learning_rate": 4.494584837545127e-05,
|
| 215 |
-
"loss": 0.1565,
|
| 216 |
-
"step": 280
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"epoch": 0.5227579990986931,
|
| 220 |
-
"grad_norm": 6.177365303039551,
|
| 221 |
-
"learning_rate": 4.4765342960288806e-05,
|
| 222 |
-
"loss": 0.1287,
|
| 223 |
-
"step": 290
|
| 224 |
-
},
|
| 225 |
-
{
|
| 226 |
-
"epoch": 0.540784136998648,
|
| 227 |
-
"grad_norm": 8.373098373413086,
|
| 228 |
-
"learning_rate": 4.458483754512636e-05,
|
| 229 |
-
"loss": 0.1553,
|
| 230 |
-
"step": 300
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 0.558810274898603,
|
| 234 |
-
"grad_norm": 10.07934284210205,
|
| 235 |
-
"learning_rate": 4.44043321299639e-05,
|
| 236 |
-
"loss": 0.1868,
|
| 237 |
-
"step": 310
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 0.5768364127985579,
|
| 241 |
-
"grad_norm": 18.686702728271484,
|
| 242 |
-
"learning_rate": 4.422382671480145e-05,
|
| 243 |
-
"loss": 0.1576,
|
| 244 |
-
"step": 320
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 0.5948625506985128,
|
| 248 |
-
"grad_norm": 10.679413795471191,
|
| 249 |
-
"learning_rate": 4.404332129963899e-05,
|
| 250 |
-
"loss": 0.1409,
|
| 251 |
-
"step": 330
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 0.6128886885984678,
|
| 255 |
-
"grad_norm": 11.381563186645508,
|
| 256 |
-
"learning_rate": 4.386281588447654e-05,
|
| 257 |
-
"loss": 0.2043,
|
| 258 |
-
"step": 340
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 0.6309148264984227,
|
| 262 |
-
"grad_norm": 40.68292236328125,
|
| 263 |
-
"learning_rate": 4.368231046931408e-05,
|
| 264 |
-
"loss": 0.1288,
|
| 265 |
-
"step": 350
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 0.6489409643983777,
|
| 269 |
-
"grad_norm": 17.46027946472168,
|
| 270 |
-
"learning_rate": 4.350180505415163e-05,
|
| 271 |
-
"loss": 0.1537,
|
| 272 |
-
"step": 360
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 0.6669671022983326,
|
| 276 |
-
"grad_norm": 13.656320571899414,
|
| 277 |
-
"learning_rate": 4.332129963898917e-05,
|
| 278 |
-
"loss": 0.1201,
|
| 279 |
-
"step": 370
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.6849932401982876,
|
| 283 |
-
"grad_norm": 20.412939071655273,
|
| 284 |
-
"learning_rate": 4.314079422382672e-05,
|
| 285 |
-
"loss": 0.1321,
|
| 286 |
-
"step": 380
|
| 287 |
-
},
|
| 288 |
-
{
|
| 289 |
-
"epoch": 0.7030193780982424,
|
| 290 |
-
"grad_norm": 9.957433700561523,
|
| 291 |
-
"learning_rate": 4.296028880866426e-05,
|
| 292 |
-
"loss": 0.141,
|
| 293 |
-
"step": 390
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 0.7210455159981974,
|
| 297 |
-
"grad_norm": 9.682558059692383,
|
| 298 |
-
"learning_rate": 4.277978339350181e-05,
|
| 299 |
-
"loss": 0.1607,
|
| 300 |
-
"step": 400
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 0.7390716538981523,
|
| 304 |
-
"grad_norm": 9.733131408691406,
|
| 305 |
-
"learning_rate": 4.259927797833935e-05,
|
| 306 |
-
"loss": 0.1037,
|
| 307 |
-
"step": 410
|
| 308 |
-
},
|
| 309 |
-
{
|
| 310 |
-
"epoch": 0.7570977917981072,
|
| 311 |
-
"grad_norm": 15.76230525970459,
|
| 312 |
-
"learning_rate": 4.24187725631769e-05,
|
| 313 |
-
"loss": 0.2101,
|
| 314 |
-
"step": 420
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.7751239296980622,
|
| 318 |
-
"grad_norm": 22.166545867919922,
|
| 319 |
-
"learning_rate": 4.223826714801444e-05,
|
| 320 |
-
"loss": 0.1459,
|
| 321 |
-
"step": 430
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.7931500675980171,
|
| 325 |
-
"grad_norm": 17.87278175354004,
|
| 326 |
-
"learning_rate": 4.205776173285199e-05,
|
| 327 |
-
"loss": 0.147,
|
| 328 |
-
"step": 440
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 0.8111762054979721,
|
| 332 |
-
"grad_norm": 5.201169490814209,
|
| 333 |
-
"learning_rate": 4.187725631768953e-05,
|
| 334 |
-
"loss": 0.1247,
|
| 335 |
-
"step": 450
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 0.829202343397927,
|
| 339 |
-
"grad_norm": 8.68251895904541,
|
| 340 |
-
"learning_rate": 4.169675090252708e-05,
|
| 341 |
-
"loss": 0.1172,
|
| 342 |
-
"step": 460
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 0.847228481297882,
|
| 346 |
-
"grad_norm": 14.086528778076172,
|
| 347 |
-
"learning_rate": 4.151624548736462e-05,
|
| 348 |
-
"loss": 0.111,
|
| 349 |
-
"step": 470
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"epoch": 0.8652546191978369,
|
| 353 |
-
"grad_norm": 5.421584606170654,
|
| 354 |
-
"learning_rate": 4.1335740072202167e-05,
|
| 355 |
-
"loss": 0.1264,
|
| 356 |
-
"step": 480
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 0.8832807570977917,
|
| 360 |
-
"grad_norm": 7.700821399688721,
|
| 361 |
-
"learning_rate": 4.115523465703972e-05,
|
| 362 |
-
"loss": 0.1278,
|
| 363 |
-
"step": 490
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 0.9013068949977467,
|
| 367 |
-
"grad_norm": 9.820999145507812,
|
| 368 |
-
"learning_rate": 4.0974729241877256e-05,
|
| 369 |
-
"loss": 0.1294,
|
| 370 |
-
"step": 500
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 0.9193330328977016,
|
| 374 |
-
"grad_norm": 15.016349792480469,
|
| 375 |
-
"learning_rate": 4.079422382671481e-05,
|
| 376 |
-
"loss": 0.1607,
|
| 377 |
-
"step": 510
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 0.9373591707976566,
|
| 381 |
-
"grad_norm": 10.43041706085205,
|
| 382 |
-
"learning_rate": 4.0613718411552346e-05,
|
| 383 |
-
"loss": 0.1091,
|
| 384 |
-
"step": 520
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 0.9553853086976115,
|
| 388 |
-
"grad_norm": 26.99540901184082,
|
| 389 |
-
"learning_rate": 4.043321299638989e-05,
|
| 390 |
-
"loss": 0.1442,
|
| 391 |
-
"step": 530
|
| 392 |
-
},
|
| 393 |
-
{
|
| 394 |
-
"epoch": 0.9734114465975665,
|
| 395 |
-
"grad_norm": 8.318906784057617,
|
| 396 |
-
"learning_rate": 4.0252707581227436e-05,
|
| 397 |
-
"loss": 0.1233,
|
| 398 |
-
"step": 540
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 0.9914375844975214,
|
| 402 |
-
"grad_norm": 8.85923957824707,
|
| 403 |
-
"learning_rate": 4.007220216606498e-05,
|
| 404 |
-
"loss": 0.1466,
|
| 405 |
-
"step": 550
|
| 406 |
}
|
| 407 |
],
|
| 408 |
-
"logging_steps":
|
| 409 |
-
"max_steps":
|
| 410 |
"num_input_tokens_seen": 0,
|
| 411 |
-
"num_train_epochs":
|
| 412 |
"save_steps": 500,
|
| 413 |
"stateful_callbacks": {
|
| 414 |
"TrainerControl": {
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
"global_step": 555,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0,
|
| 13 |
+
"eval_f1": 0.13882567137005006,
|
| 14 |
+
"eval_loss": 0.8569005727767944,
|
| 15 |
+
"eval_precision": 0.07566360704539817,
|
| 16 |
+
"eval_recall": 0.8402203856749312,
|
| 17 |
+
"eval_runtime": 50.8375,
|
| 18 |
+
"eval_samples_per_second": 91.92,
|
| 19 |
+
"eval_steps_per_second": 11.507,
|
| 20 |
"step": 0
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"grad_norm": 18.535512924194336,
|
| 25 |
+
"learning_rate": 2.4954873646209387e-05,
|
| 26 |
+
"loss": 0.1595,
|
| 27 |
+
"step": 555
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"eval_f1": 0.7377049180327869,
|
| 32 |
+
"eval_loss": 0.11871597915887833,
|
| 33 |
+
"eval_precision": 0.6415478615071283,
|
| 34 |
+
"eval_recall": 0.8677685950413223,
|
| 35 |
+
"eval_runtime": 52.321,
|
| 36 |
+
"eval_samples_per_second": 89.314,
|
| 37 |
+
"eval_steps_per_second": 11.181,
|
| 38 |
+
"step": 555
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
}
|
| 40 |
],
|
| 41 |
+
"logging_steps": 500,
|
| 42 |
+
"max_steps": 1108,
|
| 43 |
"num_input_tokens_seen": 0,
|
| 44 |
+
"num_train_epochs": 2,
|
| 45 |
"save_steps": 500,
|
| 46 |
"stateful_callbacks": {
|
| 47 |
"TrainerControl": {
|
checkpoint-555/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fec65d435d82330639f2254c3c8dd619ceaf78855b73ed7360d46e29c00bb91
|
| 3 |
size 5368
|