Commit
·
a35156c
1
Parent(s):
1415be6
Training in progress, step 25, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -16,13 +16,13 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"gate_proj",
|
| 20 |
-
"k_proj",
|
| 21 |
"v_proj",
|
|
|
|
| 22 |
"up_proj",
|
|
|
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
-
"down_proj"
|
| 25 |
-
"q_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
|
|
|
| 19 |
"v_proj",
|
| 20 |
+
"gate_proj",
|
| 21 |
"up_proj",
|
| 22 |
+
"q_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
"o_proj",
|
| 25 |
+
"down_proj"
|
|
|
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a965a0e35eb565282b2b1fcfc122cb90b82d05bbb2e9f0b12b4691a072f4cb0
|
| 3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40570324
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1edde597d127de07be7f782f6dcaf35d1273cdd6b7b1b022121fc26ce68fd22e
|
| 3 |
size 40570324
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d504d22c70365e955869229804fc73b5137014a18fd4465b41a6a55d0b2d969
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dec2630d82b42dc3f2af7f561c89bb49dcba8fb4678d8138315fec1825cabb01
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -23,447 +23,147 @@
|
|
| 23 |
{
|
| 24 |
"epoch": 0.0,
|
| 25 |
"learning_rate": 0.00012,
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.0,
|
| 31 |
"learning_rate": 0.00016,
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.0,
|
| 37 |
"learning_rate": 0.0002,
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.0,
|
| 43 |
"learning_rate": 0.00019789473684210526,
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.0,
|
| 49 |
"learning_rate": 0.00019578947368421054,
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.0,
|
| 55 |
"learning_rate": 0.0001936842105263158,
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.0,
|
| 61 |
"learning_rate": 0.00019157894736842104,
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.0,
|
| 67 |
"learning_rate": 0.00018947368421052632,
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.0,
|
| 73 |
"learning_rate": 0.0001873684210526316,
|
| 74 |
-
"loss": 1.
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.0,
|
| 79 |
"learning_rate": 0.00018526315789473685,
|
| 80 |
-
"loss": 1.
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.0,
|
| 85 |
"learning_rate": 0.0001831578947368421,
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.0,
|
| 91 |
"learning_rate": 0.00018105263157894739,
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.0,
|
| 97 |
"learning_rate": 0.00017894736842105264,
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.0,
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.0,
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 1.
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.0,
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss": 1.
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.0,
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.0,
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 1.
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.0,
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.0,
|
| 139 |
-
"learning_rate": 0.
|
| 140 |
-
"loss": 1.
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.0,
|
| 145 |
-
"learning_rate": 0.
|
| 146 |
-
"loss": 1.
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.0,
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 1.
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.0,
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 1.
|
| 159 |
"step": 25
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 0.0,
|
| 163 |
-
"learning_rate": 0.00015578947368421052,
|
| 164 |
-
"loss": 1.4779,
|
| 165 |
-
"step": 26
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.0,
|
| 169 |
-
"learning_rate": 0.0001536842105263158,
|
| 170 |
-
"loss": 1.638,
|
| 171 |
-
"step": 27
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.0,
|
| 175 |
-
"learning_rate": 0.00015157894736842108,
|
| 176 |
-
"loss": 1.5519,
|
| 177 |
-
"step": 28
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.0,
|
| 181 |
-
"learning_rate": 0.00014947368421052633,
|
| 182 |
-
"loss": 1.7623,
|
| 183 |
-
"step": 29
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 0.0,
|
| 187 |
-
"learning_rate": 0.00014736842105263158,
|
| 188 |
-
"loss": 1.2871,
|
| 189 |
-
"step": 30
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 0.0,
|
| 193 |
-
"learning_rate": 0.00014526315789473686,
|
| 194 |
-
"loss": 1.5806,
|
| 195 |
-
"step": 31
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.0,
|
| 199 |
-
"learning_rate": 0.0001431578947368421,
|
| 200 |
-
"loss": 1.5541,
|
| 201 |
-
"step": 32
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.0,
|
| 205 |
-
"learning_rate": 0.00014105263157894736,
|
| 206 |
-
"loss": 1.6991,
|
| 207 |
-
"step": 33
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.0,
|
| 211 |
-
"learning_rate": 0.00013894736842105264,
|
| 212 |
-
"loss": 1.5331,
|
| 213 |
-
"step": 34
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.0,
|
| 217 |
-
"learning_rate": 0.0001368421052631579,
|
| 218 |
-
"loss": 1.9143,
|
| 219 |
-
"step": 35
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.0,
|
| 223 |
-
"learning_rate": 0.00013473684210526317,
|
| 224 |
-
"loss": 1.6051,
|
| 225 |
-
"step": 36
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.0,
|
| 229 |
-
"learning_rate": 0.00013263157894736842,
|
| 230 |
-
"loss": 1.6311,
|
| 231 |
-
"step": 37
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 0.0,
|
| 235 |
-
"learning_rate": 0.0001305263157894737,
|
| 236 |
-
"loss": 1.4711,
|
| 237 |
-
"step": 38
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 0.0,
|
| 241 |
-
"learning_rate": 0.00012842105263157895,
|
| 242 |
-
"loss": 1.4644,
|
| 243 |
-
"step": 39
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 0.0,
|
| 247 |
-
"learning_rate": 0.0001263157894736842,
|
| 248 |
-
"loss": 1.7623,
|
| 249 |
-
"step": 40
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.0,
|
| 253 |
-
"learning_rate": 0.00012421052631578949,
|
| 254 |
-
"loss": 1.5635,
|
| 255 |
-
"step": 41
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.0,
|
| 259 |
-
"learning_rate": 0.00012210526315789474,
|
| 260 |
-
"loss": 1.3194,
|
| 261 |
-
"step": 42
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.0,
|
| 265 |
-
"learning_rate": 0.00012,
|
| 266 |
-
"loss": 1.3296,
|
| 267 |
-
"step": 43
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.0,
|
| 271 |
-
"learning_rate": 0.00011789473684210525,
|
| 272 |
-
"loss": 1.6656,
|
| 273 |
-
"step": 44
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.0,
|
| 277 |
-
"learning_rate": 0.00011578947368421053,
|
| 278 |
-
"loss": 1.5584,
|
| 279 |
-
"step": 45
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.0,
|
| 283 |
-
"learning_rate": 0.0001136842105263158,
|
| 284 |
-
"loss": 1.6557,
|
| 285 |
-
"step": 46
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 0.0,
|
| 289 |
-
"learning_rate": 0.00011157894736842105,
|
| 290 |
-
"loss": 1.4512,
|
| 291 |
-
"step": 47
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.0,
|
| 295 |
-
"learning_rate": 0.00010947368421052633,
|
| 296 |
-
"loss": 1.4563,
|
| 297 |
-
"step": 48
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.0,
|
| 301 |
-
"learning_rate": 0.00010736842105263158,
|
| 302 |
-
"loss": 1.4214,
|
| 303 |
-
"step": 49
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.0,
|
| 307 |
-
"learning_rate": 0.00010526315789473685,
|
| 308 |
-
"loss": 1.6556,
|
| 309 |
-
"step": 50
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.0,
|
| 313 |
-
"learning_rate": 0.00010315789473684211,
|
| 314 |
-
"loss": 1.5774,
|
| 315 |
-
"step": 51
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.0,
|
| 319 |
-
"learning_rate": 0.00010105263157894738,
|
| 320 |
-
"loss": 1.5624,
|
| 321 |
-
"step": 52
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.0,
|
| 325 |
-
"learning_rate": 9.894736842105263e-05,
|
| 326 |
-
"loss": 1.0224,
|
| 327 |
-
"step": 53
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.0,
|
| 331 |
-
"learning_rate": 9.68421052631579e-05,
|
| 332 |
-
"loss": 1.5792,
|
| 333 |
-
"step": 54
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.0,
|
| 337 |
-
"learning_rate": 9.473684210526316e-05,
|
| 338 |
-
"loss": 1.6203,
|
| 339 |
-
"step": 55
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.0,
|
| 343 |
-
"learning_rate": 9.263157894736843e-05,
|
| 344 |
-
"loss": 1.6145,
|
| 345 |
-
"step": 56
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.0,
|
| 349 |
-
"learning_rate": 9.052631578947369e-05,
|
| 350 |
-
"loss": 1.5488,
|
| 351 |
-
"step": 57
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 0.0,
|
| 355 |
-
"learning_rate": 8.842105263157894e-05,
|
| 356 |
-
"loss": 1.7138,
|
| 357 |
-
"step": 58
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 0.0,
|
| 361 |
-
"learning_rate": 8.631578947368421e-05,
|
| 362 |
-
"loss": 1.5731,
|
| 363 |
-
"step": 59
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 0.0,
|
| 367 |
-
"learning_rate": 8.421052631578948e-05,
|
| 368 |
-
"loss": 1.2584,
|
| 369 |
-
"step": 60
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.0,
|
| 373 |
-
"learning_rate": 8.210526315789474e-05,
|
| 374 |
-
"loss": 1.4644,
|
| 375 |
-
"step": 61
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.0,
|
| 379 |
-
"learning_rate": 8e-05,
|
| 380 |
-
"loss": 1.4227,
|
| 381 |
-
"step": 62
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.0,
|
| 385 |
-
"learning_rate": 7.789473684210526e-05,
|
| 386 |
-
"loss": 1.4762,
|
| 387 |
-
"step": 63
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 0.0,
|
| 391 |
-
"learning_rate": 7.578947368421054e-05,
|
| 392 |
-
"loss": 1.6393,
|
| 393 |
-
"step": 64
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"epoch": 0.0,
|
| 397 |
-
"learning_rate": 7.368421052631579e-05,
|
| 398 |
-
"loss": 1.6137,
|
| 399 |
-
"step": 65
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 0.0,
|
| 403 |
-
"learning_rate": 7.157894736842105e-05,
|
| 404 |
-
"loss": 1.4132,
|
| 405 |
-
"step": 66
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.0,
|
| 409 |
-
"learning_rate": 6.947368421052632e-05,
|
| 410 |
-
"loss": 1.9143,
|
| 411 |
-
"step": 67
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.0,
|
| 415 |
-
"learning_rate": 6.736842105263159e-05,
|
| 416 |
-
"loss": 1.2177,
|
| 417 |
-
"step": 68
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.0,
|
| 421 |
-
"learning_rate": 6.526315789473685e-05,
|
| 422 |
-
"loss": 1.6103,
|
| 423 |
-
"step": 69
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.0,
|
| 427 |
-
"learning_rate": 6.31578947368421e-05,
|
| 428 |
-
"loss": 1.3548,
|
| 429 |
-
"step": 70
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.0,
|
| 433 |
-
"learning_rate": 6.105263157894737e-05,
|
| 434 |
-
"loss": 1.6381,
|
| 435 |
-
"step": 71
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.0,
|
| 439 |
-
"learning_rate": 5.894736842105263e-05,
|
| 440 |
-
"loss": 1.6296,
|
| 441 |
-
"step": 72
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.0,
|
| 445 |
-
"learning_rate": 5.68421052631579e-05,
|
| 446 |
-
"loss": 1.6071,
|
| 447 |
-
"step": 73
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 0.0,
|
| 451 |
-
"learning_rate": 5.4736842105263165e-05,
|
| 452 |
-
"loss": 1.7263,
|
| 453 |
-
"step": 74
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.0,
|
| 457 |
-
"learning_rate": 5.2631578947368424e-05,
|
| 458 |
-
"loss": 1.5891,
|
| 459 |
-
"step": 75
|
| 460 |
}
|
| 461 |
],
|
| 462 |
"logging_steps": 1,
|
| 463 |
"max_steps": 100,
|
| 464 |
"num_train_epochs": 1,
|
| 465 |
"save_steps": 25,
|
| 466 |
-
"total_flos":
|
| 467 |
"trial_name": null,
|
| 468 |
"trial_params": null
|
| 469 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0006218905472636816,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 25,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 23 |
{
|
| 24 |
"epoch": 0.0,
|
| 25 |
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 2.0249,
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.0,
|
| 31 |
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 1.9519,
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.0,
|
| 37 |
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 2.1586,
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.0,
|
| 43 |
"learning_rate": 0.00019789473684210526,
|
| 44 |
+
"loss": 1.6571,
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.0,
|
| 49 |
"learning_rate": 0.00019578947368421054,
|
| 50 |
+
"loss": 1.6994,
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.0,
|
| 55 |
"learning_rate": 0.0001936842105263158,
|
| 56 |
+
"loss": 1.6263,
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.0,
|
| 61 |
"learning_rate": 0.00019157894736842104,
|
| 62 |
+
"loss": 1.5557,
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.0,
|
| 67 |
"learning_rate": 0.00018947368421052632,
|
| 68 |
+
"loss": 1.5908,
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.0,
|
| 73 |
"learning_rate": 0.0001873684210526316,
|
| 74 |
+
"loss": 1.8123,
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.0,
|
| 79 |
"learning_rate": 0.00018526315789473685,
|
| 80 |
+
"loss": 1.7386,
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.0,
|
| 85 |
"learning_rate": 0.0001831578947368421,
|
| 86 |
+
"loss": 1.6149,
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.0,
|
| 91 |
"learning_rate": 0.00018105263157894739,
|
| 92 |
+
"loss": 1.6512,
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.0,
|
| 97 |
"learning_rate": 0.00017894736842105264,
|
| 98 |
+
"loss": 1.4589,
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.0,
|
| 103 |
+
"learning_rate": 0.00017894736842105264,
|
| 104 |
+
"loss": 1.4591,
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.0,
|
| 109 |
+
"learning_rate": 0.0001768421052631579,
|
| 110 |
+
"loss": 1.4456,
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.0,
|
| 115 |
+
"learning_rate": 0.00017473684210526317,
|
| 116 |
+
"loss": 1.5533,
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.0,
|
| 121 |
+
"learning_rate": 0.00017263157894736842,
|
| 122 |
+
"loss": 1.424,
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.0,
|
| 127 |
+
"learning_rate": 0.0001705263157894737,
|
| 128 |
+
"loss": 1.4817,
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.0,
|
| 133 |
+
"learning_rate": 0.00016842105263157895,
|
| 134 |
+
"loss": 1.6008,
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.0,
|
| 139 |
+
"learning_rate": 0.00016631578947368423,
|
| 140 |
+
"loss": 1.4342,
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.0,
|
| 145 |
+
"learning_rate": 0.00016421052631578948,
|
| 146 |
+
"loss": 1.7079,
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.0,
|
| 151 |
+
"learning_rate": 0.00016210526315789473,
|
| 152 |
+
"loss": 1.761,
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.0,
|
| 157 |
+
"learning_rate": 0.00016,
|
| 158 |
+
"loss": 1.6936,
|
| 159 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
}
|
| 161 |
],
|
| 162 |
"logging_steps": 1,
|
| 163 |
"max_steps": 100,
|
| 164 |
"num_train_epochs": 1,
|
| 165 |
"save_steps": 25,
|
| 166 |
+
"total_flos": 1278571417288704.0,
|
| 167 |
"trial_name": null,
|
| 168 |
"trial_params": null
|
| 169 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64bc67c40371d89ad1c0c5799c319b73a6cbfb79d05d7cb27dd81ef6351298a8
|
| 3 |
size 4600
|