Training in progress, step 64, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1722054072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1dce664c65bb51e096d639575dafc29c2f3fd1714a025d6689ea2fe6339fcb3
|
| 3 |
size 1722054072
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 863084376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bfa1b6e7f0f7d799285b821f079fc13c29e5892353a0d99aa0b231161962f0b
|
| 3 |
size 863084376
|
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 sha256:3535a115dd66ed576001ff6370d23c91e17d7f2564bf842d10adac987c704d2b
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -119,6 +119,342 @@
|
|
| 119 |
"learning_rate": 1.0322580645161291e-06,
|
| 120 |
"loss": 1.618,
|
| 121 |
"step": 16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
}
|
| 123 |
],
|
| 124 |
"logging_steps": 1,
|
|
@@ -138,7 +474,7 @@
|
|
| 138 |
"attributes": {}
|
| 139 |
}
|
| 140 |
},
|
| 141 |
-
"total_flos":
|
| 142 |
"train_batch_size": 4,
|
| 143 |
"trial_name": null,
|
| 144 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0041376746591671315,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 64,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 119 |
"learning_rate": 1.0322580645161291e-06,
|
| 120 |
"loss": 1.618,
|
| 121 |
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0010990698313412693,
|
| 125 |
+
"grad_norm": 27.484895706176758,
|
| 126 |
+
"learning_rate": 1.0967741935483872e-06,
|
| 127 |
+
"loss": 1.5973,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0011637209978907557,
|
| 132 |
+
"grad_norm": 20.07984161376953,
|
| 133 |
+
"learning_rate": 1.1612903225806454e-06,
|
| 134 |
+
"loss": 1.6907,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0012283721644402422,
|
| 139 |
+
"grad_norm": 14.788183212280273,
|
| 140 |
+
"learning_rate": 1.2258064516129033e-06,
|
| 141 |
+
"loss": 1.6986,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.0012930233309897286,
|
| 146 |
+
"grad_norm": 9.38936996459961,
|
| 147 |
+
"learning_rate": 1.2903225806451614e-06,
|
| 148 |
+
"loss": 1.6164,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.001357674497539215,
|
| 153 |
+
"grad_norm": 8.975388526916504,
|
| 154 |
+
"learning_rate": 1.3548387096774195e-06,
|
| 155 |
+
"loss": 1.5637,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0014223256640887015,
|
| 160 |
+
"grad_norm": 14.67812442779541,
|
| 161 |
+
"learning_rate": 1.4193548387096776e-06,
|
| 162 |
+
"loss": 1.6869,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0014869768306381879,
|
| 167 |
+
"grad_norm": 8.56955337524414,
|
| 168 |
+
"learning_rate": 1.4838709677419356e-06,
|
| 169 |
+
"loss": 1.5948,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0015516279971876743,
|
| 174 |
+
"grad_norm": 5.918207168579102,
|
| 175 |
+
"learning_rate": 1.5483870967741937e-06,
|
| 176 |
+
"loss": 1.61,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0016162791637371607,
|
| 181 |
+
"grad_norm": 8.165249824523926,
|
| 182 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 183 |
+
"loss": 1.712,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.0016809303302866472,
|
| 188 |
+
"grad_norm": 9.301441192626953,
|
| 189 |
+
"learning_rate": 1.67741935483871e-06,
|
| 190 |
+
"loss": 1.6957,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0017455814968361336,
|
| 195 |
+
"grad_norm": 7.351085662841797,
|
| 196 |
+
"learning_rate": 1.7419354838709678e-06,
|
| 197 |
+
"loss": 1.5153,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.00181023266338562,
|
| 202 |
+
"grad_norm": 7.347102642059326,
|
| 203 |
+
"learning_rate": 1.8064516129032258e-06,
|
| 204 |
+
"loss": 1.6625,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0018748838299351065,
|
| 209 |
+
"grad_norm": 7.22580623626709,
|
| 210 |
+
"learning_rate": 1.870967741935484e-06,
|
| 211 |
+
"loss": 1.5632,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.001939534996484593,
|
| 216 |
+
"grad_norm": 5.857529163360596,
|
| 217 |
+
"learning_rate": 1.935483870967742e-06,
|
| 218 |
+
"loss": 1.5339,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.002004186163034079,
|
| 223 |
+
"grad_norm": 7.3882222175598145,
|
| 224 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 225 |
+
"loss": 1.5775,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.0020688373295835658,
|
| 230 |
+
"grad_norm": 6.075866222381592,
|
| 231 |
+
"learning_rate": 2.0645161290322582e-06,
|
| 232 |
+
"loss": 1.55,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.002133488496133052,
|
| 237 |
+
"grad_norm": 4.930643081665039,
|
| 238 |
+
"learning_rate": 2.129032258064516e-06,
|
| 239 |
+
"loss": 1.5525,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0021981396626825386,
|
| 244 |
+
"grad_norm": 6.426210880279541,
|
| 245 |
+
"learning_rate": 2.1935483870967745e-06,
|
| 246 |
+
"loss": 1.5845,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.002262790829232025,
|
| 251 |
+
"grad_norm": 7.546030521392822,
|
| 252 |
+
"learning_rate": 2.2580645161290324e-06,
|
| 253 |
+
"loss": 1.6313,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.0023274419957815115,
|
| 258 |
+
"grad_norm": 4.881446361541748,
|
| 259 |
+
"learning_rate": 2.3225806451612907e-06,
|
| 260 |
+
"loss": 1.5387,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.0023920931623309977,
|
| 265 |
+
"grad_norm": 5.156312942504883,
|
| 266 |
+
"learning_rate": 2.3870967741935486e-06,
|
| 267 |
+
"loss": 1.4912,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0024567443288804843,
|
| 272 |
+
"grad_norm": 6.470444202423096,
|
| 273 |
+
"learning_rate": 2.4516129032258066e-06,
|
| 274 |
+
"loss": 1.4706,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.0025213954954299705,
|
| 279 |
+
"grad_norm": 15.289785385131836,
|
| 280 |
+
"learning_rate": 2.5161290322580645e-06,
|
| 281 |
+
"loss": 1.4612,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.002586046661979457,
|
| 286 |
+
"grad_norm": 6.442019939422607,
|
| 287 |
+
"learning_rate": 2.580645161290323e-06,
|
| 288 |
+
"loss": 1.5178,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.0026506978285289434,
|
| 293 |
+
"grad_norm": 5.88471794128418,
|
| 294 |
+
"learning_rate": 2.645161290322581e-06,
|
| 295 |
+
"loss": 1.5095,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.00271534899507843,
|
| 300 |
+
"grad_norm": 7.326111316680908,
|
| 301 |
+
"learning_rate": 2.709677419354839e-06,
|
| 302 |
+
"loss": 1.5718,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.0027800001616279163,
|
| 307 |
+
"grad_norm": 4.946439266204834,
|
| 308 |
+
"learning_rate": 2.774193548387097e-06,
|
| 309 |
+
"loss": 1.5057,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.002844651328177403,
|
| 314 |
+
"grad_norm": 5.956087589263916,
|
| 315 |
+
"learning_rate": 2.8387096774193553e-06,
|
| 316 |
+
"loss": 1.4635,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.002909302494726889,
|
| 321 |
+
"grad_norm": 7.258240222930908,
|
| 322 |
+
"learning_rate": 2.903225806451613e-06,
|
| 323 |
+
"loss": 1.5494,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.0029739536612763758,
|
| 328 |
+
"grad_norm": 5.20070743560791,
|
| 329 |
+
"learning_rate": 2.967741935483871e-06,
|
| 330 |
+
"loss": 1.5329,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.003038604827825862,
|
| 335 |
+
"grad_norm": 6.215978145599365,
|
| 336 |
+
"learning_rate": 3.0322580645161295e-06,
|
| 337 |
+
"loss": 1.4822,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.0031032559943753486,
|
| 342 |
+
"grad_norm": 4.830237865447998,
|
| 343 |
+
"learning_rate": 3.0967741935483874e-06,
|
| 344 |
+
"loss": 1.457,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.003167907160924835,
|
| 349 |
+
"grad_norm": 6.3563971519470215,
|
| 350 |
+
"learning_rate": 3.1612903225806453e-06,
|
| 351 |
+
"loss": 1.4619,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.0032325583274743215,
|
| 356 |
+
"grad_norm": 5.210926532745361,
|
| 357 |
+
"learning_rate": 3.225806451612903e-06,
|
| 358 |
+
"loss": 1.446,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.0032972094940238077,
|
| 363 |
+
"grad_norm": 5.412484169006348,
|
| 364 |
+
"learning_rate": 3.2903225806451615e-06,
|
| 365 |
+
"loss": 1.4154,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.0033618606605732944,
|
| 370 |
+
"grad_norm": 5.500335693359375,
|
| 371 |
+
"learning_rate": 3.35483870967742e-06,
|
| 372 |
+
"loss": 1.4902,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.0034265118271227806,
|
| 377 |
+
"grad_norm": 5.576430320739746,
|
| 378 |
+
"learning_rate": 3.4193548387096773e-06,
|
| 379 |
+
"loss": 1.4931,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.003491162993672267,
|
| 384 |
+
"grad_norm": 4.996302604675293,
|
| 385 |
+
"learning_rate": 3.4838709677419357e-06,
|
| 386 |
+
"loss": 1.374,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.0035558141602217534,
|
| 391 |
+
"grad_norm": 4.846431255340576,
|
| 392 |
+
"learning_rate": 3.548387096774194e-06,
|
| 393 |
+
"loss": 1.5605,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.00362046532677124,
|
| 398 |
+
"grad_norm": 5.039584636688232,
|
| 399 |
+
"learning_rate": 3.6129032258064515e-06,
|
| 400 |
+
"loss": 1.4703,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.0036851164933207263,
|
| 405 |
+
"grad_norm": 4.541802406311035,
|
| 406 |
+
"learning_rate": 3.67741935483871e-06,
|
| 407 |
+
"loss": 1.4888,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.003749767659870213,
|
| 412 |
+
"grad_norm": 4.2027997970581055,
|
| 413 |
+
"learning_rate": 3.741935483870968e-06,
|
| 414 |
+
"loss": 1.5091,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.003814418826419699,
|
| 419 |
+
"grad_norm": 5.916923522949219,
|
| 420 |
+
"learning_rate": 3.8064516129032257e-06,
|
| 421 |
+
"loss": 1.4113,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.003879069992969186,
|
| 426 |
+
"grad_norm": 4.324679374694824,
|
| 427 |
+
"learning_rate": 3.870967741935484e-06,
|
| 428 |
+
"loss": 1.5304,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.0039437211595186724,
|
| 433 |
+
"grad_norm": 4.319639205932617,
|
| 434 |
+
"learning_rate": 3.935483870967742e-06,
|
| 435 |
+
"loss": 1.4203,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.004008372326068158,
|
| 440 |
+
"grad_norm": 5.848201274871826,
|
| 441 |
+
"learning_rate": 4.000000000000001e-06,
|
| 442 |
+
"loss": 1.4394,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.004073023492617645,
|
| 447 |
+
"grad_norm": 5.865200042724609,
|
| 448 |
+
"learning_rate": 4.064516129032259e-06,
|
| 449 |
+
"loss": 1.4537,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.0041376746591671315,
|
| 454 |
+
"grad_norm": 4.825560569763184,
|
| 455 |
+
"learning_rate": 4.1290322580645165e-06,
|
| 456 |
+
"loss": 1.4732,
|
| 457 |
+
"step": 64
|
| 458 |
}
|
| 459 |
],
|
| 460 |
"logging_steps": 1,
|
|
|
|
| 474 |
"attributes": {}
|
| 475 |
}
|
| 476 |
},
|
| 477 |
+
"total_flos": 6.80601377625047e+16,
|
| 478 |
"train_batch_size": 4,
|
| 479 |
"trial_name": null,
|
| 480 |
"trial_params": null
|