Training in progress, step 450, 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 527048968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:372891febfadfccbabac9570878fa86511c85965c83b7adbeef55c8d100f4f2d
|
| 3 |
size 527048968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1054136250
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:620d4f511180616a4534055c09585878071e140c18fdd5dc3beb5a71366c356b
|
| 3 |
size 1054136250
|
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 sha256:5cf065c84ff75b4c8bc24f08fcd1880a75e81b5b99444434709d4c17d68aad0f
|
| 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 1256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb248e7cc2fe7b509c9e866be7b72af3b33225d8b86373c1a62393cc3a24f4da
|
| 3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -120,6 +120,288 @@
|
|
| 120 |
"eval_samples_per_second": 22.169,
|
| 121 |
"eval_steps_per_second": 22.169,
|
| 122 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
}
|
| 124 |
],
|
| 125 |
"logging_steps": 10,
|
|
@@ -139,7 +421,7 @@
|
|
| 139 |
"attributes": {}
|
| 140 |
}
|
| 141 |
},
|
| 142 |
-
"total_flos":
|
| 143 |
"train_batch_size": 2,
|
| 144 |
"trial_name": null,
|
| 145 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7259252071380615,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-450",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 450,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 120 |
"eval_samples_per_second": 22.169,
|
| 121 |
"eval_steps_per_second": 22.169,
|
| 122 |
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.5555555555555554,
|
| 126 |
+
"grad_norm": 2.560298204421997,
|
| 127 |
+
"learning_rate": 2.9999892980750276e-05,
|
| 128 |
+
"loss": 0.6943,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.7777777777777777,
|
| 133 |
+
"grad_norm": 2.3921022415161133,
|
| 134 |
+
"learning_rate": 2.9999854334972655e-05,
|
| 135 |
+
"loss": 0.6927,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.0,
|
| 140 |
+
"grad_norm": 2.541400909423828,
|
| 141 |
+
"learning_rate": 2.999980974373202e-05,
|
| 142 |
+
"loss": 0.6681,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.222222222222222,
|
| 147 |
+
"grad_norm": 1.6048011779785156,
|
| 148 |
+
"learning_rate": 2.9999759207046055e-05,
|
| 149 |
+
"loss": 0.59,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.444444444444445,
|
| 154 |
+
"grad_norm": 1.6808319091796875,
|
| 155 |
+
"learning_rate": 2.9999702724934783e-05,
|
| 156 |
+
"loss": 0.7109,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 4.666666666666667,
|
| 161 |
+
"grad_norm": 3.4204533100128174,
|
| 162 |
+
"learning_rate": 2.99996402974206e-05,
|
| 163 |
+
"loss": 0.6277,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.888888888888889,
|
| 168 |
+
"grad_norm": 2.078854560852051,
|
| 169 |
+
"learning_rate": 2.9999571924528243e-05,
|
| 170 |
+
"loss": 0.6732,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.111111111111111,
|
| 175 |
+
"grad_norm": 2.6296238899230957,
|
| 176 |
+
"learning_rate": 2.9999497606284816e-05,
|
| 177 |
+
"loss": 0.6029,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 5.333333333333333,
|
| 182 |
+
"grad_norm": 1.4844911098480225,
|
| 183 |
+
"learning_rate": 2.9999417342719775e-05,
|
| 184 |
+
"loss": 0.6941,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 5.555555555555555,
|
| 189 |
+
"grad_norm": 2.2181289196014404,
|
| 190 |
+
"learning_rate": 2.9999331133864935e-05,
|
| 191 |
+
"loss": 0.6476,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 5.777777777777778,
|
| 196 |
+
"grad_norm": 1.705496907234192,
|
| 197 |
+
"learning_rate": 2.9999238979754465e-05,
|
| 198 |
+
"loss": 0.6095,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 6.0,
|
| 203 |
+
"grad_norm": 1.9006123542785645,
|
| 204 |
+
"learning_rate": 2.99991408804249e-05,
|
| 205 |
+
"loss": 0.5755,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.222222222222222,
|
| 210 |
+
"grad_norm": 2.1468276977539062,
|
| 211 |
+
"learning_rate": 2.999903683591511e-05,
|
| 212 |
+
"loss": 0.5742,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.444444444444445,
|
| 217 |
+
"grad_norm": 1.3946986198425293,
|
| 218 |
+
"learning_rate": 2.9998926846266345e-05,
|
| 219 |
+
"loss": 0.6137,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 6.666666666666667,
|
| 224 |
+
"grad_norm": 2.292116641998291,
|
| 225 |
+
"learning_rate": 2.9998810911522193e-05,
|
| 226 |
+
"loss": 0.6226,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 6.666666666666667,
|
| 231 |
+
"eval_loss": 0.7391407489776611,
|
| 232 |
+
"eval_runtime": 0.5623,
|
| 233 |
+
"eval_samples_per_second": 17.783,
|
| 234 |
+
"eval_steps_per_second": 17.783,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"Start_State_loss": 0.7391407489776611,
|
| 239 |
+
"Start_State_runtime": 0.5004,
|
| 240 |
+
"Start_State_samples_per_second": 19.984,
|
| 241 |
+
"Start_State_steps_per_second": 19.984,
|
| 242 |
+
"epoch": 6.666666666666667,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"SWA_loss": 0.7391407489776611,
|
| 247 |
+
"SWA_runtime": 0.5139,
|
| 248 |
+
"SWA_samples_per_second": 19.46,
|
| 249 |
+
"SWA_steps_per_second": 19.46,
|
| 250 |
+
"epoch": 6.666666666666667,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"EMA_loss": 0.7391407489776611,
|
| 255 |
+
"EMA_runtime": 0.515,
|
| 256 |
+
"EMA_samples_per_second": 19.417,
|
| 257 |
+
"EMA_steps_per_second": 19.417,
|
| 258 |
+
"epoch": 6.666666666666667,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.888888888888889,
|
| 263 |
+
"grad_norm": 2.7107701301574707,
|
| 264 |
+
"learning_rate": 2.9998689031728615e-05,
|
| 265 |
+
"loss": 0.6481,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 7.111111111111111,
|
| 270 |
+
"grad_norm": 1.764064908027649,
|
| 271 |
+
"learning_rate": 2.9998561206933918e-05,
|
| 272 |
+
"loss": 0.5866,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 7.333333333333333,
|
| 277 |
+
"grad_norm": 1.7632637023925781,
|
| 278 |
+
"learning_rate": 2.9998427437188766e-05,
|
| 279 |
+
"loss": 0.5798,
|
| 280 |
+
"step": 330
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 7.555555555555555,
|
| 284 |
+
"grad_norm": 2.3483335971832275,
|
| 285 |
+
"learning_rate": 2.999828772254618e-05,
|
| 286 |
+
"loss": 0.6034,
|
| 287 |
+
"step": 340
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.777777777777778,
|
| 291 |
+
"grad_norm": 2.47190260887146,
|
| 292 |
+
"learning_rate": 2.9998142063061544e-05,
|
| 293 |
+
"loss": 0.662,
|
| 294 |
+
"step": 350
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 8.0,
|
| 298 |
+
"grad_norm": 1.323142409324646,
|
| 299 |
+
"learning_rate": 2.9997990458792583e-05,
|
| 300 |
+
"loss": 0.6039,
|
| 301 |
+
"step": 360
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 8.222222222222221,
|
| 305 |
+
"grad_norm": 1.9020463228225708,
|
| 306 |
+
"learning_rate": 2.9997832909799397e-05,
|
| 307 |
+
"loss": 0.5489,
|
| 308 |
+
"step": 370
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.444444444444445,
|
| 312 |
+
"grad_norm": 1.9343500137329102,
|
| 313 |
+
"learning_rate": 2.9997669416144432e-05,
|
| 314 |
+
"loss": 0.641,
|
| 315 |
+
"step": 380
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.666666666666666,
|
| 319 |
+
"grad_norm": 1.0505070686340332,
|
| 320 |
+
"learning_rate": 2.999749997789249e-05,
|
| 321 |
+
"loss": 0.5396,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 8.88888888888889,
|
| 326 |
+
"grad_norm": 1.5202258825302124,
|
| 327 |
+
"learning_rate": 2.9997324595110723e-05,
|
| 328 |
+
"loss": 0.6543,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 9.11111111111111,
|
| 333 |
+
"grad_norm": 1.384507656097412,
|
| 334 |
+
"learning_rate": 2.9997143267868663e-05,
|
| 335 |
+
"loss": 0.5946,
|
| 336 |
+
"step": 410
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 9.333333333333334,
|
| 340 |
+
"grad_norm": 2.468230962753296,
|
| 341 |
+
"learning_rate": 2.999695599623817e-05,
|
| 342 |
+
"loss": 0.6231,
|
| 343 |
+
"step": 420
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 9.555555555555555,
|
| 347 |
+
"grad_norm": 2.60021710395813,
|
| 348 |
+
"learning_rate": 2.9996762780293483e-05,
|
| 349 |
+
"loss": 0.575,
|
| 350 |
+
"step": 430
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 9.777777777777779,
|
| 354 |
+
"grad_norm": 1.5323718786239624,
|
| 355 |
+
"learning_rate": 2.9996563620111176e-05,
|
| 356 |
+
"loss": 0.529,
|
| 357 |
+
"step": 440
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 10.0,
|
| 361 |
+
"grad_norm": 1.3856033086776733,
|
| 362 |
+
"learning_rate": 2.9996358515770198e-05,
|
| 363 |
+
"loss": 0.5417,
|
| 364 |
+
"step": 450
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 10.0,
|
| 368 |
+
"eval_loss": 0.7259252071380615,
|
| 369 |
+
"eval_runtime": 0.4435,
|
| 370 |
+
"eval_samples_per_second": 22.546,
|
| 371 |
+
"eval_steps_per_second": 22.546,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"Start_State_loss": 0.7391407489776611,
|
| 376 |
+
"Start_State_runtime": 0.4445,
|
| 377 |
+
"Start_State_samples_per_second": 22.495,
|
| 378 |
+
"Start_State_steps_per_second": 22.495,
|
| 379 |
+
"epoch": 10.0,
|
| 380 |
+
"step": 450
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"Raw_Model_loss": 0.7259252071380615,
|
| 384 |
+
"Raw_Model_runtime": 0.4437,
|
| 385 |
+
"Raw_Model_samples_per_second": 22.539,
|
| 386 |
+
"Raw_Model_steps_per_second": 22.539,
|
| 387 |
+
"epoch": 10.0,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"SWA_loss": 0.733832836151123,
|
| 392 |
+
"SWA_runtime": 0.4445,
|
| 393 |
+
"SWA_samples_per_second": 22.496,
|
| 394 |
+
"SWA_steps_per_second": 22.496,
|
| 395 |
+
"epoch": 10.0,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"EMA_loss": 0.738980233669281,
|
| 400 |
+
"EMA_runtime": 0.4444,
|
| 401 |
+
"EMA_samples_per_second": 22.503,
|
| 402 |
+
"EMA_steps_per_second": 22.503,
|
| 403 |
+
"epoch": 10.0,
|
| 404 |
+
"step": 450
|
| 405 |
}
|
| 406 |
],
|
| 407 |
"logging_steps": 10,
|
|
|
|
| 421 |
"attributes": {}
|
| 422 |
}
|
| 423 |
},
|
| 424 |
+
"total_flos": 4801636770840576.0,
|
| 425 |
"train_batch_size": 2,
|
| 426 |
"trial_name": null,
|
| 427 |
"trial_params": null
|