Training in progress, step 150, 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 sha256:76199f37550c237193e7b172a4297285627e555188041cbdb5f430cc437dd10c
|
| 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 1054135994
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c69a1783019f52033c5a249284550e08bebe3ffdf70a26f751e68f27100aba90
|
| 3 |
size 1054135994
|
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 sha256:5feb56512e955691dc9bb9a1e37b9dd590e06a961d7d94560b679e2730b03194
|
| 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 sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,1752 +1,157 @@
|
|
| 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,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.43478260869565216,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 3e-06,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.8695652173913043,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
"learning_rate": 6e-06,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.3043478260869565,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
"learning_rate": 9e-06,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 1.7391304347826086,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
"learning_rate": 1.2e-05,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 2.1739130434782608,
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
"learning_rate": 1.5e-05,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 2.608695652173913,
|
| 48 |
-
"grad_norm": 2.
|
| 49 |
"learning_rate": 1.8e-05,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 3.0434782608695654,
|
| 55 |
-
"grad_norm": 1.
|
| 56 |
"learning_rate": 2.1e-05,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 3.4782608695652173,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
"learning_rate": 2.4e-05,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 3.9130434782608696,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
"learning_rate": 2.7000000000000002e-05,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 4.3478260869565215,
|
| 76 |
-
"grad_norm": 1.
|
| 77 |
"learning_rate": 3e-05,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 4.782608695652174,
|
| 83 |
-
"grad_norm": 2.
|
| 84 |
"learning_rate": 2.999999702723963e-05,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 5.217391304347826,
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
"learning_rate": 2.9999988108959687e-05,
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 5.6521739130434785,
|
| 97 |
-
"grad_norm": 1.
|
| 98 |
"learning_rate": 2.9999973245163716e-05,
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 6.086956521739131,
|
| 104 |
-
"grad_norm": 1.
|
| 105 |
"learning_rate": 2.99999524358576e-05,
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 6.521739130434782,
|
| 111 |
-
"grad_norm": 1.
|
| 112 |
"learning_rate": 2.9999925681049593e-05,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 6.521739130434782,
|
| 118 |
-
"eval_loss": 0.
|
| 119 |
-
"eval_runtime": 0.
|
| 120 |
-
"eval_samples_per_second": 20.
|
| 121 |
-
"eval_steps_per_second": 20.
|
| 122 |
"step": 150
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"Start_State_loss": 0.
|
| 126 |
-
"Start_State_runtime": 0.
|
| 127 |
-
"Start_State_samples_per_second":
|
| 128 |
-
"Start_State_steps_per_second":
|
| 129 |
"epoch": 6.521739130434782,
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"Raw_Model_loss": 0.
|
| 134 |
-
"Raw_Model_runtime": 0.
|
| 135 |
-
"Raw_Model_samples_per_second":
|
| 136 |
-
"Raw_Model_steps_per_second":
|
| 137 |
"epoch": 6.521739130434782,
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"SWA_loss": 0.
|
| 142 |
-
"SWA_runtime": 0.
|
| 143 |
-
"SWA_samples_per_second":
|
| 144 |
-
"SWA_steps_per_second":
|
| 145 |
"epoch": 6.521739130434782,
|
| 146 |
"step": 150
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"EMA_loss": 0.
|
| 150 |
-
"EMA_runtime": 0.
|
| 151 |
-
"EMA_samples_per_second":
|
| 152 |
-
"EMA_steps_per_second":
|
| 153 |
"epoch": 6.521739130434782,
|
| 154 |
"step": 150
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 6.956521739130435,
|
| 158 |
-
"grad_norm": 1.540475845336914,
|
| 159 |
-
"learning_rate": 2.9999892980750297e-05,
|
| 160 |
-
"loss": 0.6588,
|
| 161 |
-
"step": 160
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 7.391304347826087,
|
| 165 |
-
"grad_norm": 1.3461687564849854,
|
| 166 |
-
"learning_rate": 2.9999854334972675e-05,
|
| 167 |
-
"loss": 0.7388,
|
| 168 |
-
"step": 170
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 7.826086956521739,
|
| 172 |
-
"grad_norm": 1.7260714769363403,
|
| 173 |
-
"learning_rate": 2.999980974373204e-05,
|
| 174 |
-
"loss": 0.7293,
|
| 175 |
-
"step": 180
|
| 176 |
-
},
|
| 177 |
-
{
|
| 178 |
-
"epoch": 8.26086956521739,
|
| 179 |
-
"grad_norm": 1.5399173498153687,
|
| 180 |
-
"learning_rate": 2.9999759207046075e-05,
|
| 181 |
-
"loss": 0.6241,
|
| 182 |
-
"step": 190
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 8.695652173913043,
|
| 186 |
-
"grad_norm": 1.742655634880066,
|
| 187 |
-
"learning_rate": 2.9999702724934804e-05,
|
| 188 |
-
"loss": 0.6766,
|
| 189 |
-
"step": 200
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 9.130434782608695,
|
| 193 |
-
"grad_norm": 1.0411487817764282,
|
| 194 |
-
"learning_rate": 2.999964029742062e-05,
|
| 195 |
-
"loss": 0.6524,
|
| 196 |
-
"step": 210
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 9.565217391304348,
|
| 200 |
-
"grad_norm": 1.2126989364624023,
|
| 201 |
-
"learning_rate": 2.9999571924528263e-05,
|
| 202 |
-
"loss": 0.559,
|
| 203 |
-
"step": 220
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 10.0,
|
| 207 |
-
"grad_norm": 1.5287680625915527,
|
| 208 |
-
"learning_rate": 2.9999497606284837e-05,
|
| 209 |
-
"loss": 0.7561,
|
| 210 |
-
"step": 230
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 10.434782608695652,
|
| 214 |
-
"grad_norm": 1.4217031002044678,
|
| 215 |
-
"learning_rate": 2.9999417342719796e-05,
|
| 216 |
-
"loss": 0.712,
|
| 217 |
-
"step": 240
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 10.869565217391305,
|
| 221 |
-
"grad_norm": 0.9795515537261963,
|
| 222 |
-
"learning_rate": 2.9999331133864956e-05,
|
| 223 |
-
"loss": 0.5899,
|
| 224 |
-
"step": 250
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 11.304347826086957,
|
| 228 |
-
"grad_norm": 1.1940442323684692,
|
| 229 |
-
"learning_rate": 2.9999238979754485e-05,
|
| 230 |
-
"loss": 0.6546,
|
| 231 |
-
"step": 260
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 11.73913043478261,
|
| 235 |
-
"grad_norm": 1.0492786169052124,
|
| 236 |
-
"learning_rate": 2.999914088042492e-05,
|
| 237 |
-
"loss": 0.6477,
|
| 238 |
-
"step": 270
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"epoch": 12.173913043478262,
|
| 242 |
-
"grad_norm": 1.31123685836792,
|
| 243 |
-
"learning_rate": 2.9999036835915132e-05,
|
| 244 |
-
"loss": 0.5938,
|
| 245 |
-
"step": 280
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 12.608695652173914,
|
| 249 |
-
"grad_norm": 1.084313154220581,
|
| 250 |
-
"learning_rate": 2.9998926846266365e-05,
|
| 251 |
-
"loss": 0.6327,
|
| 252 |
-
"step": 290
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 13.043478260869565,
|
| 256 |
-
"grad_norm": 1.387447476387024,
|
| 257 |
-
"learning_rate": 2.9998810911522213e-05,
|
| 258 |
-
"loss": 0.5806,
|
| 259 |
-
"step": 300
|
| 260 |
-
},
|
| 261 |
-
{
|
| 262 |
-
"epoch": 13.043478260869565,
|
| 263 |
-
"eval_loss": 0.7309158444404602,
|
| 264 |
-
"eval_runtime": 0.4907,
|
| 265 |
-
"eval_samples_per_second": 20.379,
|
| 266 |
-
"eval_steps_per_second": 20.379,
|
| 267 |
-
"step": 300
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"Start_State_loss": 0.8601926565170288,
|
| 271 |
-
"Start_State_runtime": 0.4,
|
| 272 |
-
"Start_State_samples_per_second": 25.001,
|
| 273 |
-
"Start_State_steps_per_second": 25.001,
|
| 274 |
-
"epoch": 13.043478260869565,
|
| 275 |
-
"step": 300
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"Raw_Model_loss": 0.7309158444404602,
|
| 279 |
-
"Raw_Model_runtime": 0.4036,
|
| 280 |
-
"Raw_Model_samples_per_second": 24.778,
|
| 281 |
-
"Raw_Model_steps_per_second": 24.778,
|
| 282 |
-
"epoch": 13.043478260869565,
|
| 283 |
-
"step": 300
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"SWA_loss": 0.775052011013031,
|
| 287 |
-
"SWA_runtime": 0.3988,
|
| 288 |
-
"SWA_samples_per_second": 25.072,
|
| 289 |
-
"SWA_steps_per_second": 25.072,
|
| 290 |
-
"epoch": 13.043478260869565,
|
| 291 |
-
"step": 300
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"EMA_loss": 0.8610683679580688,
|
| 295 |
-
"EMA_runtime": 0.3974,
|
| 296 |
-
"EMA_samples_per_second": 25.163,
|
| 297 |
-
"EMA_steps_per_second": 25.163,
|
| 298 |
-
"epoch": 13.043478260869565,
|
| 299 |
-
"step": 300
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 13.478260869565217,
|
| 303 |
-
"grad_norm": 1.78074312210083,
|
| 304 |
-
"learning_rate": 2.9998689031728636e-05,
|
| 305 |
-
"loss": 0.5146,
|
| 306 |
-
"step": 310
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"epoch": 13.91304347826087,
|
| 310 |
-
"grad_norm": 1.5320613384246826,
|
| 311 |
-
"learning_rate": 2.9998561206933938e-05,
|
| 312 |
-
"loss": 0.6499,
|
| 313 |
-
"step": 320
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 14.347826086956522,
|
| 317 |
-
"grad_norm": 1.4800745248794556,
|
| 318 |
-
"learning_rate": 2.9998427437188786e-05,
|
| 319 |
-
"loss": 0.5743,
|
| 320 |
-
"step": 330
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 14.782608695652174,
|
| 324 |
-
"grad_norm": 1.3194001913070679,
|
| 325 |
-
"learning_rate": 2.99982877225462e-05,
|
| 326 |
-
"loss": 0.6013,
|
| 327 |
-
"step": 340
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 15.217391304347826,
|
| 331 |
-
"grad_norm": 0.9749765992164612,
|
| 332 |
-
"learning_rate": 2.9998142063061564e-05,
|
| 333 |
-
"loss": 0.4989,
|
| 334 |
-
"step": 350
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 15.652173913043478,
|
| 338 |
-
"grad_norm": 1.6396143436431885,
|
| 339 |
-
"learning_rate": 2.9997990458792603e-05,
|
| 340 |
-
"loss": 0.5624,
|
| 341 |
-
"step": 360
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 16.08695652173913,
|
| 345 |
-
"grad_norm": 1.6343810558319092,
|
| 346 |
-
"learning_rate": 2.9997832909799417e-05,
|
| 347 |
-
"loss": 0.6672,
|
| 348 |
-
"step": 370
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 16.52173913043478,
|
| 352 |
-
"grad_norm": 0.9520325660705566,
|
| 353 |
-
"learning_rate": 2.9997669416144452e-05,
|
| 354 |
-
"loss": 0.5129,
|
| 355 |
-
"step": 380
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 16.956521739130434,
|
| 359 |
-
"grad_norm": 0.9396904706954956,
|
| 360 |
-
"learning_rate": 2.999749997789251e-05,
|
| 361 |
-
"loss": 0.5795,
|
| 362 |
-
"step": 390
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 17.391304347826086,
|
| 366 |
-
"grad_norm": 1.112286925315857,
|
| 367 |
-
"learning_rate": 2.9997324595110743e-05,
|
| 368 |
-
"loss": 0.5178,
|
| 369 |
-
"step": 400
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 17.82608695652174,
|
| 373 |
-
"grad_norm": 1.2840179204940796,
|
| 374 |
-
"learning_rate": 2.9997143267868683e-05,
|
| 375 |
-
"loss": 0.588,
|
| 376 |
-
"step": 410
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 18.26086956521739,
|
| 380 |
-
"grad_norm": 1.1637977361679077,
|
| 381 |
-
"learning_rate": 2.9996955996238192e-05,
|
| 382 |
-
"loss": 0.5057,
|
| 383 |
-
"step": 420
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 18.695652173913043,
|
| 387 |
-
"grad_norm": 1.201230525970459,
|
| 388 |
-
"learning_rate": 2.9996762780293503e-05,
|
| 389 |
-
"loss": 0.5316,
|
| 390 |
-
"step": 430
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 19.130434782608695,
|
| 394 |
-
"grad_norm": 1.2127166986465454,
|
| 395 |
-
"learning_rate": 2.9996563620111197e-05,
|
| 396 |
-
"loss": 0.5336,
|
| 397 |
-
"step": 440
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 19.565217391304348,
|
| 401 |
-
"grad_norm": 1.4246900081634521,
|
| 402 |
-
"learning_rate": 2.9996358515770218e-05,
|
| 403 |
-
"loss": 0.5677,
|
| 404 |
-
"step": 450
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 19.565217391304348,
|
| 408 |
-
"eval_loss": 0.7166430950164795,
|
| 409 |
-
"eval_runtime": 0.4285,
|
| 410 |
-
"eval_samples_per_second": 23.338,
|
| 411 |
-
"eval_steps_per_second": 23.338,
|
| 412 |
-
"step": 450
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"Start_State_loss": 0.8601926565170288,
|
| 416 |
-
"Start_State_runtime": 0.4149,
|
| 417 |
-
"Start_State_samples_per_second": 24.102,
|
| 418 |
-
"Start_State_steps_per_second": 24.102,
|
| 419 |
-
"epoch": 19.565217391304348,
|
| 420 |
-
"step": 450
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"Raw_Model_loss": 0.7166430950164795,
|
| 424 |
-
"Raw_Model_runtime": 0.4174,
|
| 425 |
-
"Raw_Model_samples_per_second": 23.957,
|
| 426 |
-
"Raw_Model_steps_per_second": 23.957,
|
| 427 |
-
"epoch": 19.565217391304348,
|
| 428 |
-
"step": 450
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"SWA_loss": 0.7559167146682739,
|
| 432 |
-
"SWA_runtime": 0.4126,
|
| 433 |
-
"SWA_samples_per_second": 24.237,
|
| 434 |
-
"SWA_steps_per_second": 24.237,
|
| 435 |
-
"epoch": 19.565217391304348,
|
| 436 |
-
"step": 450
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"EMA_loss": 0.8612796664237976,
|
| 440 |
-
"EMA_runtime": 0.4269,
|
| 441 |
-
"EMA_samples_per_second": 23.424,
|
| 442 |
-
"EMA_steps_per_second": 23.424,
|
| 443 |
-
"epoch": 19.565217391304348,
|
| 444 |
-
"step": 450
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 20.0,
|
| 448 |
-
"grad_norm": 2.1295206546783447,
|
| 449 |
-
"learning_rate": 2.9996147467351856e-05,
|
| 450 |
-
"loss": 0.5146,
|
| 451 |
-
"step": 460
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 20.434782608695652,
|
| 455 |
-
"grad_norm": 1.2770106792449951,
|
| 456 |
-
"learning_rate": 2.9995930474939773e-05,
|
| 457 |
-
"loss": 0.4784,
|
| 458 |
-
"step": 470
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 20.869565217391305,
|
| 462 |
-
"grad_norm": 1.4706833362579346,
|
| 463 |
-
"learning_rate": 2.9995707538619975e-05,
|
| 464 |
-
"loss": 0.5705,
|
| 465 |
-
"step": 480
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 21.304347826086957,
|
| 469 |
-
"grad_norm": 1.3234336376190186,
|
| 470 |
-
"learning_rate": 2.9995478658480822e-05,
|
| 471 |
-
"loss": 0.5167,
|
| 472 |
-
"step": 490
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 21.73913043478261,
|
| 476 |
-
"grad_norm": 1.242873191833496,
|
| 477 |
-
"learning_rate": 2.9995243834613043e-05,
|
| 478 |
-
"loss": 0.5207,
|
| 479 |
-
"step": 500
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 22.17391304347826,
|
| 483 |
-
"grad_norm": 1.77828049659729,
|
| 484 |
-
"learning_rate": 2.9995003067109707e-05,
|
| 485 |
-
"loss": 0.4832,
|
| 486 |
-
"step": 510
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 22.608695652173914,
|
| 490 |
-
"grad_norm": 1.5282888412475586,
|
| 491 |
-
"learning_rate": 2.9994756356066246e-05,
|
| 492 |
-
"loss": 0.5615,
|
| 493 |
-
"step": 520
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 23.043478260869566,
|
| 497 |
-
"grad_norm": 1.7345402240753174,
|
| 498 |
-
"learning_rate": 2.999450370158046e-05,
|
| 499 |
-
"loss": 0.4929,
|
| 500 |
-
"step": 530
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 23.47826086956522,
|
| 504 |
-
"grad_norm": 1.3091520071029663,
|
| 505 |
-
"learning_rate": 2.9994245103752478e-05,
|
| 506 |
-
"loss": 0.4383,
|
| 507 |
-
"step": 540
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 23.91304347826087,
|
| 511 |
-
"grad_norm": 1.2344285249710083,
|
| 512 |
-
"learning_rate": 2.999398056268481e-05,
|
| 513 |
-
"loss": 0.5264,
|
| 514 |
-
"step": 550
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 24.347826086956523,
|
| 518 |
-
"grad_norm": 1.409712791442871,
|
| 519 |
-
"learning_rate": 2.9993710078482306e-05,
|
| 520 |
-
"loss": 0.5206,
|
| 521 |
-
"step": 560
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 24.782608695652176,
|
| 525 |
-
"grad_norm": 0.9513388872146606,
|
| 526 |
-
"learning_rate": 2.9993433651252185e-05,
|
| 527 |
-
"loss": 0.443,
|
| 528 |
-
"step": 570
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 25.217391304347824,
|
| 532 |
-
"grad_norm": 1.7172473669052124,
|
| 533 |
-
"learning_rate": 2.9993151281104006e-05,
|
| 534 |
-
"loss": 0.5329,
|
| 535 |
-
"step": 580
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 25.652173913043477,
|
| 539 |
-
"grad_norm": 1.1298749446868896,
|
| 540 |
-
"learning_rate": 2.9992862968149695e-05,
|
| 541 |
-
"loss": 0.4737,
|
| 542 |
-
"step": 590
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 26.08695652173913,
|
| 546 |
-
"grad_norm": 1.1705174446105957,
|
| 547 |
-
"learning_rate": 2.9992568712503533e-05,
|
| 548 |
-
"loss": 0.4611,
|
| 549 |
-
"step": 600
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 26.08695652173913,
|
| 553 |
-
"eval_loss": 0.7199234366416931,
|
| 554 |
-
"eval_runtime": 0.4236,
|
| 555 |
-
"eval_samples_per_second": 23.605,
|
| 556 |
-
"eval_steps_per_second": 23.605,
|
| 557 |
-
"step": 600
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"Start_State_loss": 0.8601926565170288,
|
| 561 |
-
"Start_State_runtime": 0.4141,
|
| 562 |
-
"Start_State_samples_per_second": 24.146,
|
| 563 |
-
"Start_State_steps_per_second": 24.146,
|
| 564 |
-
"epoch": 26.08695652173913,
|
| 565 |
-
"step": 600
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"Raw_Model_loss": 0.7199234366416931,
|
| 569 |
-
"Raw_Model_runtime": 0.4101,
|
| 570 |
-
"Raw_Model_samples_per_second": 24.387,
|
| 571 |
-
"Raw_Model_steps_per_second": 24.387,
|
| 572 |
-
"epoch": 26.08695652173913,
|
| 573 |
-
"step": 600
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"SWA_loss": 0.7341524362564087,
|
| 577 |
-
"SWA_runtime": 0.4412,
|
| 578 |
-
"SWA_samples_per_second": 22.668,
|
| 579 |
-
"SWA_steps_per_second": 22.668,
|
| 580 |
-
"epoch": 26.08695652173913,
|
| 581 |
-
"step": 600
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"EMA_loss": 0.8609703183174133,
|
| 585 |
-
"EMA_runtime": 0.424,
|
| 586 |
-
"EMA_samples_per_second": 23.585,
|
| 587 |
-
"EMA_steps_per_second": 23.585,
|
| 588 |
-
"epoch": 26.08695652173913,
|
| 589 |
-
"step": 600
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"epoch": 26.52173913043478,
|
| 593 |
-
"grad_norm": 1.0925955772399902,
|
| 594 |
-
"learning_rate": 2.9992268514282142e-05,
|
| 595 |
-
"loss": 0.5116,
|
| 596 |
-
"step": 610
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 26.956521739130434,
|
| 600 |
-
"grad_norm": 1.343130111694336,
|
| 601 |
-
"learning_rate": 2.999196237360452e-05,
|
| 602 |
-
"loss": 0.4316,
|
| 603 |
-
"step": 620
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 27.391304347826086,
|
| 607 |
-
"grad_norm": 1.203368902206421,
|
| 608 |
-
"learning_rate": 2.9991650290592016e-05,
|
| 609 |
-
"loss": 0.4756,
|
| 610 |
-
"step": 630
|
| 611 |
-
},
|
| 612 |
-
{
|
| 613 |
-
"epoch": 27.82608695652174,
|
| 614 |
-
"grad_norm": 1.3935104608535767,
|
| 615 |
-
"learning_rate": 2.999133226536832e-05,
|
| 616 |
-
"loss": 0.501,
|
| 617 |
-
"step": 640
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 28.26086956521739,
|
| 621 |
-
"grad_norm": 1.412856936454773,
|
| 622 |
-
"learning_rate": 2.9991008298059493e-05,
|
| 623 |
-
"loss": 0.4107,
|
| 624 |
-
"step": 650
|
| 625 |
-
},
|
| 626 |
-
{
|
| 627 |
-
"epoch": 28.695652173913043,
|
| 628 |
-
"grad_norm": 1.5606491565704346,
|
| 629 |
-
"learning_rate": 2.9990678388793944e-05,
|
| 630 |
-
"loss": 0.5064,
|
| 631 |
-
"step": 660
|
| 632 |
-
},
|
| 633 |
-
{
|
| 634 |
-
"epoch": 29.130434782608695,
|
| 635 |
-
"grad_norm": 1.315181016921997,
|
| 636 |
-
"learning_rate": 2.999034253770244e-05,
|
| 637 |
-
"loss": 0.4347,
|
| 638 |
-
"step": 670
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 29.565217391304348,
|
| 642 |
-
"grad_norm": 1.077691674232483,
|
| 643 |
-
"learning_rate": 2.9990000744918097e-05,
|
| 644 |
-
"loss": 0.4705,
|
| 645 |
-
"step": 680
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"epoch": 30.0,
|
| 649 |
-
"grad_norm": 2.501568078994751,
|
| 650 |
-
"learning_rate": 2.9989653010576392e-05,
|
| 651 |
-
"loss": 0.4145,
|
| 652 |
-
"step": 690
|
| 653 |
-
},
|
| 654 |
-
{
|
| 655 |
-
"epoch": 30.434782608695652,
|
| 656 |
-
"grad_norm": 1.3340367078781128,
|
| 657 |
-
"learning_rate": 2.9989299334815158e-05,
|
| 658 |
-
"loss": 0.4764,
|
| 659 |
-
"step": 700
|
| 660 |
-
},
|
| 661 |
-
{
|
| 662 |
-
"epoch": 30.869565217391305,
|
| 663 |
-
"grad_norm": 1.6282958984375,
|
| 664 |
-
"learning_rate": 2.9988939717774578e-05,
|
| 665 |
-
"loss": 0.4118,
|
| 666 |
-
"step": 710
|
| 667 |
-
},
|
| 668 |
-
{
|
| 669 |
-
"epoch": 31.304347826086957,
|
| 670 |
-
"grad_norm": 0.9019575119018555,
|
| 671 |
-
"learning_rate": 2.9988574159597194e-05,
|
| 672 |
-
"loss": 0.4244,
|
| 673 |
-
"step": 720
|
| 674 |
-
},
|
| 675 |
-
{
|
| 676 |
-
"epoch": 31.73913043478261,
|
| 677 |
-
"grad_norm": 1.6408599615097046,
|
| 678 |
-
"learning_rate": 2.9988202660427907e-05,
|
| 679 |
-
"loss": 0.4821,
|
| 680 |
-
"step": 730
|
| 681 |
-
},
|
| 682 |
-
{
|
| 683 |
-
"epoch": 32.17391304347826,
|
| 684 |
-
"grad_norm": 1.1973698139190674,
|
| 685 |
-
"learning_rate": 2.9987825220413958e-05,
|
| 686 |
-
"loss": 0.4385,
|
| 687 |
-
"step": 740
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 32.608695652173914,
|
| 691 |
-
"grad_norm": 1.7692193984985352,
|
| 692 |
-
"learning_rate": 2.998744183970496e-05,
|
| 693 |
-
"loss": 0.4738,
|
| 694 |
-
"step": 750
|
| 695 |
-
},
|
| 696 |
-
{
|
| 697 |
-
"epoch": 32.608695652173914,
|
| 698 |
-
"eval_loss": 0.731913149356842,
|
| 699 |
-
"eval_runtime": 0.5751,
|
| 700 |
-
"eval_samples_per_second": 17.389,
|
| 701 |
-
"eval_steps_per_second": 17.389,
|
| 702 |
-
"step": 750
|
| 703 |
-
},
|
| 704 |
-
{
|
| 705 |
-
"Start_State_loss": 0.8601926565170288,
|
| 706 |
-
"Start_State_runtime": 0.4166,
|
| 707 |
-
"Start_State_samples_per_second": 24.004,
|
| 708 |
-
"Start_State_steps_per_second": 24.004,
|
| 709 |
-
"epoch": 32.608695652173914,
|
| 710 |
-
"step": 750
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"Raw_Model_loss": 0.731913149356842,
|
| 714 |
-
"Raw_Model_runtime": 0.402,
|
| 715 |
-
"Raw_Model_samples_per_second": 24.875,
|
| 716 |
-
"Raw_Model_steps_per_second": 24.875,
|
| 717 |
-
"epoch": 32.608695652173914,
|
| 718 |
-
"step": 750
|
| 719 |
-
},
|
| 720 |
-
{
|
| 721 |
-
"SWA_loss": 0.7290045022964478,
|
| 722 |
-
"SWA_runtime": 0.4054,
|
| 723 |
-
"SWA_samples_per_second": 24.666,
|
| 724 |
-
"SWA_steps_per_second": 24.666,
|
| 725 |
-
"epoch": 32.608695652173914,
|
| 726 |
-
"step": 750
|
| 727 |
-
},
|
| 728 |
-
{
|
| 729 |
-
"EMA_loss": 0.8603373765945435,
|
| 730 |
-
"EMA_runtime": 0.4026,
|
| 731 |
-
"EMA_samples_per_second": 24.839,
|
| 732 |
-
"EMA_steps_per_second": 24.839,
|
| 733 |
-
"epoch": 32.608695652173914,
|
| 734 |
-
"step": 750
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 33.04347826086956,
|
| 738 |
-
"grad_norm": 1.4949195384979248,
|
| 739 |
-
"learning_rate": 2.998705251845287e-05,
|
| 740 |
-
"loss": 0.43,
|
| 741 |
-
"step": 760
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 33.47826086956522,
|
| 745 |
-
"grad_norm": 1.6518038511276245,
|
| 746 |
-
"learning_rate": 2.9986657256812e-05,
|
| 747 |
-
"loss": 0.4301,
|
| 748 |
-
"step": 770
|
| 749 |
-
},
|
| 750 |
-
{
|
| 751 |
-
"epoch": 33.91304347826087,
|
| 752 |
-
"grad_norm": 1.2894669771194458,
|
| 753 |
-
"learning_rate": 2.9986256054939022e-05,
|
| 754 |
-
"loss": 0.408,
|
| 755 |
-
"step": 780
|
| 756 |
-
},
|
| 757 |
-
{
|
| 758 |
-
"epoch": 34.34782608695652,
|
| 759 |
-
"grad_norm": 1.4762516021728516,
|
| 760 |
-
"learning_rate": 2.9985848912992956e-05,
|
| 761 |
-
"loss": 0.4029,
|
| 762 |
-
"step": 790
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"epoch": 34.78260869565217,
|
| 766 |
-
"grad_norm": 1.5660409927368164,
|
| 767 |
-
"learning_rate": 2.9985435831135184e-05,
|
| 768 |
-
"loss": 0.3832,
|
| 769 |
-
"step": 800
|
| 770 |
-
},
|
| 771 |
-
{
|
| 772 |
-
"epoch": 35.21739130434783,
|
| 773 |
-
"grad_norm": 1.3075863122940063,
|
| 774 |
-
"learning_rate": 2.9985016809529437e-05,
|
| 775 |
-
"loss": 0.4744,
|
| 776 |
-
"step": 810
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 35.65217391304348,
|
| 780 |
-
"grad_norm": 1.3411126136779785,
|
| 781 |
-
"learning_rate": 2.9984591848341806e-05,
|
| 782 |
-
"loss": 0.403,
|
| 783 |
-
"step": 820
|
| 784 |
-
},
|
| 785 |
-
{
|
| 786 |
-
"epoch": 36.08695652173913,
|
| 787 |
-
"grad_norm": 1.0828583240509033,
|
| 788 |
-
"learning_rate": 2.9984160947740723e-05,
|
| 789 |
-
"loss": 0.4181,
|
| 790 |
-
"step": 830
|
| 791 |
-
},
|
| 792 |
-
{
|
| 793 |
-
"epoch": 36.52173913043478,
|
| 794 |
-
"grad_norm": 1.1622037887573242,
|
| 795 |
-
"learning_rate": 2.9983724107896993e-05,
|
| 796 |
-
"loss": 0.3806,
|
| 797 |
-
"step": 840
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 36.95652173913044,
|
| 801 |
-
"grad_norm": 1.4791110754013062,
|
| 802 |
-
"learning_rate": 2.9983281328983757e-05,
|
| 803 |
-
"loss": 0.4499,
|
| 804 |
-
"step": 850
|
| 805 |
-
},
|
| 806 |
-
{
|
| 807 |
-
"epoch": 37.391304347826086,
|
| 808 |
-
"grad_norm": 1.8963046073913574,
|
| 809 |
-
"learning_rate": 2.9982832611176523e-05,
|
| 810 |
-
"loss": 0.4181,
|
| 811 |
-
"step": 860
|
| 812 |
-
},
|
| 813 |
-
{
|
| 814 |
-
"epoch": 37.82608695652174,
|
| 815 |
-
"grad_norm": 1.270815372467041,
|
| 816 |
-
"learning_rate": 2.998237795465315e-05,
|
| 817 |
-
"loss": 0.3714,
|
| 818 |
-
"step": 870
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 38.26086956521739,
|
| 822 |
-
"grad_norm": 1.264829397201538,
|
| 823 |
-
"learning_rate": 2.9981917359593843e-05,
|
| 824 |
-
"loss": 0.4013,
|
| 825 |
-
"step": 880
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 38.69565217391305,
|
| 829 |
-
"grad_norm": 1.4431074857711792,
|
| 830 |
-
"learning_rate": 2.9981450826181172e-05,
|
| 831 |
-
"loss": 0.3552,
|
| 832 |
-
"step": 890
|
| 833 |
-
},
|
| 834 |
-
{
|
| 835 |
-
"epoch": 39.130434782608695,
|
| 836 |
-
"grad_norm": 1.9556941986083984,
|
| 837 |
-
"learning_rate": 2.9980978354600057e-05,
|
| 838 |
-
"loss": 0.463,
|
| 839 |
-
"step": 900
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 39.130434782608695,
|
| 843 |
-
"eval_loss": 0.7511647343635559,
|
| 844 |
-
"eval_runtime": 0.4145,
|
| 845 |
-
"eval_samples_per_second": 24.126,
|
| 846 |
-
"eval_steps_per_second": 24.126,
|
| 847 |
-
"step": 900
|
| 848 |
-
},
|
| 849 |
-
{
|
| 850 |
-
"Start_State_loss": 0.8601926565170288,
|
| 851 |
-
"Start_State_runtime": 0.4115,
|
| 852 |
-
"Start_State_samples_per_second": 24.303,
|
| 853 |
-
"Start_State_steps_per_second": 24.303,
|
| 854 |
-
"epoch": 39.130434782608695,
|
| 855 |
-
"step": 900
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"Raw_Model_loss": 0.7511647343635559,
|
| 859 |
-
"Raw_Model_runtime": 0.399,
|
| 860 |
-
"Raw_Model_samples_per_second": 25.063,
|
| 861 |
-
"Raw_Model_steps_per_second": 25.063,
|
| 862 |
-
"epoch": 39.130434782608695,
|
| 863 |
-
"step": 900
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"SWA_loss": 0.7235903739929199,
|
| 867 |
-
"SWA_runtime": 0.3941,
|
| 868 |
-
"SWA_samples_per_second": 25.377,
|
| 869 |
-
"SWA_steps_per_second": 25.377,
|
| 870 |
-
"epoch": 39.130434782608695,
|
| 871 |
-
"step": 900
|
| 872 |
-
},
|
| 873 |
-
{
|
| 874 |
-
"EMA_loss": 0.8609917759895325,
|
| 875 |
-
"EMA_runtime": 0.3995,
|
| 876 |
-
"EMA_samples_per_second": 25.033,
|
| 877 |
-
"EMA_steps_per_second": 25.033,
|
| 878 |
-
"epoch": 39.130434782608695,
|
| 879 |
-
"step": 900
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 39.56521739130435,
|
| 883 |
-
"grad_norm": 1.542538046836853,
|
| 884 |
-
"learning_rate": 2.9980499945037765e-05,
|
| 885 |
-
"loss": 0.3835,
|
| 886 |
-
"step": 910
|
| 887 |
-
},
|
| 888 |
-
{
|
| 889 |
-
"epoch": 40.0,
|
| 890 |
-
"grad_norm": 3.0124218463897705,
|
| 891 |
-
"learning_rate": 2.998001559768393e-05,
|
| 892 |
-
"loss": 0.3867,
|
| 893 |
-
"step": 920
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"epoch": 40.43478260869565,
|
| 897 |
-
"grad_norm": 1.5339196920394897,
|
| 898 |
-
"learning_rate": 2.9979525312730525e-05,
|
| 899 |
-
"loss": 0.4492,
|
| 900 |
-
"step": 930
|
| 901 |
-
},
|
| 902 |
-
{
|
| 903 |
-
"epoch": 40.869565217391305,
|
| 904 |
-
"grad_norm": 1.6727086305618286,
|
| 905 |
-
"learning_rate": 2.9979029090371885e-05,
|
| 906 |
-
"loss": 0.3412,
|
| 907 |
-
"step": 940
|
| 908 |
-
},
|
| 909 |
-
{
|
| 910 |
-
"epoch": 41.30434782608695,
|
| 911 |
-
"grad_norm": 2.2182319164276123,
|
| 912 |
-
"learning_rate": 2.99785269308047e-05,
|
| 913 |
-
"loss": 0.3413,
|
| 914 |
-
"step": 950
|
| 915 |
-
},
|
| 916 |
-
{
|
| 917 |
-
"epoch": 41.73913043478261,
|
| 918 |
-
"grad_norm": 1.5122953653335571,
|
| 919 |
-
"learning_rate": 2.9978018834228007e-05,
|
| 920 |
-
"loss": 0.365,
|
| 921 |
-
"step": 960
|
| 922 |
-
},
|
| 923 |
-
{
|
| 924 |
-
"epoch": 42.17391304347826,
|
| 925 |
-
"grad_norm": 1.5070980787277222,
|
| 926 |
-
"learning_rate": 2.9977504800843197e-05,
|
| 927 |
-
"loss": 0.4346,
|
| 928 |
-
"step": 970
|
| 929 |
-
},
|
| 930 |
-
{
|
| 931 |
-
"epoch": 42.608695652173914,
|
| 932 |
-
"grad_norm": 1.5313963890075684,
|
| 933 |
-
"learning_rate": 2.9976984830854022e-05,
|
| 934 |
-
"loss": 0.3752,
|
| 935 |
-
"step": 980
|
| 936 |
-
},
|
| 937 |
-
{
|
| 938 |
-
"epoch": 43.04347826086956,
|
| 939 |
-
"grad_norm": 1.653640866279602,
|
| 940 |
-
"learning_rate": 2.997645892446658e-05,
|
| 941 |
-
"loss": 0.367,
|
| 942 |
-
"step": 990
|
| 943 |
-
},
|
| 944 |
-
{
|
| 945 |
-
"epoch": 43.47826086956522,
|
| 946 |
-
"grad_norm": 1.4292306900024414,
|
| 947 |
-
"learning_rate": 2.9975927081889322e-05,
|
| 948 |
-
"loss": 0.391,
|
| 949 |
-
"step": 1000
|
| 950 |
-
},
|
| 951 |
-
{
|
| 952 |
-
"epoch": 43.91304347826087,
|
| 953 |
-
"grad_norm": 1.1838629245758057,
|
| 954 |
-
"learning_rate": 2.9975389303333047e-05,
|
| 955 |
-
"loss": 0.3456,
|
| 956 |
-
"step": 1010
|
| 957 |
-
},
|
| 958 |
-
{
|
| 959 |
-
"epoch": 44.34782608695652,
|
| 960 |
-
"grad_norm": 2.111812114715576,
|
| 961 |
-
"learning_rate": 2.997484558901093e-05,
|
| 962 |
-
"loss": 0.3922,
|
| 963 |
-
"step": 1020
|
| 964 |
-
},
|
| 965 |
-
{
|
| 966 |
-
"epoch": 44.78260869565217,
|
| 967 |
-
"grad_norm": 1.6915301084518433,
|
| 968 |
-
"learning_rate": 2.9974295939138465e-05,
|
| 969 |
-
"loss": 0.3804,
|
| 970 |
-
"step": 1030
|
| 971 |
-
},
|
| 972 |
-
{
|
| 973 |
-
"epoch": 45.21739130434783,
|
| 974 |
-
"grad_norm": 1.2465533018112183,
|
| 975 |
-
"learning_rate": 2.9973740353933523e-05,
|
| 976 |
-
"loss": 0.2648,
|
| 977 |
-
"step": 1040
|
| 978 |
-
},
|
| 979 |
-
{
|
| 980 |
-
"epoch": 45.65217391304348,
|
| 981 |
-
"grad_norm": 1.68025541305542,
|
| 982 |
-
"learning_rate": 2.997317883361632e-05,
|
| 983 |
-
"loss": 0.3611,
|
| 984 |
-
"step": 1050
|
| 985 |
-
},
|
| 986 |
-
{
|
| 987 |
-
"epoch": 45.65217391304348,
|
| 988 |
-
"eval_loss": 0.7759392261505127,
|
| 989 |
-
"eval_runtime": 0.5365,
|
| 990 |
-
"eval_samples_per_second": 18.64,
|
| 991 |
-
"eval_steps_per_second": 18.64,
|
| 992 |
-
"step": 1050
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"Start_State_loss": 0.8601926565170288,
|
| 996 |
-
"Start_State_runtime": 0.5037,
|
| 997 |
-
"Start_State_samples_per_second": 19.854,
|
| 998 |
-
"Start_State_steps_per_second": 19.854,
|
| 999 |
-
"epoch": 45.65217391304348,
|
| 1000 |
-
"step": 1050
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"Raw_Model_loss": 0.7759392261505127,
|
| 1004 |
-
"Raw_Model_runtime": 0.4675,
|
| 1005 |
-
"Raw_Model_samples_per_second": 21.389,
|
| 1006 |
-
"Raw_Model_steps_per_second": 21.389,
|
| 1007 |
-
"epoch": 45.65217391304348,
|
| 1008 |
-
"step": 1050
|
| 1009 |
-
},
|
| 1010 |
-
{
|
| 1011 |
-
"SWA_loss": 0.7227687835693359,
|
| 1012 |
-
"SWA_runtime": 0.4756,
|
| 1013 |
-
"SWA_samples_per_second": 21.025,
|
| 1014 |
-
"SWA_steps_per_second": 21.025,
|
| 1015 |
-
"epoch": 45.65217391304348,
|
| 1016 |
-
"step": 1050
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"EMA_loss": 0.8605559468269348,
|
| 1020 |
-
"EMA_runtime": 0.4881,
|
| 1021 |
-
"EMA_samples_per_second": 20.489,
|
| 1022 |
-
"EMA_steps_per_second": 20.489,
|
| 1023 |
-
"epoch": 45.65217391304348,
|
| 1024 |
-
"step": 1050
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 46.08695652173913,
|
| 1028 |
-
"grad_norm": 1.7922283411026,
|
| 1029 |
-
"learning_rate": 2.997261137840943e-05,
|
| 1030 |
-
"loss": 0.4104,
|
| 1031 |
-
"step": 1060
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 46.52173913043478,
|
| 1035 |
-
"grad_norm": 2.145780324935913,
|
| 1036 |
-
"learning_rate": 2.9972037988537758e-05,
|
| 1037 |
-
"loss": 0.3784,
|
| 1038 |
-
"step": 1070
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 46.95652173913044,
|
| 1042 |
-
"grad_norm": 1.9540642499923706,
|
| 1043 |
-
"learning_rate": 2.9971458664228595e-05,
|
| 1044 |
-
"loss": 0.3325,
|
| 1045 |
-
"step": 1080
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 47.391304347826086,
|
| 1049 |
-
"grad_norm": 2.150164842605591,
|
| 1050 |
-
"learning_rate": 2.997087340571156e-05,
|
| 1051 |
-
"loss": 0.3369,
|
| 1052 |
-
"step": 1090
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 47.82608695652174,
|
| 1056 |
-
"grad_norm": 1.539474606513977,
|
| 1057 |
-
"learning_rate": 2.997028221321863e-05,
|
| 1058 |
-
"loss": 0.3564,
|
| 1059 |
-
"step": 1100
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 48.26086956521739,
|
| 1063 |
-
"grad_norm": 2.3236191272735596,
|
| 1064 |
-
"learning_rate": 2.9969685086984132e-05,
|
| 1065 |
-
"loss": 0.3736,
|
| 1066 |
-
"step": 1110
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 48.69565217391305,
|
| 1070 |
-
"grad_norm": 1.6481757164001465,
|
| 1071 |
-
"learning_rate": 2.9969082027244755e-05,
|
| 1072 |
-
"loss": 0.2999,
|
| 1073 |
-
"step": 1120
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 49.130434782608695,
|
| 1077 |
-
"grad_norm": 1.8113096952438354,
|
| 1078 |
-
"learning_rate": 2.996847303423953e-05,
|
| 1079 |
-
"loss": 0.4149,
|
| 1080 |
-
"step": 1130
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 49.56521739130435,
|
| 1084 |
-
"grad_norm": 1.3106703758239746,
|
| 1085 |
-
"learning_rate": 2.9967858108209838e-05,
|
| 1086 |
-
"loss": 0.3714,
|
| 1087 |
-
"step": 1140
|
| 1088 |
-
},
|
| 1089 |
-
{
|
| 1090 |
-
"epoch": 50.0,
|
| 1091 |
-
"grad_norm": 2.9416587352752686,
|
| 1092 |
-
"learning_rate": 2.9967237249399417e-05,
|
| 1093 |
-
"loss": 0.292,
|
| 1094 |
-
"step": 1150
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 50.43478260869565,
|
| 1098 |
-
"grad_norm": 1.5631065368652344,
|
| 1099 |
-
"learning_rate": 2.996661045805436e-05,
|
| 1100 |
-
"loss": 0.2963,
|
| 1101 |
-
"step": 1160
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 50.869565217391305,
|
| 1105 |
-
"grad_norm": 1.8589760065078735,
|
| 1106 |
-
"learning_rate": 2.9965977734423106e-05,
|
| 1107 |
-
"loss": 0.3415,
|
| 1108 |
-
"step": 1170
|
| 1109 |
-
},
|
| 1110 |
-
{
|
| 1111 |
-
"epoch": 51.30434782608695,
|
| 1112 |
-
"grad_norm": 1.9185295104980469,
|
| 1113 |
-
"learning_rate": 2.9965339078756445e-05,
|
| 1114 |
-
"loss": 0.3539,
|
| 1115 |
-
"step": 1180
|
| 1116 |
-
},
|
| 1117 |
-
{
|
| 1118 |
-
"epoch": 51.73913043478261,
|
| 1119 |
-
"grad_norm": 1.1838868856430054,
|
| 1120 |
-
"learning_rate": 2.9964694491307514e-05,
|
| 1121 |
-
"loss": 0.2803,
|
| 1122 |
-
"step": 1190
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"epoch": 52.17391304347826,
|
| 1126 |
-
"grad_norm": 2.4929492473602295,
|
| 1127 |
-
"learning_rate": 2.996404397233182e-05,
|
| 1128 |
-
"loss": 0.4083,
|
| 1129 |
-
"step": 1200
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 52.17391304347826,
|
| 1133 |
-
"eval_loss": 0.8023056983947754,
|
| 1134 |
-
"eval_runtime": 0.4133,
|
| 1135 |
-
"eval_samples_per_second": 24.196,
|
| 1136 |
-
"eval_steps_per_second": 24.196,
|
| 1137 |
-
"step": 1200
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"Start_State_loss": 0.8601926565170288,
|
| 1141 |
-
"Start_State_runtime": 0.407,
|
| 1142 |
-
"Start_State_samples_per_second": 24.569,
|
| 1143 |
-
"Start_State_steps_per_second": 24.569,
|
| 1144 |
-
"epoch": 52.17391304347826,
|
| 1145 |
-
"step": 1200
|
| 1146 |
-
},
|
| 1147 |
-
{
|
| 1148 |
-
"Raw_Model_loss": 0.8023056983947754,
|
| 1149 |
-
"Raw_Model_runtime": 0.3981,
|
| 1150 |
-
"Raw_Model_samples_per_second": 25.122,
|
| 1151 |
-
"Raw_Model_steps_per_second": 25.122,
|
| 1152 |
-
"epoch": 52.17391304347826,
|
| 1153 |
-
"step": 1200
|
| 1154 |
-
},
|
| 1155 |
-
{
|
| 1156 |
-
"SWA_loss": 0.7237697243690491,
|
| 1157 |
-
"SWA_runtime": 0.4024,
|
| 1158 |
-
"SWA_samples_per_second": 24.852,
|
| 1159 |
-
"SWA_steps_per_second": 24.852,
|
| 1160 |
-
"epoch": 52.17391304347826,
|
| 1161 |
-
"step": 1200
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"EMA_loss": 0.8598647117614746,
|
| 1165 |
-
"EMA_runtime": 0.4326,
|
| 1166 |
-
"EMA_samples_per_second": 23.115,
|
| 1167 |
-
"EMA_steps_per_second": 23.115,
|
| 1168 |
-
"epoch": 52.17391304347826,
|
| 1169 |
-
"step": 1200
|
| 1170 |
-
},
|
| 1171 |
-
{
|
| 1172 |
-
"epoch": 52.608695652173914,
|
| 1173 |
-
"grad_norm": 1.6113795042037964,
|
| 1174 |
-
"learning_rate": 1.4982021986165911e-06,
|
| 1175 |
-
"loss": 0.2866,
|
| 1176 |
-
"step": 1210
|
| 1177 |
-
},
|
| 1178 |
-
{
|
| 1179 |
-
"epoch": 53.04347826086956,
|
| 1180 |
-
"grad_norm": 1.7770823240280151,
|
| 1181 |
-
"learning_rate": 2.9964043972331822e-06,
|
| 1182 |
-
"loss": 0.365,
|
| 1183 |
-
"step": 1220
|
| 1184 |
-
},
|
| 1185 |
-
{
|
| 1186 |
-
"epoch": 53.47826086956522,
|
| 1187 |
-
"grad_norm": 1.4132719039916992,
|
| 1188 |
-
"learning_rate": 4.494606595849773e-06,
|
| 1189 |
-
"loss": 0.2718,
|
| 1190 |
-
"step": 1230
|
| 1191 |
-
},
|
| 1192 |
-
{
|
| 1193 |
-
"epoch": 53.91304347826087,
|
| 1194 |
-
"grad_norm": 1.9334650039672852,
|
| 1195 |
-
"learning_rate": 5.9928087944663644e-06,
|
| 1196 |
-
"loss": 0.3338,
|
| 1197 |
-
"step": 1240
|
| 1198 |
-
},
|
| 1199 |
-
{
|
| 1200 |
-
"epoch": 54.34782608695652,
|
| 1201 |
-
"grad_norm": 1.9728986024856567,
|
| 1202 |
-
"learning_rate": 7.491010993082955e-06,
|
| 1203 |
-
"loss": 0.3853,
|
| 1204 |
-
"step": 1250
|
| 1205 |
-
},
|
| 1206 |
-
{
|
| 1207 |
-
"epoch": 54.78260869565217,
|
| 1208 |
-
"grad_norm": 1.1599531173706055,
|
| 1209 |
-
"learning_rate": 8.989213191699545e-06,
|
| 1210 |
-
"loss": 0.2838,
|
| 1211 |
-
"step": 1260
|
| 1212 |
-
},
|
| 1213 |
-
{
|
| 1214 |
-
"epoch": 55.21739130434783,
|
| 1215 |
-
"grad_norm": 1.558973789215088,
|
| 1216 |
-
"learning_rate": 1.0487415390316136e-05,
|
| 1217 |
-
"loss": 0.311,
|
| 1218 |
-
"step": 1270
|
| 1219 |
-
},
|
| 1220 |
-
{
|
| 1221 |
-
"epoch": 55.65217391304348,
|
| 1222 |
-
"grad_norm": 1.7310874462127686,
|
| 1223 |
-
"learning_rate": 1.1985617588932729e-05,
|
| 1224 |
-
"loss": 0.3553,
|
| 1225 |
-
"step": 1280
|
| 1226 |
-
},
|
| 1227 |
-
{
|
| 1228 |
-
"epoch": 56.08695652173913,
|
| 1229 |
-
"grad_norm": 2.2715365886688232,
|
| 1230 |
-
"learning_rate": 1.348381978754932e-05,
|
| 1231 |
-
"loss": 0.2844,
|
| 1232 |
-
"step": 1290
|
| 1233 |
-
},
|
| 1234 |
-
{
|
| 1235 |
-
"epoch": 56.52173913043478,
|
| 1236 |
-
"grad_norm": 1.467916488647461,
|
| 1237 |
-
"learning_rate": 1.498202198616591e-05,
|
| 1238 |
-
"loss": 0.3391,
|
| 1239 |
-
"step": 1300
|
| 1240 |
-
},
|
| 1241 |
-
{
|
| 1242 |
-
"epoch": 56.95652173913044,
|
| 1243 |
-
"grad_norm": 1.974404215812683,
|
| 1244 |
-
"learning_rate": 1.4982020501567203e-05,
|
| 1245 |
-
"loss": 0.3314,
|
| 1246 |
-
"step": 1310
|
| 1247 |
-
},
|
| 1248 |
-
{
|
| 1249 |
-
"epoch": 57.391304347826086,
|
| 1250 |
-
"grad_norm": 1.4068485498428345,
|
| 1251 |
-
"learning_rate": 1.4982016047771664e-05,
|
| 1252 |
-
"loss": 0.3113,
|
| 1253 |
-
"step": 1320
|
| 1254 |
-
},
|
| 1255 |
-
{
|
| 1256 |
-
"epoch": 57.82608695652174,
|
| 1257 |
-
"grad_norm": 2.7793936729431152,
|
| 1258 |
-
"learning_rate": 1.4982008624781062e-05,
|
| 1259 |
-
"loss": 0.3372,
|
| 1260 |
-
"step": 1330
|
| 1261 |
-
},
|
| 1262 |
-
{
|
| 1263 |
-
"epoch": 58.26086956521739,
|
| 1264 |
-
"grad_norm": 1.4399445056915283,
|
| 1265 |
-
"learning_rate": 1.4981998232598337e-05,
|
| 1266 |
-
"loss": 0.3301,
|
| 1267 |
-
"step": 1340
|
| 1268 |
-
},
|
| 1269 |
-
{
|
| 1270 |
-
"epoch": 58.69565217391305,
|
| 1271 |
-
"grad_norm": 1.8218740224838257,
|
| 1272 |
-
"learning_rate": 1.4981984871227611e-05,
|
| 1273 |
-
"loss": 0.3077,
|
| 1274 |
-
"step": 1350
|
| 1275 |
-
},
|
| 1276 |
-
{
|
| 1277 |
-
"epoch": 58.69565217391305,
|
| 1278 |
-
"eval_loss": 0.8209422826766968,
|
| 1279 |
-
"eval_runtime": 0.4642,
|
| 1280 |
-
"eval_samples_per_second": 21.544,
|
| 1281 |
-
"eval_steps_per_second": 21.544,
|
| 1282 |
-
"step": 1350
|
| 1283 |
-
},
|
| 1284 |
-
{
|
| 1285 |
-
"Start_State_loss": 0.8601926565170288,
|
| 1286 |
-
"Start_State_runtime": 0.4587,
|
| 1287 |
-
"Start_State_samples_per_second": 21.801,
|
| 1288 |
-
"Start_State_steps_per_second": 21.801,
|
| 1289 |
-
"epoch": 58.69565217391305,
|
| 1290 |
-
"step": 1350
|
| 1291 |
-
},
|
| 1292 |
-
{
|
| 1293 |
-
"Raw_Model_loss": 0.8209422826766968,
|
| 1294 |
-
"Raw_Model_runtime": 0.5144,
|
| 1295 |
-
"Raw_Model_samples_per_second": 19.438,
|
| 1296 |
-
"Raw_Model_steps_per_second": 19.438,
|
| 1297 |
-
"epoch": 58.69565217391305,
|
| 1298 |
-
"step": 1350
|
| 1299 |
-
},
|
| 1300 |
-
{
|
| 1301 |
-
"SWA_loss": 0.7251114249229431,
|
| 1302 |
-
"SWA_runtime": 0.4605,
|
| 1303 |
-
"SWA_samples_per_second": 21.718,
|
| 1304 |
-
"SWA_steps_per_second": 21.718,
|
| 1305 |
-
"epoch": 58.69565217391305,
|
| 1306 |
-
"step": 1350
|
| 1307 |
-
},
|
| 1308 |
-
{
|
| 1309 |
-
"EMA_loss": 0.8608489036560059,
|
| 1310 |
-
"EMA_runtime": 0.4317,
|
| 1311 |
-
"EMA_samples_per_second": 23.166,
|
| 1312 |
-
"EMA_steps_per_second": 23.166,
|
| 1313 |
-
"epoch": 58.69565217391305,
|
| 1314 |
-
"step": 1350
|
| 1315 |
-
},
|
| 1316 |
-
{
|
| 1317 |
-
"epoch": 59.130434782608695,
|
| 1318 |
-
"grad_norm": 1.5807944536209106,
|
| 1319 |
-
"learning_rate": 1.4981968540674177e-05,
|
| 1320 |
-
"loss": 0.3206,
|
| 1321 |
-
"step": 1360
|
| 1322 |
-
},
|
| 1323 |
-
{
|
| 1324 |
-
"epoch": 59.56521739130435,
|
| 1325 |
-
"grad_norm": 1.40355384349823,
|
| 1326 |
-
"learning_rate": 1.4981949240944509e-05,
|
| 1327 |
-
"loss": 0.3012,
|
| 1328 |
-
"step": 1370
|
| 1329 |
-
},
|
| 1330 |
-
{
|
| 1331 |
-
"epoch": 60.0,
|
| 1332 |
-
"grad_norm": 1.6165056228637695,
|
| 1333 |
-
"learning_rate": 1.4981926972046258e-05,
|
| 1334 |
-
"loss": 0.3098,
|
| 1335 |
-
"step": 1380
|
| 1336 |
-
},
|
| 1337 |
-
{
|
| 1338 |
-
"epoch": 60.43478260869565,
|
| 1339 |
-
"grad_norm": 1.9167027473449707,
|
| 1340 |
-
"learning_rate": 1.498190173398825e-05,
|
| 1341 |
-
"loss": 0.3171,
|
| 1342 |
-
"step": 1390
|
| 1343 |
-
},
|
| 1344 |
-
{
|
| 1345 |
-
"epoch": 60.869565217391305,
|
| 1346 |
-
"grad_norm": 1.539297342300415,
|
| 1347 |
-
"learning_rate": 1.4981873526780487e-05,
|
| 1348 |
-
"loss": 0.3049,
|
| 1349 |
-
"step": 1400
|
| 1350 |
-
},
|
| 1351 |
-
{
|
| 1352 |
-
"epoch": 61.30434782608695,
|
| 1353 |
-
"grad_norm": 1.4211211204528809,
|
| 1354 |
-
"learning_rate": 1.4981842350434152e-05,
|
| 1355 |
-
"loss": 0.3045,
|
| 1356 |
-
"step": 1410
|
| 1357 |
-
},
|
| 1358 |
-
{
|
| 1359 |
-
"epoch": 61.73913043478261,
|
| 1360 |
-
"grad_norm": 1.4864341020584106,
|
| 1361 |
-
"learning_rate": 1.49818082049616e-05,
|
| 1362 |
-
"loss": 0.3207,
|
| 1363 |
-
"step": 1420
|
| 1364 |
-
},
|
| 1365 |
-
{
|
| 1366 |
-
"epoch": 62.17391304347826,
|
| 1367 |
-
"grad_norm": 2.1776299476623535,
|
| 1368 |
-
"learning_rate": 1.4981771090376367e-05,
|
| 1369 |
-
"loss": 0.2862,
|
| 1370 |
-
"step": 1430
|
| 1371 |
-
},
|
| 1372 |
-
{
|
| 1373 |
-
"epoch": 62.608695652173914,
|
| 1374 |
-
"grad_norm": 1.8853501081466675,
|
| 1375 |
-
"learning_rate": 1.4981731006693164e-05,
|
| 1376 |
-
"loss": 0.3212,
|
| 1377 |
-
"step": 1440
|
| 1378 |
-
},
|
| 1379 |
-
{
|
| 1380 |
-
"epoch": 63.04347826086956,
|
| 1381 |
-
"grad_norm": 1.3142286539077759,
|
| 1382 |
-
"learning_rate": 1.4981687953927875e-05,
|
| 1383 |
-
"loss": 0.3127,
|
| 1384 |
-
"step": 1450
|
| 1385 |
-
},
|
| 1386 |
-
{
|
| 1387 |
-
"epoch": 63.47826086956522,
|
| 1388 |
-
"grad_norm": 1.9734851121902466,
|
| 1389 |
-
"learning_rate": 1.498164193209757e-05,
|
| 1390 |
-
"loss": 0.3447,
|
| 1391 |
-
"step": 1460
|
| 1392 |
-
},
|
| 1393 |
-
{
|
| 1394 |
-
"epoch": 63.91304347826087,
|
| 1395 |
-
"grad_norm": 1.655447006225586,
|
| 1396 |
-
"learning_rate": 1.498159294122049e-05,
|
| 1397 |
-
"loss": 0.2921,
|
| 1398 |
-
"step": 1470
|
| 1399 |
-
},
|
| 1400 |
-
{
|
| 1401 |
-
"epoch": 64.34782608695652,
|
| 1402 |
-
"grad_norm": 1.7767964601516724,
|
| 1403 |
-
"learning_rate": 1.4981540981316052e-05,
|
| 1404 |
-
"loss": 0.269,
|
| 1405 |
-
"step": 1480
|
| 1406 |
-
},
|
| 1407 |
-
{
|
| 1408 |
-
"epoch": 64.78260869565217,
|
| 1409 |
-
"grad_norm": 1.5196256637573242,
|
| 1410 |
-
"learning_rate": 1.4981486052404848e-05,
|
| 1411 |
-
"loss": 0.3583,
|
| 1412 |
-
"step": 1490
|
| 1413 |
-
},
|
| 1414 |
-
{
|
| 1415 |
-
"epoch": 65.21739130434783,
|
| 1416 |
-
"grad_norm": 1.4027047157287598,
|
| 1417 |
-
"learning_rate": 1.4981428154508652e-05,
|
| 1418 |
-
"loss": 0.2693,
|
| 1419 |
-
"step": 1500
|
| 1420 |
-
},
|
| 1421 |
-
{
|
| 1422 |
-
"epoch": 65.21739130434783,
|
| 1423 |
-
"eval_loss": 0.832839846611023,
|
| 1424 |
-
"eval_runtime": 0.4275,
|
| 1425 |
-
"eval_samples_per_second": 23.391,
|
| 1426 |
-
"eval_steps_per_second": 23.391,
|
| 1427 |
-
"step": 1500
|
| 1428 |
-
},
|
| 1429 |
-
{
|
| 1430 |
-
"Start_State_loss": 0.8601926565170288,
|
| 1431 |
-
"Start_State_runtime": 0.4059,
|
| 1432 |
-
"Start_State_samples_per_second": 24.634,
|
| 1433 |
-
"Start_State_steps_per_second": 24.634,
|
| 1434 |
-
"epoch": 65.21739130434783,
|
| 1435 |
-
"step": 1500
|
| 1436 |
-
},
|
| 1437 |
-
{
|
| 1438 |
-
"Raw_Model_loss": 0.832839846611023,
|
| 1439 |
-
"Raw_Model_runtime": 0.3946,
|
| 1440 |
-
"Raw_Model_samples_per_second": 25.341,
|
| 1441 |
-
"Raw_Model_steps_per_second": 25.341,
|
| 1442 |
-
"epoch": 65.21739130434783,
|
| 1443 |
-
"step": 1500
|
| 1444 |
-
},
|
| 1445 |
-
{
|
| 1446 |
-
"SWA_loss": 0.7298181056976318,
|
| 1447 |
-
"SWA_runtime": 0.3986,
|
| 1448 |
-
"SWA_samples_per_second": 25.087,
|
| 1449 |
-
"SWA_steps_per_second": 25.087,
|
| 1450 |
-
"epoch": 65.21739130434783,
|
| 1451 |
-
"step": 1500
|
| 1452 |
-
},
|
| 1453 |
-
{
|
| 1454 |
-
"EMA_loss": 0.8607869148254395,
|
| 1455 |
-
"EMA_runtime": 0.4036,
|
| 1456 |
-
"EMA_samples_per_second": 24.774,
|
| 1457 |
-
"EMA_steps_per_second": 24.774,
|
| 1458 |
-
"epoch": 65.21739130434783,
|
| 1459 |
-
"step": 1500
|
| 1460 |
-
},
|
| 1461 |
-
{
|
| 1462 |
-
"epoch": 65.65217391304348,
|
| 1463 |
-
"grad_norm": 2.2542121410369873,
|
| 1464 |
-
"learning_rate": 1.4981367287650419e-05,
|
| 1465 |
-
"loss": 0.3164,
|
| 1466 |
-
"step": 1510
|
| 1467 |
-
},
|
| 1468 |
-
{
|
| 1469 |
-
"epoch": 66.08695652173913,
|
| 1470 |
-
"grad_norm": 1.7643301486968994,
|
| 1471 |
-
"learning_rate": 1.4981303451854267e-05,
|
| 1472 |
-
"loss": 0.2947,
|
| 1473 |
-
"step": 1520
|
| 1474 |
-
},
|
| 1475 |
-
{
|
| 1476 |
-
"epoch": 66.52173913043478,
|
| 1477 |
-
"grad_norm": 1.7471901178359985,
|
| 1478 |
-
"learning_rate": 1.4981236647145501e-05,
|
| 1479 |
-
"loss": 0.3103,
|
| 1480 |
-
"step": 1530
|
| 1481 |
-
},
|
| 1482 |
-
{
|
| 1483 |
-
"epoch": 66.95652173913044,
|
| 1484 |
-
"grad_norm": 2.057833194732666,
|
| 1485 |
-
"learning_rate": 1.4981166873550601e-05,
|
| 1486 |
-
"loss": 0.3051,
|
| 1487 |
-
"step": 1540
|
| 1488 |
-
},
|
| 1489 |
-
{
|
| 1490 |
-
"epoch": 67.3913043478261,
|
| 1491 |
-
"grad_norm": 1.7425355911254883,
|
| 1492 |
-
"learning_rate": 1.4981094131097224e-05,
|
| 1493 |
-
"loss": 0.2713,
|
| 1494 |
-
"step": 1550
|
| 1495 |
-
},
|
| 1496 |
-
{
|
| 1497 |
-
"epoch": 67.82608695652173,
|
| 1498 |
-
"grad_norm": 2.050690174102783,
|
| 1499 |
-
"learning_rate": 1.49810184198142e-05,
|
| 1500 |
-
"loss": 0.3439,
|
| 1501 |
-
"step": 1560
|
| 1502 |
-
},
|
| 1503 |
-
{
|
| 1504 |
-
"epoch": 68.26086956521739,
|
| 1505 |
-
"grad_norm": 2.0778491497039795,
|
| 1506 |
-
"learning_rate": 1.498093973973154e-05,
|
| 1507 |
-
"loss": 0.2503,
|
| 1508 |
-
"step": 1570
|
| 1509 |
-
},
|
| 1510 |
-
{
|
| 1511 |
-
"epoch": 68.69565217391305,
|
| 1512 |
-
"grad_norm": 1.8078017234802246,
|
| 1513 |
-
"learning_rate": 1.4980858090880429e-05,
|
| 1514 |
-
"loss": 0.2862,
|
| 1515 |
-
"step": 1580
|
| 1516 |
-
},
|
| 1517 |
-
{
|
| 1518 |
-
"epoch": 69.1304347826087,
|
| 1519 |
-
"grad_norm": 1.9451018571853638,
|
| 1520 |
-
"learning_rate": 1.4980773473293232e-05,
|
| 1521 |
-
"loss": 0.368,
|
| 1522 |
-
"step": 1590
|
| 1523 |
-
},
|
| 1524 |
-
{
|
| 1525 |
-
"epoch": 69.56521739130434,
|
| 1526 |
-
"grad_norm": 1.9795953035354614,
|
| 1527 |
-
"learning_rate": 1.4980685887003486e-05,
|
| 1528 |
-
"loss": 0.3073,
|
| 1529 |
-
"step": 1600
|
| 1530 |
-
},
|
| 1531 |
-
{
|
| 1532 |
-
"epoch": 70.0,
|
| 1533 |
-
"grad_norm": 1.6645371913909912,
|
| 1534 |
-
"learning_rate": 1.498059533204591e-05,
|
| 1535 |
-
"loss": 0.2691,
|
| 1536 |
-
"step": 1610
|
| 1537 |
-
},
|
| 1538 |
-
{
|
| 1539 |
-
"epoch": 70.43478260869566,
|
| 1540 |
-
"grad_norm": 2.21379017829895,
|
| 1541 |
-
"learning_rate": 1.4980501808456398e-05,
|
| 1542 |
-
"loss": 0.3142,
|
| 1543 |
-
"step": 1620
|
| 1544 |
-
},
|
| 1545 |
-
{
|
| 1546 |
-
"epoch": 70.8695652173913,
|
| 1547 |
-
"grad_norm": 1.9500844478607178,
|
| 1548 |
-
"learning_rate": 1.4980405316272018e-05,
|
| 1549 |
-
"loss": 0.2996,
|
| 1550 |
-
"step": 1630
|
| 1551 |
-
},
|
| 1552 |
-
{
|
| 1553 |
-
"epoch": 71.30434782608695,
|
| 1554 |
-
"grad_norm": 2.359870195388794,
|
| 1555 |
-
"learning_rate": 1.4980305855531015e-05,
|
| 1556 |
-
"loss": 0.2888,
|
| 1557 |
-
"step": 1640
|
| 1558 |
-
},
|
| 1559 |
-
{
|
| 1560 |
-
"epoch": 71.73913043478261,
|
| 1561 |
-
"grad_norm": 1.8895881175994873,
|
| 1562 |
-
"learning_rate": 1.4980203426272815e-05,
|
| 1563 |
-
"loss": 0.2624,
|
| 1564 |
-
"step": 1650
|
| 1565 |
-
},
|
| 1566 |
-
{
|
| 1567 |
-
"epoch": 71.73913043478261,
|
| 1568 |
-
"eval_loss": 0.847686767578125,
|
| 1569 |
-
"eval_runtime": 0.5359,
|
| 1570 |
-
"eval_samples_per_second": 18.659,
|
| 1571 |
-
"eval_steps_per_second": 18.659,
|
| 1572 |
-
"step": 1650
|
| 1573 |
-
},
|
| 1574 |
-
{
|
| 1575 |
-
"Start_State_loss": 0.8601926565170288,
|
| 1576 |
-
"Start_State_runtime": 0.3989,
|
| 1577 |
-
"Start_State_samples_per_second": 25.067,
|
| 1578 |
-
"Start_State_steps_per_second": 25.067,
|
| 1579 |
-
"epoch": 71.73913043478261,
|
| 1580 |
-
"step": 1650
|
| 1581 |
-
},
|
| 1582 |
-
{
|
| 1583 |
-
"Raw_Model_loss": 0.847686767578125,
|
| 1584 |
-
"Raw_Model_runtime": 0.4133,
|
| 1585 |
-
"Raw_Model_samples_per_second": 24.198,
|
| 1586 |
-
"Raw_Model_steps_per_second": 24.198,
|
| 1587 |
-
"epoch": 71.73913043478261,
|
| 1588 |
-
"step": 1650
|
| 1589 |
-
},
|
| 1590 |
-
{
|
| 1591 |
-
"SWA_loss": 0.7314801216125488,
|
| 1592 |
-
"SWA_runtime": 0.3914,
|
| 1593 |
-
"SWA_samples_per_second": 25.548,
|
| 1594 |
-
"SWA_steps_per_second": 25.548,
|
| 1595 |
-
"epoch": 71.73913043478261,
|
| 1596 |
-
"step": 1650
|
| 1597 |
-
},
|
| 1598 |
-
{
|
| 1599 |
-
"EMA_loss": 0.8605908155441284,
|
| 1600 |
-
"EMA_runtime": 0.3897,
|
| 1601 |
-
"EMA_samples_per_second": 25.662,
|
| 1602 |
-
"EMA_steps_per_second": 25.662,
|
| 1603 |
-
"epoch": 71.73913043478261,
|
| 1604 |
-
"step": 1650
|
| 1605 |
-
},
|
| 1606 |
-
{
|
| 1607 |
-
"epoch": 72.17391304347827,
|
| 1608 |
-
"grad_norm": 1.664617896080017,
|
| 1609 |
-
"learning_rate": 1.4980098028538014e-05,
|
| 1610 |
-
"loss": 0.3276,
|
| 1611 |
-
"step": 1660
|
| 1612 |
-
},
|
| 1613 |
-
{
|
| 1614 |
-
"epoch": 72.6086956521739,
|
| 1615 |
-
"grad_norm": 2.0435194969177246,
|
| 1616 |
-
"learning_rate": 1.4979989662368391e-05,
|
| 1617 |
-
"loss": 0.2963,
|
| 1618 |
-
"step": 1670
|
| 1619 |
-
},
|
| 1620 |
-
{
|
| 1621 |
-
"epoch": 73.04347826086956,
|
| 1622 |
-
"grad_norm": 1.906278133392334,
|
| 1623 |
-
"learning_rate": 1.4979878327806899e-05,
|
| 1624 |
-
"loss": 0.3093,
|
| 1625 |
-
"step": 1680
|
| 1626 |
-
},
|
| 1627 |
-
{
|
| 1628 |
-
"epoch": 73.47826086956522,
|
| 1629 |
-
"grad_norm": 2.026448965072632,
|
| 1630 |
-
"learning_rate": 1.4979764024897668e-05,
|
| 1631 |
-
"loss": 0.2875,
|
| 1632 |
-
"step": 1690
|
| 1633 |
-
},
|
| 1634 |
-
{
|
| 1635 |
-
"epoch": 73.91304347826087,
|
| 1636 |
-
"grad_norm": 1.8200604915618896,
|
| 1637 |
-
"learning_rate": 1.4979646753686002e-05,
|
| 1638 |
-
"loss": 0.2793,
|
| 1639 |
-
"step": 1700
|
| 1640 |
-
},
|
| 1641 |
-
{
|
| 1642 |
-
"epoch": 74.34782608695652,
|
| 1643 |
-
"grad_norm": 1.414810061454773,
|
| 1644 |
-
"learning_rate": 1.4979526514218385e-05,
|
| 1645 |
-
"loss": 0.277,
|
| 1646 |
-
"step": 1710
|
| 1647 |
-
},
|
| 1648 |
-
{
|
| 1649 |
-
"epoch": 74.78260869565217,
|
| 1650 |
-
"grad_norm": 1.4874234199523926,
|
| 1651 |
-
"learning_rate": 1.4979403306542473e-05,
|
| 1652 |
-
"loss": 0.3277,
|
| 1653 |
-
"step": 1720
|
| 1654 |
-
},
|
| 1655 |
-
{
|
| 1656 |
-
"epoch": 75.21739130434783,
|
| 1657 |
-
"grad_norm": 1.5648179054260254,
|
| 1658 |
-
"learning_rate": 1.4979277130707107e-05,
|
| 1659 |
-
"loss": 0.2337,
|
| 1660 |
-
"step": 1730
|
| 1661 |
-
},
|
| 1662 |
-
{
|
| 1663 |
-
"epoch": 75.65217391304348,
|
| 1664 |
-
"grad_norm": 1.6863374710083008,
|
| 1665 |
-
"learning_rate": 1.4979147986762295e-05,
|
| 1666 |
-
"loss": 0.3146,
|
| 1667 |
-
"step": 1740
|
| 1668 |
-
},
|
| 1669 |
-
{
|
| 1670 |
-
"epoch": 76.08695652173913,
|
| 1671 |
-
"grad_norm": 1.7994861602783203,
|
| 1672 |
-
"learning_rate": 1.4979015874759227e-05,
|
| 1673 |
-
"loss": 0.2694,
|
| 1674 |
-
"step": 1750
|
| 1675 |
-
},
|
| 1676 |
-
{
|
| 1677 |
-
"epoch": 76.52173913043478,
|
| 1678 |
-
"grad_norm": 1.8553599119186401,
|
| 1679 |
-
"learning_rate": 1.4978880794750266e-05,
|
| 1680 |
-
"loss": 0.2661,
|
| 1681 |
-
"step": 1760
|
| 1682 |
-
},
|
| 1683 |
-
{
|
| 1684 |
-
"epoch": 76.95652173913044,
|
| 1685 |
-
"grad_norm": 1.3038052320480347,
|
| 1686 |
-
"learning_rate": 1.4978742746788957e-05,
|
| 1687 |
-
"loss": 0.3005,
|
| 1688 |
-
"step": 1770
|
| 1689 |
-
},
|
| 1690 |
-
{
|
| 1691 |
-
"epoch": 77.3913043478261,
|
| 1692 |
-
"grad_norm": 1.8376268148422241,
|
| 1693 |
-
"learning_rate": 1.4978601730930014e-05,
|
| 1694 |
-
"loss": 0.2843,
|
| 1695 |
-
"step": 1780
|
| 1696 |
-
},
|
| 1697 |
-
{
|
| 1698 |
-
"epoch": 77.82608695652173,
|
| 1699 |
-
"grad_norm": 1.8291127681732178,
|
| 1700 |
-
"learning_rate": 1.4978457747229335e-05,
|
| 1701 |
-
"loss": 0.2715,
|
| 1702 |
-
"step": 1790
|
| 1703 |
-
},
|
| 1704 |
-
{
|
| 1705 |
-
"epoch": 78.26086956521739,
|
| 1706 |
-
"grad_norm": 1.933289885520935,
|
| 1707 |
-
"learning_rate": 1.497831079574399e-05,
|
| 1708 |
-
"loss": 0.3055,
|
| 1709 |
-
"step": 1800
|
| 1710 |
-
},
|
| 1711 |
-
{
|
| 1712 |
-
"epoch": 78.26086956521739,
|
| 1713 |
-
"eval_loss": 0.8690454363822937,
|
| 1714 |
-
"eval_runtime": 0.4165,
|
| 1715 |
-
"eval_samples_per_second": 24.008,
|
| 1716 |
-
"eval_steps_per_second": 24.008,
|
| 1717 |
-
"step": 1800
|
| 1718 |
-
},
|
| 1719 |
-
{
|
| 1720 |
-
"Start_State_loss": 0.8601926565170288,
|
| 1721 |
-
"Start_State_runtime": 0.3983,
|
| 1722 |
-
"Start_State_samples_per_second": 25.109,
|
| 1723 |
-
"Start_State_steps_per_second": 25.109,
|
| 1724 |
-
"epoch": 78.26086956521739,
|
| 1725 |
-
"step": 1800
|
| 1726 |
-
},
|
| 1727 |
-
{
|
| 1728 |
-
"Raw_Model_loss": 0.8690454363822937,
|
| 1729 |
-
"Raw_Model_runtime": 0.4147,
|
| 1730 |
-
"Raw_Model_samples_per_second": 24.115,
|
| 1731 |
-
"Raw_Model_steps_per_second": 24.115,
|
| 1732 |
-
"epoch": 78.26086956521739,
|
| 1733 |
-
"step": 1800
|
| 1734 |
-
},
|
| 1735 |
-
{
|
| 1736 |
-
"SWA_loss": 0.7372413873672485,
|
| 1737 |
-
"SWA_runtime": 0.4087,
|
| 1738 |
-
"SWA_samples_per_second": 24.465,
|
| 1739 |
-
"SWA_steps_per_second": 24.465,
|
| 1740 |
-
"epoch": 78.26086956521739,
|
| 1741 |
-
"step": 1800
|
| 1742 |
-
},
|
| 1743 |
-
{
|
| 1744 |
-
"EMA_loss": 0.8606707453727722,
|
| 1745 |
-
"EMA_runtime": 0.4092,
|
| 1746 |
-
"EMA_samples_per_second": 24.44,
|
| 1747 |
-
"EMA_steps_per_second": 24.44,
|
| 1748 |
-
"epoch": 78.26086956521739,
|
| 1749 |
-
"step": 1800
|
| 1750 |
}
|
| 1751 |
],
|
| 1752 |
"logging_steps": 10,
|
|
@@ -1766,7 +171,7 @@
|
|
| 1766 |
"attributes": {}
|
| 1767 |
}
|
| 1768 |
},
|
| 1769 |
-
"total_flos":
|
| 1770 |
"train_batch_size": 4,
|
| 1771 |
"trial_name": null,
|
| 1772 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7964445352554321,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-150",
|
| 4 |
+
"epoch": 6.521739130434782,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.43478260869565216,
|
| 13 |
+
"grad_norm": 1.5021672248840332,
|
| 14 |
"learning_rate": 3e-06,
|
| 15 |
+
"loss": 0.9064,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.8695652173913043,
|
| 20 |
+
"grad_norm": 1.6870806217193604,
|
| 21 |
"learning_rate": 6e-06,
|
| 22 |
+
"loss": 0.9026,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.3043478260869565,
|
| 27 |
+
"grad_norm": 1.7296316623687744,
|
| 28 |
"learning_rate": 9e-06,
|
| 29 |
+
"loss": 0.8997,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 1.7391304347826086,
|
| 34 |
+
"grad_norm": 1.453599214553833,
|
| 35 |
"learning_rate": 1.2e-05,
|
| 36 |
+
"loss": 0.9089,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 2.1739130434782608,
|
| 41 |
+
"grad_norm": 1.351836919784546,
|
| 42 |
"learning_rate": 1.5e-05,
|
| 43 |
+
"loss": 0.8361,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 2.608695652173913,
|
| 48 |
+
"grad_norm": 2.0312016010284424,
|
| 49 |
"learning_rate": 1.8e-05,
|
| 50 |
+
"loss": 0.8893,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 3.0434782608695654,
|
| 55 |
+
"grad_norm": 1.4920508861541748,
|
| 56 |
"learning_rate": 2.1e-05,
|
| 57 |
+
"loss": 0.8911,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 3.4782608695652173,
|
| 62 |
+
"grad_norm": 1.7295340299606323,
|
| 63 |
"learning_rate": 2.4e-05,
|
| 64 |
+
"loss": 0.8233,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 3.9130434782608696,
|
| 69 |
+
"grad_norm": 1.4239747524261475,
|
| 70 |
"learning_rate": 2.7000000000000002e-05,
|
| 71 |
+
"loss": 0.8526,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 4.3478260869565215,
|
| 76 |
+
"grad_norm": 1.3656420707702637,
|
| 77 |
"learning_rate": 3e-05,
|
| 78 |
+
"loss": 0.8646,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 4.782608695652174,
|
| 83 |
+
"grad_norm": 2.2135441303253174,
|
| 84 |
"learning_rate": 2.999999702723963e-05,
|
| 85 |
+
"loss": 0.8228,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 5.217391304347826,
|
| 90 |
+
"grad_norm": 1.0727280378341675,
|
| 91 |
"learning_rate": 2.9999988108959687e-05,
|
| 92 |
+
"loss": 0.7654,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 5.6521739130434785,
|
| 97 |
+
"grad_norm": 1.559777021408081,
|
| 98 |
"learning_rate": 2.9999973245163716e-05,
|
| 99 |
+
"loss": 0.7413,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 6.086956521739131,
|
| 104 |
+
"grad_norm": 1.9066534042358398,
|
| 105 |
"learning_rate": 2.99999524358576e-05,
|
| 106 |
+
"loss": 0.765,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 6.521739130434782,
|
| 111 |
+
"grad_norm": 1.1222983598709106,
|
| 112 |
"learning_rate": 2.9999925681049593e-05,
|
| 113 |
+
"loss": 0.7855,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 6.521739130434782,
|
| 118 |
+
"eval_loss": 0.7964445352554321,
|
| 119 |
+
"eval_runtime": 0.4778,
|
| 120 |
+
"eval_samples_per_second": 20.929,
|
| 121 |
+
"eval_steps_per_second": 20.929,
|
| 122 |
"step": 150
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"Start_State_loss": 0.8603047132492065,
|
| 126 |
+
"Start_State_runtime": 0.4294,
|
| 127 |
+
"Start_State_samples_per_second": 23.291,
|
| 128 |
+
"Start_State_steps_per_second": 23.291,
|
| 129 |
"epoch": 6.521739130434782,
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"Raw_Model_loss": 0.7964445352554321,
|
| 134 |
+
"Raw_Model_runtime": 0.409,
|
| 135 |
+
"Raw_Model_samples_per_second": 24.447,
|
| 136 |
+
"Raw_Model_steps_per_second": 24.447,
|
| 137 |
"epoch": 6.521739130434782,
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"SWA_loss": 0.8603047132492065,
|
| 142 |
+
"SWA_runtime": 0.4233,
|
| 143 |
+
"SWA_samples_per_second": 23.622,
|
| 144 |
+
"SWA_steps_per_second": 23.622,
|
| 145 |
"epoch": 6.521739130434782,
|
| 146 |
"step": 150
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"EMA_loss": 0.860609233379364,
|
| 150 |
+
"EMA_runtime": 0.4245,
|
| 151 |
+
"EMA_samples_per_second": 23.56,
|
| 152 |
+
"EMA_steps_per_second": 23.56,
|
| 153 |
"epoch": 6.521739130434782,
|
| 154 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 155 |
}
|
| 156 |
],
|
| 157 |
"logging_steps": 10,
|
|
|
|
| 171 |
"attributes": {}
|
| 172 |
}
|
| 173 |
},
|
| 174 |
+
"total_flos": 3894839614291968.0,
|
| 175 |
"train_batch_size": 4,
|
| 176 |
"trial_name": null,
|
| 177 |
"trial_params": null
|
last-checkpoint/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 sha256:2ba11e02e3c662a7d3d48a1857c9dd4de50cd9d610a43e2273c0cd737526dd29
|
| 3 |
size 5368
|