Upload folder using huggingface_hub
Browse files- logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/args.json +1 -1
- logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/dataloader_04374.pt +1 -1
- logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/log2.txt +528 -547
- logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/model_04374.pt +1 -1
- logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/optimizer_04374.pt +1 -1
logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/args.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"hellaswag": true, "attention_kind": "selective", "log_dir": "logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 12, "n_embd": 264, "head_dim": 22, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": 4375, "warmup_steps": 250, "group": "fix_1_latent_mask", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1339, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "n_latent_masks", "selection_head_linear_combo_scale": 1.0, "disable_selection_head_linear_combo_bias": false, "assert_latent_matches_no_head": false, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile":
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 12, "n_embd": 264, "head_dim": 22, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": 4375, "warmup_steps": 250, "group": "fix_1_latent_mask", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1339, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "n_latent_masks", "selection_head_linear_combo_scale": 1.0, "disable_selection_head_linear_combo_bias": false, "assert_latent_matches_no_head": false, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile": true, "use_mini_model": false, "upload_to_hf": true, "seq_len": 256, "batch_size": 32, "total_batch_size": 8192, "protection_head_scaling_factor": 1.0, "protection_head_bias": 0.0, "n_sliced_masks": null, "n_latent_masks": 2, "init_latent_masks_to_identity": true, "latent_mask_scale": null, "latent_mask_sigmoid": false, "S_layernorm": false, "mask_layernorm": false, "residual_attention_masks": false, "compute_base_shapes": false, "base_shapes_savefile": null, "mup": true, "disable_selection": false, "mup_enable_coord_check_logging": false, "max_lr": 0.003, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "key": "1_latent_mask_lr_30e-4_n_latent_masks_2"}
|
logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/dataloader_04374.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c8d49024f3ab594241ab14ad69140ca5f3ff3f7a1401f0f49b94f9bdaf4a9a8
|
| 3 |
size 964
|
logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/log2.txt
CHANGED
|
@@ -1,548 +1,529 @@
|
|
| 1 |
max_steps: 4375
|
| 2 |
-
0 val loss 11.
|
| 3 |
-
0 val perplexity
|
| 4 |
-
0
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
100 val
|
| 16 |
-
100
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
200 val
|
| 28 |
-
200
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
300
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
400
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
500
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
| 212 |
-
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
|
| 216 |
-
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
|
| 230 |
-
|
| 231 |
-
|
| 232 |
-
|
| 233 |
-
|
| 234 |
-
|
| 235 |
-
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
|
| 244 |
-
|
| 245 |
-
|
| 246 |
-
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
|
| 259 |
-
|
| 260 |
-
|
| 261 |
-
|
| 262 |
-
|
| 263 |
-
|
| 264 |
-
|
| 265 |
-
|
| 266 |
-
|
| 267 |
-
|
| 268 |
-
|
| 269 |
-
|
| 270 |
-
|
| 271 |
-
|
| 272 |
-
|
| 273 |
-
|
| 274 |
-
|
| 275 |
-
|
| 276 |
-
|
| 277 |
-
|
| 278 |
-
|
| 279 |
-
|
| 280 |
-
|
| 281 |
-
|
| 282 |
-
|
| 283 |
-
|
| 284 |
-
|
| 285 |
-
|
| 286 |
-
|
| 287 |
-
|
| 288 |
-
|
| 289 |
-
|
| 290 |
-
|
| 291 |
-
|
| 292 |
-
|
| 293 |
-
|
| 294 |
-
|
| 295 |
-
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
|
| 300 |
-
|
| 301 |
-
|
| 302 |
-
|
| 303 |
-
|
| 304 |
-
|
| 305 |
-
|
| 306 |
-
|
| 307 |
-
|
| 308 |
-
|
| 309 |
-
|
| 310 |
-
|
| 311 |
-
|
| 312 |
-
|
| 313 |
-
|
| 314 |
-
|
| 315 |
-
|
| 316 |
-
|
| 317 |
-
|
| 318 |
-
|
| 319 |
-
|
| 320 |
-
|
| 321 |
-
|
| 322 |
-
|
| 323 |
-
|
| 324 |
-
|
| 325 |
-
|
| 326 |
-
|
| 327 |
-
|
| 328 |
-
|
| 329 |
-
|
| 330 |
-
|
| 331 |
-
|
| 332 |
-
|
| 333 |
-
|
| 334 |
-
|
| 335 |
-
|
| 336 |
-
|
| 337 |
-
|
| 338 |
-
|
| 339 |
-
|
| 340 |
-
|
| 341 |
-
|
| 342 |
-
|
| 343 |
-
|
| 344 |
-
|
| 345 |
-
|
| 346 |
-
|
| 347 |
-
|
| 348 |
-
|
| 349 |
-
|
| 350 |
-
|
| 351 |
-
|
| 352 |
-
|
| 353 |
-
|
| 354 |
-
|
| 355 |
-
|
| 356 |
-
|
| 357 |
-
|
| 358 |
-
|
| 359 |
-
|
| 360 |
-
|
| 361 |
-
|
| 362 |
-
|
| 363 |
-
|
| 364 |
-
|
| 365 |
-
|
| 366 |
-
|
| 367 |
-
|
| 368 |
-
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
|
| 372 |
-
|
| 373 |
-
|
| 374 |
-
|
| 375 |
-
|
| 376 |
-
|
| 377 |
-
|
| 378 |
-
|
| 379 |
-
|
| 380 |
-
|
| 381 |
-
|
| 382 |
-
|
| 383 |
-
|
| 384 |
-
|
| 385 |
-
|
| 386 |
-
|
| 387 |
-
|
| 388 |
-
|
| 389 |
-
|
| 390 |
-
|
| 391 |
-
|
| 392 |
-
|
| 393 |
-
|
| 394 |
-
|
| 395 |
-
|
| 396 |
-
|
| 397 |
-
|
| 398 |
-
|
| 399 |
-
|
| 400 |
-
|
| 401 |
-
|
| 402 |
-
|
| 403 |
-
|
| 404 |
-
|
| 405 |
-
|
| 406 |
-
|
| 407 |
-
|
| 408 |
-
|
| 409 |
-
|
| 410 |
-
|
| 411 |
-
|
| 412 |
-
|
| 413 |
-
|
| 414 |
-
|
| 415 |
-
|
| 416 |
-
|
| 417 |
-
|
| 418 |
-
|
| 419 |
-
|
| 420 |
-
|
| 421 |
-
|
| 422 |
-
|
| 423 |
-
|
| 424 |
-
|
| 425 |
-
|
| 426 |
-
|
| 427 |
-
|
| 428 |
-
|
| 429 |
-
|
| 430 |
-
|
| 431 |
-
|
| 432 |
-
|
| 433 |
-
|
| 434 |
-
|
| 435 |
-
|
| 436 |
-
|
| 437 |
-
|
| 438 |
-
|
| 439 |
-
|
| 440 |
-
|
| 441 |
-
|
| 442 |
-
|
| 443 |
-
|
| 444 |
-
|
| 445 |
-
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
|
| 449 |
-
|
| 450 |
-
|
| 451 |
-
|
| 452 |
-
|
| 453 |
-
|
| 454 |
-
|
| 455 |
-
|
| 456 |
-
|
| 457 |
-
|
| 458 |
-
|
| 459 |
-
|
| 460 |
-
|
| 461 |
-
|
| 462 |
-
|
| 463 |
-
|
| 464 |
-
|
| 465 |
-
|
| 466 |
-
|
| 467 |
-
|
| 468 |
-
|
| 469 |
-
|
| 470 |
-
|
| 471 |
-
|
| 472 |
-
|
| 473 |
-
|
| 474 |
-
|
| 475 |
-
|
| 476 |
-
|
| 477 |
-
|
| 478 |
-
|
| 479 |
-
|
| 480 |
-
|
| 481 |
-
|
| 482 |
-
|
| 483 |
-
|
| 484 |
-
|
| 485 |
-
|
| 486 |
-
|
| 487 |
-
|
| 488 |
-
|
| 489 |
-
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
|
| 493 |
-
|
| 494 |
-
|
| 495 |
-
|
| 496 |
-
|
| 497 |
-
|
| 498 |
-
|
| 499 |
-
|
| 500 |
-
|
| 501 |
-
|
| 502 |
-
|
| 503 |
-
|
| 504 |
-
|
| 505 |
-
|
| 506 |
-
|
| 507 |
-
|
| 508 |
-
|
| 509 |
-
|
| 510 |
-
|
| 511 |
-
|
| 512 |
-
|
| 513 |
-
|
| 514 |
-
|
| 515 |
-
|
| 516 |
-
|
| 517 |
-
|
| 518 |
-
|
| 519 |
-
|
| 520 |
-
|
| 521 |
-
|
| 522 |
-
|
| 523 |
-
|
| 524 |
-
|
| 525 |
-
|
| 526 |
-
|
| 527 |
-
|
| 528 |
-
|
| 529 |
-
|
| 530 |
-
4250 hella 0.2570
|
| 531 |
-
4250 train 3.935833 (lr=3.0776e-04) (hash(x)=33994768)
|
| 532 |
-
4260 train 3.919878 (lr=3.0657e-04) (hash(x)=39658687)
|
| 533 |
-
4270 train 3.800713 (lr=3.0548e-04) (hash(x)=42583064)
|
| 534 |
-
4280 train 3.863995 (lr=3.0449e-04) (hash(x)=40635811)
|
| 535 |
-
4290 train 3.765610 (lr=3.0359e-04) (hash(x)=35313841)
|
| 536 |
-
4300 val loss 3.8823
|
| 537 |
-
4300 val perplexity 48.5372
|
| 538 |
-
4300 train 3.945179 (lr=3.0280e-04) (hash(x)=39332245)
|
| 539 |
-
4310 train 3.847904 (lr=3.0210e-04) (hash(x)=43732999)
|
| 540 |
-
4320 train 3.848834 (lr=3.0150e-04) (hash(x)=40831835)
|
| 541 |
-
4330 train 3.984694 (lr=3.0101e-04) (hash(x)=41813368)
|
| 542 |
-
4340 train 3.887618 (lr=3.0061e-04) (hash(x)=36952586)
|
| 543 |
-
4350 train 3.911630 (lr=3.0031e-04) (hash(x)=42470745)
|
| 544 |
-
4360 train 3.835622 (lr=3.0011e-04) (hash(x)=39581495)
|
| 545 |
-
4370 train 4.026768 (lr=3.0001e-04) (hash(x)=35914538)
|
| 546 |
-
4374 val loss 3.8754
|
| 547 |
-
4374 val perplexity 48.2003
|
| 548 |
-
4374 hella 0.2559
|
|
|
|
| 1 |
max_steps: 4375
|
| 2 |
+
0 val loss 11.3198
|
| 3 |
+
0 val perplexity 82438.3594
|
| 4 |
+
0 train 11.379463 (lr=1.2000e-05) (hash(x)=44227275)
|
| 5 |
+
10 train 9.797939 (lr=1.3200e-04) (hash(x)=45818388)
|
| 6 |
+
20 train 8.633065 (lr=2.5200e-04) (hash(x)=39408131)
|
| 7 |
+
30 train 7.907566 (lr=3.7200e-04) (hash(x)=40882147)
|
| 8 |
+
40 train 7.893028 (lr=4.9200e-04) (hash(x)=38039067)
|
| 9 |
+
50 train 7.709972 (lr=6.1200e-04) (hash(x)=35121892)
|
| 10 |
+
60 train 7.915734 (lr=7.3200e-04) (hash(x)=38788225)
|
| 11 |
+
70 train 7.710945 (lr=8.5200e-04) (hash(x)=42846102)
|
| 12 |
+
80 train 7.764929 (lr=9.7200e-04) (hash(x)=42368835)
|
| 13 |
+
90 train 7.486595 (lr=1.0920e-03) (hash(x)=39322548)
|
| 14 |
+
100 val loss 7.3988
|
| 15 |
+
100 val perplexity 1633.9817
|
| 16 |
+
100 train 7.489345 (lr=1.2120e-03) (hash(x)=40406420)
|
| 17 |
+
110 train 7.186479 (lr=1.3320e-03) (hash(x)=35906509)
|
| 18 |
+
120 train 7.022212 (lr=1.4520e-03) (hash(x)=34719082)
|
| 19 |
+
130 train 7.233125 (lr=1.5720e-03) (hash(x)=45268027)
|
| 20 |
+
140 train 7.415177 (lr=1.6920e-03) (hash(x)=41612530)
|
| 21 |
+
150 train 7.320706 (lr=1.8120e-03) (hash(x)=41411227)
|
| 22 |
+
160 train 7.423467 (lr=1.9320e-03) (hash(x)=43258342)
|
| 23 |
+
170 train 6.987679 (lr=2.0520e-03) (hash(x)=37150406)
|
| 24 |
+
180 train 6.713885 (lr=2.1720e-03) (hash(x)=34145536)
|
| 25 |
+
190 train 6.850262 (lr=2.2920e-03) (hash(x)=38936209)
|
| 26 |
+
200 val loss 7.0850
|
| 27 |
+
200 val perplexity 1193.9506
|
| 28 |
+
200 train 6.269652 (lr=2.4120e-03) (hash(x)=30327209)
|
| 29 |
+
210 train 6.897263 (lr=2.5320e-03) (hash(x)=38350146)
|
| 30 |
+
220 train 7.218045 (lr=2.6520e-03) (hash(x)=45488529)
|
| 31 |
+
230 train 6.780678 (lr=2.7720e-03) (hash(x)=37882079)
|
| 32 |
+
240 train 6.867301 (lr=2.8920e-03) (hash(x)=40962992)
|
| 33 |
+
250 train 7.046554 (lr=3.0000e-03) (hash(x)=43216900)
|
| 34 |
+
260 train 6.939759 (lr=3.0000e-03) (hash(x)=26725679)
|
| 35 |
+
270 train 6.865248 (lr=2.9998e-03) (hash(x)=39966727)
|
| 36 |
+
280 train 7.263814 (lr=2.9996e-03) (hash(x)=46127200)
|
| 37 |
+
290 train 6.663627 (lr=2.9994e-03) (hash(x)=37965454)
|
| 38 |
+
300 val loss 6.7726
|
| 39 |
+
300 val perplexity 873.6116
|
| 40 |
+
300 train 6.809310 (lr=2.9990e-03) (hash(x)=41918472)
|
| 41 |
+
310 train 6.793670 (lr=2.9986e-03) (hash(x)=39644633)
|
| 42 |
+
320 train 6.435929 (lr=2.9981e-03) (hash(x)=37587691)
|
| 43 |
+
330 train 6.546347 (lr=2.9975e-03) (hash(x)=37481443)
|
| 44 |
+
340 train 6.849642 (lr=2.9968e-03) (hash(x)=41939532)
|
| 45 |
+
350 train 6.536463 (lr=2.9961e-03) (hash(x)=38497020)
|
| 46 |
+
360 train 6.817259 (lr=2.9953e-03) (hash(x)=39744344)
|
| 47 |
+
370 train 6.296607 (lr=2.9944e-03) (hash(x)=34941475)
|
| 48 |
+
380 train 6.493192 (lr=2.9934e-03) (hash(x)=38299371)
|
| 49 |
+
390 train 6.471909 (lr=2.9923e-03) (hash(x)=37556107)
|
| 50 |
+
400 val loss 6.6084
|
| 51 |
+
400 val perplexity 741.2896
|
| 52 |
+
400 train 6.673820 (lr=2.9912e-03) (hash(x)=44179822)
|
| 53 |
+
410 train 6.640482 (lr=2.9900e-03) (hash(x)=41220755)
|
| 54 |
+
420 train 6.587605 (lr=2.9887e-03) (hash(x)=38754098)
|
| 55 |
+
430 train 6.739646 (lr=2.9873e-03) (hash(x)=41527019)
|
| 56 |
+
440 train 6.537798 (lr=2.9859e-03) (hash(x)=41419190)
|
| 57 |
+
450 train 6.568528 (lr=2.9844e-03) (hash(x)=39961641)
|
| 58 |
+
460 train 6.380276 (lr=2.9828e-03) (hash(x)=37888686)
|
| 59 |
+
470 train 6.339571 (lr=2.9811e-03) (hash(x)=37968322)
|
| 60 |
+
480 train 6.841465 (lr=2.9793e-03) (hash(x)=43812581)
|
| 61 |
+
490 train 6.391725 (lr=2.9775e-03) (hash(x)=35797189)
|
| 62 |
+
500 val loss 6.4994
|
| 63 |
+
500 val perplexity 664.7291
|
| 64 |
+
500 train 6.251128 (lr=2.9756e-03) (hash(x)=36532055)
|
| 65 |
+
510 train 6.504333 (lr=2.9736e-03) (hash(x)=44096730)
|
| 66 |
+
520 train 6.963413 (lr=2.9716e-03) (hash(x)=48482144)
|
| 67 |
+
530 train 6.552701 (lr=2.9694e-03) (hash(x)=39203356)
|
| 68 |
+
540 train 6.309877 (lr=2.9672e-03) (hash(x)=39225929)
|
| 69 |
+
550 train 7.416578 (lr=2.9649e-03) (hash(x)=53152351)
|
| 70 |
+
560 train 6.352113 (lr=2.9625e-03) (hash(x)=37033697)
|
| 71 |
+
570 train 6.850715 (lr=2.9601e-03) (hash(x)=88200175)
|
| 72 |
+
580 train 6.499003 (lr=2.9576e-03) (hash(x)=39393936)
|
| 73 |
+
590 train 6.152848 (lr=2.9550e-03) (hash(x)=36692819)
|
| 74 |
+
600 val loss 6.5519
|
| 75 |
+
600 val perplexity 700.5750
|
| 76 |
+
600 train 6.498122 (lr=2.9523e-03) (hash(x)=41491085)
|
| 77 |
+
610 train 6.646906 (lr=2.9496e-03) (hash(x)=43232078)
|
| 78 |
+
620 train 5.665857 (lr=2.9468e-03) (hash(x)=23474131)
|
| 79 |
+
630 train 6.317541 (lr=2.9439e-03) (hash(x)=40546831)
|
| 80 |
+
640 train 6.764076 (lr=2.9409e-03) (hash(x)=51582695)
|
| 81 |
+
650 train 6.118343 (lr=2.9378e-03) (hash(x)=38302375)
|
| 82 |
+
660 train 6.353317 (lr=2.9347e-03) (hash(x)=38626801)
|
| 83 |
+
670 train 6.385187 (lr=2.9315e-03) (hash(x)=40660592)
|
| 84 |
+
680 train 6.084672 (lr=2.9283e-03) (hash(x)=31896853)
|
| 85 |
+
690 train 6.273912 (lr=2.9249e-03) (hash(x)=38331964)
|
| 86 |
+
700 val loss 6.3372
|
| 87 |
+
700 val perplexity 565.2305
|
| 88 |
+
700 train 6.271990 (lr=2.9215e-03) (hash(x)=38643410)
|
| 89 |
+
710 train 6.095592 (lr=2.9180e-03) (hash(x)=37789972)
|
| 90 |
+
720 train 6.601953 (lr=2.9144e-03) (hash(x)=40030446)
|
| 91 |
+
730 train 6.388149 (lr=2.9108e-03) (hash(x)=45839084)
|
| 92 |
+
740 train 6.416939 (lr=2.9071e-03) (hash(x)=43725009)
|
| 93 |
+
750 train 6.212621 (lr=2.9033e-03) (hash(x)=37845694)
|
| 94 |
+
760 train 6.168904 (lr=2.8994e-03) (hash(x)=40609741)
|
| 95 |
+
770 train 6.523702 (lr=2.8955e-03) (hash(x)=43323269)
|
| 96 |
+
780 train 6.212938 (lr=2.8915e-03) (hash(x)=35699653)
|
| 97 |
+
790 train 6.301132 (lr=2.8874e-03) (hash(x)=38268627)
|
| 98 |
+
800 val loss 6.2753
|
| 99 |
+
800 val perplexity 531.2865
|
| 100 |
+
800 train 6.161645 (lr=2.8833e-03) (hash(x)=41743031)
|
| 101 |
+
810 train 6.651413 (lr=2.8791e-03) (hash(x)=46688666)
|
| 102 |
+
820 train 6.507217 (lr=2.8748e-03) (hash(x)=43904433)
|
| 103 |
+
830 train 6.205750 (lr=2.8704e-03) (hash(x)=36792619)
|
| 104 |
+
840 train 6.300427 (lr=2.8660e-03) (hash(x)=43235991)
|
| 105 |
+
850 train 6.215741 (lr=2.8615e-03) (hash(x)=38699469)
|
| 106 |
+
860 train 6.401577 (lr=2.8569e-03) (hash(x)=42620243)
|
| 107 |
+
870 train 6.427041 (lr=2.8523e-03) (hash(x)=43841580)
|
| 108 |
+
880 train 6.220507 (lr=2.8476e-03) (hash(x)=39244977)
|
| 109 |
+
890 train 6.474046 (lr=2.8428e-03) (hash(x)=44897346)
|
| 110 |
+
900 val loss 6.2168
|
| 111 |
+
900 val perplexity 501.1090
|
| 112 |
+
900 train 6.524931 (lr=2.8379e-03) (hash(x)=45852497)
|
| 113 |
+
910 train 5.960623 (lr=2.8330e-03) (hash(x)=38398819)
|
| 114 |
+
920 train 6.158507 (lr=2.8280e-03) (hash(x)=39775421)
|
| 115 |
+
930 train 6.030588 (lr=2.8230e-03) (hash(x)=39701472)
|
| 116 |
+
940 train 6.094589 (lr=2.8178e-03) (hash(x)=39790089)
|
| 117 |
+
950 train 5.958650 (lr=2.8127e-03) (hash(x)=38366985)
|
| 118 |
+
960 train 6.082577 (lr=2.8074e-03) (hash(x)=39284432)
|
| 119 |
+
970 train 6.318904 (lr=2.8021e-03) (hash(x)=43609541)
|
| 120 |
+
980 train 6.221474 (lr=2.7967e-03) (hash(x)=39386797)
|
| 121 |
+
990 train 5.989091 (lr=2.7912e-03) (hash(x)=37028417)
|
| 122 |
+
1000 val loss 6.1751
|
| 123 |
+
1000 val perplexity 480.6269
|
| 124 |
+
1000 train 6.182693 (lr=2.7857e-03) (hash(x)=40181596)
|
| 125 |
+
1010 train 6.144771 (lr=2.7801e-03) (hash(x)=41599650)
|
| 126 |
+
1020 train 6.025442 (lr=2.7744e-03) (hash(x)=40205853)
|
| 127 |
+
1030 train 6.475232 (lr=2.7687e-03) (hash(x)=43271614)
|
| 128 |
+
1040 train 6.007041 (lr=2.7629e-03) (hash(x)=35882196)
|
| 129 |
+
1050 train 6.102581 (lr=2.7571e-03) (hash(x)=42513714)
|
| 130 |
+
1060 train 6.183872 (lr=2.7512e-03) (hash(x)=41941750)
|
| 131 |
+
1070 train 6.095507 (lr=2.7452e-03) (hash(x)=38670200)
|
| 132 |
+
1080 train 5.938781 (lr=2.7391e-03) (hash(x)=37161833)
|
| 133 |
+
1090 train 6.174100 (lr=2.7330e-03) (hash(x)=41885859)
|
| 134 |
+
1100 val loss 6.1634
|
| 135 |
+
1100 val perplexity 475.0564
|
| 136 |
+
1100 train 6.076378 (lr=2.7269e-03) (hash(x)=30752379)
|
| 137 |
+
1110 train 5.899285 (lr=2.7206e-03) (hash(x)=36731960)
|
| 138 |
+
1120 train 5.895706 (lr=2.7143e-03) (hash(x)=38122158)
|
| 139 |
+
1130 train 6.211620 (lr=2.7080e-03) (hash(x)=41476640)
|
| 140 |
+
1140 train 6.034586 (lr=2.7016e-03) (hash(x)=40147219)
|
| 141 |
+
1150 train 5.768303 (lr=2.6951e-03) (hash(x)=39740805)
|
| 142 |
+
1160 train 5.879625 (lr=2.6886e-03) (hash(x)=38564136)
|
| 143 |
+
1170 train 5.940179 (lr=2.6820e-03) (hash(x)=37201973)
|
| 144 |
+
1180 train 5.879993 (lr=2.6753e-03) (hash(x)=35761112)
|
| 145 |
+
1190 train 6.487927 (lr=2.6686e-03) (hash(x)=45564774)
|
| 146 |
+
1200 val loss 6.1201
|
| 147 |
+
1200 val perplexity 454.9191
|
| 148 |
+
1200 train 5.796727 (lr=2.6618e-03) (hash(x)=34912485)
|
| 149 |
+
1210 train 5.971030 (lr=2.6550e-03) (hash(x)=36630633)
|
| 150 |
+
1220 train 5.615767 (lr=2.6481e-03) (hash(x)=32533931)
|
| 151 |
+
1230 train 5.842389 (lr=2.6411e-03) (hash(x)=38233985)
|
| 152 |
+
1240 train 5.969805 (lr=2.6341e-03) (hash(x)=42794906)
|
| 153 |
+
1250 train 6.008198 (lr=2.6270e-03) (hash(x)=37951459)
|
| 154 |
+
1260 train 5.944851 (lr=2.6199e-03) (hash(x)=40970790)
|
| 155 |
+
1270 train 5.696421 (lr=2.6127e-03) (hash(x)=37853233)
|
| 156 |
+
1280 train 5.967031 (lr=2.6055e-03) (hash(x)=44243810)
|
| 157 |
+
1290 train 6.204058 (lr=2.5982e-03) (hash(x)=43089904)
|
| 158 |
+
1300 val loss 6.0491
|
| 159 |
+
1300 val perplexity 423.7339
|
| 160 |
+
1300 train 5.773164 (lr=2.5909e-03) (hash(x)=36986419)
|
| 161 |
+
1310 train 5.889661 (lr=2.5835e-03) (hash(x)=38197520)
|
| 162 |
+
1320 train 6.083013 (lr=2.5760e-03) (hash(x)=44102135)
|
| 163 |
+
1330 train 6.082072 (lr=2.5685e-03) (hash(x)=39183556)
|
| 164 |
+
1340 train 5.936688 (lr=2.5609e-03) (hash(x)=42652135)
|
| 165 |
+
1350 train 5.793446 (lr=2.5533e-03) (hash(x)=37542847)
|
| 166 |
+
1360 train 5.829593 (lr=2.5457e-03) (hash(x)=37357575)
|
| 167 |
+
1370 train 5.869967 (lr=2.5379e-03) (hash(x)=37211563)
|
| 168 |
+
1380 train 5.843562 (lr=2.5302e-03) (hash(x)=38293580)
|
| 169 |
+
1390 train 5.775048 (lr=2.5223e-03) (hash(x)=39750125)
|
| 170 |
+
1400 val loss 6.0906
|
| 171 |
+
1400 val perplexity 441.7024
|
| 172 |
+
1400 train 6.024382 (lr=2.5145e-03) (hash(x)=39537431)
|
| 173 |
+
1410 train 6.029010 (lr=2.5066e-03) (hash(x)=40644308)
|
| 174 |
+
1420 train 6.480279 (lr=2.4986e-03) (hash(x)=47023143)
|
| 175 |
+
1430 train 6.053619 (lr=2.4906e-03) (hash(x)=36669415)
|
| 176 |
+
1440 train 6.193233 (lr=2.4825e-03) (hash(x)=39721164)
|
| 177 |
+
1450 train 5.608108 (lr=2.4744e-03) (hash(x)=35718305)
|
| 178 |
+
1460 train 6.036287 (lr=2.4662e-03) (hash(x)=44235616)
|
| 179 |
+
1470 train 6.030736 (lr=2.4580e-03) (hash(x)=39483945)
|
| 180 |
+
1480 train 5.796659 (lr=2.4497e-03) (hash(x)=38800395)
|
| 181 |
+
1490 train 5.896487 (lr=2.4414e-03) (hash(x)=41087022)
|
| 182 |
+
1500 val loss 5.9756
|
| 183 |
+
1500 val perplexity 393.6914
|
| 184 |
+
1500 train 5.672778 (lr=2.4331e-03) (hash(x)=38132225)
|
| 185 |
+
1510 train 5.690163 (lr=2.4247e-03) (hash(x)=37307491)
|
| 186 |
+
1520 train 4.995702 (lr=2.4162e-03) (hash(x)=38656943)
|
| 187 |
+
1530 train 5.967829 (lr=2.4077e-03) (hash(x)=42111934)
|
| 188 |
+
1540 train 5.938928 (lr=2.3992e-03) (hash(x)=45439288)
|
| 189 |
+
1550 train 5.965722 (lr=2.3906e-03) (hash(x)=41611884)
|
| 190 |
+
1560 train 5.872955 (lr=2.3820e-03) (hash(x)=41163449)
|
| 191 |
+
1570 train 5.680617 (lr=2.3734e-03) (hash(x)=35031263)
|
| 192 |
+
1580 train 5.826626 (lr=2.3647e-03) (hash(x)=37462499)
|
| 193 |
+
1590 train 5.962614 (lr=2.3559e-03) (hash(x)=42648103)
|
| 194 |
+
1600 val loss 5.9542
|
| 195 |
+
1600 val perplexity 385.3543
|
| 196 |
+
1600 train 5.746299 (lr=2.3471e-03) (hash(x)=41299173)
|
| 197 |
+
1610 train 6.093915 (lr=2.3383e-03) (hash(x)=41251778)
|
| 198 |
+
1620 train 5.766378 (lr=2.3294e-03) (hash(x)=42046626)
|
| 199 |
+
1630 train 5.866395 (lr=2.3205e-03) (hash(x)=40406538)
|
| 200 |
+
1640 train 6.285133 (lr=2.3116e-03) (hash(x)=53507848)
|
| 201 |
+
1650 train 5.936745 (lr=2.3026e-03) (hash(x)=41616447)
|
| 202 |
+
1660 train 5.959065 (lr=2.2936e-03) (hash(x)=42076630)
|
| 203 |
+
1670 train 6.316203 (lr=2.2845e-03) (hash(x)=45363762)
|
| 204 |
+
1680 train 5.842880 (lr=2.2754e-03) (hash(x)=40213372)
|
| 205 |
+
1690 train 6.138567 (lr=2.2663e-03) (hash(x)=43005357)
|
| 206 |
+
1700 val loss 5.9327
|
| 207 |
+
1700 val perplexity 377.1550
|
| 208 |
+
1700 train 5.889496 (lr=2.2572e-03) (hash(x)=47362661)
|
| 209 |
+
1710 train 5.804827 (lr=2.2480e-03) (hash(x)=43006690)
|
| 210 |
+
1720 train 5.723139 (lr=2.2387e-03) (hash(x)=41020003)
|
| 211 |
+
1730 train 5.599441 (lr=2.2294e-03) (hash(x)=41388965)
|
| 212 |
+
1740 train 5.657528 (lr=2.2201e-03) (hash(x)=40240896)
|
| 213 |
+
1750 train 5.764262 (lr=2.2108e-03) (hash(x)=38161024)
|
| 214 |
+
1760 train 5.665637 (lr=2.2014e-03) (hash(x)=39187552)
|
| 215 |
+
1770 train 5.524759 (lr=2.1920e-03) (hash(x)=36997602)
|
| 216 |
+
1780 train 5.989076 (lr=2.1826e-03) (hash(x)=34519210)
|
| 217 |
+
1790 train 5.634367 (lr=2.1731e-03) (hash(x)=45294931)
|
| 218 |
+
1800 val loss 5.9013
|
| 219 |
+
1800 val perplexity 365.4947
|
| 220 |
+
1800 train 5.742164 (lr=2.1637e-03) (hash(x)=43856756)
|
| 221 |
+
1810 train 5.472896 (lr=2.1541e-03) (hash(x)=39538565)
|
| 222 |
+
1820 train 5.744007 (lr=2.1446e-03) (hash(x)=40850282)
|
| 223 |
+
1830 train 6.007143 (lr=2.1350e-03) (hash(x)=41530022)
|
| 224 |
+
1840 train 5.447040 (lr=2.1254e-03) (hash(x)=42128732)
|
| 225 |
+
1850 train 5.711160 (lr=2.1158e-03) (hash(x)=44294510)
|
| 226 |
+
1860 train 5.752619 (lr=2.1061e-03) (hash(x)=42547901)
|
| 227 |
+
1870 train 5.555669 (lr=2.0964e-03) (hash(x)=38750148)
|
| 228 |
+
1880 train 5.470454 (lr=2.0867e-03) (hash(x)=35073879)
|
| 229 |
+
1890 train 5.679026 (lr=2.0769e-03) (hash(x)=42170459)
|
| 230 |
+
1900 val loss 5.9074
|
| 231 |
+
1900 val perplexity 367.7443
|
| 232 |
+
1900 train 5.960515 (lr=2.0672e-03) (hash(x)=39937031)
|
| 233 |
+
1910 train 5.862342 (lr=2.0574e-03) (hash(x)=41940608)
|
| 234 |
+
1920 train 5.696874 (lr=2.0476e-03) (hash(x)=40555290)
|
| 235 |
+
1930 train 5.915828 (lr=2.0377e-03) (hash(x)=51847973)
|
| 236 |
+
1940 train 5.953328 (lr=2.0279e-03) (hash(x)=39150884)
|
| 237 |
+
1950 train 5.957563 (lr=2.0180e-03) (hash(x)=41853277)
|
| 238 |
+
1960 train 5.626873 (lr=2.0081e-03) (hash(x)=42463514)
|
| 239 |
+
1970 train 5.599295 (lr=1.9982e-03) (hash(x)=37438437)
|
| 240 |
+
1980 train 5.731918 (lr=1.9882e-03) (hash(x)=41342533)
|
| 241 |
+
1990 train 5.439400 (lr=1.9783e-03) (hash(x)=38374872)
|
| 242 |
+
2000 val loss 5.8381
|
| 243 |
+
2000 val perplexity 343.1372
|
| 244 |
+
2000 train 5.992682 (lr=1.9683e-03) (hash(x)=39550913)
|
| 245 |
+
2010 train 5.596606 (lr=1.9583e-03) (hash(x)=41949369)
|
| 246 |
+
2020 train 5.175270 (lr=1.9483e-03) (hash(x)=39876159)
|
| 247 |
+
2030 train 5.383932 (lr=1.9382e-03) (hash(x)=39465793)
|
| 248 |
+
2040 train 5.625202 (lr=1.9282e-03) (hash(x)=44765924)
|
| 249 |
+
2050 train 5.483789 (lr=1.9181e-03) (hash(x)=36425985)
|
| 250 |
+
2060 train 5.621045 (lr=1.9080e-03) (hash(x)=41478281)
|
| 251 |
+
2070 train 5.608891 (lr=1.8979e-03) (hash(x)=37088327)
|
| 252 |
+
2080 train 5.294634 (lr=1.8878e-03) (hash(x)=39731845)
|
| 253 |
+
2090 train 5.783054 (lr=1.8777e-03) (hash(x)=44481426)
|
| 254 |
+
2100 val loss 5.8146
|
| 255 |
+
2100 val perplexity 335.1568
|
| 256 |
+
2100 train 5.862079 (lr=1.8675e-03) (hash(x)=44598443)
|
| 257 |
+
2110 train 5.641122 (lr=1.8574e-03) (hash(x)=42265528)
|
| 258 |
+
2120 train 5.481261 (lr=1.8472e-03) (hash(x)=35395939)
|
| 259 |
+
2130 train 5.908422 (lr=1.8370e-03) (hash(x)=40597472)
|
| 260 |
+
2140 train 5.774949 (lr=1.8268e-03) (hash(x)=38042919)
|
| 261 |
+
2150 train 5.703743 (lr=1.8166e-03) (hash(x)=39716423)
|
| 262 |
+
2160 train 5.674555 (lr=1.8064e-03) (hash(x)=41499874)
|
| 263 |
+
2170 train 5.362947 (lr=1.7962e-03) (hash(x)=38544810)
|
| 264 |
+
2180 train 5.659645 (lr=1.7860e-03) (hash(x)=42581610)
|
| 265 |
+
2190 train 5.642224 (lr=1.7758e-03) (hash(x)=41838855)
|
| 266 |
+
2200 val loss 5.7886
|
| 267 |
+
2200 val perplexity 326.5524
|
| 268 |
+
2200 train 5.776219 (lr=1.7655e-03) (hash(x)=38519887)
|
| 269 |
+
2210 train 5.674378 (lr=1.7553e-03) (hash(x)=41058518)
|
| 270 |
+
2220 train 5.047271 (lr=1.7450e-03) (hash(x)=44141063)
|
| 271 |
+
2230 train 5.471584 (lr=1.7348e-03) (hash(x)=39348572)
|
| 272 |
+
2240 train 5.373843 (lr=1.7245e-03) (hash(x)=40565631)
|
| 273 |
+
2250 train 5.314240 (lr=1.7142e-03) (hash(x)=35679001)
|
| 274 |
+
2260 train 5.356872 (lr=1.7040e-03) (hash(x)=35327316)
|
| 275 |
+
2270 train 5.599993 (lr=1.6937e-03) (hash(x)=42319237)
|
| 276 |
+
2280 train 5.267631 (lr=1.6834e-03) (hash(x)=34722403)
|
| 277 |
+
2290 train 5.801545 (lr=1.6731e-03) (hash(x)=47167627)
|
| 278 |
+
2300 val loss 5.7348
|
| 279 |
+
2300 val perplexity 309.4472
|
| 280 |
+
2300 train 5.371782 (lr=1.6629e-03) (hash(x)=39196366)
|
| 281 |
+
2310 train 5.495155 (lr=1.6526e-03) (hash(x)=41448314)
|
| 282 |
+
2320 train 5.217525 (lr=1.6423e-03) (hash(x)=38083188)
|
| 283 |
+
2330 train 6.138095 (lr=1.6320e-03) (hash(x)=48217064)
|
| 284 |
+
2340 train 5.607168 (lr=1.6217e-03) (hash(x)=40418014)
|
| 285 |
+
2350 train 5.802357 (lr=1.6114e-03) (hash(x)=41000963)
|
| 286 |
+
2360 train 6.415450 (lr=1.6012e-03) (hash(x)=52212186)
|
| 287 |
+
2370 train 5.717125 (lr=1.5909e-03) (hash(x)=34152167)
|
| 288 |
+
2380 train 5.401453 (lr=1.5806e-03) (hash(x)=39727275)
|
| 289 |
+
2390 train 5.400539 (lr=1.5704e-03) (hash(x)=35701246)
|
| 290 |
+
2400 val loss 5.6992
|
| 291 |
+
2400 val perplexity 298.6306
|
| 292 |
+
2400 train 5.509592 (lr=1.5601e-03) (hash(x)=35750369)
|
| 293 |
+
2410 train 5.666783 (lr=1.5498e-03) (hash(x)=36921837)
|
| 294 |
+
2420 train 6.307586 (lr=1.5396e-03) (hash(x)=52333487)
|
| 295 |
+
2430 train 6.096017 (lr=1.5294e-03) (hash(x)=43700247)
|
| 296 |
+
2440 train 5.685547 (lr=1.5191e-03) (hash(x)=38790797)
|
| 297 |
+
2450 train 5.831779 (lr=1.5089e-03) (hash(x)=44909302)
|
| 298 |
+
2460 train 5.790894 (lr=1.4987e-03) (hash(x)=44520063)
|
| 299 |
+
2470 train 5.374334 (lr=1.4885e-03) (hash(x)=28926941)
|
| 300 |
+
2480 train 5.589633 (lr=1.4783e-03) (hash(x)=38034434)
|
| 301 |
+
2490 train 5.915215 (lr=1.4681e-03) (hash(x)=40370265)
|
| 302 |
+
2500 val loss 5.6744
|
| 303 |
+
2500 val perplexity 291.3057
|
| 304 |
+
2500 train 6.844440 (lr=1.4579e-03) (hash(x)=48759128)
|
| 305 |
+
2510 train 5.583824 (lr=1.4477e-03) (hash(x)=38903830)
|
| 306 |
+
2520 train 5.554042 (lr=1.4375e-03) (hash(x)=38343017)
|
| 307 |
+
2530 train 5.665951 (lr=1.4274e-03) (hash(x)=37353172)
|
| 308 |
+
2540 train 5.771531 (lr=1.4173e-03) (hash(x)=43056679)
|
| 309 |
+
2550 train 6.077626 (lr=1.4071e-03) (hash(x)=44884973)
|
| 310 |
+
2560 train 5.891807 (lr=1.3970e-03) (hash(x)=44270024)
|
| 311 |
+
2570 train 5.550761 (lr=1.3869e-03) (hash(x)=37552441)
|
| 312 |
+
2580 train 5.655738 (lr=1.3769e-03) (hash(x)=37548505)
|
| 313 |
+
2590 train 5.549836 (lr=1.3668e-03) (hash(x)=37070515)
|
| 314 |
+
2600 val loss 5.5970
|
| 315 |
+
2600 val perplexity 269.6157
|
| 316 |
+
2600 train 5.588780 (lr=1.3568e-03) (hash(x)=41861606)
|
| 317 |
+
2610 train 5.602142 (lr=1.3467e-03) (hash(x)=38749857)
|
| 318 |
+
2620 train 6.009288 (lr=1.3367e-03) (hash(x)=48282206)
|
| 319 |
+
2630 train 5.665033 (lr=1.3267e-03) (hash(x)=38695111)
|
| 320 |
+
2640 train 5.420346 (lr=1.3168e-03) (hash(x)=36162702)
|
| 321 |
+
2650 train 5.395927 (lr=1.3068e-03) (hash(x)=35619411)
|
| 322 |
+
2660 train 5.714244 (lr=1.2969e-03) (hash(x)=41525016)
|
| 323 |
+
2670 train 5.492519 (lr=1.2870e-03) (hash(x)=39454506)
|
| 324 |
+
2680 train 5.565373 (lr=1.2771e-03) (hash(x)=38205746)
|
| 325 |
+
2690 train 5.629951 (lr=1.2672e-03) (hash(x)=40239766)
|
| 326 |
+
2700 val loss 5.5653
|
| 327 |
+
2700 val perplexity 261.2092
|
| 328 |
+
2700 train 5.958931 (lr=1.2573e-03) (hash(x)=48386728)
|
| 329 |
+
2710 train 5.635997 (lr=1.2475e-03) (hash(x)=39766962)
|
| 330 |
+
2720 train 5.834649 (lr=1.2377e-03) (hash(x)=46288620)
|
| 331 |
+
2730 train 5.637322 (lr=1.2279e-03) (hash(x)=39531992)
|
| 332 |
+
2740 train 5.417400 (lr=1.2182e-03) (hash(x)=38557594)
|
| 333 |
+
2750 train 5.772608 (lr=1.2085e-03) (hash(x)=45712316)
|
| 334 |
+
2760 train 5.390047 (lr=1.1988e-03) (hash(x)=38148531)
|
| 335 |
+
2770 train 5.445625 (lr=1.1891e-03) (hash(x)=38199587)
|
| 336 |
+
2780 train 5.799500 (lr=1.1794e-03) (hash(x)=43995601)
|
| 337 |
+
2790 train 5.766082 (lr=1.1698e-03) (hash(x)=49076165)
|
| 338 |
+
2800 val loss 5.5369
|
| 339 |
+
2800 val perplexity 253.8802
|
| 340 |
+
2800 train 5.755539 (lr=1.1602e-03) (hash(x)=42585188)
|
| 341 |
+
2810 train 5.620761 (lr=1.1506e-03) (hash(x)=42076895)
|
| 342 |
+
2820 train 5.453242 (lr=1.1411e-03) (hash(x)=39243011)
|
| 343 |
+
2830 train 5.599067 (lr=1.1316e-03) (hash(x)=44189646)
|
| 344 |
+
2840 train 5.917010 (lr=1.1221e-03) (hash(x)=44534008)
|
| 345 |
+
2850 train 5.691290 (lr=1.1127e-03) (hash(x)=45896146)
|
| 346 |
+
2860 train 5.388630 (lr=1.1033e-03) (hash(x)=40607651)
|
| 347 |
+
2870 train 5.462972 (lr=1.0939e-03) (hash(x)=39953685)
|
| 348 |
+
2880 train 5.919540 (lr=1.0845e-03) (hash(x)=45594293)
|
| 349 |
+
2890 train 5.482719 (lr=1.0752e-03) (hash(x)=38530396)
|
| 350 |
+
2900 val loss 5.5202
|
| 351 |
+
2900 val perplexity 249.6909
|
| 352 |
+
2900 train 6.492098 (lr=1.0659e-03) (hash(x)=46001938)
|
| 353 |
+
2910 train 5.920892 (lr=1.0567e-03) (hash(x)=42053698)
|
| 354 |
+
2920 train 5.178813 (lr=1.0474e-03) (hash(x)=31288623)
|
| 355 |
+
2930 train 5.596229 (lr=1.0383e-03) (hash(x)=40957911)
|
| 356 |
+
2940 train 5.421710 (lr=1.0291e-03) (hash(x)=37565291)
|
| 357 |
+
2950 train 6.021412 (lr=1.0200e-03) (hash(x)=44688067)
|
| 358 |
+
2960 train 5.389401 (lr=1.0109e-03) (hash(x)=40554915)
|
| 359 |
+
2970 train 5.504748 (lr=1.0019e-03) (hash(x)=41858938)
|
| 360 |
+
2980 train 6.159545 (lr=9.9289e-04) (hash(x)=46677201)
|
| 361 |
+
2990 train 5.423365 (lr=9.8392e-04) (hash(x)=41191005)
|
| 362 |
+
3000 val loss 5.4933
|
| 363 |
+
3000 val perplexity 243.0576
|
| 364 |
+
3000 train 5.604980 (lr=9.7500e-04) (hash(x)=42901823)
|
| 365 |
+
3010 train 5.662110 (lr=9.6612e-04) (hash(x)=37714179)
|
| 366 |
+
3020 train 5.765316 (lr=9.5727e-04) (hash(x)=45451321)
|
| 367 |
+
3030 train 5.735548 (lr=9.4847e-04) (hash(x)=41111660)
|
| 368 |
+
3040 train 5.811325 (lr=9.3970e-04) (hash(x)=48126392)
|
| 369 |
+
3050 train 5.233923 (lr=9.3098e-04) (hash(x)=41165333)
|
| 370 |
+
3060 train 5.460855 (lr=9.2230e-04) (hash(x)=41222845)
|
| 371 |
+
3070 train 5.615535 (lr=9.1366e-04) (hash(x)=39756054)
|
| 372 |
+
3080 train 5.360039 (lr=9.0506e-04) (hash(x)=35102807)
|
| 373 |
+
3090 train 5.561254 (lr=8.9651e-04) (hash(x)=44800641)
|
| 374 |
+
3100 val loss 5.4559
|
| 375 |
+
3100 val perplexity 234.1353
|
| 376 |
+
3100 train 5.419527 (lr=8.8800e-04) (hash(x)=39146350)
|
| 377 |
+
3110 train 5.505163 (lr=8.7954e-04) (hash(x)=38968249)
|
| 378 |
+
3120 train 6.064114 (lr=8.7112e-04) (hash(x)=45757845)
|
| 379 |
+
3130 train 5.641373 (lr=8.6274e-04) (hash(x)=39272467)
|
| 380 |
+
3140 train 5.436275 (lr=8.5441e-04) (hash(x)=40568086)
|
| 381 |
+
3150 train 5.132092 (lr=8.4613e-04) (hash(x)=33341935)
|
| 382 |
+
3160 train 5.487285 (lr=8.3789e-04) (hash(x)=36747042)
|
| 383 |
+
3170 train 5.106658 (lr=8.2970e-04) (hash(x)=34255813)
|
| 384 |
+
3180 train 5.474054 (lr=8.2156e-04) (hash(x)=40994836)
|
| 385 |
+
3190 train 5.427584 (lr=8.1347e-04) (hash(x)=40204220)
|
| 386 |
+
3200 val loss 5.4459
|
| 387 |
+
3200 val perplexity 231.8014
|
| 388 |
+
3200 train 5.382375 (lr=8.0542e-04) (hash(x)=37855244)
|
| 389 |
+
3210 train 5.592527 (lr=7.9742e-04) (hash(x)=42937862)
|
| 390 |
+
3220 train 5.335435 (lr=7.8948e-04) (hash(x)=41573470)
|
| 391 |
+
3230 train 5.308156 (lr=7.8158e-04) (hash(x)=36922132)
|
| 392 |
+
3240 train 5.328730 (lr=7.7373e-04) (hash(x)=38756443)
|
| 393 |
+
3250 train 5.225527 (lr=7.6594e-04) (hash(x)=33303705)
|
| 394 |
+
3260 train 5.366871 (lr=7.5819e-04) (hash(x)=38545233)
|
| 395 |
+
3270 train 5.305439 (lr=7.5050e-04) (hash(x)=37078540)
|
| 396 |
+
3280 train 5.432631 (lr=7.4286e-04) (hash(x)=42842412)
|
| 397 |
+
3290 train 5.256313 (lr=7.3527e-04) (hash(x)=35416091)
|
| 398 |
+
3300 val loss 5.4374
|
| 399 |
+
3300 val perplexity 229.8350
|
| 400 |
+
3300 train 5.710620 (lr=7.2774e-04) (hash(x)=42943006)
|
| 401 |
+
3310 train 5.426646 (lr=7.2026e-04) (hash(x)=39078402)
|
| 402 |
+
3320 train 5.354695 (lr=7.1283e-04) (hash(x)=40069891)
|
| 403 |
+
3330 train 5.569634 (lr=7.0545e-04) (hash(x)=40560947)
|
| 404 |
+
3340 train 5.622434 (lr=6.9814e-04) (hash(x)=39168598)
|
| 405 |
+
3350 train 5.405854 (lr=6.9087e-04) (hash(x)=39228302)
|
| 406 |
+
3360 train 5.255980 (lr=6.8367e-04) (hash(x)=38696155)
|
| 407 |
+
3370 train 5.450393 (lr=6.7651e-04) (hash(x)=38097171)
|
| 408 |
+
3380 train 5.651337 (lr=6.6942e-04) (hash(x)=42707851)
|
| 409 |
+
3390 train 6.033101 (lr=6.6238e-04) (hash(x)=56570802)
|
| 410 |
+
3400 val loss 5.3961
|
| 411 |
+
3400 val perplexity 220.5476
|
| 412 |
+
3400 train 5.286184 (lr=6.5540e-04) (hash(x)=39381717)
|
| 413 |
+
3410 train 6.032186 (lr=6.4848e-04) (hash(x)=45129271)
|
| 414 |
+
3420 train 5.215788 (lr=6.4161e-04) (hash(x)=38942398)
|
| 415 |
+
3430 train 5.070482 (lr=6.3480e-04) (hash(x)=38488960)
|
| 416 |
+
3440 train 5.585747 (lr=6.2806e-04) (hash(x)=45767547)
|
| 417 |
+
3450 train 5.176673 (lr=6.2137e-04) (hash(x)=36198784)
|
| 418 |
+
3460 train 5.489666 (lr=6.1474e-04) (hash(x)=42778044)
|
| 419 |
+
3470 train 5.649846 (lr=6.0817e-04) (hash(x)=44950608)
|
| 420 |
+
3480 train 4.863423 (lr=6.0166e-04) (hash(x)=39044959)
|
| 421 |
+
3490 train 5.425606 (lr=5.9521e-04) (hash(x)=39987339)
|
| 422 |
+
3500 val loss 5.3831
|
| 423 |
+
3500 val perplexity 217.7065
|
| 424 |
+
3500 train 5.434652 (lr=5.8883e-04) (hash(x)=38401262)
|
| 425 |
+
3510 train 5.179955 (lr=5.8250e-04) (hash(x)=37122830)
|
| 426 |
+
3520 train 5.364791 (lr=5.7624e-04) (hash(x)=40987016)
|
| 427 |
+
3530 train 5.169059 (lr=5.7004e-04) (hash(x)=37900005)
|
| 428 |
+
3540 train 5.365578 (lr=5.6390e-04) (hash(x)=40038501)
|
| 429 |
+
3550 train 5.334502 (lr=5.5783e-04) (hash(x)=37671489)
|
| 430 |
+
3560 train 5.389966 (lr=5.5182e-04) (hash(x)=38596282)
|
| 431 |
+
3570 train 5.657457 (lr=5.4587e-04) (hash(x)=41774051)
|
| 432 |
+
3580 train 5.595036 (lr=5.3998e-04) (hash(x)=38610942)
|
| 433 |
+
3590 train 5.089818 (lr=5.3416e-04) (hash(x)=36069068)
|
| 434 |
+
3600 val loss 5.3580
|
| 435 |
+
3600 val perplexity 212.3097
|
| 436 |
+
3600 train 5.414062 (lr=5.2841e-04) (hash(x)=42363563)
|
| 437 |
+
3610 train 5.279015 (lr=5.2272e-04) (hash(x)=34615777)
|
| 438 |
+
3620 train 5.367689 (lr=5.1710e-04) (hash(x)=40899217)
|
| 439 |
+
3630 train 5.423831 (lr=5.1154e-04) (hash(x)=42238236)
|
| 440 |
+
3640 train 5.093359 (lr=5.0604e-04) (hash(x)=34553691)
|
| 441 |
+
3650 train 5.283995 (lr=5.0062e-04) (hash(x)=38697807)
|
| 442 |
+
3660 train 5.345992 (lr=4.9526e-04) (hash(x)=40766257)
|
| 443 |
+
3670 train 5.439585 (lr=4.8997e-04) (hash(x)=39337876)
|
| 444 |
+
3680 train 5.555716 (lr=4.8474e-04) (hash(x)=42335002)
|
| 445 |
+
3690 train 5.306686 (lr=4.7958e-04) (hash(x)=36528848)
|
| 446 |
+
3700 val loss 5.3439
|
| 447 |
+
3700 val perplexity 209.3265
|
| 448 |
+
3700 train 5.352815 (lr=4.7449e-04) (hash(x)=38817765)
|
| 449 |
+
3710 train 5.348447 (lr=4.6947e-04) (hash(x)=38409263)
|
| 450 |
+
3720 train 5.717241 (lr=4.6452e-04) (hash(x)=46547894)
|
| 451 |
+
3730 train 5.532721 (lr=4.5963e-04) (hash(x)=42716380)
|
| 452 |
+
3740 train 5.072857 (lr=4.5482e-04) (hash(x)=35016013)
|
| 453 |
+
3750 train 5.184477 (lr=4.5007e-04) (hash(x)=38076751)
|
| 454 |
+
3760 train 5.359593 (lr=4.4540e-04) (hash(x)=37632632)
|
| 455 |
+
3770 train 4.929888 (lr=4.4079e-04) (hash(x)=41300497)
|
| 456 |
+
3780 train 5.414285 (lr=4.3625e-04) (hash(x)=36222071)
|
| 457 |
+
3790 train 5.313930 (lr=4.3179e-04) (hash(x)=42341695)
|
| 458 |
+
3800 val loss 5.3214
|
| 459 |
+
3800 val perplexity 204.6624
|
| 460 |
+
3800 train 5.301294 (lr=4.2739e-04) (hash(x)=40448838)
|
| 461 |
+
3810 train 5.495556 (lr=4.2307e-04) (hash(x)=41458713)
|
| 462 |
+
3820 train 5.403583 (lr=4.1881e-04) (hash(x)=41813233)
|
| 463 |
+
3830 train 5.154315 (lr=4.1463e-04) (hash(x)=37783109)
|
| 464 |
+
3840 train 5.377775 (lr=4.1052e-04) (hash(x)=38909502)
|
| 465 |
+
3850 train 5.205124 (lr=4.0648e-04) (hash(x)=45321879)
|
| 466 |
+
3860 train 5.499700 (lr=4.0252e-04) (hash(x)=42854087)
|
| 467 |
+
3870 train 5.795658 (lr=3.9862e-04) (hash(x)=54309583)
|
| 468 |
+
3880 train 5.194125 (lr=3.9480e-04) (hash(x)=41118717)
|
| 469 |
+
3890 train 5.439643 (lr=3.9105e-04) (hash(x)=38995555)
|
| 470 |
+
3900 val loss 5.3088
|
| 471 |
+
3900 val perplexity 202.1078
|
| 472 |
+
3900 train 5.799438 (lr=3.8738e-04) (hash(x)=46283603)
|
| 473 |
+
3910 train 5.472976 (lr=3.8378e-04) (hash(x)=43245072)
|
| 474 |
+
3920 train 4.922875 (lr=3.8025e-04) (hash(x)=37286533)
|
| 475 |
+
3930 train 5.469273 (lr=3.7679e-04) (hash(x)=43413014)
|
| 476 |
+
3940 train 5.305347 (lr=3.7341e-04) (hash(x)=42540654)
|
| 477 |
+
3950 train 5.302908 (lr=3.7010e-04) (hash(x)=41489136)
|
| 478 |
+
3960 train 5.817022 (lr=3.6687e-04) (hash(x)=41594224)
|
| 479 |
+
3970 train 4.878980 (lr=3.6371e-04) (hash(x)=38126486)
|
| 480 |
+
3980 train 4.963630 (lr=3.6063e-04) (hash(x)=36803107)
|
| 481 |
+
3990 train 5.435699 (lr=3.5762e-04) (hash(x)=48697262)
|
| 482 |
+
4000 val loss 5.2920
|
| 483 |
+
4000 val perplexity 198.7383
|
| 484 |
+
4000 train 4.849784 (lr=3.5468e-04) (hash(x)=34780610)
|
| 485 |
+
4010 train 5.313143 (lr=3.5183e-04) (hash(x)=38957122)
|
| 486 |
+
4020 train 5.144952 (lr=3.4904e-04) (hash(x)=41312761)
|
| 487 |
+
4030 train 5.304487 (lr=3.4633e-04) (hash(x)=38815685)
|
| 488 |
+
4040 train 5.290574 (lr=3.4370e-04) (hash(x)=40548890)
|
| 489 |
+
4050 train 5.367460 (lr=3.4114e-04) (hash(x)=41487337)
|
| 490 |
+
4060 train 5.449817 (lr=3.3866e-04) (hash(x)=40326916)
|
| 491 |
+
4070 train 5.340825 (lr=3.3626e-04) (hash(x)=39315642)
|
| 492 |
+
4080 train 5.144194 (lr=3.3393e-04) (hash(x)=39593043)
|
| 493 |
+
4090 train 5.210406 (lr=3.3168e-04) (hash(x)=41855711)
|
| 494 |
+
4100 val loss 5.2902
|
| 495 |
+
4100 val perplexity 198.3822
|
| 496 |
+
4100 train 4.922108 (lr=3.2950e-04) (hash(x)=31879830)
|
| 497 |
+
4110 train 5.598635 (lr=3.2740e-04) (hash(x)=42446951)
|
| 498 |
+
4120 train 5.279421 (lr=3.2538e-04) (hash(x)=43833919)
|
| 499 |
+
4130 train 5.258513 (lr=3.2343e-04) (hash(x)=41527761)
|
| 500 |
+
4140 train 5.213408 (lr=3.2156e-04) (hash(x)=37972657)
|
| 501 |
+
4150 train 5.180491 (lr=3.1977e-04) (hash(x)=40068282)
|
| 502 |
+
4160 train 5.406243 (lr=3.1806e-04) (hash(x)=41369110)
|
| 503 |
+
4170 train 5.125205 (lr=3.1642e-04) (hash(x)=34821306)
|
| 504 |
+
4180 train 5.056667 (lr=3.1486e-04) (hash(x)=40148949)
|
| 505 |
+
4190 train 5.203684 (lr=3.1338e-04) (hash(x)=41315194)
|
| 506 |
+
4200 val loss 5.2638
|
| 507 |
+
4200 val perplexity 193.2136
|
| 508 |
+
4200 train 4.899979 (lr=3.1197e-04) (hash(x)=42586995)
|
| 509 |
+
4210 train 4.859787 (lr=3.1065e-04) (hash(x)=36718793)
|
| 510 |
+
4220 train 4.906089 (lr=3.0940e-04) (hash(x)=36462814)
|
| 511 |
+
4230 train 5.541209 (lr=3.0822e-04) (hash(x)=47694519)
|
| 512 |
+
4240 train 5.211882 (lr=3.0713e-04) (hash(x)=37953249)
|
| 513 |
+
4250 train 5.359942 (lr=3.0611e-04) (hash(x)=41039733)
|
| 514 |
+
4260 train 4.859933 (lr=3.0517e-04) (hash(x)=39791205)
|
| 515 |
+
4270 train 5.394708 (lr=3.0431e-04) (hash(x)=38797177)
|
| 516 |
+
4280 train 5.263216 (lr=3.0353e-04) (hash(x)=37485257)
|
| 517 |
+
4290 train 4.743282 (lr=3.0283e-04) (hash(x)=37238242)
|
| 518 |
+
4300 val loss 5.2628
|
| 519 |
+
4300 val perplexity 193.0162
|
| 520 |
+
4300 train 5.429446 (lr=3.0220e-04) (hash(x)=40166116)
|
| 521 |
+
4310 train 5.114768 (lr=3.0165e-04) (hash(x)=33290613)
|
| 522 |
+
4320 train 5.372978 (lr=3.0118e-04) (hash(x)=42501007)
|
| 523 |
+
4330 train 5.486688 (lr=3.0079e-04) (hash(x)=42070500)
|
| 524 |
+
4340 train 5.242562 (lr=3.0048e-04) (hash(x)=39474877)
|
| 525 |
+
4350 train 5.229932 (lr=3.0024e-04) (hash(x)=39074840)
|
| 526 |
+
4360 train 5.349564 (lr=3.0009e-04) (hash(x)=45427492)
|
| 527 |
+
4370 train 5.381782 (lr=3.0001e-04) (hash(x)=48198843)
|
| 528 |
+
4374 val loss 5.2624
|
| 529 |
+
4374 val perplexity 192.9513
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/model_04374.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 97707314
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4df22df54abde012517a6225585c7cba5451f3c4728d24085e2b48e70a98fda4
|
| 3 |
size 97707314
|
logs/fix_1_latent_mask/1_latent_mask_lr_30e-4_n_latent_masks_2_seed_1339/optimizer_04374.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 189136950
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa542e0350dd6e3379f67a45d5ea1b5744ef40c64b550535eaaa6a8ae5706151
|
| 3 |
size 189136950
|