File size: 29,886 Bytes
a9eed45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 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 | 2025-04-29,10:46:51 | INFO | No latest resume checkpoint found in /mnt/personal/zhudongy/datacomp_results/small/low_inter_only/checkpoints.
2025-04-29,10:46:53 | INFO | Running in distributed mode with multiple processes. Device: cuda:0.Process (global: 0, local 0), total 2.
2025-04-29,10:46:53 | INFO | Loaded ViT-B-32 model config.
2025-04-29,10:46:54 | INFO | Model:
2025-04-29,10:46:54 | INFO | CLIP(
(visual): VisionTransformer(
(patchnorm_pre_ln): Identity()
(conv1): Conv2d(3, 768, kernel_size=(32, 32), stride=(32, 32), bias=False)
(patch_dropout): Identity()
(ln_pre): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(transformer): Transformer(
(resblocks): ModuleList(
(0): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(1): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(2): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(3): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(4): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(5): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(6): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(7): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(8): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(9): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(10): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
(11): ResidualAttentionBlock(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=768, out_features=3072, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=3072, out_features=768, bias=True)
)
(ls_2): Identity()
)
)
)
(ln_post): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
)
(transformer): Transformer(
(resblocks): ModuleList(
(0): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(1): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(2): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(3): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(4): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(5): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(6): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(7): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(8): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(9): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(10): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
(11): ResidualAttentionBlock(
(ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(attn): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
)
(ls_1): Identity()
(ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
(mlp): Sequential(
(c_fc): Linear(in_features=512, out_features=2048, bias=True)
(gelu): GELU(approximate='none')
(c_proj): Linear(in_features=2048, out_features=512, bias=True)
)
(ls_2): Identity()
)
)
)
(token_embedding): Embedding(49408, 512)
(ln_final): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
)
2025-04-29,10:46:54 | INFO | Params:
2025-04-29,10:46:54 | INFO | accum_freq: 1
2025-04-29,10:46:54 | INFO | aug_cfg: {}
2025-04-29,10:46:54 | INFO | batch_size: 2048
2025-04-29,10:46:54 | INFO | beta1: 0.9
2025-04-29,10:46:54 | INFO | beta2: 0.98
2025-04-29,10:46:54 | INFO | checkpoint_path: /mnt/personal/zhudongy/datacomp_results/small/low_inter_only/checkpoints
2025-04-29,10:46:54 | INFO | coca_caption_loss_weight: 2.0
2025-04-29,10:46:54 | INFO | coca_contrastive_loss_weight: 1.0
2025-04-29,10:46:54 | INFO | copy_codebase: False
2025-04-29,10:46:54 | INFO | csv_caption_key: title
2025-04-29,10:46:54 | INFO | csv_img_key: filepath
2025-04-29,10:46:54 | INFO | csv_separator:
2025-04-29,10:46:54 | INFO | dataset_resampled: True
2025-04-29,10:46:54 | INFO | dataset_type: webdataset
2025-04-29,10:46:54 | INFO | ddp_static_graph: True
2025-04-29,10:46:54 | INFO | debug: False
2025-04-29,10:46:54 | INFO | delete_previous_checkpoint: False
2025-04-29,10:46:54 | INFO | device: cuda:0
2025-04-29,10:46:54 | INFO | dist_backend: nccl
2025-04-29,10:46:54 | INFO | dist_url: env://
2025-04-29,10:46:54 | INFO | distill: False
2025-04-29,10:46:54 | INFO | distill_model: None
2025-04-29,10:46:54 | INFO | distill_pretrained: None
2025-04-29,10:46:54 | INFO | distributed: True
2025-04-29,10:46:54 | INFO | epochs: 8
2025-04-29,10:46:54 | INFO | epochs_cooldown: None
2025-04-29,10:46:54 | INFO | eps: 1e-06
2025-04-29,10:46:54 | INFO | force_custom_text: False
2025-04-29,10:46:54 | INFO | force_image_size: None
2025-04-29,10:46:54 | INFO | force_patch_dropout: None
2025-04-29,10:46:54 | INFO | force_quick_gelu: False
2025-04-29,10:46:54 | INFO | gather_with_grad: True
2025-04-29,10:46:54 | INFO | grad_checkpointing: True
2025-04-29,10:46:54 | INFO | grad_clip_norm: None
2025-04-29,10:46:54 | INFO | horovod: False
2025-04-29,10:46:54 | INFO | image_mean: None
2025-04-29,10:46:54 | INFO | image_std: None
2025-04-29,10:46:54 | INFO | imagenet_v2: None
2025-04-29,10:46:54 | INFO | imagenet_val: None
2025-04-29,10:46:54 | INFO | local_loss: True
2025-04-29,10:46:54 | INFO | local_rank: 0
2025-04-29,10:46:54 | INFO | lock_image: False
2025-04-29,10:46:54 | INFO | lock_image_freeze_bn_stats: False
2025-04-29,10:46:54 | INFO | lock_image_unlocked_groups: 0
2025-04-29,10:46:54 | INFO | lock_text: False
2025-04-29,10:46:54 | INFO | lock_text_freeze_layer_norm: False
2025-04-29,10:46:54 | INFO | lock_text_unlocked_layers: 0
2025-04-29,10:46:54 | INFO | log_every_n_steps: 100
2025-04-29,10:46:54 | INFO | log_level: 20
2025-04-29,10:46:54 | INFO | log_local: False
2025-04-29,10:46:54 | INFO | log_path: /mnt/personal/zhudongy/datacomp_results/small/low_inter_only/out.log
2025-04-29,10:46:54 | INFO | logs: /mnt/personal/zhudongy/datacomp_results/small
2025-04-29,10:46:54 | INFO | lr: 0.0005
2025-04-29,10:46:54 | INFO | lr_cooldown_end: 0.0
2025-04-29,10:46:54 | INFO | lr_cooldown_power: 1.0
2025-04-29,10:46:54 | INFO | lr_scheduler: cosine
2025-04-29,10:46:54 | INFO | model: ViT-B-32
2025-04-29,10:46:54 | INFO | name: low_inter_only
2025-04-29,10:46:54 | INFO | no_set_device_rank: False
2025-04-29,10:46:54 | INFO | precision: amp_bfloat16
2025-04-29,10:46:54 | INFO | pretrained:
2025-04-29,10:46:54 | INFO | pretrained_image: False
2025-04-29,10:46:54 | INFO | rank: 0
2025-04-29,10:46:54 | INFO | remote_sync: None
2025-04-29,10:46:54 | INFO | remote_sync_frequency: 300
2025-04-29,10:46:54 | INFO | remote_sync_protocol: s3
2025-04-29,10:46:54 | INFO | report_to:
2025-04-29,10:46:54 | INFO | resume: None
2025-04-29,10:46:54 | INFO | save_frequency: 0
2025-04-29,10:46:54 | INFO | save_most_recent: True
2025-04-29,10:46:54 | INFO | seed: 0
2025-04-29,10:46:54 | INFO | skip_scheduler: False
2025-04-29,10:46:54 | INFO | tensorboard: False
2025-04-29,10:46:54 | INFO | tensorboard_path:
2025-04-29,10:46:54 | INFO | torchscript: False
2025-04-29,10:46:54 | INFO | trace: False
2025-04-29,10:46:54 | INFO | train_data: /mnt/personal/zhudongy/datacomp-small/shards/0000{0000..1287}.tar
2025-04-29,10:46:54 | INFO | train_data_upsampling_factors: None
2025-04-29,10:46:54 | INFO | train_num_samples: 1600000
2025-04-29,10:46:54 | INFO | use_bn_sync: False
2025-04-29,10:46:54 | INFO | val_data: None
2025-04-29,10:46:54 | INFO | val_frequency: 1
2025-04-29,10:46:54 | INFO | val_num_samples: None
2025-04-29,10:46:54 | INFO | wandb: False
2025-04-29,10:46:54 | INFO | wandb_notes:
2025-04-29,10:46:54 | INFO | wandb_project_name: open-clip
2025-04-29,10:46:54 | INFO | warmup: 500
2025-04-29,10:46:54 | INFO | wd: 0.2
2025-04-29,10:46:54 | INFO | workers: 4
2025-04-29,10:46:54 | INFO | world_size: 2
2025-04-29,10:46:54 | INFO | zeroshot_frequency: 2
2025-04-29,10:46:54 | INFO | Start epoch 0
2025-04-29,10:47:09 | INFO | Train Epoch: 0 [ 4096/1605632 (0%)] Data (t): 12.367 Batch (t): 14.958, 273.829/s, 136.915/s/gpu LR: 0.000001 Logit Scale: 14.286 Contrastive_loss: 8.3764 (8.3764) Loss: 8.3764 (8.3764)
2025-04-29,10:47:11 | INFO | Reducer buckets have been rebuilt in this iteration.
2025-04-29,10:51:10 | INFO | Train Epoch: 0 [ 413696/1605632 (26%)] Data (t): 0.340 Batch (t): 2.410, 1686.32/s, 843.158/s/gpu LR: 0.000101 Logit Scale: 14.265 Contrastive_loss: 8.2427 (8.3096) Loss: 8.2427 (8.3096)
2025-04-29,10:55:13 | INFO | Train Epoch: 0 [ 823296/1605632 (51%)] Data (t): 0.296 Batch (t): 2.436, 1684.03/s, 842.017/s/gpu LR: 0.000201 Logit Scale: 14.243 Contrastive_loss: 8.1236 (8.2476) Loss: 8.1236 (8.2476)
2025-04-29,10:59:20 | INFO | Train Epoch: 0 [1232896/1605632 (77%)] Data (t): 0.357 Batch (t): 2.468, 1624.40/s, 812.201/s/gpu LR: 0.000301 Logit Scale: 14.221 Contrastive_loss: 7.9420 (8.1712) Loss: 7.9420 (8.1712)
2025-04-29,11:03:10 | INFO | Train Epoch: 0 [1605632/1605632 (100%)] Data (t): 0.417 Batch (t): 2.530, 1728.75/s, 864.375/s/gpu LR: 0.000392 Logit Scale: 14.198 Contrastive_loss: 7.8148 (8.0999) Loss: 7.8148 (8.0999)
2025-04-29,11:03:12 | INFO | Start epoch 1
2025-04-29,11:03:26 | INFO | Train Epoch: 1 [ 4096/1605632 (0%)] Data (t): 11.181 Batch (t): 13.231, 309.584/s, 154.792/s/gpu LR: 0.000393 Logit Scale: 14.198 Contrastive_loss: 7.8044 (7.8044) Loss: 7.8044 (7.8044)
2025-04-29,11:07:36 | INFO | Train Epoch: 1 [ 413696/1605632 (26%)] Data (t): 0.380 Batch (t): 2.507, 1574.67/s, 787.334/s/gpu LR: 0.000493 Logit Scale: 14.191 Contrastive_loss: 7.7343 (7.7694) Loss: 7.7343 (7.7694)
2025-04-29,11:11:47 | INFO | Train Epoch: 1 [ 823296/1605632 (51%)] Data (t): 0.374 Batch (t): 2.502, 1134.29/s, 567.146/s/gpu LR: 0.000498 Logit Scale: 14.212 Contrastive_loss: 7.6846 (7.7411) Loss: 7.6846 (7.7411)
2025-04-29,11:16:16 | INFO | Train Epoch: 1 [1232896/1605632 (77%)] Data (t): 0.619 Batch (t): 2.694, 1629.58/s, 814.789/s/gpu LR: 0.000493 Logit Scale: 14.257 Contrastive_loss: 7.5485 (7.6930) Loss: 7.5485 (7.6930)
2025-04-29,11:20:17 | INFO | Train Epoch: 1 [1605632/1605632 (100%)] Data (t): 0.482 Batch (t): 2.646, 1703.80/s, 851.899/s/gpu LR: 0.000486 Logit Scale: 14.345 Contrastive_loss: 7.3599 (7.6263) Loss: 7.3599 (7.6263)
2025-04-29,11:20:19 | INFO | Start epoch 2
2025-04-29,11:20:31 | INFO | Train Epoch: 2 [ 4096/1605632 (0%)] Data (t): 10.642 Batch (t): 12.727, 321.831/s, 160.916/s/gpu LR: 0.000486 Logit Scale: 14.347 Contrastive_loss: 7.2405 (7.2405) Loss: 7.2405 (7.2405)
2025-04-29,11:24:41 | INFO | Train Epoch: 2 [ 413696/1605632 (26%)] Data (t): 0.355 Batch (t): 2.492, 1714.72/s, 857.358/s/gpu LR: 0.000474 Logit Scale: 14.450 Contrastive_loss: 7.4679 (7.3542) Loss: 7.4679 (7.3542)
2025-04-29,11:28:51 | INFO | Train Epoch: 2 [ 823296/1605632 (51%)] Data (t): 0.408 Batch (t): 2.510, 1154.44/s, 577.221/s/gpu LR: 0.000460 Logit Scale: 14.545 Contrastive_loss: 7.2964 (7.3349) Loss: 7.2964 (7.3349)
2025-04-29,11:33:00 | INFO | Train Epoch: 2 [1232896/1605632 (77%)] Data (t): 0.394 Batch (t): 2.484, 1699.79/s, 849.896/s/gpu LR: 0.000442 Logit Scale: 14.677 Contrastive_loss: 7.1794 (7.2960) Loss: 7.1794 (7.2960)
2025-04-29,11:36:40 | INFO | Train Epoch: 2 [1605632/1605632 (100%)] Data (t): 0.343 Batch (t): 2.421, 1718.76/s, 859.379/s/gpu LR: 0.000423 Logit Scale: 14.812 Contrastive_loss: 7.2101 (7.2789) Loss: 7.2101 (7.2789)
2025-04-29,11:36:42 | INFO | Start epoch 3
2025-04-29,11:36:55 | INFO | Train Epoch: 3 [ 4096/1605632 (0%)] Data (t): 10.902 Batch (t): 12.965, 315.925/s, 157.962/s/gpu LR: 0.000423 Logit Scale: 14.814 Contrastive_loss: 7.1536 (7.1536) Loss: 7.1536 (7.1536)
2025-04-29,11:41:22 | INFO | Train Epoch: 3 [ 413696/1605632 (26%)] Data (t): 0.491 Batch (t): 2.665, 1701.82/s, 850.912/s/gpu LR: 0.000400 Logit Scale: 14.984 Contrastive_loss: 7.1237 (7.1387) Loss: 7.1237 (7.1387)
2025-04-29,11:45:33 | INFO | Train Epoch: 3 [ 823296/1605632 (51%)] Data (t): 0.387 Batch (t): 2.511, 1014.82/s, 507.408/s/gpu LR: 0.000376 Logit Scale: 15.179 Contrastive_loss: 6.8644 (7.0472) Loss: 6.8644 (7.0472)
2025-04-29,11:49:47 | INFO | Train Epoch: 3 [1232896/1605632 (77%)] Data (t): 0.452 Batch (t): 2.541, 1693.74/s, 846.870/s/gpu LR: 0.000349 Logit Scale: 15.355 Contrastive_loss: 6.6430 (6.9462) Loss: 6.6430 (6.9462)
2025-04-29,11:53:29 | INFO | Train Epoch: 3 [1605632/1605632 (100%)] Data (t): 0.371 Batch (t): 2.446, 1680.22/s, 840.108/s/gpu LR: 0.000324 Logit Scale: 15.544 Contrastive_loss: 6.8729 (6.9315) Loss: 6.8729 (6.9315)
2025-04-29,11:53:31 | INFO | Start epoch 4
2025-04-29,11:53:45 | INFO | Train Epoch: 4 [ 4096/1605632 (0%)] Data (t): 11.803 Batch (t): 13.888, 294.923/s, 147.461/s/gpu LR: 0.000323 Logit Scale: 15.546 Contrastive_loss: 6.8561 (6.8561) Loss: 6.8561 (6.8561)
2025-04-29,11:57:50 | INFO | Train Epoch: 4 [ 413696/1605632 (26%)] Data (t): 0.373 Batch (t): 2.446, 1742.13/s, 871.064/s/gpu LR: 0.000294 Logit Scale: 15.744 Contrastive_loss: 6.6737 (6.7649) Loss: 6.6737 (6.7649)
2025-04-29,12:01:49 | INFO | Train Epoch: 4 [ 823296/1605632 (51%)] Data (t): 0.263 Batch (t): 2.394, 1726.45/s, 863.225/s/gpu LR: 0.000265 Logit Scale: 15.914 Contrastive_loss: 6.7540 (6.7613) Loss: 6.7540 (6.7613)
2025-04-29,12:05:52 | INFO | Train Epoch: 4 [1232896/1605632 (77%)] Data (t): 0.278 Batch (t): 2.430, 1668.21/s, 834.103/s/gpu LR: 0.000235 Logit Scale: 16.076 Contrastive_loss: 6.7919 (6.7689) Loss: 6.7919 (6.7689)
2025-04-29,12:09:34 | INFO | Train Epoch: 4 [1605632/1605632 (100%)] Data (t): 0.279 Batch (t): 2.440, 1555.69/s, 777.845/s/gpu LR: 0.000208 Logit Scale: 16.253 Contrastive_loss: 6.6502 (6.7452) Loss: 6.6502 (6.7452)
2025-04-29,12:09:36 | INFO | Start epoch 5
2025-04-29,12:09:50 | INFO | Train Epoch: 5 [ 4096/1605632 (0%)] Data (t): 11.275 Batch (t): 13.347, 306.892/s, 153.446/s/gpu LR: 0.000208 Logit Scale: 16.255 Contrastive_loss: 6.6999 (6.6999) Loss: 6.6999 (6.6999)
2025-04-29,12:14:05 | INFO | Train Epoch: 5 [ 413696/1605632 (26%)] Data (t): 0.431 Batch (t): 2.551, 1723.17/s, 861.587/s/gpu LR: 0.000179 Logit Scale: 16.426 Contrastive_loss: 6.5666 (6.6333) Loss: 6.5666 (6.6333)
2025-04-29,12:18:18 | INFO | Train Epoch: 5 [ 823296/1605632 (51%)] Data (t): 0.404 Batch (t): 2.528, 1332.54/s, 666.268/s/gpu LR: 0.000151 Logit Scale: 16.569 Contrastive_loss: 6.4771 (6.5812) Loss: 6.4771 (6.5812)
2025-04-29,12:22:19 | INFO | Train Epoch: 5 [1232896/1605632 (77%)] Data (t): 0.336 Batch (t): 2.412, 1709.31/s, 854.657/s/gpu LR: 0.000124 Logit Scale: 16.692 Contrastive_loss: 6.5475 (6.5728) Loss: 6.5475 (6.5728)
2025-04-29,12:25:58 | INFO | Train Epoch: 5 [1605632/1605632 (100%)] Data (t): 0.336 Batch (t): 2.405, 1729.43/s, 864.715/s/gpu LR: 0.000102 Logit Scale: 16.794 Contrastive_loss: 6.5236 (6.5629) Loss: 6.5236 (6.5629)
2025-04-29,12:26:00 | INFO | Start epoch 6
2025-04-29,12:26:13 | INFO | Train Epoch: 6 [ 4096/1605632 (0%)] Data (t): 11.106 Batch (t): 13.199, 310.322/s, 155.161/s/gpu LR: 0.000101 Logit Scale: 16.795 Contrastive_loss: 6.4957 (6.4957) Loss: 6.4957 (6.4957)
2025-04-29,12:30:20 | INFO | Train Epoch: 6 [ 413696/1605632 (26%)] Data (t): 0.374 Batch (t): 2.472, 1508.63/s, 754.316/s/gpu LR: 0.000079 Logit Scale: 16.882 Contrastive_loss: 6.0769 (6.2863) Loss: 6.0769 (6.2863)
2025-04-29,12:34:22 | INFO | Train Epoch: 6 [ 823296/1605632 (51%)] Data (t): 0.286 Batch (t): 2.416, 1530.56/s, 765.282/s/gpu LR: 0.000058 Logit Scale: 16.958 Contrastive_loss: 6.2138 (6.2621) Loss: 6.2138 (6.2621)
2025-04-29,12:38:24 | INFO | Train Epoch: 6 [1232896/1605632 (77%)] Data (t): 0.277 Batch (t): 2.422, 1757.06/s, 878.529/s/gpu LR: 0.000040 Logit Scale: 17.014 Contrastive_loss: 6.1187 (6.2263) Loss: 6.1187 (6.2263)
2025-04-29,12:42:22 | INFO | Train Epoch: 6 [1605632/1605632 (100%)] Data (t): 0.538 Batch (t): 2.620, 1698.75/s, 849.373/s/gpu LR: 0.000027 Logit Scale: 17.051 Contrastive_loss: 6.2108 (6.2232) Loss: 6.2108 (6.2232)
2025-04-29,12:42:24 | INFO | Start epoch 7
2025-04-29,12:42:38 | INFO | Train Epoch: 7 [ 4096/1605632 (0%)] Data (t): 11.138 Batch (t): 13.217, 309.905/s, 154.953/s/gpu LR: 0.000027 Logit Scale: 17.051 Contrastive_loss: 6.2225 (6.2225) Loss: 6.2225 (6.2225)
2025-04-29,12:46:42 | INFO | Train Epoch: 7 [ 413696/1605632 (26%)] Data (t): 0.329 Batch (t): 2.443, 1574.65/s, 787.324/s/gpu LR: 0.000015 Logit Scale: 17.075 Contrastive_loss: 6.2199 (6.2212) Loss: 6.2199 (6.2212)
2025-04-29,12:50:48 | INFO | Train Epoch: 7 [ 823296/1605632 (51%)] Data (t): 0.363 Batch (t): 2.459, 1682.10/s, 841.051/s/gpu LR: 0.000007 Logit Scale: 17.089 Contrastive_loss: 6.2006 (6.2143) Loss: 6.2006 (6.2143)
2025-04-29,12:54:50 | INFO | Train Epoch: 7 [1232896/1605632 (77%)] Data (t): 0.336 Batch (t): 2.418, 1614.35/s, 807.177/s/gpu LR: 0.000002 Logit Scale: 17.093 Contrastive_loss: 6.0595 (6.1756) Loss: 6.0595 (6.1756)
2025-04-29,12:58:34 | INFO | Train Epoch: 7 [1605632/1605632 (100%)] Data (t): 0.342 Batch (t): 2.461, 1719.27/s, 859.635/s/gpu LR: 0.000000 Logit Scale: 17.094 Contrastive_loss: 6.1999 (6.1805) Loss: 6.1999 (6.1805)
|