Text Generation
Transformers
TensorBoard
Safetensors
English
qwen3
byte-level
pretraining
symbolic
text-generation-inference
Instructions to use dotlabs/void.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dotlabs/void.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dotlabs/void.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dotlabs/void.1") model = AutoModelForCausalLM.from_pretrained("dotlabs/void.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dotlabs/void.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dotlabs/void.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dotlabs/void.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dotlabs/void.1
- SGLang
How to use dotlabs/void.1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "dotlabs/void.1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dotlabs/void.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "dotlabs/void.1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dotlabs/void.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dotlabs/void.1 with Docker Model Runner:
docker model run hf.co/dotlabs/void.1
Update TensorBoard training metrics
Browse files
benchmark_cache/performance.json
CHANGED
|
@@ -49,11 +49,11 @@
|
|
| 49 |
"selected": {
|
| 50 |
"microbatch": 86,
|
| 51 |
"mode": "compiled",
|
| 52 |
-
"microbatch_seconds": 0.
|
| 53 |
-
"peak_gb": 85.
|
| 54 |
"fits_budget": true,
|
| 55 |
-
"estimated_update_seconds": 0.
|
| 56 |
-
"input_tokens_per_second":
|
| 57 |
},
|
| 58 |
"measurements": [
|
| 59 |
{
|
|
|
|
| 49 |
"selected": {
|
| 50 |
"microbatch": 86,
|
| 51 |
"mode": "compiled",
|
| 52 |
+
"microbatch_seconds": 0.8971913670000049,
|
| 53 |
+
"peak_gb": 85.39913082122803,
|
| 54 |
"fits_budget": true,
|
| 55 |
+
"estimated_update_seconds": 0.9531432340000379,
|
| 56 |
+
"input_tokens_per_second": 196310.40431087767
|
| 57 |
},
|
| 58 |
"measurements": [
|
| 59 |
{
|
benchmark_cache/shard_scheduler.json
CHANGED
|
@@ -22,8 +22,8 @@
|
|
| 22 |
"tokens_per_second": 1062967.6168812835,
|
| 23 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 24 |
"estimated_pages_for_buffer": 1,
|
| 25 |
-
"required_token_positions_per_second":
|
| 26 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"source": "rewrite6",
|
|
@@ -36,8 +36,8 @@
|
|
| 36 |
"tokens_per_second": 1206672.263377472,
|
| 37 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 38 |
"estimated_pages_for_buffer": 1,
|
| 39 |
-
"required_token_positions_per_second":
|
| 40 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"source": "openmath",
|
|
@@ -50,8 +50,8 @@
|
|
| 50 |
"tokens_per_second": 410042.7581134458,
|
| 51 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 52 |
"estimated_pages_for_buffer": 1,
|
| 53 |
-
"required_token_positions_per_second":
|
| 54 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"source": "ultra_qa",
|
|
@@ -64,8 +64,8 @@
|
|
| 64 |
"tokens_per_second": 2163486.5624068812,
|
| 65 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 66 |
"estimated_pages_for_buffer": 1,
|
| 67 |
-
"required_token_positions_per_second":
|
| 68 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"source": "ultra_style",
|
|
@@ -78,8 +78,8 @@
|
|
| 78 |
"tokens_per_second": 1546694.2737633225,
|
| 79 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 80 |
"estimated_pages_for_buffer": 1,
|
| 81 |
-
"required_token_positions_per_second":
|
| 82 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"source": "cortex",
|
|
@@ -92,8 +92,8 @@
|
|
| 92 |
"tokens_per_second": 1015177.8395898147,
|
| 93 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 94 |
"estimated_pages_for_buffer": 22,
|
| 95 |
-
"required_token_positions_per_second":
|
| 96 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 97 |
}
|
| 98 |
],
|
| 99 |
"gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
|
|
@@ -155,415 +155,30 @@
|
|
| 155 |
"shard_benchmark_scope": "Local packing/read measurements; upload capacity measured only on real data commits. Targets larger than available pages are sample-limited.",
|
| 156 |
"estimated_fresh_generation_batch_seconds": 0.1434574083060457,
|
| 157 |
"selected": {
|
| 158 |
-
"prefetch_batches":
|
| 159 |
"prefetch_capacity_limit": 512,
|
| 160 |
"batch_memory_estimate_bytes": 688946,
|
| 161 |
-
"producer_batch_seconds":
|
| 162 |
-
"producer_p95_seconds":
|
| 163 |
-
"gpu_update_seconds": 0.
|
| 164 |
-
"producer_batches_per_second":
|
| 165 |
-
"gpu_batches_per_second": 1.
|
| 166 |
-
"producer_headroom":
|
| 167 |
-
"sustainable":
|
| 168 |
-
"buffer_seconds": 60.
|
| 169 |
-
"buffer_drain_seconds":
|
| 170 |
"shard_target_mib": 16,
|
| 171 |
-
"upload_pages_per_commit":
|
| 172 |
-
"max_pending_pages":
|
| 173 |
-
"generation_bytes_per_second":
|
| 174 |
-
"upload_bytes_per_second":
|
| 175 |
-
"upload_sustainable":
|
| 176 |
"logical_page_rows": 4096,
|
| 177 |
"logical_cortex_page_rows": 128,
|
| 178 |
-
"estimated_full_shards_per_hour":
|
| 179 |
"selection_policy": "Smallest shard within 90% of measured local peak, enlarged to amortize 30 seconds of measured page production; bounded to 256 MiB."
|
| 180 |
},
|
| 181 |
-
"upload_measurements": [
|
| 182 |
-
{
|
| 183 |
-
"seconds": 1.2104173959960463,
|
| 184 |
-
"bytes": 11923116,
|
| 185 |
-
"pages": 37,
|
| 186 |
-
"shards": 3
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"seconds": 1.3382599670003401,
|
| 190 |
-
"bytes": 7199956,
|
| 191 |
-
"pages": 28,
|
| 192 |
-
"shards": 3
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"seconds": 1.2495986109934165,
|
| 196 |
-
"bytes": 6159261,
|
| 197 |
-
"pages": 36,
|
| 198 |
-
"shards": 2
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"seconds": 1.4083330920038861,
|
| 202 |
-
"bytes": 7782602,
|
| 203 |
-
"pages": 38,
|
| 204 |
-
"shards": 3
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"seconds": 0.8252346610024688,
|
| 208 |
-
"bytes": 897645,
|
| 209 |
-
"pages": 26,
|
| 210 |
-
"shards": 1
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"seconds": 1.2508048210002016,
|
| 214 |
-
"bytes": 6000035,
|
| 215 |
-
"pages": 32,
|
| 216 |
-
"shards": 2
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"seconds": 1.173013809006079,
|
| 220 |
-
"bytes": 12591906,
|
| 221 |
-
"pages": 40,
|
| 222 |
-
"shards": 4
|
| 223 |
-
},
|
| 224 |
-
{
|
| 225 |
-
"seconds": 0.9398781409981893,
|
| 226 |
-
"bytes": 5766570,
|
| 227 |
-
"pages": 28,
|
| 228 |
-
"shards": 2
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"seconds": 1.1578597999978228,
|
| 232 |
-
"bytes": 6291400,
|
| 233 |
-
"pages": 36,
|
| 234 |
-
"shards": 2
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"seconds": 1.1973399740018067,
|
| 238 |
-
"bytes": 6867540,
|
| 239 |
-
"pages": 31,
|
| 240 |
-
"shards": 3
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"seconds": 1.0004031040007249,
|
| 244 |
-
"bytes": 6252534,
|
| 245 |
-
"pages": 36,
|
| 246 |
-
"shards": 2
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"seconds": 0.9013959430012619,
|
| 250 |
-
"bytes": 1172916,
|
| 251 |
-
"pages": 35,
|
| 252 |
-
"shards": 1
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"seconds": 1.3720371540039196,
|
| 256 |
-
"bytes": 13095615,
|
| 257 |
-
"pages": 33,
|
| 258 |
-
"shards": 4
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"seconds": 1.1362720050019561,
|
| 262 |
-
"bytes": 5854630,
|
| 263 |
-
"pages": 28,
|
| 264 |
-
"shards": 2
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"seconds": 1.0005343860029825,
|
| 268 |
-
"bytes": 7274137,
|
| 269 |
-
"pages": 40,
|
| 270 |
-
"shards": 3
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"seconds": 0.9837193970015505,
|
| 274 |
-
"bytes": 6134787,
|
| 275 |
-
"pages": 28,
|
| 276 |
-
"shards": 2
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"seconds": 0.8095773189997999,
|
| 280 |
-
"bytes": 1214722,
|
| 281 |
-
"pages": 34,
|
| 282 |
-
"shards": 1
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"seconds": 1.0524650669976836,
|
| 286 |
-
"bytes": 7528154,
|
| 287 |
-
"pages": 39,
|
| 288 |
-
"shards": 3
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"seconds": 1.1210896519987728,
|
| 292 |
-
"bytes": 9406921,
|
| 293 |
-
"pages": 24,
|
| 294 |
-
"shards": 3
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"seconds": 0.883425399006228,
|
| 298 |
-
"bytes": 6847863,
|
| 299 |
-
"pages": 36,
|
| 300 |
-
"shards": 2
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"seconds": 1.1994957349961624,
|
| 304 |
-
"bytes": 7913979,
|
| 305 |
-
"pages": 39,
|
| 306 |
-
"shards": 3
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"seconds": 0.9844400470028631,
|
| 310 |
-
"bytes": 5585376,
|
| 311 |
-
"pages": 31,
|
| 312 |
-
"shards": 2
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"seconds": 1.2727246810027282,
|
| 316 |
-
"bytes": 7625766,
|
| 317 |
-
"pages": 39,
|
| 318 |
-
"shards": 3
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"seconds": 1.004631062001863,
|
| 322 |
-
"bytes": 5973803,
|
| 323 |
-
"pages": 28,
|
| 324 |
-
"shards": 3
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"seconds": 0.8451246749973507,
|
| 328 |
-
"bytes": 1134510,
|
| 329 |
-
"pages": 31,
|
| 330 |
-
"shards": 1
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"seconds": 1.538072485003795,
|
| 334 |
-
"bytes": 17347426,
|
| 335 |
-
"pages": 42,
|
| 336 |
-
"shards": 5
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"seconds": 0.7935998479952104,
|
| 340 |
-
"bytes": 915809,
|
| 341 |
-
"pages": 26,
|
| 342 |
-
"shards": 1
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"seconds": 1.023697215001448,
|
| 346 |
-
"bytes": 5944681,
|
| 347 |
-
"pages": 28,
|
| 348 |
-
"shards": 2
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"seconds": 1.1792278270004317,
|
| 352 |
-
"bytes": 7823958,
|
| 353 |
-
"pages": 39,
|
| 354 |
-
"shards": 3
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"seconds": 0.8525673530020867,
|
| 358 |
-
"bytes": 874907,
|
| 359 |
-
"pages": 29,
|
| 360 |
-
"shards": 1
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"seconds": 1.313098856000579,
|
| 364 |
-
"bytes": 12314988,
|
| 365 |
-
"pages": 40,
|
| 366 |
-
"shards": 4
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"seconds": 1.0287573200039333,
|
| 370 |
-
"bytes": 6604059,
|
| 371 |
-
"pages": 29,
|
| 372 |
-
"shards": 2
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"seconds": 1.7441577479985426,
|
| 376 |
-
"bytes": 6315821,
|
| 377 |
-
"pages": 37,
|
| 378 |
-
"shards": 2
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"seconds": 1.1457721929982654,
|
| 382 |
-
"bytes": 7494949,
|
| 383 |
-
"pages": 31,
|
| 384 |
-
"shards": 3
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"seconds": 1.081332374997146,
|
| 388 |
-
"bytes": 4594114,
|
| 389 |
-
"pages": 33,
|
| 390 |
-
"shards": 2
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"seconds": 1.2605919760026154,
|
| 394 |
-
"bytes": 7665641,
|
| 395 |
-
"pages": 39,
|
| 396 |
-
"shards": 3
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"seconds": 0.8218483260061475,
|
| 400 |
-
"bytes": 877627,
|
| 401 |
-
"pages": 26,
|
| 402 |
-
"shards": 1
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"seconds": 1.2613383260031696,
|
| 406 |
-
"bytes": 16394940,
|
| 407 |
-
"pages": 36,
|
| 408 |
-
"shards": 4
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"seconds": 0.905758473003516,
|
| 412 |
-
"bytes": 2394822,
|
| 413 |
-
"pages": 29,
|
| 414 |
-
"shards": 2
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"seconds": 1.1017353439965518,
|
| 418 |
-
"bytes": 6253503,
|
| 419 |
-
"pages": 37,
|
| 420 |
-
"shards": 2
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"seconds": 0.9588809769993532,
|
| 424 |
-
"bytes": 6125282,
|
| 425 |
-
"pages": 36,
|
| 426 |
-
"shards": 2
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"seconds": 0.9744295950004016,
|
| 430 |
-
"bytes": 2367982,
|
| 431 |
-
"pages": 28,
|
| 432 |
-
"shards": 2
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"seconds": 1.3454053969981032,
|
| 436 |
-
"bytes": 10041564,
|
| 437 |
-
"pages": 36,
|
| 438 |
-
"shards": 3
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"seconds": 1.0813021310023032,
|
| 442 |
-
"bytes": 11884187,
|
| 443 |
-
"pages": 33,
|
| 444 |
-
"shards": 3
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"seconds": 1.40637977100414,
|
| 448 |
-
"bytes": 2510183,
|
| 449 |
-
"pages": 32,
|
| 450 |
-
"shards": 2
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"seconds": 1.0644101150028291,
|
| 454 |
-
"bytes": 6182736,
|
| 455 |
-
"pages": 31,
|
| 456 |
-
"shards": 2
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"seconds": 0.9900214689987479,
|
| 460 |
-
"bytes": 7195842,
|
| 461 |
-
"pages": 39,
|
| 462 |
-
"shards": 3
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"seconds": 0.9428835689977859,
|
| 466 |
-
"bytes": 6081294,
|
| 467 |
-
"pages": 29,
|
| 468 |
-
"shards": 2
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"seconds": 1.0487947950023226,
|
| 472 |
-
"bytes": 6119662,
|
| 473 |
-
"pages": 36,
|
| 474 |
-
"shards": 2
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"seconds": 1.450646893994417,
|
| 478 |
-
"bytes": 8376549,
|
| 479 |
-
"pages": 35,
|
| 480 |
-
"shards": 3
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"seconds": 1.3019169199978933,
|
| 484 |
-
"bytes": 10756780,
|
| 485 |
-
"pages": 38,
|
| 486 |
-
"shards": 3
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"seconds": 0.8772854299968458,
|
| 490 |
-
"bytes": 890505,
|
| 491 |
-
"pages": 27,
|
| 492 |
-
"shards": 1
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"seconds": 1.5016928080003709,
|
| 496 |
-
"bytes": 7912541,
|
| 497 |
-
"pages": 39,
|
| 498 |
-
"shards": 3
|
| 499 |
-
},
|
| 500 |
-
{
|
| 501 |
-
"seconds": 1.108448890998261,
|
| 502 |
-
"bytes": 5841766,
|
| 503 |
-
"pages": 29,
|
| 504 |
-
"shards": 2
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"seconds": 1.3174200319990632,
|
| 508 |
-
"bytes": 6541341,
|
| 509 |
-
"pages": 36,
|
| 510 |
-
"shards": 4
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"seconds": 0.8383738030024688,
|
| 514 |
-
"bytes": 5644417,
|
| 515 |
-
"pages": 20,
|
| 516 |
-
"shards": 2
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"seconds": 1.0810062999953516,
|
| 520 |
-
"bytes": 7189534,
|
| 521 |
-
"pages": 45,
|
| 522 |
-
"shards": 2
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"seconds": 1.0300960800013854,
|
| 526 |
-
"bytes": 7293613,
|
| 527 |
-
"pages": 30,
|
| 528 |
-
"shards": 3
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"seconds": 1.0630002480029361,
|
| 532 |
-
"bytes": 10382512,
|
| 533 |
-
"pages": 40,
|
| 534 |
-
"shards": 3
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"seconds": 0.9968646140041528,
|
| 538 |
-
"bytes": 2322828,
|
| 539 |
-
"pages": 29,
|
| 540 |
-
"shards": 2
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"seconds": 1.0511976910056546,
|
| 544 |
-
"bytes": 6096964,
|
| 545 |
-
"pages": 37,
|
| 546 |
-
"shards": 2
|
| 547 |
-
},
|
| 548 |
-
{
|
| 549 |
-
"seconds": 1.0299214569968171,
|
| 550 |
-
"bytes": 6792847,
|
| 551 |
-
"pages": 29,
|
| 552 |
-
"shards": 2
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"seconds": 1.0909810750017641,
|
| 556 |
-
"bytes": 11694230,
|
| 557 |
-
"pages": 35,
|
| 558 |
-
"shards": 4
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"seconds": 0.9577424080052879,
|
| 562 |
-
"bytes": 6389346,
|
| 563 |
-
"pages": 38,
|
| 564 |
-
"shards": 2
|
| 565 |
-
}
|
| 566 |
-
],
|
| 567 |
"cache_key": {
|
| 568 |
"version": 1,
|
| 569 |
"kind": "data",
|
|
@@ -606,7 +221,7 @@
|
|
| 606 |
},
|
| 607 |
"cache_reused": true,
|
| 608 |
"resume_probe_seconds": [
|
| 609 |
-
|
| 610 |
-
0.
|
| 611 |
]
|
| 612 |
}
|
|
|
|
| 22 |
"tokens_per_second": 1062967.6168812835,
|
| 23 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 24 |
"estimated_pages_for_buffer": 1,
|
| 25 |
+
"required_token_positions_per_second": 77352.4874016963,
|
| 26 |
+
"required_pages_per_second_upper_estimate": 0.006704717559892074
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"source": "rewrite6",
|
|
|
|
| 36 |
"tokens_per_second": 1206672.263377472,
|
| 37 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 38 |
"estimated_pages_for_buffer": 1,
|
| 39 |
+
"required_token_positions_per_second": 9669.060925212038,
|
| 40 |
+
"required_pages_per_second_upper_estimate": 0.003857132968410738
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"source": "openmath",
|
|
|
|
| 50 |
"tokens_per_second": 410042.7581134458,
|
| 51 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 52 |
"estimated_pages_for_buffer": 1,
|
| 53 |
+
"required_token_positions_per_second": 19338.121850424075,
|
| 54 |
+
"required_pages_per_second_upper_estimate": 0.004473534150775073
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"source": "ultra_qa",
|
|
|
|
| 64 |
"tokens_per_second": 2163486.5624068812,
|
| 65 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 66 |
"estimated_pages_for_buffer": 1,
|
| 67 |
+
"required_token_positions_per_second": 29007.182775636113,
|
| 68 |
+
"required_pages_per_second_upper_estimate": 0.0017663852421099956
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"source": "ultra_style",
|
|
|
|
| 78 |
"tokens_per_second": 1546694.2737633225,
|
| 79 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 80 |
"estimated_pages_for_buffer": 1,
|
| 81 |
+
"required_token_positions_per_second": 29007.182775636113,
|
| 82 |
+
"required_pages_per_second_upper_estimate": 0.002233053227089629
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"source": "cortex",
|
|
|
|
| 92 |
"tokens_per_second": 1015177.8395898147,
|
| 93 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 94 |
"estimated_pages_for_buffer": 22,
|
| 95 |
+
"required_token_positions_per_second": 29007.182775636113,
|
| 96 |
+
"required_pages_per_second_upper_estimate": 0.360172129277675
|
| 97 |
}
|
| 98 |
],
|
| 99 |
"gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
|
|
|
|
| 155 |
"shard_benchmark_scope": "Local packing/read measurements; upload capacity measured only on real data commits. Targets larger than available pages are sample-limited.",
|
| 156 |
"estimated_fresh_generation_batch_seconds": 0.1434574083060457,
|
| 157 |
"selected": {
|
| 158 |
+
"prefetch_batches": 63,
|
| 159 |
"prefetch_capacity_limit": 512,
|
| 160 |
"batch_memory_estimate_bytes": 688946,
|
| 161 |
+
"producer_batch_seconds": 1.3070202665000181,
|
| 162 |
+
"producer_p95_seconds": 2.5993740069999944,
|
| 163 |
+
"gpu_update_seconds": 0.9531432340000379,
|
| 164 |
+
"producer_batches_per_second": 0.7650990773676624,
|
| 165 |
+
"gpu_batches_per_second": 1.0491602566419311,
|
| 166 |
+
"producer_headroom": 0.7292490089326589,
|
| 167 |
+
"sustainable": false,
|
| 168 |
+
"buffer_seconds": 60.048023742002385,
|
| 169 |
+
"buffer_drain_seconds": 221.7832093810038,
|
| 170 |
"shard_target_mib": 16,
|
| 171 |
+
"upload_pages_per_commit": 6,
|
| 172 |
+
"max_pending_pages": 1491,
|
| 173 |
+
"generation_bytes_per_second": 0,
|
| 174 |
+
"upload_bytes_per_second": null,
|
| 175 |
+
"upload_sustainable": null,
|
| 176 |
"logical_page_rows": 4096,
|
| 177 |
"logical_cortex_page_rows": 128,
|
| 178 |
+
"estimated_full_shards_per_hour": 0.0,
|
| 179 |
"selection_policy": "Smallest shard within 90% of measured local peak, enlarged to amortize 30 seconds of measured page production; bounded to 256 MiB."
|
| 180 |
},
|
| 181 |
+
"upload_measurements": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
"cache_key": {
|
| 183 |
"version": 1,
|
| 184 |
"kind": "data",
|
|
|
|
| 221 |
},
|
| 222 |
"cache_reused": true,
|
| 223 |
"resume_probe_seconds": [
|
| 224 |
+
2.5993740069999944,
|
| 225 |
+
0.014666526000041813
|
| 226 |
]
|
| 227 |
}
|
runs/void-byte-v1/events.out.tfevents.1790519810.cad0b19a-59f2-43f0-8fb4-2a94097843e2-tjh7c.1336.0.1790519810984249790-cb9c9513
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e816b1b74fa778aabeb409d57fc60405d66acfb92db3986dcd27fab7128b252
|
| 3 |
+
size 165
|