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": 0.9004576890000067,
|
| 53 |
+
"peak_gb": 85.39913082122803,
|
| 54 |
"fits_budget": true,
|
| 55 |
+
"estimated_update_seconds": 0.9568634569999972,
|
| 56 |
+
"input_tokens_per_second": 195598.30756245417
|
| 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": 690670,
|
| 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": 1.2669872590049636,
|
| 184 |
-
"bytes": 5719604,
|
| 185 |
-
"pages": 21,
|
| 186 |
-
"shards": 2
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"seconds": 1.032783564995043,
|
| 190 |
-
"bytes": 5149031,
|
| 191 |
-
"pages": 45,
|
| 192 |
-
"shards": 2
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"seconds": 1.4498847849972663,
|
| 196 |
-
"bytes": 7603712,
|
| 197 |
-
"pages": 36,
|
| 198 |
-
"shards": 3
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"seconds": 1.3791402839997318,
|
| 202 |
-
"bytes": 11555501,
|
| 203 |
-
"pages": 30,
|
| 204 |
-
"shards": 3
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"seconds": 1.030656152004667,
|
| 208 |
-
"bytes": 6775920,
|
| 209 |
-
"pages": 30,
|
| 210 |
-
"shards": 3
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"seconds": 1.0988766239970573,
|
| 214 |
-
"bytes": 6218344,
|
| 215 |
-
"pages": 37,
|
| 216 |
-
"shards": 2
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"seconds": 1.1409971860048245,
|
| 220 |
-
"bytes": 830736,
|
| 221 |
-
"pages": 27,
|
| 222 |
-
"shards": 1
|
| 223 |
-
},
|
| 224 |
-
{
|
| 225 |
-
"seconds": 1.1426053430041065,
|
| 226 |
-
"bytes": 7670085,
|
| 227 |
-
"pages": 37,
|
| 228 |
-
"shards": 3
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"seconds": 1.1845013959973585,
|
| 232 |
-
"bytes": 10539391,
|
| 233 |
-
"pages": 31,
|
| 234 |
-
"shards": 3
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"seconds": 0.8672450950034545,
|
| 238 |
-
"bytes": 606235,
|
| 239 |
-
"pages": 21,
|
| 240 |
-
"shards": 1
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"seconds": 1.3488649450009689,
|
| 244 |
-
"bytes": 13749450,
|
| 245 |
-
"pages": 49,
|
| 246 |
-
"shards": 4
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"seconds": 0.8790644170003361,
|
| 250 |
-
"bytes": 1116619,
|
| 251 |
-
"pages": 35,
|
| 252 |
-
"shards": 1
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"seconds": 1.4015686020065914,
|
| 256 |
-
"bytes": 11114007,
|
| 257 |
-
"pages": 33,
|
| 258 |
-
"shards": 4
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"seconds": 1.0096355339992442,
|
| 262 |
-
"bytes": 5988067,
|
| 263 |
-
"pages": 29,
|
| 264 |
-
"shards": 2
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"seconds": 1.234346370001731,
|
| 268 |
-
"bytes": 974463,
|
| 269 |
-
"pages": 34,
|
| 270 |
-
"shards": 1
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"seconds": 1.1329207589951693,
|
| 274 |
-
"bytes": 7046164,
|
| 275 |
-
"pages": 25,
|
| 276 |
-
"shards": 3
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"seconds": 1.0467858490010258,
|
| 280 |
-
"bytes": 11558244,
|
| 281 |
-
"pages": 41,
|
| 282 |
-
"shards": 4
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"seconds": 1.1082996040058788,
|
| 286 |
-
"bytes": 6095964,
|
| 287 |
-
"pages": 36,
|
| 288 |
-
"shards": 2
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"seconds": 1.0661074119998375,
|
| 292 |
-
"bytes": 7367457,
|
| 293 |
-
"pages": 30,
|
| 294 |
-
"shards": 3
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"seconds": 0.7073749000046519,
|
| 298 |
-
"bytes": 1147032,
|
| 299 |
-
"pages": 34,
|
| 300 |
-
"shards": 1
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"seconds": 2.1967378000044846,
|
| 304 |
-
"bytes": 12230231,
|
| 305 |
-
"pages": 35,
|
| 306 |
-
"shards": 4
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"seconds": 1.34678302899556,
|
| 310 |
-
"bytes": 6766636,
|
| 311 |
-
"pages": 30,
|
| 312 |
-
"shards": 2
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"seconds": 0.8585810450022109,
|
| 316 |
-
"bytes": 306974,
|
| 317 |
-
"pages": 9,
|
| 318 |
-
"shards": 1
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"seconds": 1.175691934004135,
|
| 322 |
-
"bytes": 6239046,
|
| 323 |
-
"pages": 37,
|
| 324 |
-
"shards": 2
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"seconds": 1.251433448996977,
|
| 328 |
-
"bytes": 7613150,
|
| 329 |
-
"pages": 31,
|
| 330 |
-
"shards": 3
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"seconds": 0.8646319059989764,
|
| 334 |
-
"bytes": 4940868,
|
| 335 |
-
"pages": 32,
|
| 336 |
-
"shards": 2
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"seconds": 0.9655562699990696,
|
| 340 |
-
"bytes": 7648817,
|
| 341 |
-
"pages": 39,
|
| 342 |
-
"shards": 3
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"seconds": 1.2715992000012193,
|
| 346 |
-
"bytes": 6184683,
|
| 347 |
-
"pages": 36,
|
| 348 |
-
"shards": 2
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"seconds": 0.9518272349960171,
|
| 352 |
-
"bytes": 6809793,
|
| 353 |
-
"pages": 31,
|
| 354 |
-
"shards": 2
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"seconds": 1.123792185993807,
|
| 358 |
-
"bytes": 11983615,
|
| 359 |
-
"pages": 37,
|
| 360 |
-
"shards": 4
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"seconds": 1.1926247609953862,
|
| 364 |
-
"bytes": 798107,
|
| 365 |
-
"pages": 26,
|
| 366 |
-
"shards": 1
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"seconds": 0.9836393130026408,
|
| 370 |
-
"bytes": 5980946,
|
| 371 |
-
"pages": 38,
|
| 372 |
-
"shards": 2
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"seconds": 1.1501939880035934,
|
| 376 |
-
"bytes": 7275318,
|
| 377 |
-
"pages": 33,
|
| 378 |
-
"shards": 3
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"seconds": 1.0238104009986273,
|
| 382 |
-
"bytes": 4591810,
|
| 383 |
-
"pages": 32,
|
| 384 |
-
"shards": 2
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"seconds": 2.234572448003746,
|
| 388 |
-
"bytes": 13274402,
|
| 389 |
-
"pages": 35,
|
| 390 |
-
"shards": 4
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"seconds": 1.07868888899975,
|
| 394 |
-
"bytes": 1300513,
|
| 395 |
-
"pages": 36,
|
| 396 |
-
"shards": 1
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"seconds": 1.4324448540064623,
|
| 400 |
-
"bytes": 9935435,
|
| 401 |
-
"pages": 35,
|
| 402 |
-
"shards": 3
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"seconds": 1.2297556650009938,
|
| 406 |
-
"bytes": 7626325,
|
| 407 |
-
"pages": 34,
|
| 408 |
-
"shards": 3
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"seconds": 0.8381233459949726,
|
| 412 |
-
"bytes": 1148268,
|
| 413 |
-
"pages": 32,
|
| 414 |
-
"shards": 1
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"seconds": 0.9499172950017964,
|
| 418 |
-
"bytes": 7609450,
|
| 419 |
-
"pages": 39,
|
| 420 |
-
"shards": 3
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"seconds": 0.9056497909987229,
|
| 424 |
-
"bytes": 4987206,
|
| 425 |
-
"pages": 25,
|
| 426 |
-
"shards": 2
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"seconds": 1.4441368190018693,
|
| 430 |
-
"bytes": 11962393,
|
| 431 |
-
"pages": 36,
|
| 432 |
-
"shards": 3
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"seconds": 1.1221481789980317,
|
| 436 |
-
"bytes": 7553276,
|
| 437 |
-
"pages": 38,
|
| 438 |
-
"shards": 3
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"seconds": 0.8207161469981656,
|
| 442 |
-
"bytes": 1164563,
|
| 443 |
-
"pages": 36,
|
| 444 |
-
"shards": 1
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"seconds": 1.0845683700026711,
|
| 448 |
-
"bytes": 10426904,
|
| 449 |
-
"pages": 28,
|
| 450 |
-
"shards": 3
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"seconds": 1.0798400059939013,
|
| 454 |
-
"bytes": 7684665,
|
| 455 |
-
"pages": 39,
|
| 456 |
-
"shards": 3
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"seconds": 1.0031564969976898,
|
| 460 |
-
"bytes": 997756,
|
| 461 |
-
"pages": 28,
|
| 462 |
-
"shards": 1
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"seconds": 1.3090939850007999,
|
| 466 |
-
"bytes": 13205063,
|
| 467 |
-
"pages": 36,
|
| 468 |
-
"shards": 4
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"seconds": 1.0676715709996643,
|
| 472 |
-
"bytes": 4977396,
|
| 473 |
-
"pages": 37,
|
| 474 |
-
"shards": 3
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"seconds": 0.9372590880011558,
|
| 478 |
-
"bytes": 6217543,
|
| 479 |
-
"pages": 37,
|
| 480 |
-
"shards": 2
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"seconds": 1.0400478770025074,
|
| 484 |
-
"bytes": 7313545,
|
| 485 |
-
"pages": 31,
|
| 486 |
-
"shards": 3
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"seconds": 0.8696056030021282,
|
| 490 |
-
"bytes": 1079259,
|
| 491 |
-
"pages": 34,
|
| 492 |
-
"shards": 1
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"seconds": 1.1580835760032642,
|
| 496 |
-
"bytes": 10392878,
|
| 497 |
-
"pages": 30,
|
| 498 |
-
"shards": 3
|
| 499 |
-
},
|
| 500 |
-
{
|
| 501 |
-
"seconds": 1.3803016649981146,
|
| 502 |
-
"bytes": 13473573,
|
| 503 |
-
"pages": 39,
|
| 504 |
-
"shards": 4
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"seconds": 0.9864481259937747,
|
| 508 |
-
"bytes": 1047459,
|
| 509 |
-
"pages": 35,
|
| 510 |
-
"shards": 1
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"seconds": 1.009063662000699,
|
| 514 |
-
"bytes": 7464078,
|
| 515 |
-
"pages": 31,
|
| 516 |
-
"shards": 3
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"seconds": 1.1531412479962455,
|
| 520 |
-
"bytes": 5169545,
|
| 521 |
-
"pages": 35,
|
| 522 |
-
"shards": 2
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"seconds": 1.040382787999988,
|
| 526 |
-
"bytes": 5992429,
|
| 527 |
-
"pages": 33,
|
| 528 |
-
"shards": 2
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"seconds": 1.0942238300049212,
|
| 532 |
-
"bytes": 7544195,
|
| 533 |
-
"pages": 32,
|
| 534 |
-
"shards": 3
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"seconds": 1.183839971999987,
|
| 538 |
-
"bytes": 6786466,
|
| 539 |
-
"pages": 32,
|
| 540 |
-
"shards": 2
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"seconds": 1.5759701440038043,
|
| 544 |
-
"bytes": 11667943,
|
| 545 |
-
"pages": 39,
|
| 546 |
-
"shards": 4
|
| 547 |
-
},
|
| 548 |
-
{
|
| 549 |
-
"seconds": 1.0282209380020504,
|
| 550 |
-
"bytes": 1021880,
|
| 551 |
-
"pages": 32,
|
| 552 |
-
"shards": 1
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"seconds": 1.0568422009964706,
|
| 556 |
-
"bytes": 6256138,
|
| 557 |
-
"pages": 38,
|
| 558 |
-
"shards": 2
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"seconds": 0.9614676109995344,
|
| 562 |
-
"bytes": 1727275,
|
| 563 |
-
"pages": 10,
|
| 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": 77051.74595250555,
|
| 26 |
+
"required_pages_per_second_upper_estimate": 0.006678650053298455
|
| 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": 9631.468244063193,
|
| 40 |
+
"required_pages_per_second_upper_estimate": 0.003842136685839793
|
| 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": 19262.936488126386,
|
| 54 |
+
"required_pages_per_second_upper_estimate": 0.004456141340424686
|
| 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": 28894.40473218958,
|
| 68 |
+
"required_pages_per_second_upper_estimate": 0.0017595176509647666
|
| 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": 28894.40473218958,
|
| 82 |
+
"required_pages_per_second_upper_estimate": 0.0022243712611155096
|
| 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": 28894.40473218958,
|
| 96 |
+
"required_pages_per_second_upper_estimate": 0.35877180342190024
|
| 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": 690670,
|
| 161 |
+
"producer_batch_seconds": 1.1856436634999739,
|
| 162 |
+
"producer_p95_seconds": 2.358020696999972,
|
| 163 |
+
"gpu_update_seconds": 0.9568634569999972,
|
| 164 |
+
"producer_batches_per_second": 0.8434237290553547,
|
| 165 |
+
"gpu_batches_per_second": 1.0450811896769958,
|
| 166 |
+
"producer_headroom": 0.8070413450997356,
|
| 167 |
+
"sustainable": false,
|
| 168 |
+
"buffer_seconds": 60.28239779099982,
|
| 169 |
+
"buffer_drain_seconds": 312.4109557156601,
|
| 170 |
"shard_target_mib": 16,
|
| 171 |
+
"upload_pages_per_commit": 7,
|
| 172 |
+
"max_pending_pages": 1726,
|
| 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 |
+
2.358020696999972,
|
| 225 |
+
0.013266629999975521
|
| 226 |
]
|
| 227 |
}
|
runs/void-byte-v1/events.out.tfevents.1790738827.1a46e860-412e-40b5-8c01-42d24543f8c9-dfnph.319.0.1790738827394728502-c744ae20
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46954b1df954862d20a91d0d94cf8e6d6c6424f64c1ec7dafe2dcaff34a00bef
|
| 3 |
+
size 165
|