developer_uid: chai_backend_admin
submission_id: zonemercy-lexical-viral-_8779_v1
model_name: tempv1-3
model_group: zonemercy/Lexical-Viral-
status: inactive
timestamp: 2024-11-19T14:22:22+00:00
num_battles: 11508
num_wins: 6192
celo_rating: 1278.75
family_friendly_score: 0.594
family_friendly_standard_error: 0.006944983801277006
submission_type: basic
model_repo: zonemercy/Lexical-Viral-v6ava-22b11e5r256la64
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3851609061549855, 'latency_mean': 2.596234314441681, 'latency_p50': 2.5818865299224854, 'latency_p90': 2.8769633531570435}, {'batch_size': 3, 'throughput': 0.8083507254744744, 'latency_mean': 3.6893483603000643, 'latency_p50': 3.6860636472702026, 'latency_p90': 4.132507610321045}, {'batch_size': 5, 'throughput': 1.0682459627629062, 'latency_mean': 4.6577376973629, 'latency_p50': 4.648950695991516, 'latency_p90': 5.189329433441162}, {'batch_size': 6, 'throughput': 1.1601088567910778, 'latency_mean': 5.136384550333023, 'latency_p50': 5.1016281843185425, 'latency_p90': 5.768548822402954}, {'batch_size': 10, 'throughput': 1.3632937447092905, 'latency_mean': 7.259170330762863, 'latency_p50': 7.258650898933411, 'latency_p90': 8.239565896987914}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: tempv1-3
is_internal_developer: True
language_model: zonemercy/Lexical-Viral-v6ava-22b11e5r256la64
model_size: 22B
ranking_group: single
throughput_3p7s: 0.82
us_pacific_date: 2024-11-19
win_ratio: 0.5380604796663191
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name zonemercy-lexical-viral-8779-v1-mkmlizer
Waiting for job on zonemercy-lexical-viral-8779-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-lexical-viral-8779-v1-mkmlizer: Downloaded to shared memory in 90.943s
zonemercy-lexical-viral-8779-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6rk8tiqp, device:0
zonemercy-lexical-viral-8779-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-lexical-viral-8779-v1-mkmlizer: quantized model in 50.188s
zonemercy-lexical-viral-8779-v1-mkmlizer: Processed model zonemercy/Lexical-Viral-v6ava-22b11e5r256la64 in 141.131s
zonemercy-lexical-viral-8779-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-lexical-viral-8779-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-lexical-viral-8779-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1
zonemercy-lexical-viral-8779-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1/config.json
zonemercy-lexical-viral-8779-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1/special_tokens_map.json
zonemercy-lexical-viral-8779-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1/tokenizer_config.json
zonemercy-lexical-viral-8779-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1/tokenizer.json
zonemercy-lexical-viral-8779-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1/flywheel_model.1.safetensors
zonemercy-lexical-viral-8779-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-8779-v1/flywheel_model.0.safetensors
zonemercy-lexical-viral-8779-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 3/507 [00:00<00:31, 15.89it/s] Loading 0: 1%| | 5/507 [00:00<01:04, 7.76it/s] Loading 0: 2%|▏ | 10/507 [00:00<00:31, 15.85it/s] Loading 0: 3%|▎ | 14/507 [00:00<00:28, 17.22it/s] Loading 0: 4%|▎ | 19/507 [00:01<00:21, 22.94it/s] Loading 0: 5%|▍ | 23/507 [00:01<00:21, 22.67it/s] Loading 0: 6%|▌ | 28/507 [00:01<00:17, 26.91it/s] Loading 0: 6%|▋ | 32/507 [00:01<00:18, 25.43it/s] Loading 0: 7%|▋ | 37/507 [00:01<00:15, 29.44it/s] Loading 0: 8%|▊ | 41/507 [00:01<00:18, 25.23it/s] Loading 0: 9%|▉ | 46/507 [00:01<00:15, 29.20it/s] Loading 0: 10%|▉ | 50/507 [00:02<00:16, 27.33it/s] Loading 0: 10%|█ | 53/507 [00:02<00:24, 18.43it/s] Loading 0: 11%|█ | 56/507 [00:02<00:25, 17.61it/s] Loading 0: 12%|█▏ | 61/507 [00:02<00:19, 22.30it/s] Loading 0: 13%|█▎ | 65/507 [00:02<00:20, 21.86it/s] Loading 0: 14%|█▍ | 70/507 [00:03<00:16, 26.03it/s] Loading 0: 14%|█▍ | 73/507 [00:03<00:16, 26.36it/s] Loading 0: 16%|█▌ | 80/507 [00:03<00:15, 28.19it/s] Loading 0: 17%|█▋ | 85/507 [00:03<00:13, 31.16it/s] Loading 0: 18%|█▊ | 89/507 [00:03<00:15, 27.19it/s] Loading 0: 19%|█▊ | 94/507 [00:03<00:13, 30.25it/s] Loading 0: 19%|█▉ | 98/507 [00:04<00:15, 26.99it/s] Loading 0: 20%|██ | 103/507 [00:04<00:13, 29.24it/s] Loading 0: 21%|██ | 107/507 [00:04<00:15, 26.55it/s] Loading 0: 22%|██▏ | 112/507 [00:04<00:13, 29.70it/s] Loading 0: 23%|██▎ | 116/507 [00:04<00:20, 19.44it/s] Loading 0: 24%|██▍ | 122/507 [00:05<00:17, 22.12it/s] Loading 0: 25%|██▌ | 127/507 [00:05<00:14, 25.67it/s] Loading 0: 26%|██▌ | 131/507 [00:05<00:15, 24.25it/s] Loading 0: 27%|██▋ | 136/507 [00:05<00:13, 27.86it/s] Loading 0: 28%|██▊ | 140/507 [00:05<00:14, 26.08it/s] Loading 0: 29%|██▊ | 145/507 [00:05<00:12, 29.58it/s] Loading 0: 29%|██▉ | 149/507 [00:06<00:13, 26.78it/s] Loading 0: 30%|███ | 154/507 [00:06<00:11, 29.82it/s] Loading 0: 31%|███ | 158/507 [00:06<00:12, 27.41it/s] Loading 0: 32%|███▏ | 163/507 [00:06<00:11, 31.18it/s] Loading 0: 33%|███▎ | 168/507 [00:06<00:10, 31.84it/s] Loading 0: 34%|███▍ | 172/507 [00:07<00:15, 21.20it/s] Loading 0: 35%|███▍ | 176/507 [00:07<00:15, 21.34it/s] Loading 0: 36%|███▌ | 181/507 [00:07<00:12, 25.37it/s] Loading 0: 36%|███▋ | 185/507 [00:07<00:13, 24.15it/s] Loading 0: 37%|███▋ | 190/507 [00:07<00:11, 27.89it/s] Loading 0: 38%|███▊ | 194/507 [00:07<00:12, 25.64it/s] Loading 0: 39%|███▉ | 199/507 [00:07<00:10, 29.25it/s] Loading 0: 40%|████ | 203/507 [00:08<00:11, 26.74it/s] Loading 0: 41%|████ | 208/507 [00:08<00:09, 30.39it/s] Loading 0: 42%|████▏ | 212/507 [00:08<00:10, 27.62it/s] Loading 0: 43%|████▎ | 217/507 [00:08<00:09, 31.25it/s] Loading 0: 44%|████▎ | 221/507 [00:08<00:10, 28.43it/s] Loading 0: 44%|████▍ | 225/507 [00:09<00:14, 20.07it/s] Loading 0: 45%|████▌ | 230/507 [00:09<00:12, 21.76it/s] Loading 0: 46%|████▋ | 235/507 [00:09<00:10, 25.54it/s] Loading 0: 47%|████▋ | 239/507 [00:09<00:11, 24.07it/s] Loading 0: 48%|████▊ | 244/507 [00:09<00:09, 27.69it/s] Loading 0: 49%|████▉ | 248/507 [00:09<00:10, 25.72it/s] Loading 0: 50%|████▉ | 253/507 [00:10<00:08, 29.19it/s] Loading 0: 51%|█████ | 257/507 [00:10<00:09, 26.34it/s] Loading 0: 52%|█████▏ | 262/507 [00:10<00:08, 29.70it/s] Loading 0: 52%|█████▏ | 266/507 [00:10<00:08, 26.86it/s] Loading 0: 53%|█████▎ | 271/507 [00:10<00:07, 30.08it/s] Loading 0: 54%|█████▍ | 275/507 [00:10<00:08, 27.16it/s] Loading 0: 55%|█████▌ | 280/507 [00:10<00:07, 30.66it/s] Loading 0: 56%|█████▌ | 284/507 [00:11<00:10, 21.71it/s] Loading 0: 57%|█████▋ | 287/507 [00:11<00:10, 20.11it/s] Loading 0: 58%|█████▊ | 293/507 [00:11<00:09, 22.61it/s] Loading 0: 59%|█████▉ | 298/507 [00:11<00:07, 26.27it/s] Loading 0: 59%|█████▉ | 301/507 [00:27<03:56, 1.15s/it] Loading 0: 60%|█████▉ | 302/507 [00:27<03:36, 1.05s/it] Loading 0: 61%|██████ | 307/507 [00:27<02:09, 1.54it/s] Loading 0: 61%|██████ | 310/507 [00:27<01:37, 2.02it/s] Loading 0: 62%|██████▏ | 313/507 [00:28<01:12, 2.67it/s] Loading 0: 62%|██████▏ | 316/507 [00:28<00:53, 3.55it/s] Loading 0: 63%|██████▎ | 320/507 [00:28<00:37, 5.00it/s] Loading 0: 64%|██████▍ | 325/507 [00:28<00:24, 7.56it/s] Loading 0: 65%|██████▍ | 329/507 [00:28<00:18, 9.45it/s] Loading 0: 66%|██████▌ | 334/507 [00:28<00:13, 12.98it/s] Loading 0: 67%|██████▋ | 339/507 [00:28<00:10, 16.37it/s] Loading 0: 68%|██████▊ | 343/507 [00:29<00:11, 14.43it/s] Loading 0: 68%|██████▊ | 347/507 [00:29<00:10, 15.80it/s] Loading 0: 69%|██████▉ | 352/507 [00:29<00:07, 19.92it/s] Loading 0: 70%|███████ | 356/507 [00:29<00:07, 20.58it/s] Loading 0: 71%|███████ | 361/507 [00:29<00:05, 24.78it/s] Loading 0: 72%|███████▏ | 365/507 [00:30<00:05, 24.16it/s] Loading 0: 73%|███████▎ | 370/507 [00:30<00:04, 27.88it/s] Loading 0: 74%|███████▍ | 374/507 [00:30<00:05, 26.30it/s] Loading 0: 75%|███████▍ | 379/507 [00:30<00:04, 29.53it/s] Loading 0: 76%|███████▌ | 383/507 [00:30<00:04, 27.29it/s] Loading 0: 77%|███████▋ | 388/507 [00:30<00:03, 31.30it/s] Loading 0: 77%|███████▋ | 392/507 [00:30<00:03, 28.95it/s] Loading 0: 78%|███████▊ | 396/507 [00:31<00:05, 20.76it/s] Loading 0: 79%|███████▉ | 401/507 [00:31<00:04, 22.63it/s] Loading 0: 80%|████████ | 406/507 [00:31<00:03, 26.57it/s] Loading 0: 81%|████████ | 410/507 [00:31<00:03, 24.87it/s] Loading 0: 82%|████████▏ | 415/507 [00:31<00:03, 28.08it/s] Loading 0: 83%|████████▎ | 419/507 [00:32<00:03, 25.08it/s] Loading 0: 84%|████████▎ | 424/507 [00:32<00:02, 28.59it/s] Loading 0: 84%|████████▍ | 428/507 [00:32<00:03, 26.04it/s] Loading 0: 85%|████████▌ | 433/507 [00:32<00:02, 29.41it/s] Loading 0: 86%|████████▌ | 437/507 [00:32<00:02, 27.06it/s] Loading 0: 87%|████████▋ | 442/507 [00:32<00:02, 30.91it/s] Loading 0: 88%|████████▊ | 446/507 [00:32<00:02, 28.27it/s] Loading 0: 89%|████████▉ | 451/507 [00:33<00:01, 31.65it/s] Loading 0: 90%|████████▉ | 455/507 [00:35<00:09, 5.26it/s] Loading 0: 91%|█████████ | 459/507 [00:35<00:07, 6.67it/s] Loading 0: 92%|█████████▏| 465/507 [00:35<00:04, 9.45it/s] Loading 0: 93%|█████████▎| 470/507 [00:36<00:02, 12.49it/s] Loading 0: 93%|█████████▎| 474/507 [00:36<00:02, 14.07it/s] Loading 0: 94%|█████████▍| 479/507 [00:36<00:01, 17.91it/s] Loading 0: 95%|█████████▌| 483/507 [00:36<00:01, 19.02it/s] Loading 0: 96%|█████████▋| 488/507 [00:36<00:00, 23.44it/s] Loading 0: 97%|█████████▋| 492/507 [00:36<00:00, 22.40it/s] Loading 0: 98%|█████████▊| 497/507 [00:36<00:00, 26.55it/s] Loading 0: 99%|█████████▉| 501/507 [00:37<00:00, 24.54it/s] Loading 0: 100%|█████████▉| 506/507 [00:37<00:00, 28.17it/s]
Job zonemercy-lexical-viral-8779-v1-mkmlizer completed after 184.86s with status: succeeded
Stopping job with name zonemercy-lexical-viral-8779-v1-mkmlizer
Pipeline stage MKMLizer completed in 185.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-lexical-viral-8779-v1
Waiting for inference service zonemercy-lexical-viral-8779-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-lexical-viral-8779-v1 ready after 211.033371925354s
Pipeline stage MKMLDeployer completed in 211.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9363298416137695s
Received healthy response to inference request in 2.4414596557617188s
Received healthy response to inference request in 2.256287097930908s
Received healthy response to inference request in 2.413209915161133s
Received healthy response to inference request in 2.2758870124816895s
5 requests
0 failed requests
5th percentile: 2.2602070808410644
10th percentile: 2.2641270637512205
20th percentile: 2.2719670295715333
30th percentile: 2.3033515930175783
40th percentile: 2.3582807540893556
50th percentile: 2.413209915161133
60th percentile: 2.424509811401367
70th percentile: 2.4358097076416017
80th percentile: 2.540433692932129
90th percentile: 2.738381767272949
95th percentile: 2.837355804443359
99th percentile: 2.9165350341796876
mean time: 2.4646347045898436
Pipeline stage StressChecker completed in 14.01s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.57s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.47s
Shutdown handler de-registered
zonemercy-lexical-viral-_8779_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-lexical-viral-8779-v1-profiler
Waiting for inference service zonemercy-lexical-viral-8779-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3193.63s
Shutdown handler de-registered
zonemercy-lexical-viral-_8779_v1 status is now inactive due to auto deactivation removed underperforming models