zonemercy-lexical-viral_3982

developer_uid: chai_backend_admin

submission_id: zonemercy-lexical-viral_3982_v11

model_name: tempv1-2

model_group: zonemercy/Lexical-Viral-

status: inactive

timestamp: 2024-11-21T15:17:56+00:00

num_battles: 12953

num_wins: 6822

celo_rating: 1271.93

family_friendly_score: 0.5958

family_friendly_standard_error: 0.0069400628239231375

submission_type: basic

model_repo: zonemercy/Lexical-Viral-v6ava-22b11e5r256

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38687798406011925, 'latency_mean': 2.5846923565864564, 'latency_p50': 2.5989954471588135, 'latency_p90': 2.859328198432922}, {'batch_size': 3, 'throughput': 0.8201103641504364, 'latency_mean': 3.642009654045105, 'latency_p50': 3.652398705482483, 'latency_p90': 3.995139145851135}, {'batch_size': 5, 'throughput': 1.0852769377230196, 'latency_mean': 4.573505575656891, 'latency_p50': 4.568852663040161, 'latency_p90': 5.070939993858337}, {'batch_size': 6, 'throughput': 1.1782751033065049, 'latency_mean': 5.062727602720261, 'latency_p50': 5.060369372367859, 'latency_p90': 5.630104804039002}, {'batch_size': 10, 'throughput': 1.3836897890731992, 'latency_mean': 7.1602421271801, 'latency_p50': 7.212441682815552, 'latency_p90': 7.9731509447097775}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: tempv1-2

is_internal_developer: True

language_model: zonemercy/Lexical-Viral-v6ava-22b11e5r256

model_size: 22B

ranking_group: single

throughput_3p7s: 0.84

us_pacific_date: 2024-11-21

win_ratio: 0.5266733575233536

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-3982-v11-mkmlizer
Waiting for job on zonemercy-lexical-viral-3982-v11-mkmlizer to finish
zonemercy-lexical-viral-3982-v11-mkmlizer: Downloaded to shared memory in 70.584s
zonemercy-lexical-viral-3982-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvw526zrf, device:0
zonemercy-lexical-viral-3982-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-lexical-viral-3982-v11-mkmlizer: quantized model in 48.073s
zonemercy-lexical-viral-3982-v11-mkmlizer: Processed model zonemercy/Lexical-Viral-v6ava-22b11e5r256 in 118.658s
zonemercy-lexical-viral-3982-v11-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-lexical-viral-3982-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-lexical-viral-3982-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11
zonemercy-lexical-viral-3982-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11/config.json
zonemercy-lexical-viral-3982-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11/special_tokens_map.json
zonemercy-lexical-viral-3982-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11/tokenizer_config.json
zonemercy-lexical-viral-3982-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11/tokenizer.json
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-3982-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11/flywheel_model.1.safetensors
zonemercy-lexical-viral-3982-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-3982-v11/flywheel_model.0.safetensors
zonemercy-lexical-viral-3982-v11-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:23, 21.09it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:17, 27.99it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:21, 23.19it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:17, 27.93it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:19, 25.32it/s]
Loading 0:   6%|▌         | 28/507 [00:01<00:16, 29.31it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:18, 26.38it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:16, 29.32it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:18, 25.27it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:16, 27.93it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:19, 23.96it/s]
Loading 0:  10%|█         | 52/507 [00:02<00:19, 23.88it/s]
Loading 0:  11%|█         | 55/507 [00:02<00:25, 17.75it/s]
Loading 0:  11%|█▏        | 58/507 [00:02<00:23, 19.21it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:21, 20.65it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:22, 19.56it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:18, 23.99it/s]
Loading 0:  14%|█▍        | 73/507 [00:03<00:17, 24.72it/s]
Loading 0:  16%|█▌        | 80/507 [00:03<00:15, 28.02it/s]
Loading 0:  17%|█▋        | 85/507 [00:03<00:13, 30.91it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:15, 27.48it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:13, 29.88it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:16, 24.45it/s]
Loading 0:  20%|██        | 103/507 [00:04<00:15, 25.95it/s]
Loading 0:  21%|██        | 107/507 [00:04<00:16, 23.97it/s]
Loading 0:  22%|██▏       | 112/507 [00:04<00:14, 26.61it/s]
Loading 0:  23%|██▎       | 115/507 [00:04<00:21, 18.52it/s]
Loading 0:  23%|██▎       | 118/507 [00:04<00:20, 18.75it/s]
Loading 0:  24%|██▍       | 122/507 [00:05<00:19, 19.69it/s]
Loading 0:  25%|██▌       | 127/507 [00:05<00:15, 24.53it/s]
Loading 0:  26%|██▌       | 131/507 [00:05<00:16, 23.40it/s]
Loading 0:  27%|██▋       | 136/507 [00:05<00:14, 26.44it/s]
Loading 0:  28%|██▊       | 140/507 [00:05<00:15, 23.82it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:13, 27.37it/s]
Loading 0:  29%|██▉       | 149/507 [00:06<00:13, 25.97it/s]
Loading 0:  30%|███       | 154/507 [00:06<00:11, 29.79it/s]
Loading 0:  31%|███       | 158/507 [00:06<00:12, 27.22it/s]
Loading 0:  32%|███▏      | 163/507 [00:06<00:10, 31.60it/s]
Loading 0:  33%|███▎      | 168/507 [00:06<00:10, 33.90it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:14, 23.54it/s]
Loading 0:  35%|███▍      | 176/507 [00:07<00:14, 23.58it/s]
Loading 0:  36%|███▌      | 181/507 [00:07<00:11, 28.20it/s]
Loading 0:  36%|███▋      | 185/507 [00:07<00:11, 27.67it/s]
Loading 0:  37%|███▋      | 190/507 [00:07<00:09, 32.35it/s]
Loading 0:  38%|███▊      | 194/507 [00:07<00:10, 30.75it/s]
Loading 0:  39%|███▉      | 199/507 [00:07<00:08, 35.01it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:09, 31.84it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:08, 36.04it/s]
Loading 0:  42%|████▏     | 212/507 [00:08<00:09, 31.58it/s]
Loading 0:  43%|████▎     | 217/507 [00:08<00:08, 34.61it/s]
Loading 0:  44%|████▎     | 221/507 [00:08<00:09, 30.81it/s]
Loading 0:  44%|████▍     | 225/507 [00:08<00:12, 21.94it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:11, 23.99it/s]
Loading 0:  46%|████▋     | 235/507 [00:09<00:09, 28.03it/s]
Loading 0:  47%|████▋     | 239/507 [00:09<00:10, 26.42it/s]
Loading 0:  48%|████▊     | 244/507 [00:09<00:08, 30.39it/s]
Loading 0:  49%|████▉     | 248/507 [00:09<00:09, 28.19it/s]
Loading 0:  50%|████▉     | 253/507 [00:09<00:07, 32.19it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:08, 29.04it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:07, 32.36it/s]
Loading 0:  52%|█████▏    | 266/507 [00:10<00:08, 28.70it/s]
Loading 0:  53%|█████▎    | 271/507 [00:10<00:07, 31.77it/s]
Loading 0:  54%|█████▍    | 275/507 [00:10<00:08, 28.68it/s]
Loading 0:  55%|█████▌    | 280/507 [00:10<00:07, 32.24it/s]
Loading 0:  56%|█████▌    | 284/507 [00:10<00:09, 23.20it/s]
Loading 0:  57%|█████▋    | 287/507 [00:10<00:10, 21.34it/s]
Loading 0:  58%|█████▊    | 293/507 [00:11<00:08, 24.38it/s]
Loading 0:  59%|█████▉    | 298/507 [00:11<00:07, 28.46it/s]
Loading 0:  60%|█████▉    | 302/507 [00:26<03:32,  1.04s/it]
Loading 0:  61%|██████    | 307/507 [00:26<02:22,  1.40it/s]
Loading 0:  61%|██████▏   | 311/507 [00:26<01:44,  1.87it/s]
Loading 0:  63%|██████▎   | 318/507 [00:26<01:01,  3.06it/s]
Loading 0:  64%|██████▎   | 322/507 [00:27<00:46,  3.95it/s]
Loading 0:  64%|██████▍   | 327/507 [00:27<00:32,  5.48it/s]
Loading 0:  65%|██████▌   | 331/507 [00:27<00:25,  6.98it/s]
Loading 0:  66%|██████▌   | 335/507 [00:27<00:19,  8.80it/s]
Loading 0:  67%|██████▋   | 340/507 [00:27<00:15, 10.74it/s]
Loading 0:  68%|██████▊   | 344/507 [00:27<00:12, 13.00it/s]
Loading 0:  69%|██████▊   | 348/507 [00:27<00:10, 14.95it/s]
Loading 0:  69%|██████▉   | 352/507 [00:28<00:08, 18.08it/s]
Loading 0:  70%|███████   | 356/507 [00:28<00:07, 19.46it/s]
Loading 0:  71%|███████   | 361/507 [00:28<00:06, 24.28it/s]
Loading 0:  72%|███████▏  | 365/507 [00:28<00:05, 24.25it/s]
Loading 0:  73%|███████▎  | 370/507 [00:28<00:04, 28.64it/s]
Loading 0:  74%|███████▍  | 374/507 [00:28<00:04, 27.37it/s]
Loading 0:  75%|███████▍  | 379/507 [00:28<00:04, 31.77it/s]
Loading 0:  76%|███████▌  | 383/507 [00:29<00:04, 29.42it/s]
Loading 0:  77%|███████▋  | 388/507 [00:29<00:03, 33.91it/s]
Loading 0:  77%|███████▋  | 392/507 [00:29<00:03, 31.10it/s]
Loading 0:  78%|███████▊  | 396/507 [00:29<00:04, 22.44it/s]
Loading 0:  79%|███████▉  | 401/507 [00:29<00:04, 24.51it/s]
Loading 0:  80%|████████  | 406/507 [00:29<00:03, 28.82it/s]
Loading 0:  81%|████████  | 410/507 [00:30<00:03, 27.15it/s]
Loading 0:  82%|████████▏ | 415/507 [00:30<00:02, 31.23it/s]
Loading 0:  83%|████████▎ | 419/507 [00:30<00:03, 28.71it/s]
Loading 0:  84%|████████▎ | 424/507 [00:30<00:02, 32.62it/s]
Loading 0:  84%|████████▍ | 428/507 [00:30<00:02, 29.88it/s]
Loading 0:  85%|████████▌ | 433/507 [00:30<00:02, 33.73it/s]
Loading 0:  86%|████████▌ | 437/507 [00:30<00:02, 30.79it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 37.60it/s]
Loading 0:  88%|████████▊ | 448/507 [00:31<00:01, 35.55it/s]
Loading 0:  89%|████████▉ | 452/507 [00:31<00:01, 36.39it/s]
Loading 0:  90%|████████▉ | 456/507 [00:33<00:09,  5.62it/s]
Loading 0:  91%|█████████ | 459/507 [00:33<00:07,  6.64it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  9.69it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:02, 12.96it/s]
Loading 0:  93%|█████████▎| 474/507 [00:34<00:02, 14.76it/s]
Loading 0:  94%|█████████▍| 479/507 [00:34<00:01, 18.74it/s]
Loading 0:  95%|█████████▌| 483/507 [00:34<00:01, 19.89it/s]
Loading 0:  96%|█████████▋| 488/507 [00:34<00:00, 24.41it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 23.91it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 27.96it/s]
Loading 0:  99%|█████████▉| 501/507 [00:35<00:00, 26.31it/s]
Loading 0: 100%|█████████▉| 506/507 [00:35<00:00, 30.18it/s]
                                                            
Job zonemercy-lexical-viral-3982-v11-mkmlizer completed after 146.16s with status: succeeded
Stopping job with name zonemercy-lexical-viral-3982-v11-mkmlizer
Pipeline stage MKMLizer completed in 146.76s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.77s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-lexical-viral-3982-v11
Waiting for inference service zonemercy-lexical-viral-3982-v11 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
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
Inference service zonemercy-lexical-viral-3982-v11 ready after 210.7812864780426s
Pipeline stage MKMLDeployer completed in 211.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.660149335861206s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.211365222930908s
Received healthy response to inference request in 2.4612185955047607s
Received healthy response to inference request in 2.960491180419922s
Received healthy response to inference request in 2.5043139457702637s
5 requests
0 failed requests
5th percentile: 2.2613358974456785
10th percentile: 2.3113065719604493
20th percentile: 2.4112479209899904
30th percentile: 2.4698376655578613
40th percentile: 2.4870758056640625
50th percentile: 2.5043139457702637
60th percentile: 2.5666481018066407
70th percentile: 2.6289822578430178
80th percentile: 2.720217704772949
90th percentile: 2.8403544425964355
95th percentile: 2.9004228115081787
99th percentile: 2.9484775066375732
mean time: 2.559507656097412
Pipeline stage StressChecker completed in 14.35s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.87s
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 2.77s
Shutdown handler de-registered
zonemercy-lexical-viral_3982_v11 status is now deployed due to DeploymentManager action
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 3269.51s
Shutdown handler de-registered
zonemercy-lexical-viral_3982_v11 status is now inactive due to auto deactivation removed underperforming models