developer_uid: chai_backend_admin
submission_id: zonemercy-lexical-viral_3667_v10
model_name: tempv1-1
model_group: zonemercy/Lexical-Viral-
status: inactive
timestamp: 2024-11-19T12:45:12+00:00
num_battles: 10384
num_wins: 5429
celo_rating: 1266.63
family_friendly_score: 0.5856
family_friendly_standard_error: 0.006966672663474293
submission_type: basic
model_repo: zonemercy/Lexical-Viral-v5ava-22b11e5r128
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38917598212890897, 'latency_mean': 2.569467295408249, 'latency_p50': 2.563873529434204, 'latency_p90': 2.830236625671387}, {'batch_size': 3, 'throughput': 0.831089271753494, 'latency_mean': 3.6013747131824494, 'latency_p50': 3.6003860235214233, 'latency_p90': 3.9528465270996094}, {'batch_size': 5, 'throughput': 1.1056475064776785, 'latency_mean': 4.501290249824524, 'latency_p50': 4.489634990692139, 'latency_p90': 5.091110420227051}, {'batch_size': 6, 'throughput': 1.2052768795051285, 'latency_mean': 4.9530869996547695, 'latency_p50': 4.943816065788269, 'latency_p90': 5.505229854583741}, {'batch_size': 8, 'throughput': 1.335846600367838, 'latency_mean': 5.943083503246307, 'latency_p50': 5.894532203674316, 'latency_p90': 6.690192103385925}, {'batch_size': 10, 'throughput': 1.4220172146440078, 'latency_mean': 6.955241335630417, 'latency_p50': 7.008499264717102, 'latency_p90': 7.715955758094788}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: tempv1-1
is_internal_developer: True
language_model: zonemercy/Lexical-Viral-v5ava-22b11e5r128
model_size: 22B
ranking_group: single
throughput_3p7s: 0.87
us_pacific_date: 2024-11-19
win_ratio: 0.5228235747303543
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-3667-v10-mkmlizer
Waiting for job on zonemercy-lexical-viral-3667-v10-mkmlizer to finish
zonemercy-lexical-viral-3667-v10-mkmlizer: Downloaded to shared memory in 80.084s
zonemercy-lexical-viral-3667-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprjy8_mmd, device:0
zonemercy-lexical-viral-3667-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v12: ('http://sao10k-mn-12b-lyra-v4a1-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40136->127.0.0.1:8080: read: connection reset by peer\n')
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-3667-v10-mkmlizer: quantized model in 46.425s
zonemercy-lexical-viral-3667-v10-mkmlizer: Processed model zonemercy/Lexical-Viral-v5ava-22b11e5r128 in 126.509s
zonemercy-lexical-viral-3667-v10-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-lexical-viral-3667-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-lexical-viral-3667-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10
zonemercy-lexical-viral-3667-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10/special_tokens_map.json
zonemercy-lexical-viral-3667-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10/config.json
zonemercy-lexical-viral-3667-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10/tokenizer_config.json
zonemercy-lexical-viral-3667-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10/tokenizer.json
zonemercy-lexical-viral-3667-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10/flywheel_model.1.safetensors
zonemercy-lexical-viral-3667-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-lexical-viral-3667-v10/flywheel_model.0.safetensors
zonemercy-lexical-viral-3667-v10-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.74it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:14, 34.76it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:16, 30.22it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:13, 35.25it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:15, 30.82it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:13, 34.99it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:15, 31.00it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:13, 34.88it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:15, 30.92it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:13, 35.11it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:14, 31.05it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:20, 22.05it/s]
Loading 0:  11%|█         | 57/507 [00:02<00:20, 22.06it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:17, 25.09it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:18, 23.63it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 27.92it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 30.79it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 30.59it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:12, 33.96it/s]
Loading 0:  18%|█▊        | 89/507 [00:03<00:14, 29.85it/s]
Loading 0:  19%|█▊        | 94/507 [00:03<00:12, 33.04it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:14, 28.88it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 32.36it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:15, 26.55it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:13, 29.90it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:19, 19.88it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:16, 23.33it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 27.38it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:14, 25.96it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:12, 30.11it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 28.78it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:10, 32.94it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:12, 29.66it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 33.39it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 30.29it/s]
Loading 0:  32%|███▏      | 163/507 [00:05<00:10, 34.34it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:09, 34.77it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:14, 22.91it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:14, 22.98it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 27.26it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:12, 26.33it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:10, 30.31it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:11, 28.26it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 32.15it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:10, 29.47it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:08, 33.64it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:09, 30.34it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:08, 33.96it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:09, 30.97it/s]
Loading 0:  44%|████▍     | 225/507 [00:07<00:12, 21.77it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:11, 23.72it/s]
Loading 0:  46%|████▋     | 235/507 [00:08<00:09, 27.72it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:10, 25.95it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:09, 29.03it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:09, 26.54it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 30.57it/s]
Loading 0:  51%|█████     | 257/507 [00:08<00:08, 28.35it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:07, 32.35it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:08, 29.47it/s]
Loading 0:  53%|█████▎    | 271/507 [00:09<00:07, 33.39it/s]
Loading 0:  54%|█████▍    | 275/507 [00:09<00:07, 30.68it/s]
Loading 0:  55%|█████▌    | 280/507 [00:09<00:06, 34.53it/s]
Loading 0:  56%|█████▌    | 284/507 [00:09<00:08, 25.12it/s]
Loading 0:  57%|█████▋    | 288/507 [00:10<00:08, 24.39it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 24.29it/s]
Loading 0:  59%|█████▉    | 298/507 [00:10<00:07, 28.66it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<03:33,  1.04s/it]
Loading 0:  61%|██████    | 307/507 [00:25<02:22,  1.40it/s]
Loading 0:  61%|██████▏   | 311/507 [00:25<01:45,  1.86it/s]
Loading 0:  62%|██████▏   | 316/507 [00:25<01:10,  2.71it/s]
Loading 0:  63%|██████▎   | 320/507 [00:26<00:52,  3.58it/s]
Loading 0:  64%|██████▍   | 325/507 [00:26<00:35,  5.13it/s]
Loading 0:  65%|██████▍   | 329/507 [00:26<00:27,  6.53it/s]
Loading 0:  66%|██████▌   | 334/507 [00:26<00:19,  9.10it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:14, 11.97it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:13, 12.24it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:11, 14.20it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:08, 18.55it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:07, 19.98it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:05, 24.79it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 24.45it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 29.12it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:04, 27.60it/s]
Loading 0:  75%|███████▌  | 381/507 [00:28<00:03, 35.08it/s]
Loading 0:  76%|███████▌  | 386/507 [00:28<00:03, 35.32it/s]
Loading 0:  77%|███████▋  | 390/507 [00:28<00:03, 29.43it/s]
Loading 0:  78%|███████▊  | 395/507 [00:28<00:04, 25.11it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:03, 27.17it/s]
Loading 0:  80%|████████  | 406/507 [00:28<00:03, 31.28it/s]
Loading 0:  81%|████████  | 410/507 [00:29<00:03, 29.28it/s]
Loading 0:  82%|████████▏ | 415/507 [00:29<00:02, 33.38it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:02, 30.45it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 34.75it/s]
Loading 0:  84%|████████▍ | 428/507 [00:29<00:02, 32.11it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:01, 38.51it/s]
Loading 0:  87%|████████▋ | 440/507 [00:29<00:01, 37.59it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 37.20it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 35.17it/s]
Loading 0:  89%|████████▉ | 453/507 [00:30<00:01, 38.63it/s]
Loading 0:  90%|█████████ | 457/507 [00:32<00:08,  5.83it/s]
Loading 0:  91%|█████████ | 460/507 [00:32<00:06,  7.02it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  9.48it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.27it/s]
Loading 0:  94%|█████████▍| 476/507 [00:33<00:01, 16.41it/s]
Loading 0:  95%|█████████▍| 481/507 [00:33<00:01, 20.06it/s]
Loading 0:  96%|█████████▌| 485/507 [00:33<00:00, 22.06it/s]
Loading 0:  97%|█████████▋| 490/507 [00:33<00:00, 23.69it/s]
Loading 0:  97%|█████████▋| 494/507 [00:33<00:00, 24.62it/s]
Loading 0:  98%|█████████▊| 498/507 [00:33<00:00, 27.12it/s]
Loading 0:  99%|█████████▉| 502/507 [00:33<00:00, 26.07it/s]
Loading 0: 100%|█████████▉| 506/507 [00:34<00:00, 28.69it/s]
                                                            

Job zonemercy-lexical-viral-3667-v10-mkmlizer completed after 155.12s with status: succeeded
Stopping job with name zonemercy-lexical-viral-3667-v10-mkmlizer
Pipeline stage MKMLizer completed in 155.66s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-lexical-viral-3667-v10
Waiting for inference service zonemercy-lexical-viral-3667-v10 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-3667-v10 ready after 211.24249172210693s
Pipeline stage MKMLDeployer completed in 211.84s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.256768226623535s
Received healthy response to inference request in 2.301084041595459s
Received healthy response to inference request in 2.231490135192871s
Received healthy response to inference request in 2.448181629180908s
5 requests
1 failed requests
5th percentile: 2.2454089164733886
10th percentile: 2.259327697753906
20th percentile: 2.2871652603149415
30th percentile: 2.330503559112549
40th percentile: 2.3893425941467283
50th percentile: 2.448181629180908
60th percentile: 2.771616268157959
70th percentile: 3.0950509071350094
80th percentile: 6.637533473968508
90th percentile: 13.39906396865845
95th percentile: 16.779829216003414
99th percentile: 19.484441413879395
mean time: 6.079623699188232
%s, retrying in %s seconds...
Received healthy response to inference request in 2.2954652309417725s
Received healthy response to inference request in 3.0137381553649902s
Received healthy response to inference request in 2.6918485164642334s
Received healthy response to inference request in 2.6973531246185303s
Received healthy response to inference request in 2.423236846923828s
5 requests
0 failed requests
5th percentile: 2.3210195541381835
10th percentile: 2.3465738773345945
20th percentile: 2.397682523727417
30th percentile: 2.4769591808319094
40th percentile: 2.5844038486480714
50th percentile: 2.6918485164642334
60th percentile: 2.694050359725952
70th percentile: 2.696252202987671
80th percentile: 2.7606301307678223
90th percentile: 2.8871841430664062
95th percentile: 2.9504611492156982
99th percentile: 3.001082754135132
mean time: 2.624328374862671
Pipeline stage StressChecker completed in 46.80s
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 5.54s
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 2.12s
Shutdown handler de-registered
zonemercy-lexical-viral_3667_v10 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 3138.46s
Shutdown handler de-registered
zonemercy-lexical-viral_3667_v10 status is now inactive due to auto deactivation removed underperforming models