sometimesanotion-qwenve_49379

developer_uid: azuruce

submission_id: sometimesanotion-qwenve_49379_v1

model_name: nis-best-config

model_group: sometimesanotion/Qwenver

status: torndown

timestamp: 2025-04-11T20:39:30+00:00

num_battles: 5311

num_wins: 2536

celo_rating: 1253.01

family_friendly_score: 0.639

family_friendly_standard_error: 0.006792333914053402

submission_type: basic

model_repo: sometimesanotion/Qwenvergence-14B-v12-Prose-DS

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14765603840.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4766162956592412, 'latency_mean': 2.0980614972114564, 'latency_p50': 2.11514413356781, 'latency_p90': 2.291259217262268}, {'batch_size': 3, 'throughput': 0.870464458892005, 'latency_mean': 3.4334316980838775, 'latency_p50': 3.4153850078582764, 'latency_p90': 3.783823251724243}, {'batch_size': 5, 'throughput': 1.0605126692824318, 'latency_mean': 4.695462223291397, 'latency_p50': 4.708374619483948, 'latency_p90': 5.3098687648773195}, {'batch_size': 6, 'throughput': 1.1068896751883601, 'latency_mean': 5.378589609861374, 'latency_p50': 5.408203482627869, 'latency_p90': 5.998306083679199}, {'batch_size': 10, 'throughput': 1.1940775189443793, 'latency_mean': 8.302021435499192, 'latency_p50': 8.398475527763367, 'latency_p90': 9.426580905914307}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nis-best-config

is_internal_developer: False

language_model: sometimesanotion/Qwenvergence-14B-v12-Prose-DS

model_size: 15B

ranking_group: single

throughput_3p7s: 0.92

us_pacific_date: 2025-04-11

win_ratio: 0.4774995292788552

generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 sometimesanotion-qwenve-49379-v1-mkmlizer
Waiting for job on sometimesanotion-qwenve-49379-v1-mkmlizer to finish
sometimesanotion-qwenve-49379-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sometimesanotion-qwenve-49379-v1-mkmlizer: ║     _____            __           __                                ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║       /___/                                                         ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║                                                                     ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║                                                                     ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  belonging to:                                                      ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║                                                                     ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ║                                                                     ║
sometimesanotion-qwenve-49379-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Failed to get response for submission jellywibble-tyler-james_92283_v1: HTTPConnectionPool(host='jellywibble-tyler-james-92283-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
sometimesanotion-qwenve-49379-v1-mkmlizer: quantized model in 36.988s
sometimesanotion-qwenve-49379-v1-mkmlizer: Processed model sometimesanotion/Qwenvergence-14B-v12-Prose-DS in 84.073s
sometimesanotion-qwenve-49379-v1-mkmlizer: creating bucket guanaco-mkml-models
sometimesanotion-qwenve-49379-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sometimesanotion-qwenve-49379-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/config.json
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/added_tokens.json
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/special_tokens_map.json
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/tokenizer_config.json
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/merges.txt
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/vocab.json
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/tokenizer.json
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/flywheel_model.1.safetensors
sometimesanotion-qwenve-49379-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sometimesanotion-qwenve-49379-v1/flywheel_model.0.safetensors
sometimesanotion-qwenve-49379-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/579 [00:07<34:40,  3.61s/it]
Loading 0:   3%|▎         | 16/579 [00:07<03:08,  2.99it/s]
Loading 0:   5%|▌         | 29/579 [00:07<01:25,  6.40it/s]
Loading 0:   7%|▋         | 41/579 [00:07<00:55,  9.75it/s]
Loading 0:   9%|▉         | 54/579 [00:07<00:34, 15.23it/s]
Loading 0:  12%|█▏        | 72/579 [00:07<00:20, 25.32it/s]
Loading 0:  15%|█▌        | 88/579 [00:08<00:13, 36.02it/s]
Loading 0:  17%|█▋        | 101/579 [00:08<00:10, 45.57it/s]
Loading 0:  20%|█▉        | 114/579 [00:08<00:08, 56.13it/s]
Loading 0:  23%|██▎       | 132/579 [00:08<00:05, 74.56it/s]
Loading 0:  26%|██▌       | 148/579 [00:08<00:04, 87.81it/s]
Loading 0:  28%|██▊       | 163/579 [00:08<00:05, 69.84it/s]
Loading 0:  31%|███       | 180/579 [00:08<00:04, 86.41it/s]
Loading 0:  34%|███▍      | 196/579 [00:09<00:03, 100.22it/s]
Loading 0:  36%|███▋      | 210/579 [00:09<00:03, 104.50it/s]
Loading 0:  40%|████      | 232/579 [00:09<00:02, 124.92it/s]
Loading 0:  43%|████▎     | 247/579 [00:09<00:02, 123.66it/s]
Loading 0:  45%|████▌     | 261/579 [00:09<00:03, 91.14it/s] 
Loading 0:  48%|████▊     | 278/579 [00:09<00:02, 106.66it/s]
Loading 0:  50%|█████     | 292/579 [00:09<00:02, 111.49it/s]
Loading 0:  53%|█████▎    | 305/579 [00:09<00:02, 115.09it/s]
Loading 0:  55%|█████▍    | 318/579 [00:10<00:02, 116.80it/s]
Loading 0:  58%|█████▊    | 336/579 [00:10<00:01, 131.73it/s]
Loading 0:  61%|██████    | 352/579 [00:10<00:01, 137.31it/s]
Loading 0:  63%|██████▎   | 367/579 [00:10<00:02, 88.38it/s] 
Loading 0:  66%|██████▋   | 384/579 [00:10<00:01, 103.15it/s]
Loading 0:  69%|██████▉   | 400/579 [00:10<00:01, 111.93it/s]
Loading 0:  72%|███████▏  | 414/579 [00:10<00:01, 109.64it/s]
Loading 0:  75%|███████▍  | 432/579 [00:11<00:01, 124.94it/s]
Loading 0:  77%|███████▋  | 448/579 [00:11<00:00, 131.83it/s]
Loading 0:  80%|███████▉  | 463/579 [00:11<00:00, 123.98it/s]
Loading 0:  82%|████████▏ | 477/579 [00:11<00:01, 88.29it/s] 
Loading 0:  84%|████████▍ | 488/579 [00:26<00:29,  3.07it/s]
Loading 0:  87%|████████▋ | 502/579 [00:26<00:17,  4.35it/s]
Loading 0:  90%|████████▉ | 520/579 [00:26<00:08,  6.65it/s]
Loading 0:  92%|█████████▏| 533/579 [00:26<00:05,  8.90it/s]
Loading 0:  94%|█████████▍| 546/579 [00:26<00:02, 11.96it/s]
Loading 0:  97%|█████████▋| 564/579 [00:26<00:00, 17.85it/s]
                                                            
Job sometimesanotion-qwenve-49379-v1-mkmlizer completed after 116.67s with status: succeeded
Stopping job with name sometimesanotion-qwenve-49379-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.12s
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 sometimesanotion-qwenve-49379-v1
Waiting for inference service sometimesanotion-qwenve-49379-v1 to be ready
Inference service sometimesanotion-qwenve-49379-v1 ready after 100.38860654830933s
Pipeline stage MKMLDeployer completed in 100.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.135733127593994s
Received healthy response to inference request in 2.2616500854492188s
Received healthy response to inference request in 1.4413821697235107s
Received healthy response to inference request in 1.9002370834350586s
Received healthy response to inference request in 1.3157765865325928s
5 requests
0 failed requests
5th percentile: 1.3408977031707763
10th percentile: 1.36601881980896
20th percentile: 1.4162610530853272
30th percentile: 1.5331531524658204
40th percentile: 1.7166951179504395
50th percentile: 1.9002370834350586
60th percentile: 1.9944355010986328
70th percentile: 2.088633918762207
80th percentile: 2.1609165191650392
90th percentile: 2.211283302307129
95th percentile: 2.2364666938781737
99th percentile: 2.25661340713501
mean time: 1.810955810546875
Pipeline stage StressChecker completed in 10.56s
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 0.83s
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 0.73s
Shutdown handler de-registered
sometimesanotion-qwenve_49379_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sometimesanotion-qwenve-49379-v1-profiler
Waiting for inference service sometimesanotion-qwenve-49379-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 2740.84s
Shutdown handler de-registered
sometimesanotion-qwenve_49379_v1 status is now inactive due to auto deactivation removed underperforming models
sometimesanotion-qwenve_49379_v1 status is now torndown due to DeploymentManager action