developer_uid: NischayDnk
submission_id: chaiml-nis-qwen32b-simp_98336_v3
model_name: chaiml-nis-qwen32b-simp_98336_v3
model_group: ChaiML/nis-qwen32b-simpo
status: torndown
timestamp: 2025-04-21T19:40:05+00:00
num_battles: 6882
num_wins: 3836
celo_rating: 1331.72
family_friendly_score: 0.47440000000000004
family_friendly_standard_error: 0.007061793539887725
submission_type: basic
model_repo: ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32759331840.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3909798257692441, 'latency_mean': 2.5576178562641143, 'latency_p50': 2.54450786113739, 'latency_p90': 2.845594048500061}, {'batch_size': 3, 'throughput': 0.8692627879127138, 'latency_mean': 3.4403357815742495, 'latency_p50': 3.448349952697754, 'latency_p90': 3.813312458992004}, {'batch_size': 5, 'throughput': 1.181774193286853, 'latency_mean': 4.193649351596832, 'latency_p50': 4.1872416734695435, 'latency_p90': 4.782173109054566}, {'batch_size': 6, 'throughput': 1.2812758113858902, 'latency_mean': 4.634697226285934, 'latency_p50': 4.658354163169861, 'latency_p90': 5.18523907661438}, {'batch_size': 8, 'throughput': 1.4556760783105576, 'latency_mean': 5.439421325922012, 'latency_p50': 5.423612952232361, 'latency_p90': 6.090870356559753}, {'batch_size': 10, 'throughput': 1.5969553956197073, 'latency_mean': 6.1811162900924685, 'latency_p50': 6.149831295013428, 'latency_p90': 6.971980547904968}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-nis-qwen32b-simp_98336_v3
is_internal_developer: False
language_model: ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2
model_size: 33B
ranking_group: single
throughput_3p7s: 1.0
us_pacific_date: 2025-04-21
win_ratio: 0.5573961057832025
generation_params: {'temperature': 0.475, 'top_p': 0.925, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 768, 'best_of': 5, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{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 chaiml-nis-qwen32b-simp-98336-v3-mkmlizer
Waiting for job on chaiml-nis-qwen32b-simp-98336-v3-mkmlizer to finish
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ _____ __ __ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ /___/ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ belonging to: ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: Downloaded to shared memory in 99.704s
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpngyqd5lk, device:0
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: quantized model in 63.509s
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: Processed model ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2 in 163.213s
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/added_tokens.json
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/config.json
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/tokenizer_config.json
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/special_tokens_map.json
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/merges.txt
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/vocab.json
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/tokenizer.json
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/flywheel_model.2.safetensors
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98336-v3/flywheel_model.1.safetensors
Failed to get response for submission jellywibble-sam-montgom_38443_v1: HTTPConnectionPool(host='jellywibble-sam-montgom-38443-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-sam-montgom_38443_v1: HTTPConnectionPool(host='jellywibble-sam-montgom-38443-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-nis-qwen32b-simp-98336-v3-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:18, 40.61it/s] Loading 0: 2%|▏ | 17/771 [00:00<00:10, 68.78it/s] Loading 0: 4%|▍ | 29/771 [00:00<00:09, 76.50it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:11, 64.52it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:13, 53.69it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:11, 63.04it/s] Loading 0: 10%|▉ | 77/771 [00:01<00:09, 69.92it/s] Loading 0: 11%|█▏ | 88/771 [00:01<00:08, 78.01it/s] Loading 0: 13%|█▎ | 98/771 [00:01<00:08, 82.79it/s] Loading 0: 14%|█▍ | 107/771 [00:01<00:10, 63.45it/s] Loading 0: 15%|█▍ | 115/771 [00:01<00:09, 66.75it/s] Loading 0: 16%|█▌ | 123/771 [00:01<00:09, 66.68it/s] Loading 0: 17%|█▋ | 133/771 [00:01<00:09, 69.38it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 92.54it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 81.29it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:09, 60.87it/s] Loading 0: 23%|██▎ | 178/771 [00:02<00:09, 60.91it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:09, 60.10it/s] Loading 0: 26%|██▌ | 197/771 [00:02<00:08, 67.93it/s] Loading 0: 27%|██▋ | 208/771 [00:02<00:07, 77.20it/s] Loading 0: 28%|██▊ | 218/771 [00:03<00:06, 82.48it/s] Loading 0: 29%|██▉ | 227/771 [00:03<00:08, 63.54it/s] Loading 0: 30%|███ | 235/771 [00:03<00:09, 58.42it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 61.98it/s] Loading 0: 33%|███▎ | 256/771 [00:03<00:07, 71.83it/s] Loading 0: 35%|███▍ | 267/771 [00:03<00:06, 80.74it/s] Loading 0: 36%|███▌ | 276/771 [00:03<00:05, 82.80it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 63.49it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 54.67it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:47, 2.06it/s] Loading 0: 40%|████ | 312/771 [00:19<02:38, 2.89it/s] Loading 0: 42%|████▏ | 320/771 [00:19<01:55, 3.90it/s] Loading 0: 43%|████▎ | 329/771 [00:19<01:20, 5.47it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:46, 9.23it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:39, 10.48it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:27, 14.74it/s] Loading 0: 49%|████▊ | 375/771 [00:20<00:19, 20.19it/s] Loading 0: 50%|████▉ | 383/771 [00:20<00:15, 24.73it/s] Loading 0: 51%|█████ | 391/771 [00:20<00:12, 29.36it/s] Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 36.15it/s] Loading 0: 54%|█████▎ | 413/771 [00:20<00:10, 35.54it/s] Loading 0: 55%|█████▍ | 424/771 [00:20<00:07, 45.51it/s] Loading 0: 57%|█████▋ | 436/771 [00:21<00:06, 53.85it/s] Loading 0: 58%|█████▊ | 447/771 [00:21<00:05, 63.66it/s] Loading 0: 59%|█████▉ | 456/771 [00:21<00:04, 68.82it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 57.63it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 51.10it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 57.81it/s] Loading 0: 64%|██████▍ | 496/771 [00:22<00:04, 67.96it/s] Loading 0: 66%|██████▌ | 507/771 [00:22<00:03, 76.65it/s] Loading 0: 67%|██████▋ | 516/771 [00:22<00:03, 79.49it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 62.08it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:04, 52.93it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 59.42it/s] Loading 0: 72%|███████▏ | 556/771 [00:22<00:03, 69.37it/s] Loading 0: 74%|███████▎ | 567/771 [00:23<00:02, 77.54it/s] Loading 0: 75%|███████▍ | 577/771 [00:23<00:02, 82.63it/s] Loading 0: 76%|███████▌ | 587/771 [00:23<00:03, 58.71it/s] Loading 0: 77%|███████▋ | 595/771 [00:23<00:03, 55.58it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 59.67it/s] Loading 0: 80%|███████▉ | 616/771 [00:23<00:02, 70.13it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<01:01, 2.32it/s] Loading 0: 82%|████████▏ | 635/771 [00:38<00:44, 3.06it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:28, 4.41it/s] Loading 0: 85%|████████▍ | 653/771 [00:39<00:21, 5.38it/s] Loading 0: 86%|████████▌ | 664/771 [00:39<00:13, 7.94it/s] Loading 0: 88%|████████▊ | 675/771 [00:39<00:08, 11.40it/s] Loading 0: 89%|████████▊ | 684/771 [00:39<00:05, 15.02it/s] Loading 0: 90%|████████▉ | 693/771 [00:39<00:04, 19.25it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:02, 25.01it/s] Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 27.30it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 34.71it/s] Loading 0: 95%|█████████▌| 736/771 [00:40<00:00, 44.22it/s] Loading 0: 97%|█████████▋| 747/771 [00:40<00:00, 54.09it/s] Loading 0: 98%|█████████▊| 756/771 [00:40<00:00, 60.33it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.10it/s]
Job chaiml-nis-qwen32b-simp-98336-v3-mkmlizer completed after 196.62s with status: succeeded
Stopping job with name chaiml-nis-qwen32b-simp-98336-v3-mkmlizer
Pipeline stage MKMLizer completed in 197.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-qwen32b-simp-98336-v3
Waiting for inference service chaiml-nis-qwen32b-simp-98336-v3 to be ready
Failed to get response for submission jellywibble-sam-montgom_38443_v1: HTTPConnectionPool(host='jellywibble-sam-montgom-38443-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-nis-qwen32b-simp-98336-v3 ready after 130.4562861919403s
Pipeline stage MKMLDeployer completed in 130.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.851362943649292s
Received healthy response to inference request in 3.61641526222229s
Received healthy response to inference request in 3.3295984268188477s
Received healthy response to inference request in 3.7143561840057373s
Received healthy response to inference request in 3.568612575531006s
5 requests
0 failed requests
5th percentile: 3.377401256561279
10th percentile: 3.4252040863037108
20th percentile: 3.5208097457885743
30th percentile: 3.578173112869263
40th percentile: 3.5972941875457765
50th percentile: 3.61641526222229
60th percentile: 3.655591630935669
70th percentile: 3.6947679996490477
80th percentile: 3.741757535934448
90th percentile: 3.7965602397918703
95th percentile: 3.823961591720581
99th percentile: 3.84588267326355
mean time: 3.6160690784454346
Pipeline stage StressChecker completed in 19.21s
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 0.86s
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 0.61s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_98336_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6144.26s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_98336_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-qwen32b-simp_98336_v3 status is now torndown due to DeploymentManager action