developer_uid: NischayDnk
submission_id: chaiml-nis-qwen32b-simp_98783_v1
model_name: chaiml-nis-qwen32b-simp_98783_v1
model_group: ChaiML/nis-qwen32b-simpo
status: torndown
timestamp: 2025-04-20T03:03:36+00:00
num_battles: 10040
num_wins: 5505
celo_rating: 1318.52
family_friendly_score: 0.48660000000000003
family_friendly_standard_error: 0.00706852799386124
submission_type: basic
model_repo: ChaiML/nis-qwen32b-simpoexp3-s1-pref-1295datav1sft
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': 0.27605273993788493, 'latency_mean': 3.62241268157959, 'latency_p50': 3.6178473234176636, 'latency_p90': 4.05232675075531}, {'batch_size': 2, 'throughput': 0.4461607972872547, 'latency_mean': 4.472917356491089, 'latency_p50': 4.447443008422852, 'latency_p90': 4.945565223693848}, {'batch_size': 3, 'throughput': 0.5967544410352935, 'latency_mean': 5.009529694318771, 'latency_p50': 4.979816198348999, 'latency_p90': 5.6126028299331665}, {'batch_size': 4, 'throughput': 0.7086644816630165, 'latency_mean': 5.606717482805252, 'latency_p50': 5.627490758895874, 'latency_p90': 6.1834321975708}, {'batch_size': 5, 'throughput': 0.7918749004086293, 'latency_mean': 6.279675853252411, 'latency_p50': 6.276067018508911, 'latency_p90': 6.9005207300186155}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-nis-qwen32b-simp_98783_v1
is_internal_developer: False
language_model: ChaiML/nis-qwen32b-simpoexp3-s1-pref-1295datav1sft
model_size: 33B
ranking_group: single
throughput_3p7s: 0.29
us_pacific_date: 2025-04-19
win_ratio: 0.5483067729083665
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, '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-98783-v1-mkmlizer
Waiting for job on chaiml-nis-qwen32b-simp-98783-v1-mkmlizer to finish
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ _____ __ __ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ /___/ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ belonging to: ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: Downloaded to shared memory in 113.496s
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjyzrfciw, device:0
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: quantized model in 62.890s
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: Processed model ChaiML/nis-qwen32b-simpoexp3-s1-pref-1295datav1sft in 176.386s
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/config.json
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/added_tokens.json
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/tokenizer_config.json
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/special_tokens_map.json
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/vocab.json
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/merges.txt
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/tokenizer.json
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/flywheel_model.2.safetensors
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/flywheel_model.0.safetensors
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-98783-v1/flywheel_model.1.safetensors
chaiml-nis-qwen32b-simp-98783-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:19, 39.29it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 74.93it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 88.67it/s] Loading 0: 5%|▍ | 37/771 [00:00<00:08, 91.39it/s] Loading 0: 6%|▌ | 47/771 [00:00<00:13, 52.24it/s] Loading 0: 7%|▋ | 55/771 [00:00<00:14, 51.10it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:12, 56.74it/s] Loading 0: 10%|▉ | 77/771 [00:01<00:10, 65.06it/s] Loading 0: 11%|█▏ | 88/771 [00:01<00:09, 75.01it/s] Loading 0: 13%|█▎ | 99/771 [00:01<00:08, 83.06it/s] Loading 0: 14%|█▍ | 109/771 [00:01<00:12, 54.75it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:10, 62.27it/s] Loading 0: 17%|█▋ | 133/771 [00:02<00:09, 68.14it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:07, 87.83it/s] Loading 0: 21%|██ | 162/771 [00:02<00:07, 79.22it/s] Loading 0: 22%|██▏ | 171/771 [00:02<00:11, 54.32it/s] Loading 0: 23%|██▎ | 181/771 [00:02<00:09, 62.00it/s] Loading 0: 25%|██▍ | 189/771 [00:02<00:09, 61.95it/s] Loading 0: 26%|██▌ | 197/771 [00:03<00:09, 62.07it/s] Loading 0: 27%|██▋ | 209/771 [00:03<00:08, 68.90it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 66.16it/s] Loading 0: 30%|███ | 234/771 [00:03<00:09, 57.76it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 62.95it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 69.22it/s] Loading 0: 35%|███▍ | 269/771 [00:04<00:06, 73.97it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:06, 70.11it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:07, 60.31it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:08, 2.49it/s] Loading 0: 41%|████ | 315/771 [00:18<02:05, 3.62it/s] Loading 0: 42%|████▏ | 323/771 [00:18<01:35, 4.67it/s] Loading 0: 43%|████▎ | 331/771 [00:18<01:12, 6.09it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:45, 9.25it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:39, 10.70it/s] Loading 0: 47%|████▋ | 364/771 [00:19<00:26, 15.08it/s] Loading 0: 49%|████▊ | 375/771 [00:19<00:19, 20.65it/s] Loading 0: 50%|█████ | 387/771 [00:19<00:13, 27.67it/s] Loading 0: 51%|█████▏ | 397/771 [00:20<00:10, 34.74it/s] Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 34.69it/s] Loading 0: 54%|█████▎ | 414/771 [00:20<00:10, 35.62it/s] Loading 0: 55%|█████▌ | 425/771 [00:20<00:07, 43.82it/s] Loading 0: 57%|█████▋ | 437/771 [00:20<00:06, 52.44it/s] Loading 0: 58%|█████▊ | 449/771 [00:20<00:05, 60.33it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:04, 62.24it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 55.57it/s] Loading 0: 63%|██████▎ | 484/771 [00:21<00:04, 63.22it/s] Loading 0: 64%|██████▍ | 496/771 [00:21<00:03, 69.51it/s] Loading 0: 66%|██████▌ | 508/771 [00:21<00:03, 74.51it/s] Loading 0: 67%|██████▋ | 519/771 [00:21<00:03, 82.14it/s] Loading 0: 68%|██████▊ | 528/771 [00:22<00:04, 58.87it/s] Loading 0: 70%|██████▉ | 536/771 [00:22<00:03, 60.28it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 62.25it/s] Loading 0: 72%|███████▏ | 557/771 [00:22<00:03, 69.14it/s] Loading 0: 74%|███████▍ | 569/771 [00:22<00:02, 74.75it/s] Loading 0: 76%|███████▌ | 586/771 [00:22<00:02, 70.01it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:02, 60.32it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 65.68it/s] Loading 0: 80%|████████ | 617/771 [00:23<00:02, 71.38it/s] Loading 0: 81%|████████▏ | 627/771 [00:37<00:57, 2.49it/s] Loading 0: 83%|████████▎ | 638/771 [00:37<00:37, 3.52it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:28, 4.44it/s] Loading 0: 85%|████████▍ | 653/771 [00:38<00:21, 5.47it/s] Loading 0: 86%|████████▋ | 665/771 [00:38<00:12, 8.25it/s] Loading 0: 88%|████████▊ | 677/771 [00:38<00:07, 11.91it/s] Loading 0: 89%|████████▉ | 689/771 [00:38<00:04, 16.62it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:02, 23.44it/s] Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 25.76it/s] Loading 0: 94%|█████████▍| 725/771 [00:39<00:01, 32.29it/s] Loading 0: 96%|█████████▌| 737/771 [00:39<00:00, 40.24it/s] Loading 0: 97%|█████████▋| 749/771 [00:39<00:00, 48.32it/s] Loading 0: 99%|█████████▉| 766/771 [00:47<00:00, 5.27it/s]
Job chaiml-nis-qwen32b-simp-98783-v1-mkmlizer completed after 207.7s with status: succeeded
Stopping job with name chaiml-nis-qwen32b-simp-98783-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.21s
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 chaiml-nis-qwen32b-simp-98783-v1
Waiting for inference service chaiml-nis-qwen32b-simp-98783-v1 to be ready
Inference service chaiml-nis-qwen32b-simp-98783-v1 ready after 130.41714715957642s
Pipeline stage MKMLDeployer completed in 130.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9645233154296875s
Received healthy response to inference request in 3.4164822101593018s
Received healthy response to inference request in 3.596069097518921s
Received healthy response to inference request in 3.5866799354553223s
Received healthy response to inference request in 3.382469892501831s
5 requests
0 failed requests
5th percentile: 3.389272356033325
10th percentile: 3.396074819564819
20th percentile: 3.4096797466278077
30th percentile: 3.4505217552185057
40th percentile: 3.518600845336914
50th percentile: 3.5866799354553223
60th percentile: 3.590435600280762
70th percentile: 3.5941912651062013
80th percentile: 3.6697599411010744
90th percentile: 3.817141628265381
95th percentile: 3.890832471847534
99th percentile: 3.949785146713257
mean time: 3.5892448902130125
Pipeline stage StressChecker completed in 19.34s
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 0.67s
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 0.67s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_98783_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nis-qwen32b-simp-98783-v1-profiler
Waiting for inference service chaiml-nis-qwen32b-simp-98783-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6945.40s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_98783_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-qwen32b-simp_98783_v1 status is now torndown due to DeploymentManager action