chaiml-nis-qwenrp-32b-s_16659

developer_uid: NischayDnk

submission_id: chaiml-nis-qwenrp-32b-s_16659_v1

model_name: chaiml-nis-qwenrp-32b-s_16659_v1

model_group: ChaiML/nis-qwenrp-32b-sf

status: torndown

timestamp: 2025-04-18T03:02:13+00:00

num_battles: 7304

num_wins: 3474

celo_rating: 1269.7

family_friendly_score: 0.5820000000000001

family_friendly_standard_error: 0.006975327949279518

submission_type: basic

model_repo: ChaiML/nis-qwenrp-32b-sft-exp1-datav1ffsys20k

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32763417600.0

best_of: 1

max_input_tokens: 720

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.2907877071412788, 'latency_mean': 3.438865509033203, 'latency_p50': 3.4591749906539917, 'latency_p90': 3.817003846168518}, {'batch_size': 2, 'throughput': 0.4833384488898858, 'latency_mean': 4.1254342019557955, 'latency_p50': 4.160705327987671, 'latency_p90': 4.578146457672119}, {'batch_size': 3, 'throughput': 0.6509708983918221, 'latency_mean': 4.582543747425079, 'latency_p50': 4.587931871414185, 'latency_p90': 5.024807691574097}, {'batch_size': 4, 'throughput': 0.7980501778398889, 'latency_mean': 4.9719638192653655, 'latency_p50': 4.935980796813965, 'latency_p90': 5.4507080078125}, {'batch_size': 5, 'throughput': 0.9286664210691026, 'latency_mean': 5.368962814807892, 'latency_p50': 5.36092734336853, 'latency_p90': 5.9490375280380245}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-nis-qwenrp-32b-s_16659_v1

is_internal_developer: False

language_model: ChaiML/nis-qwenrp-32b-sft-exp1-datav1ffsys20k

model_size: 33B

ranking_group: single

throughput_3p7s: 0.37

us_pacific_date: 2025-04-17

win_ratio: 0.47562979189485216

generation_params: {'temperature': 0.55, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 720, 'best_of': 1, 'max_output_tokens': 64}

formatter: {'memory_template': '', '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-qwenrp-32b-s-16659-v1-mkmlizer
Waiting for job on chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer to finish
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: Downloaded to shared memory in 117.514s
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3y871mqc, device:0
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: quantized model in 64.204s
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: Processed model ChaiML/nis-qwenrp-32b-sft-exp1-datav1ffsys20k in 181.720s
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/added_tokens.json
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/config.json
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/special_tokens_map.json
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/tokenizer_config.json
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/merges.txt
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/vocab.json
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/tokenizer.json
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/flywheel_model.2.safetensors
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/flywheel_model.1.safetensors
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwenrp-32b-s-16659-v1/flywheel_model.0.safetensors
chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 38.27it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 73.72it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 88.14it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 90.36it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:14, 50.79it/s]
Loading 0:   7%|▋         | 54/771 [00:00<00:15, 47.63it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 57.83it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 68.74it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 73.02it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 69.44it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:11, 57.78it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 56.28it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 57.24it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 67.30it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 73.03it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 78.24it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 74.59it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:12, 49.88it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 50.24it/s]
Loading 0:  24%|██▍       | 185/771 [00:03<00:10, 53.90it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:08, 65.00it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 75.18it/s]
Loading 0:  28%|██▊       | 217/771 [00:03<00:06, 81.19it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 60.16it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.99it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 60.23it/s]
Loading 0:  33%|███▎      | 257/771 [00:04<00:07, 66.53it/s]
Loading 0:  35%|███▍      | 269/771 [00:04<00:06, 72.35it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:06, 70.37it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 57.47it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:22,  2.31it/s]
Loading 0:  40%|████      | 312/771 [00:19<02:26,  3.12it/s]
Loading 0:  42%|████▏     | 320/771 [00:19<01:49,  4.11it/s]
Loading 0:  43%|████▎     | 329/771 [00:19<01:18,  5.64it/s]
Loading 0:  45%|████▍     | 346/771 [00:20<00:46,  9.20it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:39, 10.54it/s]
Loading 0:  47%|████▋     | 365/771 [00:20<00:27, 14.95it/s]
Loading 0:  49%|████▉     | 377/771 [00:20<00:19, 20.45it/s]
Loading 0:  50%|█████     | 389/771 [00:20<00:14, 26.93it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:10, 34.48it/s]
Loading 0:  54%|█████▎    | 414/771 [00:21<00:10, 35.69it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:08, 42.71it/s]
Loading 0:  57%|█████▋    | 437/771 [00:21<00:06, 50.84it/s]
Loading 0:  58%|█████▊    | 448/771 [00:21<00:05, 60.01it/s]
Loading 0:  60%|█████▉    | 460/771 [00:21<00:04, 70.94it/s]
Loading 0:  61%|██████    | 470/771 [00:22<00:05, 56.89it/s]
Loading 0:  62%|██████▏   | 478/771 [00:22<00:05, 57.96it/s]
Loading 0:  63%|██████▎   | 486/771 [00:22<00:04, 58.02it/s]
Loading 0:  64%|██████▍   | 497/771 [00:22<00:04, 63.60it/s]
Loading 0:  66%|██████▌   | 509/771 [00:22<00:03, 70.22it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 69.35it/s]
Loading 0:  69%|██████▉   | 534/771 [00:23<00:03, 59.51it/s]
Loading 0:  71%|███████   | 545/771 [00:23<00:03, 64.36it/s]
Loading 0:  72%|███████▏  | 557/771 [00:23<00:03, 70.53it/s]
Loading 0:  74%|███████▎  | 568/771 [00:23<00:02, 77.01it/s]
Loading 0:  75%|███████▍  | 578/771 [00:23<00:02, 79.76it/s]
Loading 0:  76%|███████▌  | 587/771 [00:23<00:03, 60.84it/s]
Loading 0:  77%|███████▋  | 594/771 [00:24<00:03, 55.80it/s]
Loading 0:  78%|███████▊  | 605/771 [00:24<00:02, 62.63it/s]
Loading 0:  80%|████████  | 617/771 [00:24<00:02, 69.85it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:02,  2.31it/s]
Loading 0:  83%|████████▎ | 638/771 [00:39<00:40,  3.32it/s]
Loading 0:  84%|████████▍ | 646/771 [00:39<00:29,  4.29it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:22,  5.26it/s]
Loading 0:  86%|████████▋ | 665/771 [00:39<00:13,  8.01it/s]
Loading 0:  88%|████████▊ | 677/771 [00:39<00:08, 11.65it/s]
Loading 0:  89%|████████▉ | 689/771 [00:39<00:05, 16.26it/s]
Loading 0:  92%|█████████▏| 706/771 [00:40<00:02, 23.07it/s]
Loading 0:  93%|█████████▎| 714/771 [00:40<00:02, 25.37it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 31.83it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 39.76it/s]
Loading 0:  97%|█████████▋| 748/771 [00:40<00:00, 48.65it/s]
Loading 0:  98%|█████████▊| 758/771 [00:40<00:00, 56.58it/s]
Loading 0:  99%|█████████▉| 767/771 [00:48<00:00,  4.23it/s]
                                                            
Job chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer completed after 217.79s with status: succeeded
Stopping job with name chaiml-nis-qwenrp-32b-s-16659-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-qwenrp-32b-s-16659-v1
Waiting for inference service chaiml-nis-qwenrp-32b-s-16659-v1 to be ready
Inference service chaiml-nis-qwenrp-32b-s-16659-v1 ready after 130.69295644760132s
Pipeline stage MKMLDeployer completed in 131.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5922529697418213s
Received healthy response to inference request in 3.0599942207336426s
Received healthy response to inference request in 3.060929775238037s
Received healthy response to inference request in 3.0535569190979004s
Received healthy response to inference request in 3.0576210021972656s
5 requests
0 failed requests
5th percentile: 3.0543697357177733
10th percentile: 3.0551825523376466
20th percentile: 3.0568081855773928
30th percentile: 3.058095645904541
40th percentile: 3.059044933319092
50th percentile: 3.0599942207336426
60th percentile: 3.0603684425354003
70th percentile: 3.060742664337158
80th percentile: 3.167194414138794
90th percentile: 3.3797236919403075
95th percentile: 3.485988330841064
99th percentile: 3.57100004196167
mean time: 3.1648709774017334
Pipeline stage StressChecker completed in 17.15s
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 0.79s
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 0.66s
Shutdown handler de-registered
chaiml-nis-qwenrp-32b-s_16659_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 0.10s
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 chaiml-nis-qwenrp-32b-s-16659-v1-profiler
Waiting for inference service chaiml-nis-qwenrp-32b-s-16659-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 3173.22s
Shutdown handler de-registered
chaiml-nis-qwenrp-32b-s_16659_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-qwenrp-32b-s_16659_v1 status is now torndown due to DeploymentManager action