chaiml-nis-qwen25-32b-s_16023

developer_uid: NischayDnk

submission_id: chaiml-nis-qwen25-32b-s_16023_v1

model_name: chaiml-nis-qwen25-32b-s_16023_v1

model_group: ChaiML/nis-qwen25-32b-sf

status: torndown

timestamp: 2025-04-17T15:03:08+00:00

num_battles: 9072

num_wins: 4274

celo_rating: 1266.58

family_friendly_score: 0.5924

family_friendly_standard_error: 0.006949276796904841

submission_type: basic

model_repo: ChaiML/nis-qwen25-32b-sft-stage2-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': 0.28801594134131875, 'latency_mean': 3.4719668650627136, 'latency_p50': 3.470990300178528, 'latency_p90': 3.8650158882141112}, {'batch_size': 2, 'throughput': 0.4814727661499675, 'latency_mean': 4.143547668457031, 'latency_p50': 4.15140163898468, 'latency_p90': 4.518354845046997}, {'batch_size': 3, 'throughput': 0.6502960320129968, 'latency_mean': 4.593623268604278, 'latency_p50': 4.562469124794006, 'latency_p90': 5.10946524143219}, {'batch_size': 4, 'throughput': 0.7962807726080396, 'latency_mean': 5.003576169013977, 'latency_p50': 4.989028215408325, 'latency_p90': 5.554616618156433}, {'batch_size': 5, 'throughput': 0.9245698376141097, 'latency_mean': 5.373191361427307, 'latency_p50': 5.357239127159119, 'latency_p90': 6.001758146286011}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-nis-qwen25-32b-s_16023_v1

is_internal_developer: False

language_model: ChaiML/nis-qwen25-32b-sft-stage2-exp1-datav1ffsys20k

model_size: 33B

ranking_group: single

throughput_3p7s: 0.36

us_pacific_date: 2025-04-17

win_ratio: 0.4711199294532628

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': '<|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-qwen25-32b-s-16023-v1-mkmlizer
Waiting for job on chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer to finish
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ║                                                                     ║
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: quantized model in 65.500s
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: Processed model ChaiML/nis-qwen25-32b-sft-stage2-exp1-datav1ffsys20k in 179.443s
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/added_tokens.json
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/config.json
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/special_tokens_map.json
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/tokenizer_config.json
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/merges.txt
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/vocab.json
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/tokenizer.json
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/flywheel_model.2.safetensors
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/flywheel_model.1.safetensors
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen25-32b-s-16023-v1/flywheel_model.0.safetensors
chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:20, 37.05it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 72.87it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 86.87it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 89.52it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:14, 50.65it/s]
Loading 0:   7%|▋         | 54/771 [00:00<00:15, 47.45it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:12, 58.07it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:10, 68.71it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:09, 73.32it/s]
Loading 0:  12%|█▏        | 93/771 [00:01<00:09, 71.11it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 60.68it/s]
Loading 0:  15%|█▍        | 113/771 [00:01<00:11, 57.93it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 58.20it/s]
Loading 0:  17%|█▋        | 132/771 [00:02<00:09, 68.87it/s]
Loading 0:  18%|█▊        | 142/771 [00:02<00:08, 75.27it/s]
Loading 0:  20%|█▉        | 152/771 [00:02<00:07, 79.74it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 74.54it/s]
Loading 0:  22%|██▏       | 169/771 [00:02<00:12, 49.47it/s]
Loading 0:  23%|██▎       | 176/771 [00:02<00:11, 50.38it/s]
Loading 0:  24%|██▍       | 185/771 [00:03<00:10, 53.94it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:08, 65.14it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 74.67it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:07, 78.03it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 58.51it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 51.13it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 60.40it/s]
Loading 0:  33%|███▎      | 255/771 [00:03<00:07, 70.22it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:06, 73.68it/s]
Loading 0:  35%|███▌      | 273/771 [00:04<00:07, 70.86it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:08, 59.40it/s]
Loading 0:  38%|███▊      | 293/771 [00:04<00:09, 50.06it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:47,  2.05it/s]
Loading 0:  40%|████      | 311/771 [00:20<02:46,  2.76it/s]
Loading 0:  41%|████      | 318/771 [00:20<02:05,  3.60it/s]
Loading 0:  43%|████▎     | 328/771 [00:20<01:23,  5.32it/s]
Loading 0:  44%|████▍     | 338/771 [00:20<00:56,  7.67it/s]
Loading 0:  45%|████▍     | 346/771 [00:20<00:44,  9.66it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:37, 11.23it/s]
Loading 0:  47%|████▋     | 364/771 [00:21<00:24, 16.59it/s]
Loading 0:  49%|████▊     | 375/771 [00:21<00:17, 23.27it/s]
Loading 0:  50%|████▉     | 383/771 [00:21<00:13, 28.55it/s]
Loading 0:  51%|█████     | 391/771 [00:21<00:11, 33.53it/s]
Loading 0:  53%|█████▎    | 406/771 [00:21<00:09, 40.23it/s]
Loading 0:  54%|█████▎    | 413/771 [00:21<00:09, 38.43it/s]
Loading 0:  55%|█████▍    | 424/771 [00:21<00:07, 48.74it/s]
Loading 0:  56%|█████▋    | 435/771 [00:22<00:05, 59.16it/s]
Loading 0:  58%|█████▊    | 444/771 [00:22<00:05, 65.05it/s]
Loading 0:  59%|█████▉    | 453/771 [00:22<00:04, 65.89it/s]
Loading 0:  60%|██████    | 466/771 [00:22<00:05, 57.77it/s]
Loading 0:  61%|██████▏   | 474/771 [00:22<00:05, 50.78it/s]
Loading 0:  63%|██████▎   | 485/771 [00:22<00:04, 57.34it/s]
Loading 0:  64%|██████▍   | 496/771 [00:23<00:04, 67.32it/s]
Loading 0:  66%|██████▌   | 507/771 [00:23<00:03, 76.08it/s]
Loading 0:  67%|██████▋   | 517/771 [00:23<00:03, 81.44it/s]
Loading 0:  68%|██████▊   | 527/771 [00:23<00:04, 55.52it/s]
Loading 0:  69%|██████▉   | 535/771 [00:23<00:04, 52.83it/s]
Loading 0:  71%|███████   | 544/771 [00:23<00:03, 59.90it/s]
Loading 0:  72%|███████▏  | 555/771 [00:23<00:03, 70.24it/s]
Loading 0:  73%|███████▎  | 564/771 [00:24<00:02, 74.33it/s]
Loading 0:  74%|███████▍  | 573/771 [00:24<00:02, 71.14it/s]
Loading 0:  76%|███████▌  | 586/771 [00:24<00:03, 60.59it/s]
Loading 0:  77%|███████▋  | 593/771 [00:24<00:03, 51.16it/s]
Loading 0:  78%|███████▊  | 604/771 [00:24<00:02, 61.97it/s]
Loading 0:  80%|███████▉  | 615/771 [00:24<00:02, 71.84it/s]
Loading 0:  81%|████████  | 624/771 [00:24<00:01, 75.22it/s]
Loading 0:  82%|████████▏ | 633/771 [00:39<01:06,  2.09it/s]
Loading 0:  84%|████████▍ | 646/771 [00:40<00:39,  3.19it/s]
Loading 0:  85%|████████▍ | 654/771 [00:40<00:28,  4.08it/s]
Loading 0:  86%|████████▋ | 665/771 [00:40<00:18,  5.88it/s]
Loading 0:  88%|████████▊ | 677/771 [00:40<00:10,  8.55it/s]
Loading 0:  89%|████████▉ | 689/771 [00:41<00:06, 12.08it/s]
Loading 0:  92%|█████████▏| 706/771 [00:41<00:03, 17.66it/s]
Loading 0:  93%|█████████▎| 714/771 [00:41<00:02, 19.92it/s]
Loading 0:  94%|█████████▍| 725/771 [00:41<00:01, 25.49it/s]
Loading 0:  95%|█████████▌| 736/771 [00:41<00:01, 32.85it/s]
Loading 0:  97%|█████████▋| 748/771 [00:41<00:00, 40.86it/s]
Loading 0:  98%|█████████▊| 758/771 [00:42<00:00, 48.70it/s]
Loading 0:  99%|█████████▉| 767/771 [00:49<00:00,  4.17it/s]
                                                            
Job chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer completed after 217.73s with status: succeeded
Stopping job with name chaiml-nis-qwen25-32b-s-16023-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.25s
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-qwen25-32b-s-16023-v1
Waiting for inference service chaiml-nis-qwen25-32b-s-16023-v1 to be ready
Inference service chaiml-nis-qwen25-32b-s-16023-v1 ready after 130.61009192466736s
Pipeline stage MKMLDeployer completed in 131.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5957438945770264s
Received healthy response to inference request in 3.081024646759033s
Received healthy response to inference request in 3.080491542816162s
Received healthy response to inference request in 3.0882039070129395s
Received healthy response to inference request in 3.075054168701172s
5 requests
0 failed requests
5th percentile: 3.0761416435241697
10th percentile: 3.077229118347168
20th percentile: 3.0794040679931642
30th percentile: 3.080598163604736
40th percentile: 3.0808114051818847
50th percentile: 3.081024646759033
60th percentile: 3.083896350860596
70th percentile: 3.086768054962158
80th percentile: 3.189711904525757
90th percentile: 3.3927278995513914
95th percentile: 3.494235897064209
99th percentile: 3.575442295074463
mean time: 3.1841036319732665
Pipeline stage StressChecker completed in 17.17s
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 0.69s
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 0.71s
Shutdown handler de-registered
chaiml-nis-qwen25-32b-s_16023_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 0.12s
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-qwen25-32b-s-16023-v1-profiler
Waiting for inference service chaiml-nis-qwen25-32b-s-16023-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 3195.25s
Shutdown handler de-registered
chaiml-nis-qwen25-32b-s_16023_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-qwen25-32b-s_16023_v1 status is now torndown due to DeploymentManager action