developer_uid: NischayDnk
submission_id: chaiml-nis-qwen32b-simp_63569_v2
model_name: chaiml-nis-qwen32b-simp_63569_v2
model_group: ChaiML/nis-qwen32b-simpo
status: torndown
timestamp: 2025-04-19T19:13:55+00:00
num_battles: 60
num_wins: 36
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/nis-qwen32b-simpoexp4-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': 0.27727717911975513, 'latency_mean': 3.606436368227005, 'latency_p50': 3.607025623321533, 'latency_p90': 4.012470436096192}, {'batch_size': 2, 'throughput': 0.45238361465564925, 'latency_mean': 4.417592117786407, 'latency_p50': 4.401984214782715, 'latency_p90': 4.869153642654418}, {'batch_size': 3, 'throughput': 0.6025521004294262, 'latency_mean': 4.960285717248917, 'latency_p50': 4.916338682174683, 'latency_p90': 5.487781405448914}, {'batch_size': 4, 'throughput': 0.7076064369294985, 'latency_mean': 5.611508584022522, 'latency_p50': 5.604470491409302, 'latency_p90': 6.324398112297058}, {'batch_size': 5, 'throughput': 0.7942128243635821, 'latency_mean': 6.263397867679596, 'latency_p50': 6.265899419784546, 'latency_p90': 7.091770625114441}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-nis-qwen32b-simp_63569_v2
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ChaiML/nis-qwen32b-simpoexp4-s1-pref-1295datav1sft
model_size: 33B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-04-19
win_ratio: 0.6
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, '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-63569-v2-mkmlizer
Waiting for job on chaiml-nis-qwen32b-simp-63569-v2-mkmlizer to finish
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ _____ __ __ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ /___/ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ belonging to: ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ║ ║
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: Downloaded to shared memory in 88.418s
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2wvhqvc3, device:0
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: quantized model in 64.634s
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: Processed model ChaiML/nis-qwen32b-simpoexp4-s1-pref-1295datav1sft in 153.053s
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2/config.json
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2/special_tokens_map.json
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2/added_tokens.json
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2/flywheel_model.2.safetensors
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2/flywheel_model.1.safetensors
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-simp-63569-v2/flywheel_model.0.safetensors
chaiml-nis-qwen32b-simp-63569-v2-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:20, 37.97it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 73.32it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 86.71it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 86.25it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:15, 48.24it/s] Loading 0: 7%|▋ | 53/771 [00:01<00:16, 42.74it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 54.84it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 65.82it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 70.56it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 68.62it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:11, 58.00it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 56.14it/s] Loading 0: 16%|█▌ | 121/771 [00:02<00:11, 56.82it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 67.60it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 74.28it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 79.79it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 74.61it/s] Loading 0: 22%|██▏ | 169/771 [00:02<00:12, 49.92it/s] Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 50.23it/s] Loading 0: 24%|██▍ | 184/771 [00:03<00:10, 55.96it/s] Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 67.11it/s] Loading 0: 26%|██▋ | 203/771 [00:03<00:08, 69.27it/s] Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 66.78it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 59.03it/s] Loading 0: 30%|███ | 233/771 [00:03<00:10, 50.43it/s] Loading 0: 32%|███▏ | 245/771 [00:04<00:08, 59.30it/s] Loading 0: 33%|███▎ | 256/771 [00:04<00:07, 69.27it/s] Loading 0: 35%|███▍ | 267/771 [00:04<00:06, 77.62it/s] Loading 0: 36%|███▌ | 276/771 [00:04<00:06, 79.62it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 61.34it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:09, 52.64it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:50, 2.03it/s] Loading 0: 40%|████ | 311/771 [00:19<02:47, 2.75it/s] Loading 0: 41%|████ | 318/771 [00:19<02:05, 3.61it/s] Loading 0: 43%|████▎ | 328/771 [00:20<01:22, 5.37it/s] Loading 0: 44%|████▍ | 338/771 [00:20<00:55, 7.76it/s] Loading 0: 45%|████▍ | 346/771 [00:20<00:43, 9.72it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:37, 11.27it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:24, 16.67it/s] Loading 0: 49%|████▊ | 375/771 [00:20<00:16, 23.38it/s] Loading 0: 50%|████▉ | 383/771 [00:21<00:13, 28.58it/s] Loading 0: 51%|█████ | 391/771 [00:21<00:11, 33.43it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:09, 38.45it/s] Loading 0: 54%|█████▎ | 413/771 [00:21<00:09, 37.13it/s] Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 47.11it/s] Loading 0: 56%|█████▋ | 435/771 [00:21<00:05, 57.19it/s] Loading 0: 58%|█████▊ | 444/771 [00:21<00:05, 62.90it/s] Loading 0: 59%|█████▉ | 453/771 [00:22<00:05, 63.37it/s] Loading 0: 60%|██████ | 466/771 [00:22<00:05, 56.22it/s] Loading 0: 61%|██████▏ | 473/771 [00:22<00:06, 48.75it/s] Loading 0: 63%|██████▎ | 484/771 [00:22<00:04, 59.28it/s] Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 69.19it/s] Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 73.06it/s] Loading 0: 67%|██████▋ | 513/771 [00:23<00:03, 70.00it/s] Loading 0: 68%|██████▊ | 526/771 [00:23<00:04, 57.99it/s] Loading 0: 69%|██████▉ | 533/771 [00:23<00:04, 49.44it/s] Loading 0: 71%|███████ | 544/771 [00:23<00:03, 59.85it/s] Loading 0: 72%|███████▏ | 555/771 [00:23<00:03, 69.60it/s] Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 71.80it/s] Loading 0: 74%|███████▍ | 573/771 [00:24<00:02, 67.57it/s] Loading 0: 76%|███████▌ | 586/771 [00:24<00:03, 57.96it/s] Loading 0: 77%|███████▋ | 593/771 [00:24<00:03, 49.59it/s] Loading 0: 78%|███████▊ | 604/771 [00:24<00:02, 60.20it/s] Loading 0: 80%|███████▉ | 615/771 [00:24<00:02, 69.98it/s] Loading 0: 81%|████████ | 624/771 [00:24<00:01, 74.04it/s] Loading 0: 82%|████████▏ | 633/771 [00:39<01:05, 2.12it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:38, 3.27it/s] Loading 0: 85%|████████▍ | 654/771 [00:40<00:28, 4.14it/s] Loading 0: 86%|████████▌ | 664/771 [00:40<00:18, 5.82it/s] Loading 0: 88%|████████▊ | 676/771 [00:40<00:11, 8.55it/s] Loading 0: 89%|████████▉ | 688/771 [00:40<00:06, 12.13it/s] Loading 0: 91%|█████████ | 698/771 [00:40<00:04, 16.11it/s] Loading 0: 92%|█████████▏| 707/771 [00:41<00:03, 18.94it/s] Loading 0: 93%|█████████▎| 714/771 [00:41<00:02, 21.72it/s] Loading 0: 94%|█████████▍| 725/771 [00:41<00:01, 28.85it/s] Loading 0: 95%|█████████▌| 736/771 [00:41<00:00, 37.98it/s] Loading 0: 97%|█████████▋| 747/771 [00:41<00:00, 47.84it/s] Loading 0: 98%|█████████▊| 757/771 [00:41<00:00, 56.33it/s] Loading 0: 99%|█████████▉| 767/771 [00:49<00:00, 4.13it/s]
Job chaiml-nis-qwen32b-simp-63569-v2-mkmlizer completed after 186.54s with status: succeeded
Stopping job with name chaiml-nis-qwen32b-simp-63569-v2-mkmlizer
Pipeline stage MKMLizer completed in 187.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-qwen32b-simp-63569-v2
Waiting for inference service chaiml-nis-qwen32b-simp-63569-v2 to be ready
Inference service chaiml-nis-qwen32b-simp-63569-v2 ready after 130.43604946136475s
Pipeline stage MKMLDeployer completed in 130.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.018786191940308s
Received healthy response to inference request in 3.3144125938415527s
Received healthy response to inference request in 3.497436761856079s
Received healthy response to inference request in 3.3071367740631104s
{"detail":"('http://alexdaoud-trainer-bajem-28556-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45914->127.0.0.1:8080: read: connection reset by peer\\n')"}
Received unhealthy response to inference request!
5 requests
1 failed requests
5th percentile: 3.308591938018799
10th percentile: 3.3100471019744875
20th percentile: 3.312957429885864
30th percentile: 3.3227371692657472
40th percentile: 3.339386320114136
50th percentile: 3.3560354709625244
60th percentile: 3.4125959873199463
70th percentile: 3.469156503677368
80th percentile: 3.6017066478729247
90th percentile: 3.8102464199066164
95th percentile: 3.914516305923462
99th percentile: 3.9979322147369385
mean time: 3.4987615585327148
%s, retrying in %s seconds...
Received healthy response to inference request in 3.363783359527588s
Received healthy response to inference request in 3.325786828994751s
Received healthy response to inference request in 3.489058017730713s
Received healthy response to inference request in 3.4007503986358643s
Received healthy response to inference request in 3.329758882522583s
5 requests
0 failed requests
5th percentile: 3.3265812397003174
10th percentile: 3.327375650405884
20th percentile: 3.3289644718170166
30th percentile: 3.336563777923584
40th percentile: 3.350173568725586
50th percentile: 3.363783359527588
60th percentile: 3.3785701751708985
70th percentile: 3.393356990814209
80th percentile: 3.418411922454834
90th percentile: 3.4537349700927735
95th percentile: 3.471396493911743
99th percentile: 3.485525712966919
mean time: 3.3818274974822997
Pipeline stage StressChecker completed in 37.12s
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 0.88s
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 0.79s
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_63569_v2 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
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
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
chaiml-nis-qwen32b-simp_63569_v2 status is now inactive due to admin request
chaiml-nis-qwen32b-simp_63569_v2 status is now torndown due to DeploymentManager action