junhua024-chai-16-full-qkv_72

developer_uid: junhua024

submission_id: junhua024-chai-16-full-qkv_72_v1

model_name: junhua024-chai-16-full-qkv_72_v1

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T15:25:43+00:00

num_battles: 6374

num_wins: 3081

celo_rating: 1271.1

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: junhua024/chai_16_full_qkv100_o106_ffn106_1624

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5962552367937746, 'latency_mean': 1.6770170545578003, 'latency_p50': 1.6732732057571411, 'latency_p90': 1.8532002925872804}, {'batch_size': 3, 'throughput': 1.084651126324351, 'latency_mean': 2.757101683616638, 'latency_p50': 2.7403095960617065, 'latency_p90': 3.0653289318084718}, {'batch_size': 5, 'throughput': 1.2817916723459155, 'latency_mean': 3.8756909239292145, 'latency_p50': 3.855457067489624, 'latency_p90': 4.449345445632934}, {'batch_size': 6, 'throughput': 1.3590005302131802, 'latency_mean': 4.39795203924179, 'latency_p50': 4.380558967590332, 'latency_p90': 4.941381502151489}, {'batch_size': 8, 'throughput': 1.4000039270034317, 'latency_mean': 5.668662257194519, 'latency_p50': 5.716750621795654, 'latency_p90': 6.290936303138733}, {'batch_size': 10, 'throughput': 1.4394221039606807, 'latency_mean': 6.891403088569641, 'latency_p50': 6.899409651756287, 'latency_p90': 7.761912751197815}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-qkv_72_v1

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1624

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-07-20

win_ratio: 0.4833699403828051

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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 junhua024-chai-16-full-qkv-72-v1-mkmlizer
Waiting for job on junhua024-chai-16-full-qkv-72-v1-mkmlizer to finish
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission junhua024-chai-16-full-_94000_v7: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v1-mkmlizer: Downloaded to shared memory in 94.598s
junhua024-chai-16-full-qkv-72-v1-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1624 already exists in ChaiML
junhua024-chai-16-full-qkv-72-v1-mkmlizer: Creating repo ChaiML/chai_16_full_qkv100_o106_ffn106_1624 and uploading /tmp/tmpcrju4y1k to it
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:03<01:17,  3.08s/it]
  8%|▊         | 2/26 [00:05<01:02,  2.62s/it]
 12%|█▏        | 3/26 [00:07<00:50,  2.18s/it]
 15%|█▌        | 4/26 [00:08<00:43,  1.97s/it]
 19%|█▉        | 5/26 [00:10<00:39,  1.88s/it]
 23%|██▎       | 6/26 [00:13<00:43,  2.17s/it]
 27%|██▋       | 7/26 [00:16<00:46,  2.43s/it]
 31%|███       | 8/26 [00:18<00:40,  2.26s/it]
 35%|███▍      | 9/26 [00:20<00:39,  2.35s/it]
 38%|███▊      | 10/26 [00:22<00:35,  2.20s/it]
 42%|████▏     | 11/26 [00:25<00:36,  2.45s/it]
 46%|████▌     | 12/26 [00:27<00:32,  2.33s/it]
 50%|█████     | 13/26 [00:28<00:26,  2.04s/it]
 54%|█████▍    | 14/26 [00:31<00:26,  2.20s/it]
 58%|█████▊    | 15/26 [00:33<00:24,  2.27s/it]
 62%|██████▏   | 16/26 [00:36<00:24,  2.42s/it]
 65%|██████▌   | 17/26 [00:38<00:19,  2.22s/it]
 69%|██████▉   | 18/26 [00:40<00:16,  2.10s/it]
 73%|███████▎  | 19/26 [00:42<00:15,  2.15s/it]
 77%|███████▋  | 20/26 [00:44<00:12,  2.04s/it]
 81%|████████  | 21/26 [00:45<00:09,  1.92s/it]
 85%|████████▍ | 22/26 [00:47<00:07,  1.78s/it]
 88%|████████▊ | 23/26 [00:53<00:09,  3.11s/it]
 92%|█████████▏| 24/26 [00:56<00:05,  2.94s/it]
 96%|█████████▌| 25/26 [00:58<00:02,  2.62s/it]
100%|██████████| 26/26 [00:59<00:00,  2.19s/it]
100%|██████████| 26/26 [00:59<00:00,  2.28s/it]
junhua024-chai-16-full-qkv-72-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcrju4y1k, device:0
junhua024-chai-16-full-qkv-72-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-qkv-72-v1-mkmlizer: quantized model in 30.942s
junhua024-chai-16-full-qkv-72-v1-mkmlizer: Processed model junhua024/chai_16_full_qkv100_o106_ffn106_1624 in 210.394s
junhua024-chai-16-full-qkv-72-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-qkv-72-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-qkv-72-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v1/nvidia
junhua024-chai-16-full-qkv-72-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v1/nvidia/config.json
junhua024-chai-16-full-qkv-72-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v1/nvidia/special_tokens_map.json
junhua024-chai-16-full-qkv-72-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v1/nvidia/tokenizer_config.json
junhua024-chai-16-full-qkv-72-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v1/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-qkv-72-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 15.96it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.33it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.25it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.26it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.71it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 48.34it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 37.72it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 37.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 41.77it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.80it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.61it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 36.59it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:08, 35.33it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 35.08it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.65it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 39.35it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 38.70it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 39.43it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:06, 38.47it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 38.05it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:05, 42.32it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.08it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 34.42it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 36.52it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 35.20it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.62it/s]
Loading 0:  39%|███▉      | 143/363 [00:03<00:06, 35.52it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 36.09it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 41.26it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 39.69it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 38.58it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 37.73it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 41.60it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:05, 35.10it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.73it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 36.26it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.03it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:04, 37.43it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 37.14it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:04, 33.46it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 32.28it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 43.45it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 33.38it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 34.26it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:02, 41.80it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 36.05it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.09it/s]
Loading 0:  70%|██████▉   | 254/363 [00:06<00:02, 36.99it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:02, 35.68it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 36.03it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 34.94it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.51it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 38.38it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 36.75it/s]
Loading 0:  80%|███████▉  | 290/363 [00:07<00:01, 36.61it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 34.78it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 41.56it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 34.77it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 34.04it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 35.87it/s]
Loading 0:  88%|████████▊ | 321/363 [00:08<00:01, 34.26it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.22it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.31it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.08it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 43.51it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 25.02it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 27.08it/s]
Loading 0:  99%|█████████▉| 359/363 [00:10<00:00, 29.35it/s]
                                                            
Job junhua024-chai-16-full-qkv-72-v1-mkmlizer completed after 230.49s with status: succeeded
Stopping job with name junhua024-chai-16-full-qkv-72-v1-mkmlizer
Pipeline stage MKMLizer completed in 231.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-qkv-72-v1
Waiting for inference service junhua024-chai-16-full-qkv-72-v1 to be ready
Failed to get response for submission junhua024-chai-16-full-_94000_v7: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_94000_v7: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service junhua024-chai-16-full-qkv-72-v1 ready after 331.4990975856781s
Pipeline stage MKMLDeployer completed in 332.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.834174156188965s
Received healthy response to inference request in 2.853764057159424s
Received healthy response to inference request in 2.115074396133423s
Received healthy response to inference request in 2.1762099266052246s
Received healthy response to inference request in 2.1994564533233643s
5 requests
0 failed requests
5th percentile: 2.127301502227783
10th percentile: 2.1395286083221436
20th percentile: 2.1639828205108644
30th percentile: 2.1808592319488525
40th percentile: 2.1901578426361086
50th percentile: 2.1994564533233643
60th percentile: 2.4533435344696044
70th percentile: 2.7072306156158445
80th percentile: 2.8380921363830565
90th percentile: 2.84592809677124
95th percentile: 2.849846076965332
99th percentile: 2.8529804611206053
mean time: 2.43573579788208
Pipeline stage StressChecker completed in 14.48s
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 0.65s
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
junhua024-chai-16-full-qkv_72_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-16-full-qkv-72-v1-profiler
Waiting for inference service junhua024-chai-16-full-qkv-72-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
%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
junhua024-chai-16-full-qkv_72_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-qkv_72_v1 status is now torndown due to DeploymentManager action