developer_uid: richhx
submission_id: chaiml-collin-servant-pr_8683_v3
model_name: chaiml-collin-servant-pr_8683_v3
model_group: ChaiML/Collin-Servant-Pr
status: torndown
timestamp: 2025-07-10T17:58:24+00:00
num_battles: 8884
num_wins: 4425
celo_rating: 1289.83
family_friendly_score: 0.5176000000000001
family_friendly_standard_error: 0.007066685786137658
submission_type: basic
model_repo: ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5172340971569244, 'latency_mean': 1.933262107372284, 'latency_p50': 1.9409751892089844, 'latency_p90': 2.1329524517059326}, {'batch_size': 3, 'throughput': 1.0551924258272862, 'latency_mean': 2.8342867040634157, 'latency_p50': 2.873138904571533, 'latency_p90': 3.129867148399353}, {'batch_size': 5, 'throughput': 1.3443841952827997, 'latency_mean': 3.692541036605835, 'latency_p50': 3.7110016345977783, 'latency_p90': 4.099288392066955}, {'batch_size': 6, 'throughput': 1.4613300295313951, 'latency_mean': 4.082661616802215, 'latency_p50': 4.068441152572632, 'latency_p90': 4.565287375450134}, {'batch_size': 8, 'throughput': 1.5820165292148967, 'latency_mean': 5.013161829710007, 'latency_p50': 4.973778963088989, 'latency_p90': 5.499470543861389}, {'batch_size': 10, 'throughput': 1.662596573250733, 'latency_mean': 5.952512928247452, 'latency_p50': 5.985165357589722, 'latency_p90': 6.600957298278809}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-collin-servant-pr_8683_v3
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2025-07-10
win_ratio: 0.4980864475461504
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:', '####\n', '</s>', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-collin-servant-pr-8683-v3-mkmlizer
Waiting for job on chaiml-collin-servant-pr-8683-v3-mkmlizer to finish
chaiml-collin-servant-pr-8683-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ Version: 0.29.15 ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ belonging to: ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-collin-servant-pr-8683-v3-mkmlizer: Downloaded to shared memory in 61.353s
chaiml-collin-servant-pr-8683-v3-mkmlizer: Checking if ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft already exists in ChaiML
chaiml-collin-servant-pr-8683-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8_y78ja3, device:0
chaiml-collin-servant-pr-8683-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-collin-servant-pr-8683-v3-mkmlizer: quantized model in 50.912s
chaiml-collin-servant-pr-8683-v3-mkmlizer: Processed model ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft in 112.265s
chaiml-collin-servant-pr-8683-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-collin-servant-pr-8683-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v3/nvidia/special_tokens_map.json
chaiml-collin-servant-pr-8683-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v3/nvidia/tokenizer_config.json
chaiml-collin-servant-pr-8683-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v3/nvidia/tokenizer.json
chaiml-collin-servant-pr-8683-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v3/nvidia/flywheel_model.0.safetensors
chaiml-collin-servant-pr-8683-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 37.40it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:11, 29.77it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:11, 31.27it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:12, 27.54it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:11, 30.78it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:12, 27.99it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:10, 32.65it/s] Loading 0: 10%|▉ | 36/363 [00:01<00:16, 19.35it/s] Loading 0: 11%|█ | 40/363 [00:01<00:14, 21.93it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:14, 22.48it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:12, 25.91it/s] Loading 0: 14%|█▍ | 51/363 [00:02<00:13, 23.59it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:11, 26.96it/s] Loading 0: 16%|█▋ | 59/363 [00:02<00:13, 22.80it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 27.58it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 23.47it/s] Loading 0: 20%|██ | 73/363 [00:02<00:14, 20.45it/s] Loading 0: 22%|██▏ | 79/363 [00:03<00:11, 25.16it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 23.87it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 25.19it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:10, 25.23it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:13, 19.95it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:09, 26.69it/s] Loading 0: 28%|██▊ | 102/363 [00:04<00:10, 24.28it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:11, 21.41it/s] Loading 0: 31%|███ | 111/363 [00:04<00:10, 24.62it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:11, 22.53it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:09, 26.97it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:09, 24.69it/s] Loading 0: 36%|███▌ | 129/363 [00:05<00:08, 28.94it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:08, 27.37it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:07, 29.60it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 27.58it/s] Loading 0: 40%|████ | 147/363 [00:05<00:06, 31.83it/s] Loading 0: 42%|████▏ | 151/363 [00:06<00:09, 23.33it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:09, 21.90it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:09, 22.71it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:08, 23.17it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 26.28it/s] Loading 0: 46%|████▋ | 168/363 [00:06<00:08, 23.78it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 27.87it/s] Loading 0: 49%|████▉ | 177/363 [00:07<00:07, 24.54it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:06, 27.06it/s] Loading 0: 52%|█████▏ | 187/363 [00:07<00:07, 23.72it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 22.27it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 23.29it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:07, 23.18it/s] Loading 0: 55%|█████▌ | 200/363 [00:07<00:06, 26.86it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:06, 26.86it/s] Loading 0: 55%|█████▌ | 201/363 [00:22<04:20, 1.61s/it] Loading 0: 56%|█████▌ | 203/363 [00:23<03:22, 1.26s/it] Loading 0: 57%|█████▋ | 208/363 [00:23<01:49, 1.41it/s] Loading 0: 58%|█████▊ | 211/363 [00:23<01:20, 1.88it/s] Loading 0: 59%|█████▉ | 214/363 [00:23<00:58, 2.53it/s] Loading 0: 60%|█████▉ | 217/363 [00:23<00:42, 3.42it/s] Loading 0: 61%|██████ | 220/363 [00:24<00:32, 4.39it/s] Loading 0: 61%|██████▏ | 223/363 [00:24<00:24, 5.77it/s] Loading 0: 62%|██████▏ | 226/363 [00:24<00:20, 6.65it/s] Loading 0: 63%|██████▎ | 229/363 [00:24<00:15, 8.61it/s] Loading 0: 64%|██████▍ | 232/363 [00:24<00:12, 10.40it/s] Loading 0: 65%|██████▍ | 235/363 [00:24<00:10, 12.63it/s] Loading 0: 66%|██████▌ | 238/363 [00:25<00:08, 14.76it/s] Loading 0: 66%|██████▋ | 241/363 [00:25<00:07, 15.73it/s] Loading 0: 67%|██████▋ | 244/363 [00:25<00:06, 17.61it/s] Loading 0: 68%|██████▊ | 247/363 [00:25<00:05, 19.40it/s] Loading 0: 69%|██████▉ | 250/363 [00:25<00:05, 19.59it/s] Loading 0: 70%|██████▉ | 253/363 [00:25<00:05, 21.12it/s] Loading 0: 71%|███████ | 256/363 [00:25<00:04, 22.01it/s] Loading 0: 71%|███████▏ | 259/363 [00:25<00:04, 21.20it/s] Loading 0: 72%|███████▏ | 262/363 [00:26<00:04, 22.44it/s] Loading 0: 73%|███████▎ | 266/363 [00:26<00:03, 25.43it/s] Loading 0: 74%|███████▍ | 269/363 [00:26<00:05, 16.46it/s] Loading 0: 75%|███████▍ | 272/363 [00:26<00:05, 17.37it/s] Loading 0: 76%|███████▌ | 275/363 [00:26<00:05, 14.83it/s] Loading 0: 77%|███████▋ | 280/363 [00:27<00:04, 19.84it/s] Loading 0: 78%|███████▊ | 283/363 [00:27<00:03, 20.88it/s] Loading 0: 79%|███████▉ | 286/363 [00:27<00:03, 20.73it/s] Loading 0: 80%|███████▉ | 289/363 [00:27<00:03, 21.92it/s] Loading 0: 80%|████████ | 292/363 [00:27<00:03, 22.80it/s] Loading 0: 81%|████████▏ | 295/363 [00:27<00:03, 21.72it/s] Loading 0: 82%|████████▏ | 298/363 [00:27<00:02, 22.93it/s] Loading 0: 83%|████████▎ | 303/363 [00:28<00:02, 24.85it/s] Loading 0: 84%|████████▍ | 306/363 [00:28<00:03, 15.01it/s] Loading 0: 85%|████████▌ | 310/363 [00:28<00:02, 18.40it/s] Loading 0: 86%|████████▌ | 313/363 [00:28<00:02, 18.51it/s] Loading 0: 87%|████████▋ | 316/363 [00:28<00:02, 19.82it/s] Loading 0: 88%|████████▊ | 319/363 [00:28<00:02, 21.34it/s] Loading 0: 89%|████████▊ | 322/363 [00:29<00:01, 21.19it/s] Loading 0: 90%|████████▉ | 325/363 [00:29<00:01, 22.27it/s] Loading 0: 90%|█████████ | 328/363 [00:29<00:01, 23.68it/s] Loading 0: 91%|█████████ | 331/363 [00:29<00:01, 22.90it/s] Loading 0: 92%|█████████▏| 334/363 [00:29<00:01, 24.15it/s] Loading 0: 93%|█████████▎| 337/363 [00:29<00:01, 19.75it/s] Loading 0: 94%|█████████▎| 340/363 [00:29<00:01, 21.28it/s] Loading 0: 94%|█████████▍| 343/363 [00:30<00:01, 12.99it/s] Loading 0: 96%|█████████▌| 347/363 [00:30<00:00, 17.18it/s] Loading 0: 96%|█████████▋| 350/363 [00:30<00:00, 18.18it/s] Loading 0: 97%|█████████▋| 353/363 [00:30<00:00, 19.68it/s] Loading 0: 98%|█████████▊| 356/363 [00:30<00:00, 21.67it/s] Loading 0: 99%|█████████▉| 359/363 [00:30<00:00, 21.28it/s] Loading 0: 100%|█████████▉| 362/363 [00:31<00:00, 22.81it/s]
Job chaiml-collin-servant-pr-8683-v3-mkmlizer completed after 146.51s with status: succeeded
Stopping job with name chaiml-collin-servant-pr-8683-v3-mkmlizer
Pipeline stage MKMLizer completed in 147.63s
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-collin-servant-pr-8683-v3
Waiting for inference service chaiml-collin-servant-pr-8683-v3 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service chaiml-collin-servant-pr-8683-v3 ready after 190.9886507987976s
Pipeline stage MKMLDeployer completed in 191.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5791542530059814s
Received healthy response to inference request in 2.2193121910095215s
Received healthy response to inference request in 2.342423439025879s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.9446001052856445s
Received healthy response to inference request in 2.0538618564605713s
5 requests
0 failed requests
5th percentile: 1.96645245552063
10th percentile: 1.9883048057556152
20th percentile: 2.032009506225586
30th percentile: 2.0869519233703615
40th percentile: 2.1531320571899415
50th percentile: 2.2193121910095215
60th percentile: 2.2685566902160645
70th percentile: 2.3178011894226076
80th percentile: 2.3897696018218992
90th percentile: 2.4844619274139403
95th percentile: 2.531808090209961
99th percentile: 2.5696850204467774
mean time: 2.2278703689575194
Pipeline stage StressChecker completed in 12.69s
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 0.71s
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 0.92s
Shutdown handler de-registered
chaiml-collin-servant-pr_8683_v3 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 0.14s
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-collin-servant-pr-8683-v3-profiler
Waiting for inference service chaiml-collin-servant-pr-8683-v3-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 3068.54s
Shutdown handler de-registered
chaiml-collin-servant-pr_8683_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-collin-servant-pr_8683_v3 status is now torndown due to DeploymentManager action