developer_uid: richhx
submission_id: chaiml-collin-servant-pr_8683_v2
model_name: chaiml-collin-servant-pr_8683_v2
model_group: ChaiML/Collin-Servant-Pr
status: torndown
timestamp: 2025-07-09T16:35:19+00:00
num_battles: 6898
num_wins: 3436
celo_rating: 1290.16
family_friendly_score: 0.5174000000000001
family_friendly_standard_error: 0.007066784841779181
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': 0.5117488295265042, 'latency_mean': 1.9539592850208283, 'latency_p50': 1.9647011756896973, 'latency_p90': 2.146285390853882}, {'batch_size': 3, 'throughput': 1.024931132167434, 'latency_mean': 2.9216787338256838, 'latency_p50': 2.9306451082229614, 'latency_p90': 3.203959274291992}, {'batch_size': 5, 'throughput': 1.3056384652933786, 'latency_mean': 3.8107434165477754, 'latency_p50': 3.8299721479415894, 'latency_p90': 4.2492622375488285}, {'batch_size': 6, 'throughput': 1.40592533359006, 'latency_mean': 4.2335577082633975, 'latency_p50': 4.28180468082428, 'latency_p90': 4.6898208379745485}, {'batch_size': 8, 'throughput': 1.5455320120854643, 'latency_mean': 5.148649065494538, 'latency_p50': 5.131440043449402, 'latency_p90': 5.7399986505508425}, {'batch_size': 10, 'throughput': 1.6201860143898168, 'latency_mean': 6.124996982812881, 'latency_p50': 6.092867732048035, 'latency_p90': 6.954115509986877}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-collin-servant-pr_8683_v2
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: 1.28
us_pacific_date: 2025-07-09
win_ratio: 0.49811539576688896
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', '####', '</s>', '####\n', 'You:'], '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-v2-mkmlizer
Waiting for job on chaiml-collin-servant-pr-8683-v2-mkmlizer to finish
chaiml-collin-servant-pr-8683-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ belonging to: ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ║ ║
chaiml-collin-servant-pr-8683-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-collin-servant-pr-8683-v2-mkmlizer: Downloaded to shared memory in 108.462s
chaiml-collin-servant-pr-8683-v2-mkmlizer: Checking if ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft already exists in ChaiML
chaiml-collin-servant-pr-8683-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp595rs6av, device:0
chaiml-collin-servant-pr-8683-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-collin-servant-pr-8683-v2-mkmlizer: quantized model in 49.791s
chaiml-collin-servant-pr-8683-v2-mkmlizer: Processed model ChaiML/Collin-Servant-Prince-forbidden-love_K250512125136_sft in 158.253s
chaiml-collin-servant-pr-8683-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-collin-servant-pr-8683-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-collin-servant-pr-8683-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia
chaiml-collin-servant-pr-8683-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia/config.json
chaiml-collin-servant-pr-8683-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia/special_tokens_map.json
chaiml-collin-servant-pr-8683-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia/tokenizer_config.json
chaiml-collin-servant-pr-8683-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia/tokenizer.json
chaiml-collin-servant-pr-8683-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia/flywheel_model.1.safetensors
chaiml-collin-servant-pr-8683-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-pr-8683-v2/nvidia/flywheel_model.0.safetensors
chaiml-collin-servant-pr-8683-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 37.52it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:12, 29.43it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:11, 30.37it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:12, 27.00it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:11, 30.56it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:12, 26.50it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:09, 33.94it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:15, 21.26it/s] Loading 0: 10%|█ | 38/363 [00:01<00:14, 22.05it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:17, 18.71it/s] Loading 0: 13%|█▎ | 47/363 [00:01<00:12, 26.16it/s] Loading 0: 14%|█▍ | 51/363 [00:02<00:13, 22.73it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:11, 25.82it/s] Loading 0: 16%|█▋ | 59/363 [00:02<00:13, 22.57it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:11, 26.98it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 22.99it/s] Loading 0: 20%|██ | 73/363 [00:03<00:14, 19.56it/s] Loading 0: 22%|██▏ | 79/363 [00:03<00:11, 24.39it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 23.65it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.84it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:10, 25.11it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:13, 20.20it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:10, 25.80it/s] Loading 0: 28%|██▊ | 101/363 [00:04<00:11, 22.61it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:11, 21.49it/s] Loading 0: 31%|███ | 111/363 [00:04<00:10, 24.29it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:11, 21.68it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:09, 26.11it/s] Loading 0: 34%|███▍ | 123/363 [00:05<00:10, 23.70it/s] Loading 0: 36%|███▌ | 129/363 [00:05<00:08, 27.72it/s] Loading 0: 36%|███▋ | 132/363 [00:05<00:09, 24.75it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:07, 28.34it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:08, 24.87it/s] Loading 0: 40%|████ | 146/363 [00:05<00:07, 29.68it/s] Loading 0: 41%|████▏ | 150/363 [00:06<00:09, 22.63it/s] Loading 0: 42%|████▏ | 153/363 [00:06<00:10, 19.46it/s] Loading 0: 43%|████▎ | 157/363 [00:06<00:09, 22.56it/s] Loading 0: 44%|████▍ | 160/363 [00:06<00:08, 22.56it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 25.26it/s] Loading 0: 46%|████▋ | 168/363 [00:06<00:08, 22.84it/s] Loading 0: 48%|████▊ | 174/363 [00:07<00:06, 27.63it/s] Loading 0: 49%|████▉ | 177/363 [00:07<00:07, 24.62it/s] Loading 0: 50%|█████ | 182/363 [00:07<00:06, 26.83it/s] Loading 0: 52%|█████▏ | 187/363 [00:07<00:07, 23.28it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 21.70it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 22.57it/s] Loading 0: 54%|█████▍ | 196/363 [00:08<00:07, 22.48it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:07, 22.48it/s] Loading 0: 55%|█████▌ | 201/363 [00:22<03:05, 1.15s/it] Loading 0: 56%|█████▌ | 203/363 [00:23<02:33, 1.04it/s] Loading 0: 57%|█████▋ | 208/363 [00:23<01:32, 1.67it/s] Loading 0: 58%|█████▊ | 211/363 [00:23<01:11, 2.13it/s] Loading 0: 59%|█████▉ | 214/363 [00:23<00:53, 2.81it/s] Loading 0: 60%|██████ | 218/363 [00:23<00:36, 4.00it/s] Loading 0: 61%|██████ | 221/363 [00:23<00:27, 5.08it/s] Loading 0: 62%|██████▏ | 224/363 [00:24<00:23, 6.02it/s] Loading 0: 63%|██████▎ | 229/363 [00:24<00:15, 8.90it/s] Loading 0: 64%|██████▍ | 232/363 [00:24<00:12, 10.60it/s] Loading 0: 65%|██████▌ | 237/363 [00:24<00:08, 14.27it/s] Loading 0: 66%|██████▌ | 240/363 [00:24<00:08, 15.09it/s] Loading 0: 68%|██████▊ | 246/363 [00:24<00:05, 20.16it/s] Loading 0: 69%|██████▊ | 249/363 [00:25<00:05, 19.61it/s] Loading 0: 70%|██████▉ | 253/363 [00:25<00:05, 21.79it/s] Loading 0: 71%|███████ | 256/363 [00:25<00:04, 22.73it/s] Loading 0: 71%|███████▏ | 259/363 [00:25<00:04, 23.06it/s] Loading 0: 73%|███████▎ | 264/363 [00:25<00:03, 28.53it/s] Loading 0: 74%|███████▍ | 268/363 [00:25<00:04, 21.18it/s] Loading 0: 75%|███████▍ | 271/363 [00:26<00:04, 20.31it/s] Loading 0: 75%|███████▌ | 274/363 [00:26<00:04, 21.51it/s] Loading 0: 76%|███████▋ | 277/363 [00:26<00:03, 21.93it/s] Loading 0: 78%|███████▊ | 282/363 [00:26<00:03, 25.02it/s] Loading 0: 79%|███████▊ | 285/363 [00:26<00:03, 22.38it/s] Loading 0: 80%|███████▉ | 289/363 [00:26<00:02, 25.62it/s] Loading 0: 80%|████████ | 292/363 [00:26<00:02, 25.99it/s] Loading 0: 81%|████████▏ | 295/363 [00:26<00:02, 24.82it/s] Loading 0: 82%|████████▏ | 299/363 [00:27<00:02, 25.38it/s] Loading 0: 84%|████████▎ | 304/363 [00:27<00:02, 21.63it/s] Loading 0: 85%|████████▍ | 307/363 [00:27<00:02, 20.36it/s] Loading 0: 85%|████████▌ | 310/363 [00:27<00:02, 21.74it/s] Loading 0: 86%|████████▌ | 313/363 [00:27<00:02, 22.32it/s] Loading 0: 88%|████████▊ | 318/363 [00:27<00:01, 25.54it/s] Loading 0: 88%|████████▊ | 321/363 [00:28<00:01, 23.16it/s] Loading 0: 90%|█████████ | 327/363 [00:28<00:01, 27.74it/s] Loading 0: 91%|█████████ | 330/363 [00:28<00:01, 24.71it/s] Loading 0: 92%|█████████▏| 335/363 [00:28<00:01, 27.00it/s] Loading 0: 93%|█████████▎| 338/363 [00:28<00:00, 25.64it/s] Loading 0: 94%|█████████▍| 341/363 [00:29<00:01, 14.93it/s] Loading 0: 96%|█████████▌| 347/363 [00:29<00:00, 20.25it/s] Loading 0: 96%|█████████▋| 350/363 [00:29<00:00, 20.94it/s] Loading 0: 97%|█████████▋| 353/363 [00:29<00:00, 22.62it/s] Loading 0: 98%|█████████▊| 357/363 [00:29<00:00, 21.34it/s]
Job chaiml-collin-servant-pr-8683-v2-mkmlizer completed after 199.29s with status: succeeded
Stopping job with name chaiml-collin-servant-pr-8683-v2-mkmlizer
Pipeline stage MKMLizer completed in 199.91s
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-collin-servant-pr-8683-v2
Waiting for inference service chaiml-collin-servant-pr-8683-v2 to be ready
Inference service chaiml-collin-servant-pr-8683-v2 ready after 341.60743165016174s
Pipeline stage MKMLDeployer completed in 342.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6431987285614014s
Received healthy response to inference request in 1.9073827266693115s
Received healthy response to inference request in 1.875533103942871s
Received healthy response to inference request in 2.4701170921325684s
Received healthy response to inference request in 2.0232510566711426s
5 requests
0 failed requests
5th percentile: 1.8819030284881593
10th percentile: 1.8882729530334472
20th percentile: 1.9010128021240233
30th percentile: 1.9305563926696778
40th percentile: 1.9769037246704102
50th percentile: 2.0232510566711426
60th percentile: 2.201997470855713
70th percentile: 2.380743885040283
80th percentile: 2.504733419418335
90th percentile: 2.573966073989868
95th percentile: 2.6085824012756347
99th percentile: 2.636275463104248
mean time: 2.183896541595459
Pipeline stage StressChecker completed in 12.65s
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 0.78s
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 0.90s
Shutdown handler de-registered
chaiml-collin-servant-pr_8683_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5651.68s
Shutdown handler de-registered
chaiml-collin-servant-pr_8683_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-collin-servant-pr_8683_v2 status is now torndown due to DeploymentManager action