developer_uid: NischayDnk
submission_id: chaiml-mistralnemo-12b-_31569_v1
model_name: chaiml-mistralnemo-12b-_31569_v1
model_group: ChaiML/mistralnemo-12b-s
status: torndown
timestamp: 2025-07-01T16:25:50+00:00
num_battles: 8183
num_wins: 4270
celo_rating: 1302.64
family_friendly_score: 0.5226
family_friendly_standard_error: 0.007063840881560116
submission_type: basic
model_repo: ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.480539837317445, 'latency_mean': 2.080859249830246, 'latency_p50': 2.088952898979187, 'latency_p90': 2.2374664068222043}, {'batch_size': 2, 'throughput': 0.6569553457423836, 'latency_mean': 3.039328622817993, 'latency_p50': 3.0484466552734375, 'latency_p90': 3.288446068763733}, {'batch_size': 3, 'throughput': 0.767206862210784, 'latency_mean': 3.9003263998031614, 'latency_p50': 3.8743890523910522, 'latency_p90': 4.352445268630982}, {'batch_size': 4, 'throughput': 0.8311413593593381, 'latency_mean': 4.800330877304077, 'latency_p50': 4.781623959541321, 'latency_p90': 5.293064618110657}, {'batch_size': 5, 'throughput': 0.8662602370742356, 'latency_mean': 5.756754709482193, 'latency_p50': 5.752906441688538, 'latency_p90': 6.415170097351074}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistralnemo-12b-_31569_v1
is_internal_developer: False
language_model: ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2
model_size: 13B
ranking_group: single
throughput_3p7s: 0.75
us_pacific_date: 2025-07-01
win_ratio: 0.5218135158254918
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>{bot_name}memory: {memory}\n', 'prompt_template': '<|system|>Family Friendly{prompt}\n', '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': 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-mistralnemo-12b-31569-v1-mkmlizer
Waiting for job on chaiml-mistralnemo-12b-31569-v1-mkmlizer to finish
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ belonging to: ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ║ ║
chaiml-mistralnemo-12b-31569-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistralnemo-12b-31569-v1-mkmlizer: Downloaded to shared memory in 79.420s
chaiml-mistralnemo-12b-31569-v1-mkmlizer: Checking if ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2 already exists in ChaiML
chaiml-mistralnemo-12b-31569-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzaquydf7, device:0
chaiml-mistralnemo-12b-31569-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistralnemo-12b-31569-v1-mkmlizer: quantized model in 39.498s
chaiml-mistralnemo-12b-31569-v1-mkmlizer: Processed model ChaiML/mistralnemo-12b-sfts1-exp1-deepseek-s3000-fullft-2048-lastmsgv2 in 118.919s
chaiml-mistralnemo-12b-31569-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistralnemo-12b-31569-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistralnemo-12b-31569-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v1
chaiml-mistralnemo-12b-31569-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v1/config.json
chaiml-mistralnemo-12b-31569-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v1/special_tokens_map.json
chaiml-mistralnemo-12b-31569-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v1/tokenizer_config.json
chaiml-mistralnemo-12b-31569-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v1/tokenizer.json
chaiml-mistralnemo-12b-31569-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistralnemo-12b-31569-v1/flywheel_model.0.safetensors
chaiml-mistralnemo-12b-31569-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.97it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 43.22it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 41.55it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 40.42it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 41.35it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 32.81it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 40.35it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:08, 39.41it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:08, 38.31it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 39.88it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 40.80it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:13, 21.62it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 28.37it/s] Loading 0: 21%|██ | 76/363 [00:02<00:09, 29.56it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:09, 30.66it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:09, 30.04it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:08, 32.03it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:08, 30.68it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 33.75it/s] Loading 0: 28%|██▊ | 102/363 [00:03<00:07, 33.06it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 33.66it/s] Loading 0: 31%|███ | 112/363 [00:03<00:06, 37.46it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:06, 35.56it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 34.19it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 36.74it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 34.90it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 36.59it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 34.79it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:09, 23.58it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 23.41it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.25it/s] Loading 0: 42%|████▏ | 154/363 [00:04<00:07, 29.54it/s] Loading 0: 44%|████▎ | 158/363 [00:04<00:07, 27.66it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:05, 35.25it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:05, 34.33it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 35.49it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 33.42it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:05, 35.96it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:05, 31.87it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:05, 34.17it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 33.76it/s] Loading 0: 55%|█████▌ | 201/363 [00:06<00:04, 36.36it/s] Loading 0: 56%|█████▋ | 205/363 [00:06<00:04, 34.66it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 36.66it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 34.99it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 34.55it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 24.98it/s] Loading 0: 62%|██████▏ | 226/363 [00:07<00:05, 24.47it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:05, 24.57it/s] Loading 0: 65%|██████▍ | 235/363 [00:07<00:04, 29.68it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 28.51it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 36.01it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.22it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 36.45it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 35.45it/s] Loading 0: 73%|███████▎ | 264/363 [00:08<00:02, 37.52it/s] Loading 0: 74%|███████▍ | 268/363 [00:08<00:02, 35.96it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 37.04it/s] Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 34.02it/s] Loading 0: 77%|███████▋ | 281/363 [00:08<00:02, 34.29it/s] Loading 0: 79%|███████▊ | 285/363 [00:08<00:02, 31.71it/s] Loading 0: 80%|███████▉ | 289/363 [00:08<00:02, 32.25it/s] Loading 0: 81%|████████ | 293/363 [00:08<00:02, 29.91it/s] Loading 0: 82%|████████▏ | 299/363 [00:09<00:01, 35.05it/s] Loading 0: 84%|████████▎ | 304/363 [00:09<00:03, 18.33it/s] Loading 0: 85%|████████▍ | 307/363 [00:09<00:02, 19.12it/s] Loading 0: 86%|████████▌ | 312/363 [00:09<00:02, 21.57it/s] Loading 0: 88%|████████▊ | 319/363 [00:10<00:01, 29.28it/s] Loading 0: 89%|████████▉ | 323/363 [00:10<00:01, 29.31it/s] Loading 0: 90%|█████████ | 328/363 [00:10<00:01, 32.61it/s] Loading 0: 91%|█████████▏| 332/363 [00:10<00:00, 32.27it/s] Loading 0: 93%|█████████▎| 337/363 [00:10<00:00, 34.94it/s] Loading 0: 94%|█████████▍| 341/363 [00:10<00:00, 33.48it/s] Loading 0: 95%|█████████▌| 346/363 [00:10<00:00, 36.67it/s] Loading 0: 96%|█████████▋| 350/363 [00:10<00:00, 33.63it/s] Loading 0: 98%|█████████▊| 355/363 [00:11<00:00, 36.70it/s] Loading 0: 99%|█████████▉| 359/363 [00:11<00:00, 35.06it/s]
Job chaiml-mistralnemo-12b-31569-v1-mkmlizer completed after 147.53s with status: succeeded
Stopping job with name chaiml-mistralnemo-12b-31569-v1-mkmlizer
Pipeline stage MKMLizer completed in 148.19s
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 chaiml-mistralnemo-12b-31569-v1
Waiting for inference service chaiml-mistralnemo-12b-31569-v1 to be ready
Inference service chaiml-mistralnemo-12b-31569-v1 ready after 211.03746676445007s
Pipeline stage MKMLDeployer completed in 211.52s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.516935110092163s
Received healthy response to inference request in 1.7178592681884766s
Received healthy response to inference request in 1.7329061031341553s
Received healthy response to inference request in 2.2036244869232178s
5 requests
1 failed requests
5th percentile: 1.7208686351776123
10th percentile: 1.7238780021667481
20th percentile: 1.7298967361450195
30th percentile: 1.8270497798919678
40th percentile: 2.0153371334075927
50th percentile: 2.2036244869232178
60th percentile: 2.328948736190796
70th percentile: 2.454272985458374
80th percentile: 6.041082143783573
90th percentile: 13.089376211166384
95th percentile: 16.613523244857785
99th percentile: 19.432840871810914
mean time: 5.661799049377441
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9422285556793213s
Failed to get response for submission auriaetherwiing-mn-12b-_82974_v3: HTTPConnectionPool(host='auriaetherwiing-mn-12b-82974-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 1.75700044631958s
Received healthy response to inference request in 1.5832581520080566s
Received healthy response to inference request in 2.504117012023926s
Received healthy response to inference request in 2.221721887588501s
5 requests
0 failed requests
5th percentile: 1.6180066108703612
10th percentile: 1.652755069732666
20th percentile: 1.7222519874572755
30th percentile: 1.7940460681915282
40th percentile: 1.8681373119354248
50th percentile: 1.9422285556793213
60th percentile: 2.054025888442993
70th percentile: 2.165823221206665
80th percentile: 2.278200912475586
90th percentile: 2.3911589622497558
95th percentile: 2.4476379871368406
99th percentile: 2.4928212070465086
mean time: 2.001665210723877
Pipeline stage StressChecker completed in 40.81s
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 0.67s
Shutdown handler de-registered
chaiml-mistralnemo-12b-_31569_v1 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 6170.25s
Shutdown handler de-registered
chaiml-mistralnemo-12b-_31569_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistralnemo-12b-_31569_v1 status is now torndown due to DeploymentManager action