developer_uid: Luna1040
submission_id: intervitens-mini-magnu_51806_v12
model_name: intervitens-mini-magnu_51806_v12
model_group: intervitens/mini-magnum-
status: torndown
timestamp: 2025-02-19T08:36:51+00:00
num_battles: 6416
num_wins: 3185
celo_rating: 1263.34
family_friendly_score: 0.5538000000000001
family_friendly_standard_error: 0.0070300150782199615
submission_type: basic
model_repo: intervitens/mini-magnum-12b-v1.1
model_architecture: MistralForCausalLM
model_num_parameters: 12772080640.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6019332428943718, 'latency_mean': 1.6612212884426116, 'latency_p50': 1.645220398902893, 'latency_p90': 1.8314620018005372}, {'batch_size': 3, 'throughput': 1.098952787002187, 'latency_mean': 2.722913019657135, 'latency_p50': 2.716117739677429, 'latency_p90': 2.9822569370269774}, {'batch_size': 5, 'throughput': 1.311367817750981, 'latency_mean': 3.791139713525772, 'latency_p50': 3.810921549797058, 'latency_p90': 4.231621217727661}, {'batch_size': 6, 'throughput': 1.3818520749042773, 'latency_mean': 4.31988832950592, 'latency_p50': 4.309705972671509, 'latency_p90': 4.846434259414673}, {'batch_size': 8, 'throughput': 1.4303572359231305, 'latency_mean': 5.547911155223846, 'latency_p50': 5.5547034740448, 'latency_p90': 6.213668537139893}, {'batch_size': 10, 'throughput': 1.480318169951693, 'latency_mean': 6.7009878563880925, 'latency_p50': 6.62718939781189, 'latency_p90': 7.560794043540954}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: intervitens-mini-magnu_51806_v12
is_internal_developer: False
language_model: intervitens/mini-magnum-12b-v1.1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-02-19
win_ratio: 0.4964152119700748
generation_params: {'temperature': 0.6, 'top_p': 0.75, 'min_p': 0.15, 'top_k': 80, 'presence_penalty': 0.15, 'frequency_penalty': 0.15, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 intervitens-mini-magnu-51806-v12-mkmlizer
Waiting for job on intervitens-mini-magnu-51806-v12-mkmlizer to finish
intervitens-mini-magnu-51806-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
intervitens-mini-magnu-51806-v12-mkmlizer: ║     _____            __           __                                ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║       /___/                                                         ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║                                                                     ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  Version: 0.12.8                                                    ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  https://mk1.ai                                                     ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║                                                                     ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  belonging to:                                                      ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║                                                                     ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  Chai Research Corp.                                                ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
intervitens-mini-magnu-51806-v12-mkmlizer: ║                                                                     ║
intervitens-mini-magnu-51806-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
intervitens-mini-magnu-51806-v12-mkmlizer: Downloaded to shared memory in 32.737s
intervitens-mini-magnu-51806-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw2pfmdhl, device:0
intervitens-mini-magnu-51806-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
intervitens-mini-magnu-51806-v12-mkmlizer: quantized model in 38.944s
intervitens-mini-magnu-51806-v12-mkmlizer: Processed model intervitens/mini-magnum-12b-v1.1 in 71.682s
intervitens-mini-magnu-51806-v12-mkmlizer: creating bucket guanaco-mkml-models
intervitens-mini-magnu-51806-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
intervitens-mini-magnu-51806-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/intervitens-mini-magnu-51806-v12
intervitens-mini-magnu-51806-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/intervitens-mini-magnu-51806-v12/config.json
intervitens-mini-magnu-51806-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/intervitens-mini-magnu-51806-v12/special_tokens_map.json
intervitens-mini-magnu-51806-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/intervitens-mini-magnu-51806-v12/tokenizer_config.json
intervitens-mini-magnu-51806-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/intervitens-mini-magnu-51806-v12/tokenizer.json
intervitens-mini-magnu-51806-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/intervitens-mini-magnu-51806-v12/flywheel_model.0.safetensors
intervitens-mini-magnu-51806-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.71it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 43.28it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 41.00it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 39.46it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 40.73it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 31.94it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 38.87it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 38.21it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 37.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:08, 36.86it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.81it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:12, 23.56it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.29it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.33it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 26.65it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:09, 31.10it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:09, 29.73it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:08, 33.73it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 30.91it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:07, 34.76it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 32.09it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 36.14it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:06, 38.07it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:06, 35.93it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 32.21it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:06, 36.34it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 33.26it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 39.82it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:05, 38.33it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:08, 26.04it/s]
Loading 0:  40%|████      | 147/363 [00:04<00:08, 26.96it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:07, 28.07it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 31.36it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.04it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 33.57it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.72it/s]
Loading 0:  48%|████▊     | 173/363 [00:05<00:05, 33.62it/s]
Loading 0:  49%|████▉     | 177/363 [00:05<00:06, 30.77it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 32.33it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 30.03it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:05, 34.19it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 31.37it/s]
Loading 0:  55%|█████▍    | 199/363 [00:06<00:04, 35.26it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:05, 31.94it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 35.74it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 32.41it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 36.26it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 36.83it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:05, 24.86it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 25.10it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 32.39it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:03, 31.94it/s]
Loading 0:  67%|██████▋   | 245/363 [00:07<00:03, 33.72it/s]
Loading 0:  69%|██████▊   | 249/363 [00:07<00:03, 31.41it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 36.50it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.24it/s]
Loading 0:  73%|███████▎  | 264/363 [00:08<00:02, 37.22it/s]
Loading 0:  74%|███████▍  | 268/363 [00:08<00:02, 35.52it/s]
Loading 0:  75%|███████▌  | 273/363 [00:08<00:02, 37.82it/s]
Loading 0:  76%|███████▋  | 277/363 [00:08<00:02, 36.31it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:02, 39.14it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 37.16it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 38.73it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 35.78it/s]
Loading 0:  82%|████████▏ | 299/363 [00:09<00:01, 34.12it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 34.56it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:29,  1.90it/s]
Loading 0:  86%|████████▌ | 311/363 [00:16<00:19,  2.63it/s]
Loading 0:  87%|████████▋ | 314/363 [00:16<00:14,  3.36it/s]
Loading 0:  87%|████████▋ | 317/363 [00:16<00:10,  4.33it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:07,  5.96it/s]
Loading 0:  90%|████████▉ | 326/363 [00:16<00:04,  8.77it/s]
Loading 0:  91%|█████████ | 330/363 [00:16<00:03, 10.88it/s]
Loading 0:  92%|█████████▏| 335/363 [00:16<00:01, 14.77it/s]
Loading 0:  93%|█████████▎| 339/363 [00:17<00:01, 16.59it/s]
Loading 0:  95%|█████████▍| 344/363 [00:17<00:00, 21.07it/s]
Loading 0:  96%|█████████▌| 348/363 [00:17<00:00, 22.02it/s]
Loading 0:  97%|█████████▋| 353/363 [00:17<00:00, 26.34it/s]
Loading 0:  98%|█████████▊| 357/363 [00:17<00:00, 25.88it/s]
Loading 0: 100%|█████████▉| 362/363 [00:17<00:00, 30.12it/s]
                                                            

Job intervitens-mini-magnu-51806-v12-mkmlizer completed after 94.16s with status: succeeded
Stopping job with name intervitens-mini-magnu-51806-v12-mkmlizer
Pipeline stage MKMLizer completed in 94.73s
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 intervitens-mini-magnu-51806-v12
Waiting for inference service intervitens-mini-magnu-51806-v12 to be ready
Failed to get response for submission chaiml-20250218-c-4epoc_55567_v2: HTTPConnectionPool(host='chaiml-20250218-c-4epoc-55567-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service intervitens-mini-magnu-51806-v12 ready after 160.57044386863708s
Pipeline stage MKMLDeployer completed in 161.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5726358890533447s
Received healthy response to inference request in 1.6032209396362305s
Received healthy response to inference request in 1.6591503620147705s
Received healthy response to inference request in 1.539189338684082s
Received healthy response to inference request in 1.4755747318267822s
5 requests
0 failed requests
5th percentile: 1.4882976531982421
10th percentile: 1.501020574569702
20th percentile: 1.5264664173126221
30th percentile: 1.5519956588745116
40th percentile: 1.577608299255371
50th percentile: 1.6032209396362305
60th percentile: 1.6255927085876465
70th percentile: 1.6479644775390625
80th percentile: 1.8418474674224856
90th percentile: 2.207241678237915
95th percentile: 2.3899387836456296
99th percentile: 2.536096467971802
mean time: 1.769954252243042
Pipeline stage StressChecker completed in 10.33s
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 0.82s
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
intervitens-mini-magnu_51806_v12 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 0.10s
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 intervitens-mini-magnu-51806-v12-profiler
Waiting for inference service intervitens-mini-magnu-51806-v12-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 2624.06s
Shutdown handler de-registered
intervitens-mini-magnu_51806_v12 status is now inactive due to auto deactivation removed underperforming models
intervitens-mini-magnu_51806_v12 status is now torndown due to DeploymentManager action
intervitens-mini-magnu_51806_v12 status is now torndown due to DeploymentManager action
intervitens-mini-magnu_51806_v12 status is now torndown due to DeploymentManager action