developer_uid: azuruce
submission_id: nbeerbower-mistral-smal_64966_v1
model_name: nbeerbower-mistral-smal_64966_v1
model_group: nbeerbower/Mistral-Small
status: torndown
timestamp: 2025-01-08T23:37:34+00:00
num_battles: 7195
num_wins: 3333
celo_rating: 1221.49
family_friendly_score: 0.5876
family_friendly_standard_error: 0.006961698643291018
submission_type: basic
model_repo: nbeerbower/Mistral-Small-Drummer-22B
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38807256522959577, 'latency_mean': 2.5767613780498504, 'latency_p50': 2.5594199895858765, 'latency_p90': 2.841435503959656}, {'batch_size': 3, 'throughput': 0.8265449903529938, 'latency_mean': 3.6202464580535887, 'latency_p50': 3.5842102766036987, 'latency_p90': 4.002269601821899}, {'batch_size': 5, 'throughput': 1.095977230295826, 'latency_mean': 4.5353514146804805, 'latency_p50': 4.472166538238525, 'latency_p90': 5.1216593265533445}, {'batch_size': 6, 'throughput': 1.1758966673133069, 'latency_mean': 5.076725276708603, 'latency_p50': 5.067978501319885, 'latency_p90': 5.778072381019593}, {'batch_size': 10, 'throughput': 1.3926201845379524, 'latency_mean': 7.102235703468323, 'latency_p50': 7.043395042419434, 'latency_p90': 7.963785886764526}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: nbeerbower-mistral-smal_64966_v1
is_internal_developer: True
language_model: nbeerbower/Mistral-Small-Drummer-22B
model_size: 22B
ranking_group: single
throughput_3p7s: 0.86
us_pacific_date: 2025-01-08
win_ratio: 0.4632383599722029
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', 'Me', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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 nbeerbower-mistral-smal-64966-v1-mkmlizer
Waiting for job on nbeerbower-mistral-smal-64966-v1-mkmlizer to finish
nbeerbower-mistral-smal-64966-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║     _____            __           __                                ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║       /___/                                                         ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║                                                                     ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  https://mk1.ai                                                     ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║                                                                     ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  belonging to:                                                      ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║                                                                     ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  Chai Research Corp.                                                ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ║                                                                     ║
nbeerbower-mistral-smal-64966-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nbeerbower-mistral-smal-64966-v1-mkmlizer: Downloaded to shared memory in 84.814s
nbeerbower-mistral-smal-64966-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpue5d9wt7, device:0
nbeerbower-mistral-smal-64966-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nbeerbower-mistral-smal-64966-v1-mkmlizer: quantized model in 46.763s
nbeerbower-mistral-smal-64966-v1-mkmlizer: Processed model nbeerbower/Mistral-Small-Drummer-22B in 131.577s
nbeerbower-mistral-smal-64966-v1-mkmlizer: creating bucket guanaco-mkml-models
nbeerbower-mistral-smal-64966-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nbeerbower-mistral-smal-64966-v1/config.json
nbeerbower-mistral-smal-64966-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nbeerbower-mistral-smal-64966-v1/special_tokens_map.json
nbeerbower-mistral-smal-64966-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nbeerbower-mistral-smal-64966-v1/tokenizer_config.json
nbeerbower-mistral-smal-64966-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nbeerbower-mistral-smal-64966-v1/tokenizer.model
nbeerbower-mistral-smal-64966-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nbeerbower-mistral-smal-64966-v1/tokenizer.json
nbeerbower-mistral-smal-64966-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/nbeerbower-mistral-smal-64966-v1/flywheel_model.1.safetensors
nbeerbower-mistral-smal-64966-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.06it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:14, 33.62it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:16, 29.95it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:12, 37.77it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 35.45it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 38.00it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:12, 36.93it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 37.65it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 35.21it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 34.95it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 35.37it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:18, 24.92it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:17, 25.56it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 28.69it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 28.65it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:14, 30.36it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 30.26it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 29.80it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:13, 32.45it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:14, 28.81it/s]
Loading 0:  19%|█▊        | 94/507 [00:02<00:12, 32.57it/s]
Loading 0:  19%|█▉        | 98/507 [00:03<00:14, 28.52it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:12, 32.41it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:13, 28.91it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 32.49it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:18, 20.59it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:16, 23.40it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 27.51it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:14, 26.21it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:12, 30.04it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:13, 27.51it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:11, 31.40it/s]
Loading 0:  29%|██▉       | 149/507 [00:04<00:12, 28.50it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 32.24it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:12, 28.63it/s]
Loading 0:  32%|███▏      | 163/507 [00:05<00:10, 32.50it/s]
Loading 0:  33%|███▎      | 168/507 [00:05<00:10, 31.99it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:15, 21.57it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:15, 21.71it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:12, 25.40it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:13, 24.68it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:11, 28.73it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:11, 26.19it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:10, 28.60it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:11, 26.25it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:10, 28.38it/s]
Loading 0:  42%|████▏     | 212/507 [00:07<00:11, 25.53it/s]
Loading 0:  43%|████▎     | 217/507 [00:07<00:10, 28.77it/s]
Loading 0:  44%|████▎     | 221/507 [00:07<00:10, 26.89it/s]
Loading 0:  44%|████▍     | 224/507 [00:07<00:14, 18.94it/s]
Loading 0:  45%|████▌     | 229/507 [00:08<00:11, 24.13it/s]
Loading 0:  46%|████▌     | 233/507 [00:08<00:10, 25.12it/s]
Loading 0:  47%|████▋     | 236/507 [00:08<00:10, 25.83it/s]
Loading 0:  47%|████▋     | 239/507 [00:08<00:12, 22.33it/s]
Loading 0:  48%|████▊     | 244/507 [00:08<00:09, 26.99it/s]
Loading 0:  49%|████▉     | 248/507 [00:08<00:10, 24.91it/s]
Loading 0:  50%|████▉     | 253/507 [00:08<00:08, 29.09it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:09, 27.38it/s]
Loading 0:  52%|█████▏    | 262/507 [00:09<00:07, 31.90it/s]
Loading 0:  52%|█████▏    | 266/507 [00:09<00:08, 29.30it/s]
Loading 0:  54%|█████▍    | 273/507 [00:09<00:06, 35.93it/s]
Loading 0:  55%|█████▍    | 277/507 [00:09<00:06, 34.21it/s]
Loading 0:  55%|█████▌    | 281/507 [00:09<00:06, 35.19it/s]
Loading 0:  56%|█████▌    | 285/507 [00:10<00:08, 24.80it/s]
Loading 0:  57%|█████▋    | 288/507 [00:10<00:08, 24.46it/s]
Loading 0:  58%|█████▊    | 293/507 [00:10<00:08, 26.10it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<03:02,  1.14it/s]
Loading 0:  60%|█████▉    | 302/507 [00:25<02:36,  1.31it/s]
Loading 0:  61%|██████    | 307/507 [00:25<01:43,  1.93it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:21,  2.42it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:02,  3.10it/s]
Loading 0:  62%|██████▏   | 316/507 [00:25<00:47,  4.01it/s]
Loading 0:  63%|██████▎   | 320/507 [00:25<00:34,  5.46it/s]
Loading 0:  64%|██████▍   | 325/507 [00:25<00:22,  8.04it/s]
Loading 0:  65%|██████▍   | 329/507 [00:26<00:18,  9.86it/s]
Loading 0:  66%|██████▌   | 334/507 [00:26<00:12, 13.40it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:10, 16.19it/s]
Loading 0:  67%|██████▋   | 342/507 [00:26<00:12, 13.25it/s]
Loading 0:  68%|██████▊   | 347/507 [00:27<00:10, 15.82it/s]
Loading 0:  69%|██████▉   | 352/507 [00:27<00:07, 19.56it/s]
Loading 0:  70%|███████   | 356/507 [00:27<00:07, 20.13it/s]
Loading 0:  71%|███████   | 361/507 [00:27<00:06, 24.17it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 23.79it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 27.89it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:05, 25.78it/s]
Loading 0:  75%|███████▍  | 379/507 [00:28<00:04, 29.36it/s]
Loading 0:  76%|███████▌  | 383/507 [00:28<00:04, 27.33it/s]
Loading 0:  77%|███████▋  | 388/507 [00:28<00:03, 31.25it/s]
Loading 0:  77%|███████▋  | 392/507 [00:28<00:04, 28.74it/s]
Loading 0:  78%|███████▊  | 396/507 [00:28<00:05, 21.02it/s]
Loading 0:  79%|███████▉  | 401/507 [00:29<00:04, 22.93it/s]
Loading 0:  80%|████████  | 406/507 [00:29<00:03, 27.31it/s]
Loading 0:  81%|████████  | 410/507 [00:29<00:03, 25.72it/s]
Loading 0:  82%|████████▏ | 415/507 [00:29<00:03, 29.72it/s]
Loading 0:  83%|████████▎ | 419/507 [00:29<00:03, 27.85it/s]
Loading 0:  84%|████████▍ | 426/507 [00:29<00:02, 34.38it/s]
Loading 0:  85%|████████▍ | 430/507 [00:29<00:02, 33.63it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:02, 35.01it/s]
Loading 0:  87%|████████▋ | 439/507 [00:30<00:01, 34.36it/s]
Loading 0:  88%|████████▊ | 444/507 [00:30<00:01, 36.50it/s]
Loading 0:  88%|████████▊ | 448/507 [00:30<00:01, 35.12it/s]
Loading 0:  89%|████████▉ | 453/507 [00:30<00:01, 37.62it/s]
Loading 0:  90%|█████████ | 457/507 [00:32<00:08,  5.71it/s]
Loading 0:  91%|█████████ | 460/507 [00:32<00:06,  6.81it/s]
Loading 0:  92%|█████████▏| 465/507 [00:33<00:04,  9.10it/s]
Loading 0:  93%|█████████▎| 470/507 [00:33<00:03, 12.33it/s]
Loading 0:  93%|█████████▎| 474/507 [00:33<00:02, 14.09it/s]
Loading 0:  94%|█████████▍| 479/507 [00:33<00:01, 18.01it/s]
Loading 0:  95%|█████████▌| 483/507 [00:33<00:01, 19.15it/s]
Loading 0:  96%|█████████▋| 488/507 [00:33<00:00, 23.37it/s]
Loading 0:  97%|█████████▋| 492/507 [00:34<00:00, 22.82it/s]
Loading 0:  98%|█████████▊| 497/507 [00:34<00:00, 26.76it/s]
Loading 0:  99%|█████████▉| 501/507 [00:34<00:00, 25.08it/s]
Loading 0: 100%|█████████▉| 506/507 [00:34<00:00, 28.59it/s]
                                                            

Job nbeerbower-mistral-smal-64966-v1-mkmlizer completed after 175.84s with status: succeeded
Stopping job with name nbeerbower-mistral-smal-64966-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nbeerbower-mistral-smal-64966-v1
Waiting for inference service nbeerbower-mistral-smal-64966-v1 to be ready
Failed to get response for submission nohobby-ms-schisandra-2_40194_v1: HTTPConnectionPool(host='nohobby-ms-schisandra-2-40194-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service nbeerbower-mistral-smal-64966-v1 ready after 362.34653782844543s
Pipeline stage MKMLDeployer completed in 362.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5241997241973877s
Received healthy response to inference request in 2.1998655796051025s
Received healthy response to inference request in 1.636784553527832s
Received healthy response to inference request in 0.6206560134887695s
Received healthy response to inference request in 1.7789037227630615s
5 requests
0 failed requests
5th percentile: 0.8013647556304931
10th percentile: 0.9820734977722168
20th percentile: 1.3434909820556642
30th percentile: 1.5467166900634766
40th percentile: 1.5917506217956543
50th percentile: 1.636784553527832
60th percentile: 1.693632221221924
70th percentile: 1.7504798889160156
80th percentile: 1.8630960941314698
90th percentile: 2.031480836868286
95th percentile: 2.1156732082366942
99th percentile: 2.183027105331421
mean time: 1.5520819187164308
Pipeline stage StressChecker completed in 9.43s
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 0.67s
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
nbeerbower-mistral-smal_64966_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3091.50s
Shutdown handler de-registered
nbeerbower-mistral-smal_64966_v1 status is now inactive due to auto deactivation removed underperforming models
nbeerbower-mistral-smal_64966_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1