developer_uid: azuruce
submission_id: arliai-mistral-small-22_86032_v2
model_name: arliai-mistral-small-22_86032_v2
model_group: ArliAI/Mistral-Small-22B
status: torndown
timestamp: 2025-01-08T23:26:16+00:00
num_battles: 6714
num_wins: 3027
celo_rating: 1215.73
family_friendly_score: 0.5822
family_friendly_standard_error: 0.006974857131153297
submission_type: basic
model_repo: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3916558963226547, 'latency_mean': 2.5531988096237184, 'latency_p50': 2.5351641178131104, 'latency_p90': 2.8422737598419188}, {'batch_size': 3, 'throughput': 0.8237824087107548, 'latency_mean': 3.630342447757721, 'latency_p50': 3.617307186126709, 'latency_p90': 3.989481496810913}, {'batch_size': 5, 'throughput': 1.0872694488652932, 'latency_mean': 4.571543873548507, 'latency_p50': 4.582041621208191, 'latency_p90': 5.17192575931549}, {'batch_size': 6, 'throughput': 1.164624529365196, 'latency_mean': 5.125207748413086, 'latency_p50': 5.163902401924133, 'latency_p90': 5.7539630889892575}, {'batch_size': 10, 'throughput': 1.3886844971162484, 'latency_mean': 7.137927803993225, 'latency_p50': 7.111975312232971, 'latency_p90': 8.06022026538849}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: arliai-mistral-small-22_86032_v2
is_internal_developer: True
language_model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2025-01-08
win_ratio: 0.45084897229669346
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 arliai-mistral-small-22-86032-v2-mkmlizer
Waiting for job on arliai-mistral-small-22-86032-v2-mkmlizer to finish
arliai-mistral-small-22-86032-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arliai-mistral-small-22-86032-v2-mkmlizer: ║     _____            __           __                                ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║       /___/                                                         ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║                                                                     ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  https://mk1.ai                                                     ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║                                                                     ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  belonging to:                                                      ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║                                                                     ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  Chai Research Corp.                                                ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
arliai-mistral-small-22-86032-v2-mkmlizer: ║                                                                     ║
arliai-mistral-small-22-86032-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
arliai-mistral-small-22-86032-v2-mkmlizer: Downloaded to shared memory in 78.388s
arliai-mistral-small-22-86032-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt8_6m4mi, device:0
arliai-mistral-small-22-86032-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
arliai-mistral-small-22-86032-v2-mkmlizer: quantized model in 43.802s
arliai-mistral-small-22-86032-v2-mkmlizer: Processed model ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 in 122.190s
arliai-mistral-small-22-86032-v2-mkmlizer: creating bucket guanaco-mkml-models
arliai-mistral-small-22-86032-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arliai-mistral-small-22-86032-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2
arliai-mistral-small-22-86032-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2/config.json
arliai-mistral-small-22-86032-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2/special_tokens_map.json
arliai-mistral-small-22-86032-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2/tokenizer.model
arliai-mistral-small-22-86032-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2/tokenizer.json
arliai-mistral-small-22-86032-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2/tokenizer_config.json
arliai-mistral-small-22-86032-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/arliai-mistral-small-22-86032-v2/flywheel_model.1.safetensors
arliai-mistral-small-22-86032-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:18, 26.63it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.53it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.47it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 36.53it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 35.11it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:13, 36.26it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 34.47it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 36.39it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 34.46it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 33.31it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 33.41it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 23.43it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:17, 25.98it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 28.42it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 29.58it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 34.05it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:11, 38.11it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 37.73it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 37.41it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:11, 36.09it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 36.84it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 34.84it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 36.55it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 35.57it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.64it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 24.18it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 27.42it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 33.87it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 33.63it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 35.45it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.40it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 36.21it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 35.34it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 36.41it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:10, 34.70it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:10, 34.24it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 28.11it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.98it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 27.69it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:10, 32.40it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 32.02it/s]
Loading 0:  38%|███▊      | 191/507 [00:05<00:09, 33.65it/s]
Loading 0:  38%|███▊      | 195/507 [00:05<00:10, 31.10it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 35.46it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 34.43it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 36.25it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 35.24it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 34.10it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 33.50it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:11, 24.68it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 25.24it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 32.51it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 32.27it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.19it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 33.15it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 34.73it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 33.70it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 35.44it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 34.59it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 35.75it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 34.74it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 37.99it/s]
Loading 0:  56%|█████▋    | 286/507 [00:08<00:08, 26.26it/s]
Loading 0:  57%|█████▋    | 290/507 [00:08<00:07, 28.56it/s]
Loading 0:  58%|█████▊    | 294/507 [00:09<00:07, 28.33it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.33it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<03:14,  1.06it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:45,  1.24it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:46,  1.88it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:23,  2.37it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:57,  3.33it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:41,  4.61it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:29,  6.23it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:20,  8.80it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.12it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 13.74it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.52it/s]
Loading 0:  68%|██████▊   | 343/507 [00:25<00:09, 17.01it/s]
Loading 0:  68%|██████▊   | 347/507 [00:25<00:08, 19.00it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 26.29it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.82it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 31.09it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.39it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 33.75it/s]
Loading 0:  74%|███████▍  | 376/507 [00:26<00:03, 33.52it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 35.48it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 34.60it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 33.70it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 33.73it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 24.96it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 24.85it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:03, 32.01it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 32.12it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 34.18it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 33.78it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 35.79it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 34.90it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 36.25it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 35.07it/s]
Loading 0:  88%|████████▊ | 444/507 [00:28<00:01, 36.83it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 35.02it/s]
Loading 0:  89%|████████▉ | 453/507 [00:28<00:01, 37.66it/s]
Loading 0:  90%|█████████ | 457/507 [00:30<00:08,  5.84it/s]
Loading 0:  91%|█████████ | 460/507 [00:30<00:06,  7.05it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.64it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.60it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:01, 16.89it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 20.70it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 22.70it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.59it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 27.77it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.11it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 31.31it/s]
                                                            

Job arliai-mistral-small-22-86032-v2-mkmlizer completed after 156.11s with status: succeeded
Stopping job with name arliai-mistral-small-22-86032-v2-mkmlizer
Pipeline stage MKMLizer completed in 156.64s
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 arliai-mistral-small-22-86032-v2
Waiting for inference service arliai-mistral-small-22-86032-v2 to be ready
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service arliai-mistral-small-22-86032-v2 ready after 351.32924342155457s
Pipeline stage MKMLDeployer completed in 351.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.216170310974121s
Received healthy response to inference request in 2.198767900466919s
Received healthy response to inference request in 0.7617921829223633s
Received healthy response to inference request in 1.3980958461761475s
Received healthy response to inference request in 2.2001190185546875s
5 requests
0 failed requests
5th percentile: 0.8890529155731202
10th percentile: 1.016313648223877
20th percentile: 1.2708351135253906
30th percentile: 1.5582302570343018
40th percentile: 1.8784990787506104
50th percentile: 2.198767900466919
60th percentile: 2.1993083477020265
70th percentile: 2.1998487949371337
80th percentile: 2.2033292770385744
90th percentile: 2.2097497940063477
95th percentile: 2.212960052490234
99th percentile: 2.2155282592773435
mean time: 1.7549890518188476
Pipeline stage StressChecker completed in 10.16s
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 0.69s
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 0.66s
Shutdown handler de-registered
arliai-mistral-small-22_86032_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3248.60s
Shutdown handler de-registered
arliai-mistral-small-22_86032_v2 status is now inactive due to auto deactivation removed underperforming models
arliai-mistral-small-22_86032_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1