developer_uid: rirv938
submission_id: rirv938-v9-pref-plus-03-_7925_v2
model_name: rirv938-v9-pref-plus-03-_7925_v2
model_group: rirv938/v9_pref_plus_03_
status: torndown
timestamp: 2024-12-23T07:24:32+00:00
num_battles: 19062
num_wins: 10587
celo_rating: 1306.06
family_friendly_score: 0.5636
family_friendly_standard_error: 0.007013630158484265
submission_type: basic
model_repo: rirv938/v9_pref_plus_03_mistral_1116_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6287366637009306, 'latency_mean': 1.5904300570487977, 'latency_p50': 1.6001534461975098, 'latency_p90': 1.7447637557983398}, {'batch_size': 3, 'throughput': 1.2678611752674966, 'latency_mean': 2.3586047649383546, 'latency_p50': 2.3679041862487793, 'latency_p90': 2.6395697116851804}, {'batch_size': 5, 'throughput': 1.6015149768159327, 'latency_mean': 3.1073701584339144, 'latency_p50': 3.1058870553970337, 'latency_p90': 3.5113845825195313}, {'batch_size': 6, 'throughput': 1.7078102727407825, 'latency_mean': 3.48857293844223, 'latency_p50': 3.4737132787704468, 'latency_p90': 3.9135667085647583}, {'batch_size': 8, 'throughput': 1.872749893795898, 'latency_mean': 4.241909147500992, 'latency_p50': 4.231687784194946, 'latency_p90': 4.8991882562637326}, {'batch_size': 10, 'throughput': 1.9637147270893507, 'latency_mean': 5.062243051528931, 'latency_p50': 5.045437216758728, 'latency_p90': 5.640105962753296}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-v9-pref-plus-03-_7925_v2
is_internal_developer: True
language_model: rirv938/v9_pref_plus_03_mistral_1116_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.77
us_pacific_date: 2024-12-22
win_ratio: 0.5553981743783444
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:', '<|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 rirv938-v9-pref-plus-03-7925-v2-mkmlizer
Waiting for job on rirv938-v9-pref-plus-03-7925-v2-mkmlizer to finish
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║       /___/                                                         ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║                                                                     ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║                                                                     ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║                                                                     ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ║                                                                     ║
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: Downloaded to shared memory in 93.578s
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppfy476zk, device:0
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: quantized model in 42.383s
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: Processed model rirv938/v9_pref_plus_03_mistral_1116_v2 in 135.961s
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-v9-pref-plus-03-7925-v2
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-v9-pref-plus-03-7925-v2/config.json
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-v9-pref-plus-03-7925-v2/special_tokens_map.json
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-v9-pref-plus-03-7925-v2/tokenizer_config.json
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-v9-pref-plus-03-7925-v2/tokenizer.json
rirv938-v9-pref-plus-03-7925-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.17it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.99it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.72it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.72it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.06it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.69it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 25.55it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.19it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 25.71it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.17it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 26.33it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 26.76it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.44it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.44it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 26.03it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:11, 25.38it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:12, 23.46it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.62it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.94it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.11it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.40it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.33it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.87it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.59it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 22.85it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.38it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:09, 24.62it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 29.44it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:08, 25.91it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 30.18it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.63it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.67it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.21it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.55it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.02it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.18it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 31.13it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.23it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:08, 22.43it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 19.93it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 26.51it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 24.63it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 27.62it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 25.30it/s]
Loading 0:  58%|█████▊    | 210/363 [00:08<00:04, 31.47it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 28.98it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 29.05it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.35it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 20.84it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.17it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 25.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.96it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.92it/s]
Loading 0:  68%|██████▊   | 248/363 [00:09<00:04, 25.35it/s]
Loading 0:  70%|██████▉   | 254/363 [00:09<00:03, 32.26it/s]
Loading 0:  71%|███████   | 258/363 [00:10<00:03, 28.28it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:03, 25.43it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.84it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 26.66it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 24.40it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.30it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 28.97it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 30.76it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 29.15it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.60it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.94it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.09it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 22.76it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 27.83it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 24.94it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 31.53it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 30.00it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.77it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.44it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.01it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.70it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.89it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.03it/s]
                                                            

Job rirv938-v9-pref-plus-03-7925-v2-mkmlizer completed after 165.38s with status: succeeded
Stopping job with name rirv938-v9-pref-plus-03-7925-v2-mkmlizer
Pipeline stage MKMLizer completed in 165.88s
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 rirv938-v9-pref-plus-03-7925-v2
Waiting for inference service rirv938-v9-pref-plus-03-7925-v2 to be ready
Inference service rirv938-v9-pref-plus-03-7925-v2 ready after 271.3068163394928s
Pipeline stage MKMLDeployer completed in 271.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9864928722381592s
Received healthy response to inference request in 1.477113962173462s
Received healthy response to inference request in 1.436643362045288s
Received healthy response to inference request in 1.5642611980438232s
Received healthy response to inference request in 1.20281982421875s
5 requests
0 failed requests
5th percentile: 1.2495845317840577
10th percentile: 1.2963492393493652
20th percentile: 1.3898786544799804
30th percentile: 1.444737482070923
40th percentile: 1.4609257221221923
50th percentile: 1.477113962173462
60th percentile: 1.5119728565216064
70th percentile: 1.5468317508697509
80th percentile: 1.6487075328826906
90th percentile: 1.8176002025604248
95th percentile: 1.9020465373992919
99th percentile: 1.9696036052703858
mean time: 1.5334662437438964
Pipeline stage StressChecker completed in 8.93s
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 0.65s
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 0.62s
Shutdown handler de-registered
rirv938-v9-pref-plus-03-_7925_v2 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-v9-pref-plus-03-7925-v2-profiler
Waiting for inference service rirv938-v9-pref-plus-03-7925-v2-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 2538.96s
Shutdown handler de-registered
rirv938-v9-pref-plus-03-_7925_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-v9-pref-plus-03-_7925_v2 status is now torndown due to DeploymentManager action
rirv938-v9-pref-plus-03-_7925_v2 status is now torndown due to DeploymentManager action
rirv938-v9-pref-plus-03-_7925_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1