developer_uid: rirv938
submission_id: rirv938-v6-pref-plus-03-_3022_v1
model_name: rirv938-v6-pref-plus-03-_3022_v1
model_group: rirv938/v6_pref_plus_03_
status: torndown
timestamp: 2024-12-23T04:14:33+00:00
num_battles: 27720
num_wins: 14144
celo_rating: 1269.99
family_friendly_score: 0.6066
family_friendly_standard_error: 0.006908493902436334
submission_type: basic
model_repo: rirv938/v6_pref_plus_03_mistral_558_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': 0.6279672732599214, 'latency_mean': 1.5923484480381012, 'latency_p50': 1.6063005924224854, 'latency_p90': 1.7570701360702514}, {'batch_size': 3, 'throughput': 1.2530957272741912, 'latency_mean': 2.3812280213832855, 'latency_p50': 2.3554797172546387, 'latency_p90': 2.647696328163147}, {'batch_size': 5, 'throughput': 1.5703203999234552, 'latency_mean': 3.1736333751678467, 'latency_p50': 3.178648591041565, 'latency_p90': 3.518893337249756}, {'batch_size': 6, 'throughput': 1.6808921087809352, 'latency_mean': 3.5533818805217745, 'latency_p50': 3.548143148422241, 'latency_p90': 3.9479721546173097}, {'batch_size': 8, 'throughput': 1.8507134288726883, 'latency_mean': 4.287132955789566, 'latency_p50': 4.265867471694946, 'latency_p90': 4.826953387260437}, {'batch_size': 10, 'throughput': 1.9112770744513503, 'latency_mean': 5.193312733173371, 'latency_p50': 5.220781564712524, 'latency_p90': 5.7434508323669435}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-v6-pref-plus-03-_3022_v1
is_internal_developer: True
language_model: rirv938/v6_pref_plus_03_mistral_558_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-22
win_ratio: 0.5102453102453103
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-v6-pref-plus-03-3022-v1-mkmlizer
Waiting for job on rirv938-v6-pref-plus-03-3022-v1-mkmlizer to finish
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
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║       /___/                                                         ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║                                                                     ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║                                                                     ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║                                                                     ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ║                                                                     ║
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: Downloaded to shared memory in 109.585s
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg3t1lnp2, device:0
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: quantized model in 42.262s
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: Processed model rirv938/v6_pref_plus_03_mistral_558_v2 in 151.847s
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-v6-pref-plus-03-3022-v1
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-v6-pref-plus-03-3022-v1/config.json
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-v6-pref-plus-03-3022-v1/special_tokens_map.json
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-v6-pref-plus-03-3022-v1/tokenizer_config.json
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
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-v6-pref-plus-03-3022-v1/flywheel_model.0.safetensors
rirv938-v6-pref-plus-03-3022-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.46it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.98it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.35it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.07it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.35it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.96it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.51it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.13it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.47it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.33it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.66it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.15it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.62it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.22it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.94it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.34it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:11, 25.33it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.76it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.01it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.82it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.35it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 22.75it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.10it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.01it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.28it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.77it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 28.14it/s]
Loading 0:  36%|███▌      | 131/363 [00:04<00:09, 24.64it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.38it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 31.61it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 22.04it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 21.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 28.34it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.10it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.92it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 29.72it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.23it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.44it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.82it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.83it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 29.12it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.07it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.76it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.21it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.59it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.13it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.19it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 25.45it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.38it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.20it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.88it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.37it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 31.22it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.04it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.38it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.84it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.87it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.03it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.22it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.46it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.26it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.21it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.56it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.65it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.11it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.63it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.70it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.81it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 29.41it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 28.45it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 31.07it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.78it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.87it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.02it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.93it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.59it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.74it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.83it/s]
                                                            

Job rirv938-v6-pref-plus-03-3022-v1-mkmlizer completed after 175.86s with status: succeeded
Stopping job with name rirv938-v6-pref-plus-03-3022-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-v6-pref-plus-03-3022-v1
Waiting for inference service rirv938-v6-pref-plus-03-3022-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rirv938-v6-pref-plus-03-3022-v1 ready after 271.38012647628784s
Pipeline stage MKMLDeployer completed in 271.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7661099433898926s
Received healthy response to inference request in 1.2589046955108643s
Received healthy response to inference request in 1.6904635429382324s
Received healthy response to inference request in 1.0920441150665283s
Received healthy response to inference request in 1.052114725112915s
5 requests
0 failed requests
5th percentile: 1.0601006031036377
10th percentile: 1.0680864810943604
20th percentile: 1.0840582370758056
30th percentile: 1.1254162311553955
40th percentile: 1.19216046333313
50th percentile: 1.2589046955108643
60th percentile: 1.4315282344818114
70th percentile: 1.6041517734527586
80th percentile: 1.7055928230285644
90th percentile: 1.7358513832092286
95th percentile: 1.7509806632995606
99th percentile: 1.763084087371826
mean time: 1.3719274044036864
Pipeline stage StressChecker completed in 8.15s
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 0.73s
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 0.76s
Shutdown handler de-registered
rirv938-v6-pref-plus-03-_3022_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-v6-pref-plus-03-3022-v1-profiler
Waiting for inference service rirv938-v6-pref-plus-03-3022-v1-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 2485.38s
Shutdown handler de-registered
rirv938-v6-pref-plus-03-_3022_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-v6-pref-plus-03-_3022_v1 status is now torndown due to DeploymentManager action
rirv938-v6-pref-plus-03-_3022_v1 status is now torndown due to DeploymentManager action
rirv938-v6-pref-plus-03-_3022_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1