developer_uid: rirv938
submission_id: rirv938-v4-pref-plus-03-_1536_v1
model_name: rirv938-v4-pref-plus-03-_1536_v1
model_group: rirv938/v4_pref_plus_03_
status: torndown
timestamp: 2024-12-22T23:39:29+00:00
num_battles: 20377
num_wins: 9720
celo_rating: 1242.69
family_friendly_score: 0.634
family_friendly_standard_error: 0.006812400457988359
submission_type: basic
model_repo: rirv938/v4_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': 0.6323018890025416, 'latency_mean': 1.5814594042301178, 'latency_p50': 1.5810582637786865, 'latency_p90': 1.7358620643615723}, {'batch_size': 3, 'throughput': 1.2622071073025982, 'latency_mean': 2.368136924505234, 'latency_p50': 2.356982946395874, 'latency_p90': 2.6266650199890136}, {'batch_size': 5, 'throughput': 1.571463385131935, 'latency_mean': 3.165713049173355, 'latency_p50': 3.1754084825515747, 'latency_p90': 3.4982043981552122}, {'batch_size': 6, 'throughput': 1.6916018699839663, 'latency_mean': 3.536616460084915, 'latency_p50': 3.533774256706238, 'latency_p90': 4.050182056427002}, {'batch_size': 8, 'throughput': 1.8455936782270268, 'latency_mean': 4.298450230360031, 'latency_p50': 4.309987664222717, 'latency_p90': 4.822696471214294}, {'batch_size': 10, 'throughput': 1.9268415576645248, 'latency_mean': 5.150641806125641, 'latency_p50': 5.140213251113892, 'latency_p90': 5.753921580314636}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-v4-pref-plus-03-_1536_v1
is_internal_developer: True
language_model: rirv938/v4_pref_plus_03_mistral_558_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2024-12-22
win_ratio: 0.47700839181430044
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-v4-pref-plus-03-1536-v1-mkmlizer
Waiting for job on rirv938-v4-pref-plus-03-1536-v1-mkmlizer to finish
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║       /___/                                                         ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║                                                                     ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║                                                                     ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║                                                                     ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ║                                                                     ║
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: Downloaded to shared memory in 103.294s
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpipp2owq4, device:0
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: quantized model in 41.103s
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: Processed model rirv938/v4_pref_plus_03_mistral_558_v2 in 144.397s
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-v4-pref-plus-03-1536-v1/config.json
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-v4-pref-plus-03-1536-v1/special_tokens_map.json
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-v4-pref-plus-03-1536-v1/tokenizer_config.json
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-v4-pref-plus-03-1536-v1/tokenizer.json
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-v4-pref-plus-03-1536-v1/flywheel_model.0.safetensors
rirv938-v4-pref-plus-03-1536-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.98it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.41it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.65it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 32.80it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:15, 21.62it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:16, 20.87it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.15it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:13, 24.27it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.88it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 26.77it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.18it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 27.69it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 28.24it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.91it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.23it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.83it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.49it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 25.76it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.24it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.80it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.83it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 25.23it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.74it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.28it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.75it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.61it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.43it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.82it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.33it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 30.03it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 30.53it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.72it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.25it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.08it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.18it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:06, 29.34it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 31.41it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.54it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.99it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.04it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.97it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.81it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:05, 28.52it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.24it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 30.11it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.54it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 31.02it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.11it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 26.63it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.77it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.29it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 28.51it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 25.57it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 31.92it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.55it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.97it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 31.60it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 25.74it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.38it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.10it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 28.02it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.10it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.28it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.16it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 31.09it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 31.30it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 27.04it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.90it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.85it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.67it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.73it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.27it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.49it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.76it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.84it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.95it/s]
                                                            

Job rirv938-v4-pref-plus-03-1536-v1-mkmlizer completed after 165.86s with status: succeeded
Stopping job with name rirv938-v4-pref-plus-03-1536-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-v4-pref-plus-03-1536-v1
Waiting for inference service rirv938-v4-pref-plus-03-1536-v1 to be ready
Failed to get response for submission rirv938-v5-pref-plus-03-_2088_v1: ('http://rirv938-v5-pref-plus-03-2088-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service rirv938-v4-pref-plus-03-1536-v1 ready after 271.1085982322693s
Pipeline stage MKMLDeployer completed in 271.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8932058811187744s
Received healthy response to inference request in 1.4614500999450684s
Received healthy response to inference request in 1.383918285369873s
Received healthy response to inference request in 1.4644300937652588s
Received healthy response to inference request in 1.5714614391326904s
5 requests
0 failed requests
5th percentile: 1.3994246482849122
10th percentile: 1.4149310111999511
20th percentile: 1.4459437370300292
30th percentile: 1.4620460987091064
40th percentile: 1.4632380962371827
50th percentile: 1.4644300937652588
60th percentile: 1.5072426319122314
70th percentile: 1.550055170059204
80th percentile: 1.6358103275299072
90th percentile: 1.764508104324341
95th percentile: 1.8288569927215577
99th percentile: 1.880336103439331
mean time: 1.554893159866333
Pipeline stage StressChecker completed in 8.99s
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 0.91s
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 0.63s
Shutdown handler de-registered
rirv938-v4-pref-plus-03-_1536_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 2530.09s
Shutdown handler de-registered
rirv938-v4-pref-plus-03-_1536_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-v4-pref-plus-03-_1536_v1 status is now torndown due to DeploymentManager action
rirv938-v4-pref-plus-03-_1536_v1 status is now torndown due to DeploymentManager action
rirv938-v4-pref-plus-03-_1536_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1