developer_uid: rica40325
submission_id: rica40325-filterv2_v1
model_name: rica40325-filterv2_v1
model_group: rica40325/filterv2
status: torndown
timestamp: 2025-04-21T04:53:23+00:00
num_battles: 6697
num_wins: 3209
celo_rating: 1270.63
family_friendly_score: 0.6064
family_friendly_standard_error: 0.006909110507149239
submission_type: basic
model_repo: rica40325/filterv2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.609449977499536, 'latency_mean': 1.6407234585285186, 'latency_p50': 1.6459064483642578, 'latency_p90': 1.799200677871704}, {'batch_size': 3, 'throughput': 1.1238630821337532, 'latency_mean': 2.656748102903366, 'latency_p50': 2.6555815935134888, 'latency_p90': 2.899853229522705}, {'batch_size': 5, 'throughput': 1.363601399758601, 'latency_mean': 3.6506876933574675, 'latency_p50': 3.631352663040161, 'latency_p90': 4.118363928794861}, {'batch_size': 6, 'throughput': 1.4239842380647871, 'latency_mean': 4.183062478303909, 'latency_p50': 4.1910024881362915, 'latency_p90': 4.66392183303833}, {'batch_size': 8, 'throughput': 1.4927072372170298, 'latency_mean': 5.326413300037384, 'latency_p50': 5.349801182746887, 'latency_p90': 6.00649242401123}, {'batch_size': 10, 'throughput': 1.5269083798709182, 'latency_mean': 6.4931350409984585, 'latency_p50': 6.48290479183197, 'latency_p90': 7.28345000743866}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-filterv2_v1
is_internal_developer: False
language_model: rica40325/filterv2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2025-04-20
win_ratio: 0.47916977751231893
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 rica40325-filterv2-v1-mkmlizer
Waiting for job on rica40325-filterv2-v1-mkmlizer to finish
rica40325-filterv2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filterv2-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-filterv2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-filterv2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-filterv2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-filterv2-v1-mkmlizer: ║       /___/                                                         ║
rica40325-filterv2-v1-mkmlizer: ║                                                                     ║
rica40325-filterv2-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-filterv2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-filterv2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filterv2-v1-mkmlizer: ║                                                                     ║
rica40325-filterv2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filterv2-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-filterv2-v1-mkmlizer: ║                                                                     ║
rica40325-filterv2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filterv2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filterv2-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filterv2-v1-mkmlizer: ║                                                                     ║
rica40325-filterv2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filterv2-v1-mkmlizer: Downloaded to shared memory in 41.661s
rica40325-filterv2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp66es1ul3, device:0
rica40325-filterv2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filterv2-v1-mkmlizer: quantized model in 38.485s
rica40325-filterv2-v1-mkmlizer: Processed model rica40325/filterv2 in 80.147s
rica40325-filterv2-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filterv2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filterv2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filterv2-v1
rica40325-filterv2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filterv2-v1/special_tokens_map.json
rica40325-filterv2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filterv2-v1/tokenizer.json
rica40325-filterv2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filterv2-v1/flywheel_model.0.safetensors
rica40325-filterv2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.83it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.55it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.67it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 35.07it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 42.63it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 41.62it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 41.49it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 42.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:09, 33.70it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:08, 38.02it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:17, 17.74it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:16, 18.36it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:14, 19.87it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.83it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:12, 23.01it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:12, 21.94it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:10, 26.81it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.42it/s]
Loading 0:  27%|██▋       | 98/363 [00:03<00:07, 34.68it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:07, 33.84it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:07, 34.26it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 38.04it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:06, 35.43it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 33.73it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:06, 36.05it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 35.45it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:05, 38.45it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 37.02it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 25.47it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:07, 27.86it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 28.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:05, 35.06it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:05, 36.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:05, 39.16it/s]
Loading 0:  47%|████▋     | 170/363 [00:05<00:04, 39.99it/s]
Loading 0:  48%|████▊     | 175/363 [00:05<00:04, 41.44it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:04, 40.51it/s]
Loading 0:  51%|█████     | 186/363 [00:05<00:04, 40.26it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:03, 44.09it/s]
Loading 0:  54%|█████▍    | 197/363 [00:06<00:03, 44.19it/s]
Loading 0:  56%|█████▌    | 202/363 [00:06<00:03, 44.72it/s]
Loading 0:  57%|█████▋    | 207/363 [00:06<00:03, 46.13it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 35.49it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 39.28it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 28.70it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 29.42it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 29.09it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 33.78it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:03, 33.39it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 35.37it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 35.06it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 37.17it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 36.08it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.12it/s]
Loading 0:  74%|███████▍  | 268/363 [00:08<00:02, 35.78it/s]
Loading 0:  75%|███████▌  | 273/363 [00:08<00:02, 37.49it/s]
Loading 0:  76%|███████▋  | 277/363 [00:08<00:02, 34.60it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 35.88it/s]
Loading 0:  79%|███████▊  | 285/363 [00:08<00:02, 31.94it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:02, 33.35it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 31.09it/s]
Loading 0:  82%|████████▏ | 299/363 [00:09<00:01, 35.96it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:26,  2.22it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:20,  2.75it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:12,  3.96it/s]
Loading 0:  87%|████████▋ | 317/363 [00:16<00:08,  5.64it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:05,  7.19it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:03, 11.17it/s]
Loading 0:  92%|█████████▏| 333/363 [00:16<00:02, 14.06it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 16.62it/s]
Loading 0:  94%|█████████▍| 341/363 [00:16<00:01, 18.95it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 23.03it/s]
Loading 0:  96%|█████████▋| 350/363 [00:17<00:00, 24.94it/s]
Loading 0:  98%|█████████▊| 355/363 [00:17<00:00, 29.04it/s]
Loading 0:  99%|█████████▉| 359/363 [00:17<00:00, 30.37it/s]
                                                            

Job rica40325-filterv2-v1-mkmlizer completed after 114.96s with status: succeeded
Stopping job with name rica40325-filterv2-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.42s
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 rica40325-filterv2-v1
Waiting for inference service rica40325-filterv2-v1 to be ready
Inference service rica40325-filterv2-v1 ready after 130.44593214988708s
Pipeline stage MKMLDeployer completed in 130.93s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.44498610496521s
Received healthy response to inference request in 1.5519938468933105s
Received healthy response to inference request in 1.8880021572113037s
Received healthy response to inference request in 1.889371633529663s
5 requests
1 failed requests
5th percentile: 1.6191955089569092
10th percentile: 1.686397171020508
20th percentile: 1.820800495147705
30th percentile: 1.8882760524749755
40th percentile: 1.8888238430023194
50th percentile: 1.889371633529663
60th percentile: 2.111617422103882
70th percentile: 2.3338632106781003
80th percentile: 6.0371218204498325
90th percentile: 13.22139325141907
95th percentile: 16.813528966903682
99th percentile: 19.68723753929138
mean time: 5.636003684997559
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5109245777130127s
Received healthy response to inference request in 1.519730567932129s
Received healthy response to inference request in 1.7713837623596191s
Received healthy response to inference request in 1.8000857830047607s
Received healthy response to inference request in 1.8937208652496338s
5 requests
0 failed requests
5th percentile: 1.512685775756836
10th percentile: 1.5144469738006592
20th percentile: 1.5179693698883057
30th percentile: 1.570061206817627
40th percentile: 1.670722484588623
50th percentile: 1.7713837623596191
60th percentile: 1.7828645706176758
70th percentile: 1.7943453788757324
80th percentile: 1.8188127994537353
90th percentile: 1.8562668323516847
95th percentile: 1.8749938488006592
99th percentile: 1.8899754619598388
mean time: 1.699169111251831
Pipeline stage StressChecker completed in 39.75s
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 0.83s
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 0.79s
Shutdown handler de-registered
rica40325-filterv2_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-filterv2-v1-profiler
Waiting for inference service rica40325-filterv2-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 2747.93s
Shutdown handler de-registered
rica40325-filterv2_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-filterv2_v1 status is now torndown due to DeploymentManager action