rica40325-mistral-13b-2452

developer_uid: Riverise

submission_id: rica40325-mistral-13b-2452_v8

model_name: rica40325-mistral-13b-2452_v8

model_group: rica40325/mistral-13B-24

status: torndown

timestamp: 2025-05-06T08:30:49+00:00

num_battles: 7338

num_wins: 3499

celo_rating: 1268.5

family_friendly_score: 0.5884

family_friendly_standard_error: 0.006959675854520813

submission_type: basic

model_repo: rica40325/mistral-13B-2452

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6041511276144222, 'latency_mean': 1.655127546787262, 'latency_p50': 1.6383056640625, 'latency_p90': 1.8243301868438722}, {'batch_size': 3, 'throughput': 1.1091305181717686, 'latency_mean': 2.700136853456497, 'latency_p50': 2.7109344005584717, 'latency_p90': 2.9515288829803468}, {'batch_size': 5, 'throughput': 1.3489179351519265, 'latency_mean': 3.6942924308776854, 'latency_p50': 3.7038155794143677, 'latency_p90': 4.075506258010864}, {'batch_size': 6, 'throughput': 1.3942627050243686, 'latency_mean': 4.275923364162445, 'latency_p50': 4.271672606468201, 'latency_p90': 4.74110095500946}, {'batch_size': 8, 'throughput': 1.4621946190686232, 'latency_mean': 5.435921444892883, 'latency_p50': 5.470194101333618, 'latency_p90': 6.115893602371216}, {'batch_size': 10, 'throughput': 1.508811493164806, 'latency_mean': 6.585872044563294, 'latency_p50': 6.598902225494385, 'latency_p90': 7.4386152744293215}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-mistral-13b-2452_v8

is_internal_developer: False

language_model: rica40325/mistral-13B-2452

model_size: 13B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-05-06

win_ratio: 0.47683292450258924

generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, '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-mistral-13b-2452-v8-mkmlizer
Waiting for job on rica40325-mistral-13b-2452-v8-mkmlizer to finish
rica40325-mistral-13b-2452-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-mistral-13b-2452-v8-mkmlizer: ║     _____            __           __                                ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║       /___/                                                         ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  belonging to:                                                      ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-mistral-13b-2452-v8-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-mistral-13b-2452-v8-mkmlizer: Downloaded to shared memory in 31.697s
rica40325-mistral-13b-2452-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvec5ea14, device:0
rica40325-mistral-13b-2452-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-mistral-13b-2452-v8-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
rica40325-mistral-13b-2452-v8-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-mistral-13b-2452-v8-mkmlizer: quantized model in 37.053s
rica40325-mistral-13b-2452-v8-mkmlizer: Processed model rica40325/mistral-13B-2452 in 68.750s
rica40325-mistral-13b-2452-v8-mkmlizer: creating bucket guanaco-mkml-models
rica40325-mistral-13b-2452-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-mistral-13b-2452-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v8
rica40325-mistral-13b-2452-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v8/config.json
rica40325-mistral-13b-2452-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v8/special_tokens_map.json
rica40325-mistral-13b-2452-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v8/tokenizer_config.json
rica40325-mistral-13b-2452-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v8/tokenizer.json
rica40325-mistral-13b-2452-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v8/flywheel_model.0.safetensors
rica40325-mistral-13b-2452-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 47.76it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.95it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:05, 64.63it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:05, 65.79it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:06, 50.39it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:07, 44.31it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 47.56it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.26it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:26, 11.51it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:17, 16.93it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:12, 23.11it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:09, 29.07it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:07, 36.44it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:05, 43.35it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:04, 50.03it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:04, 56.72it/s]
Loading 0:  37%|███▋      | 133/363 [00:03<00:03, 61.28it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 20.07it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 24.80it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.75it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 36.64it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:04, 42.26it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:03, 47.72it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:03, 53.19it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:02, 56.56it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 60.04it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.42it/s]
Loading 0:  64%|██████▍   | 232/363 [00:07<00:05, 25.92it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:03, 31.58it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:02, 38.32it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 45.16it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:01, 50.79it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:01, 56.99it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:01, 61.26it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 65.81it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 21.06it/s]
Loading 0:  86%|████████▌ | 313/363 [00:09<00:01, 27.05it/s]
Loading 0:  89%|████████▊ | 322/363 [00:09<00:01, 33.96it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 40.77it/s]
Loading 0:  94%|█████████▎| 340/363 [00:09<00:00, 46.66it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 52.46it/s]
Loading 0:  99%|█████████▊| 358/363 [00:09<00:00, 58.17it/s]
                                                            
Job rica40325-mistral-13b-2452-v8-mkmlizer completed after 94.43s with status: succeeded
Stopping job with name rica40325-mistral-13b-2452-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-mistral-13b-2452-v8
Waiting for inference service rica40325-mistral-13b-2452-v8 to be ready
Inference service rica40325-mistral-13b-2452-v8 ready after 150.4945502281189s
Pipeline stage MKMLDeployer completed in 151.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1648526191711426s
Received healthy response to inference request in 1.7428181171417236s
Received healthy response to inference request in 1.8420348167419434s
Received healthy response to inference request in 1.7740788459777832s
Received healthy response to inference request in 1.655012607574463s
5 requests
0 failed requests
5th percentile: 1.672573709487915
10th percentile: 1.6901348114013672
20th percentile: 1.7252570152282716
30th percentile: 1.7490702629089356
40th percentile: 1.7615745544433594
50th percentile: 1.7740788459777832
60th percentile: 1.8012612342834473
70th percentile: 1.8284436225891114
80th percentile: 1.9065983772277832
90th percentile: 2.035725498199463
95th percentile: 2.1002890586853025
99th percentile: 2.1519399070739746
mean time: 1.8357594013214111
Pipeline stage StressChecker completed in 10.40s
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 0.66s
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 0.67s
Shutdown handler de-registered
rica40325-mistral-13b-2452_v8 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 0.13s
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-mistral-13b-2452-v8-profiler
Waiting for inference service rica40325-mistral-13b-2452-v8-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4362.57s
Shutdown handler de-registered
rica40325-mistral-13b-2452_v8 status is now inactive due to auto deactivation removed underperforming models
rica40325-mistral-13b-2452_v8 status is now torndown due to DeploymentManager action