ilyagusev-saiga-nemo-12b

developer_uid: huohuo12
submission_id: ilyagusev-saiga-nemo-12b_v25
model_name: ilyagusev-saiga-nemo-12b_v23
model_group: IlyaGusev/saiga_nemo_12b
status: torndown
timestamp: 2025-02-18T11:45:38+00:00
num_battles: 7680
num_wins: 3603
celo_rating: 1244.54
family_friendly_score: 0.6517999999999999
family_friendly_standard_error: 0.0067373104426024484
submission_type: basic
model_repo: IlyaGusev/saiga_nemo_12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: ilyagusev-saiga-nemo-12b_v23
is_internal_developer: False
language_model: IlyaGusev/saiga_nemo_12b
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-18
win_ratio: 0.469140625
generation_params: {'temperature': 0.77, 'top_p': 0.82, 'min_p': 0.025, 'top_k': 30, 'presence_penalty': 0.65, 'frequency_penalty': 0.2, '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 ilyagusev-saiga-nemo-12b-v25-mkmlizer
Waiting for job on ilyagusev-saiga-nemo-12b-v25-mkmlizer to finish
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║     _____            __           __                                ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║       /___/                                                         ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║                                                                     ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  Version: 0.12.8                                                    ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  https://mk1.ai                                                     ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║                                                                     ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  belonging to:                                                      ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║                                                                     ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  Chai Research Corp.                                                ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ║                                                                     ║
ilyagusev-saiga-nemo-12b-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
ilyagusev-saiga-nemo-12b-v25-mkmlizer: Downloaded to shared memory in 31.623s
ilyagusev-saiga-nemo-12b-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7y67afyv, device:0
ilyagusev-saiga-nemo-12b-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
ilyagusev-saiga-nemo-12b-v25-mkmlizer: quantized model in 39.193s
ilyagusev-saiga-nemo-12b-v25-mkmlizer: Processed model IlyaGusev/saiga_nemo_12b in 70.816s
ilyagusev-saiga-nemo-12b-v25-mkmlizer: creating bucket guanaco-mkml-models
ilyagusev-saiga-nemo-12b-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
ilyagusev-saiga-nemo-12b-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v25
ilyagusev-saiga-nemo-12b-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v25/config.json
ilyagusev-saiga-nemo-12b-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v25/special_tokens_map.json
ilyagusev-saiga-nemo-12b-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v25/tokenizer_config.json
ilyagusev-saiga-nemo-12b-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v25/tokenizer.json
ilyagusev-saiga-nemo-12b-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v25/flywheel_model.0.safetensors
ilyagusev-saiga-nemo-12b-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.52it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.07it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.30it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 40.99it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.14it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 32.87it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:08, 39.78it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 39.06it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 38.99it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 40.28it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 40.98it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 24.05it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.75it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 31.99it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.47it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 31.76it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 34.45it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:08, 33.47it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 35.03it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:08, 31.64it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.28it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:07, 35.22it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:07, 33.02it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:08, 30.61it/s]
Loading 0:  34%|███▍      | 123/363 [00:03<00:06, 34.80it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 31.57it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 35.54it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:07, 31.78it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 35.31it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 23.11it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:09, 23.16it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.27it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 26.47it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:06, 30.77it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:06, 29.12it/s]
Loading 0:  47%|████▋     | 172/363 [00:05<00:05, 33.19it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:06, 31.16it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.14it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.36it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:04, 36.20it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 32.17it/s]
Loading 0:  55%|█████▍    | 199/363 [00:06<00:04, 35.43it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:04, 32.03it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 35.91it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 32.27it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 35.97it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 36.00it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 24.62it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 25.04it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 29.48it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 28.54it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 33.07it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 31.14it/s]
Loading 0:  70%|██████▉   | 253/363 [00:07<00:03, 35.15it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 32.11it/s]
Loading 0:  72%|███████▏  | 262/363 [00:08<00:02, 36.17it/s]
Loading 0:  73%|███████▎  | 266/363 [00:08<00:02, 33.01it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:02, 35.74it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 31.78it/s]
Loading 0:  77%|███████▋  | 280/363 [00:08<00:02, 34.45it/s]
Loading 0:  78%|███████▊  | 284/363 [00:08<00:02, 30.72it/s]
Loading 0:  80%|███████▉  | 289/363 [00:08<00:02, 33.98it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 31.15it/s]
Loading 0:  82%|████████▏ | 298/363 [00:09<00:01, 35.14it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:01, 35.97it/s]
Loading 0:  85%|████████▍ | 307/363 [00:16<00:27,  2.07it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:17,  2.97it/s]
Loading 0:  88%|████████▊ | 318/363 [00:16<00:10,  4.49it/s]
Loading 0:  89%|████████▊ | 322/363 [00:16<00:07,  5.69it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:04,  8.26it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:03, 10.14it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 13.22it/s]
Loading 0:  94%|█████████▍| 341/363 [00:17<00:01, 15.49it/s]
Loading 0:  95%|█████████▌| 346/363 [00:17<00:00, 19.35it/s]
Loading 0:  96%|█████████▋| 350/363 [00:17<00:00, 21.49it/s]
Loading 0:  98%|█████████▊| 355/363 [00:17<00:00, 25.61it/s]
Loading 0:  99%|█████████▉| 359/363 [00:17<00:00, 26.88it/s]
                                                            
Job ilyagusev-saiga-nemo-12b-v25-mkmlizer completed after 93.72s with status: succeeded
Stopping job with name ilyagusev-saiga-nemo-12b-v25-mkmlizer
Pipeline stage MKMLizer completed in 94.17s
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 ilyagusev-saiga-nemo-12b-v25
Waiting for inference service ilyagusev-saiga-nemo-12b-v25 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service ilyagusev-saiga-nemo-12b-v25 ready after 270.7249836921692s
Pipeline stage MKMLDeployer completed in 271.12s
run pipeline stage %s
Running pipeline stage StressChecker
('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
Received unhealthy response to inference request!
Received healthy response to inference request in 2.4584546089172363s
Received healthy response to inference request in 1.6345221996307373s
Received healthy response to inference request in 1.697274923324585s
Received healthy response to inference request in 1.8435344696044922s
5 requests
1 failed requests
5th percentile: 0.4047027111053467
10th percentile: 0.7121575832366944
20th percentile: 1.3270673274993898
30th percentile: 1.6470727443695068
40th percentile: 1.672173833847046
50th percentile: 1.697274923324585
60th percentile: 1.7557787418365478
70th percentile: 1.8142825603485107
80th percentile: 1.966518497467041
90th percentile: 2.2124865531921385
95th percentile: 2.3354705810546874
99th percentile: 2.4338578033447265
mean time: 1.54620680809021
%s, retrying in %s seconds...
Received healthy response to inference request in 1.548093318939209s
Received healthy response to inference request in 1.5969228744506836s
Received healthy response to inference request in 1.5553319454193115s
Received healthy response to inference request in 1.9611876010894775s
Received healthy response to inference request in 1.6273925304412842s
5 requests
0 failed requests
5th percentile: 1.5495410442352295
10th percentile: 1.55098876953125
20th percentile: 1.553884220123291
30th percentile: 1.563650131225586
40th percentile: 1.5802865028381348
50th percentile: 1.5969228744506836
60th percentile: 1.6091107368469237
70th percentile: 1.621298599243164
80th percentile: 1.694151544570923
90th percentile: 1.8276695728302002
95th percentile: 1.8944285869598387
99th percentile: 1.9478357982635497
mean time: 1.6577856540679932
Pipeline stage StressChecker completed in 18.31s
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 0.63s
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 0.65s
Shutdown handler de-registered
ilyagusev-saiga-nemo-12b_v25 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 ilyagusev-saiga-nemo-12b-v25-profiler
Waiting for inference service ilyagusev-saiga-nemo-12b-v25-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 2825.61s
Shutdown handler de-registered
ilyagusev-saiga-nemo-12b_v25 status is now inactive due to auto deactivation removed underperforming models
ilyagusev-saiga-nemo-12b_v25 status is now torndown due to DeploymentManager action
ilyagusev-saiga-nemo-12b_v25 status is now torndown due to DeploymentManager action
ilyagusev-saiga-nemo-12b_v25 status is now torndown due to DeploymentManager action