rirv938-mistral-24b-40k_43012

developer_uid: Jellywibble
submission_id: rirv938-mistral-24b-40k_43012_v2
model_name: rirv938-mistral-24b-40k_43012_v2
model_group: rirv938/mistral_24b_40k_
status: torndown
timestamp: 2025-02-14T00:09:18+00:00
num_battles: 5883
num_wins: 2890
celo_rating: 1265.65
family_friendly_score: 0.6008
family_friendly_standard_error: 0.006925884203479005
submission_type: basic
model_repo: rirv938/mistral_24b_40k_2500_10w_bo32_lr_half_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
display_name: rirv938-mistral-24b-40k_43012_v2
is_internal_developer: True
language_model: rirv938/mistral_24b_40k_2500_10w_bo32_lr_half_v2
model_size: 24B
ranking_group: single
us_pacific_date: 2025-02-13
win_ratio: 0.49124596294407613
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', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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-mistral-24b-40k-43012-v2-mkmlizer
Waiting for job on rirv938-mistral-24b-40k-43012-v2-mkmlizer to finish
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-40k-43012-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-40k-43012-v2-mkmlizer: Downloaded to shared memory in 186.933s
rirv938-mistral-24b-40k-43012-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpizljbo7s, device:0
rirv938-mistral-24b-40k-43012-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-40k-43012-v2-mkmlizer: quantized model in 59.406s
rirv938-mistral-24b-40k-43012-v2-mkmlizer: Processed model rirv938/mistral_24b_40k_2500_10w_bo32_lr_half_v2 in 246.339s
rirv938-mistral-24b-40k-43012-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-40k-43012-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-40k-43012-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2
rirv938-mistral-24b-40k-43012-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2/config.json
rirv938-mistral-24b-40k-43012-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2/special_tokens_map.json
rirv938-mistral-24b-40k-43012-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2/tokenizer_config.json
rirv938-mistral-24b-40k-43012-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2/tokenizer.json
rirv938-mistral-24b-40k-43012-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2/flywheel_model.1.safetensors
rirv938-mistral-24b-40k-43012-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-40k-43012-v2/flywheel_model.0.safetensors
rirv938-mistral-24b-40k-43012-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:15, 23.27it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:17, 19.97it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 23.82it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:22, 15.45it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:23, 14.92it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:18, 18.74it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:23, 14.46it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:15, 22.24it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 20.28it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:20, 15.64it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:18, 17.20it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:18, 17.69it/s]
Loading 0:  13%|█▎        | 47/363 [00:02<00:14, 21.53it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:15, 20.05it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:19, 15.53it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:17, 17.14it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:18, 16.28it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:14, 20.19it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:12, 24.01it/s]
Loading 0:  20%|█▉        | 71/363 [00:03<00:16, 17.21it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:15, 18.14it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:20, 14.27it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:14, 19.78it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:11, 23.48it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:17, 15.71it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:12, 21.94it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:10, 23.89it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:14, 17.93it/s]
Loading 0:  30%|██▉       | 108/363 [00:06<00:17, 14.82it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:14, 16.82it/s]
Loading 0:  31%|███▏      | 114/363 [00:06<00:16, 15.51it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:12, 19.39it/s]
Loading 0:  34%|███▎      | 122/363 [00:06<00:10, 23.02it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:14, 16.29it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:13, 17.06it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 13.64it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:11, 19.00it/s]
Loading 0:  39%|███▊      | 140/363 [00:07<00:09, 22.50it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 14.30it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 16.36it/s]
Loading 0:  41%|████▏     | 150/363 [00:08<00:13, 15.24it/s]
Loading 0:  42%|████▏     | 154/363 [00:08<00:11, 18.86it/s]
Loading 0:  44%|████▎     | 158/363 [00:08<00:09, 22.51it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:12, 16.37it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:11, 17.29it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:14, 13.67it/s]
Loading 0:  47%|████▋     | 172/363 [00:09<00:10, 19.07it/s]
Loading 0:  48%|████▊     | 176/363 [00:09<00:08, 22.35it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 16.45it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:11, 15.39it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:13, 12.74it/s]
Loading 0:  52%|█████▏    | 190/363 [00:10<00:09, 17.73it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:07, 21.22it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 16.23it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.91it/s]
Loading 0:  55%|█████▌    | 200/363 [00:25<00:09, 16.91it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<04:16,  1.58s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<03:17,  1.23s/it]
Loading 0:  57%|█████▋    | 207/363 [00:25<01:55,  1.35it/s]
Loading 0:  58%|█████▊    | 210/363 [00:25<01:20,  1.90it/s]
Loading 0:  59%|█████▊    | 213/363 [00:25<00:58,  2.55it/s]
Loading 0:  60%|█████▉    | 216/363 [00:26<00:45,  3.22it/s]
Loading 0:  60%|██████    | 219/363 [00:26<00:32,  4.39it/s]
Loading 0:  61%|██████    | 222/363 [00:26<00:25,  5.47it/s]
Loading 0:  62%|██████▏   | 226/363 [00:26<00:17,  7.96it/s]
Loading 0:  63%|██████▎   | 230/363 [00:26<00:12, 10.89it/s]
Loading 0:  64%|██████▍   | 233/363 [00:27<00:12, 10.12it/s]
Loading 0:  65%|██████▌   | 236/363 [00:27<00:10, 11.63it/s]
Loading 0:  66%|██████▌   | 239/363 [00:27<00:11, 10.66it/s]
Loading 0:  67%|██████▋   | 244/363 [00:27<00:07, 15.52it/s]
Loading 0:  68%|██████▊   | 248/363 [00:27<00:06, 18.78it/s]
Loading 0:  69%|██████▉   | 251/363 [00:28<00:07, 14.58it/s]
Loading 0:  70%|██████▉   | 254/363 [00:28<00:07, 15.56it/s]
Loading 0:  71%|███████   | 257/363 [00:28<00:08, 12.97it/s]
Loading 0:  72%|███████▏  | 262/363 [00:28<00:05, 18.14it/s]
Loading 0:  73%|███████▎  | 266/363 [00:28<00:04, 21.63it/s]
Loading 0:  74%|███████▍  | 269/363 [00:29<00:05, 16.08it/s]
Loading 0:  75%|███████▍  | 272/363 [00:29<00:05, 17.01it/s]
Loading 0:  76%|███████▌  | 275/363 [00:29<00:06, 13.80it/s]
Loading 0:  77%|███████▋  | 280/363 [00:29<00:04, 19.14it/s]
Loading 0:  78%|███████▊  | 284/363 [00:29<00:03, 22.75it/s]
Loading 0:  79%|███████▉  | 288/363 [00:30<00:04, 15.07it/s]
Loading 0:  80%|████████  | 292/363 [00:30<00:04, 16.59it/s]
Loading 0:  81%|████████▏ | 295/363 [00:30<00:03, 17.07it/s]
Loading 0:  82%|████████▏ | 299/363 [00:30<00:03, 20.62it/s]
Loading 0:  83%|████████▎ | 303/363 [00:30<00:03, 19.45it/s]
Loading 0:  84%|████████▍ | 306/363 [00:31<00:03, 15.28it/s]
Loading 0:  85%|████████▌ | 310/363 [00:31<00:03, 16.97it/s]
Loading 0:  86%|████████▌ | 313/363 [00:31<00:02, 17.53it/s]
Loading 0:  87%|████████▋ | 317/363 [00:31<00:02, 21.28it/s]
Loading 0:  88%|████████▊ | 321/363 [00:31<00:02, 19.84it/s]
Loading 0:  89%|████████▉ | 324/363 [00:32<00:02, 15.38it/s]
Loading 0:  90%|█████████ | 328/363 [00:32<00:02, 17.06it/s]
Loading 0:  91%|█████████ | 330/363 [00:32<00:02, 16.31it/s]
Loading 0:  92%|█████████▏| 334/363 [00:32<00:01, 20.38it/s]
Loading 0:  93%|█████████▎| 338/363 [00:32<00:01, 24.15it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:01, 17.23it/s]
Loading 0:  95%|█████████▍| 344/363 [00:33<00:01, 17.96it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:01, 14.06it/s]
Loading 0:  97%|█████████▋| 352/363 [00:33<00:00, 19.56it/s]
Loading 0:  98%|█████████▊| 356/363 [00:33<00:00, 22.94it/s]
Loading 0:  99%|█████████▉| 359/363 [00:40<00:02,  1.67it/s]
Loading 0: 100%|█████████▉| 362/363 [00:40<00:00,  2.17it/s]
                                                            
Job rirv938-mistral-24b-40k-43012-v2-mkmlizer completed after 286.63s with status: succeeded
Stopping job with name rirv938-mistral-24b-40k-43012-v2-mkmlizer
Pipeline stage MKMLizer completed in 287.11s
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 rirv938-mistral-24b-40k-43012-v2
Waiting for inference service rirv938-mistral-24b-40k-43012-v2 to be ready
Inference service rirv938-mistral-24b-40k-43012-v2 ready after 180.8965916633606s
Pipeline stage MKMLDeployer completed in 181.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9155490398406982s
Received healthy response to inference request in 2.624445676803589s
Received healthy response to inference request in 2.6389148235321045s
Received healthy response to inference request in 2.3772475719451904s
Received healthy response to inference request in 2.814657688140869s
5 requests
0 failed requests
5th percentile: 2.4266871929168703
10th percentile: 2.4761268138885497
20th percentile: 2.575006055831909
30th percentile: 2.627339506149292
40th percentile: 2.6331271648406984
50th percentile: 2.6389148235321045
60th percentile: 2.7092119693756103
70th percentile: 2.779509115219116
80th percentile: 2.834835958480835
90th percentile: 2.8751924991607667
95th percentile: 2.8953707695007322
99th percentile: 2.911513385772705
mean time: 2.6741629600524903
Pipeline stage StressChecker completed in 14.74s
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 0.78s
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
rirv938-mistral-24b-40k_43012_v2 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-40k-43012-v2-profiler
Waiting for inference service rirv938-mistral-24b-40k-43012-v2-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 2834.37s
Shutdown handler de-registered
rirv938-mistral-24b-40k_43012_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-40k_43012_v2 status is now torndown due to DeploymentManager action