rirv938-100p-0ff-rirv93_76723

developer_uid: rirv938

submission_id: rirv938-100p-0ff-rirv93_76723_v1

model_name: rirv938-100p-0ff-rirv93_76723_v1

model_group: rirv938/100p_0ff_rirv938

status: torndown

timestamp: 2025-04-03T03:34:44+00:00

num_battles: 5938

num_wins: 3170

celo_rating: 1331.33

family_friendly_score: 0.474

family_friendly_standard_error: 0.007061501256815012

submission_type: basic

model_repo: rirv938/100p_0ff_rirv938_20k_100p_0ff_ri_19485_v1_cp748_v3

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.38660575440405043, 'latency_mean': 2.586547108888626, 'latency_p50': 2.5797606706619263, 'latency_p90': 2.8808682680130007}, {'batch_size': 3, 'throughput': 0.7918912632285227, 'latency_mean': 3.7816707634925844, 'latency_p50': 3.8200440406799316, 'latency_p90': 4.146312737464904}, {'batch_size': 5, 'throughput': 1.0542513287753557, 'latency_mean': 4.717072139978409, 'latency_p50': 4.6936274766922, 'latency_p90': 5.2352139234542845}, {'batch_size': 6, 'throughput': 1.1248092706185893, 'latency_mean': 5.3016720032691955, 'latency_p50': 5.351131439208984, 'latency_p90': 5.894318270683288}, {'batch_size': 10, 'throughput': 1.3087561194208943, 'latency_mean': 7.5680669867992405, 'latency_p50': 7.579190254211426, 'latency_p90': 8.576742506027221}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-100p-0ff-rirv93_76723_v1

is_internal_developer: True

language_model: rirv938/100p_0ff_rirv938_20k_100p_0ff_ri_19485_v1_cp748_v3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.77

us_pacific_date: 2025-04-02

win_ratio: 0.5338497810710677

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['You:', '</s>', '###', '\n'], '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 rirv938-100p-0ff-rirv93-76723-v1-mkmlizer
Waiting for job on rirv938-100p-0ff-rirv93-76723-v1-mkmlizer to finish
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║       /___/                                                         ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v4: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: Downloaded to shared memory in 206.709s
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp86wwpnup, device:0
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: quantized model in 63.846s
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: Processed model rirv938/100p_0ff_rirv938_20k_100p_0ff_ri_19485_v1_cp748_v3 in 270.556s
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1/config.json
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1/special_tokens_map.json
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1/tokenizer_config.json
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1/tokenizer.json
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1/flywheel_model.1.safetensors
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-76723-v1/flywheel_model.0.safetensors
rirv938-100p-0ff-rirv93-76723-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.42it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.30it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.62it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.79it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.27it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.88it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.17it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.65it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.56it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.13it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.63it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.73it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.07it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.91it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:15, 20.22it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.17it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.42it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.28it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:26, 11.47it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.21it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.49it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.82it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:20, 14.23it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:19, 14.69it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:23, 12.21it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:14, 18.81it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:14, 19.57it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:18, 14.52it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:13, 19.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.77it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.30it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.44it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.22it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 12.78it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.52it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.20it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.93it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.41it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.42it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.58it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.33it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.39it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.06it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:11, 20.12it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.07it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 13.43it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:15, 14.17it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:18, 11.66it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.84it/s]
Loading 0:  44%|████▍     | 159/363 [00:10<00:10, 18.93it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:13, 14.38it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:11, 16.59it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:13, 14.86it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:09, 20.25it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:09, 19.33it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:12, 14.25it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:11, 16.35it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:12, 14.63it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 18.33it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:07, 21.30it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 15.09it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.81it/s]
Loading 0:  55%|█████▌    | 200/363 [00:27<00:10, 15.81it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:42,  1.75s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:36,  1.35s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:05,  1.24it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:27,  1.75it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:03,  2.36it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:51,  2.86it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.52it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.45it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  5.07it/s]
Loading 0:  63%|██████▎   | 227/363 [00:29<00:13,  9.88it/s]
Loading 0:  64%|██████▎   | 231/363 [00:29<00:11, 11.55it/s]
Loading 0:  64%|██████▍   | 234/363 [00:29<00:12, 10.54it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:10, 12.41it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:10, 12.14it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.72it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:05, 19.37it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.54it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.32it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 11.93it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.58it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 19.44it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.58it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:06, 14.95it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:06, 13.47it/s]
Loading 0:  76%|███████▌  | 276/363 [00:32<00:06, 12.96it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.01it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.34it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 14.63it/s]
Loading 0:  80%|███████▉  | 289/363 [00:33<00:05, 13.81it/s]
Loading 0:  80%|████████  | 291/363 [00:33<00:04, 14.73it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 11.82it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.75it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.44it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 15.27it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.93it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.31it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 16.88it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 19.75it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.48it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.36it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:02, 13.90it/s]
Loading 0:  91%|█████████ | 330/363 [00:35<00:02, 13.59it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.97it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 22.12it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 15.86it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.66it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 13.05it/s]
Loading 0:  97%|█████████▋| 353/363 [00:36<00:00, 19.90it/s]
Loading 0:  98%|█████████▊| 357/363 [00:43<00:03,  1.77it/s]
Loading 0:  99%|█████████▉| 360/363 [00:44<00:01,  2.26it/s]
Loading 0: 100%|█████████▉| 362/363 [00:44<00:00,  2.66it/s]
                                                            
Job rirv938-100p-0ff-rirv93-76723-v1-mkmlizer completed after 321.14s with status: succeeded
Stopping job with name rirv938-100p-0ff-rirv93-76723-v1-mkmlizer
Pipeline stage MKMLizer completed in 321.66s
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 rirv938-100p-0ff-rirv93-76723-v1
Waiting for inference service rirv938-100p-0ff-rirv93-76723-v1 to be ready
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-100p-0ff-rirv93-76723-v1 ready after 120.58244061470032s
Pipeline stage MKMLDeployer completed in 121.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0304324626922607s
Received healthy response to inference request in 2.747546434402466s
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v4: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.7048285007476807s
Received healthy response to inference request in 2.829826593399048s
Received healthy response to inference request in 2.7525031566619873s
5 requests
0 failed requests
5th percentile: 2.713372087478638
10th percentile: 2.721915674209595
20th percentile: 2.7390028476715087
30th percentile: 2.74853777885437
40th percentile: 2.7505204677581787
50th percentile: 2.7525031566619873
60th percentile: 2.7834325313568113
70th percentile: 2.814361906051636
80th percentile: 2.8699477672576905
90th percentile: 2.9501901149749754
95th percentile: 2.990311288833618
99th percentile: 3.022408227920532
mean time: 2.8130274295806883
Pipeline stage StressChecker completed in 15.34s
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 0.62s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_76723_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-100p-0ff-rirv93-76723-v1-profiler
Waiting for inference service rirv938-100p-0ff-rirv93-76723-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 2955.31s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_76723_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-100p-0ff-rirv93_76723_v1 status is now torndown due to DeploymentManager action