rirv938-100p-0ff-rirv93_34479

developer_uid: rirv938

submission_id: rirv938-100p-0ff-rirv93_34479_v1

model_name: rirv938-100p-0ff-rirv93_34479_v1

model_group: rirv938/100p_0ff_rirv938

status: torndown

timestamp: 2025-04-03T03:34:41+00:00

num_battles: 5942

num_wins: 3171

celo_rating: 1332.98

family_friendly_score: 0.48140000000000005

family_friendly_standard_error: 0.007066173504804422

submission_type: basic

model_repo: rirv938/100p_0ff_rirv938_20k_100p_0ff_ri_19485_v1_cp374_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': 0.39033414277530626, 'latency_mean': 2.561839106082916, 'latency_p50': 2.548024296760559, 'latency_p90': 2.8607861280441282}, {'batch_size': 3, 'throughput': 0.7903306134860023, 'latency_mean': 3.7781352961063384, 'latency_p50': 3.7751379013061523, 'latency_p90': 4.177704453468323}, {'batch_size': 5, 'throughput': 1.0433595556597508, 'latency_mean': 4.748818795681, 'latency_p50': 4.743533611297607, 'latency_p90': 5.295965933799743}, {'batch_size': 6, 'throughput': 1.1253252739769226, 'latency_mean': 5.293350754976273, 'latency_p50': 5.285809278488159, 'latency_p90': 5.867053103446961}, {'batch_size': 10, 'throughput': 1.2906115084148932, 'latency_mean': 7.686541215181351, 'latency_p50': 7.670894742012024, 'latency_p90': 8.76871645450592}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-100p-0ff-rirv93_34479_v1

is_internal_developer: True

language_model: rirv938/100p_0ff_rirv938_20k_100p_0ff_ri_19485_v1_cp374_v3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-04-02

win_ratio: 0.5336587007741501

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': ['###', '\n', '</s>', 'You:'], '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-rirv93-34479-v1-mkmlizer
Waiting for job on rirv938-100p-0ff-rirv93-34479-v1-mkmlizer to finish
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-rirv93-34479-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║       /___/                                                         ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: ║                                                                     ║
rirv938-100p-0ff-rirv93-34479-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)
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: Downloaded to shared memory in 177.158s
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl9hh3jcg, device:0
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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)
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: quantized model in 68.581s
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: Processed model rirv938/100p_0ff_rirv938_20k_100p_0ff_ri_19485_v1_cp374_v3 in 245.740s
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1/config.json
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1/special_tokens_map.json
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1/tokenizer_config.json
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1/tokenizer.json
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1/flywheel_model.1.safetensors
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-100p-0ff-rirv93-34479-v1/flywheel_model.0.safetensors
rirv938-100p-0ff-rirv93-34479-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 27.59it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:28, 12.66it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:18, 18.85it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:27, 12.63it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:34, 10.14it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:24, 14.24it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:23, 14.56it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:29, 11.34it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 16.77it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:17, 19.05it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:26, 12.18it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:28, 11.33it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:26, 12.08it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:32,  9.96it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:21, 14.89it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:18, 17.32it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:25, 12.13it/s]
Loading 0:  15%|█▌        | 55/363 [00:04<00:26, 11.42it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:25, 12.16it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:31,  9.78it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:20, 14.48it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:17, 17.27it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:23, 12.22it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:25, 11.57it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:23, 12.32it/s]
Loading 0:  21%|██        | 77/363 [00:06<00:28, 10.11it/s]
Loading 0:  23%|██▎       | 82/363 [00:06<00:18, 15.17it/s]
Loading 0:  24%|██▎       | 86/363 [00:06<00:15, 18.12it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:21, 12.96it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.39it/s]
Loading 0:  26%|██▌       | 95/363 [00:07<00:16, 15.96it/s]
Loading 0:  27%|██▋       | 99/363 [00:07<00:13, 18.92it/s]
Loading 0:  28%|██▊       | 102/363 [00:07<00:14, 17.53it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.38it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 12.11it/s]
Loading 0:  30%|███       | 109/363 [00:08<00:22, 11.52it/s]
Loading 0:  31%|███       | 111/363 [00:08<00:20, 12.42it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:24, 10.03it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:15, 15.47it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 18.73it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:17, 13.41it/s]
Loading 0:  35%|███▍      | 127/363 [00:09<00:19, 12.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:18, 12.93it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:21, 10.84it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.53it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:11, 20.08it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:15, 14.20it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:16, 13.40it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 14.10it/s]
Loading 0:  41%|████      | 149/363 [00:11<00:19, 10.88it/s]
Loading 0:  42%|████▏     | 154/363 [00:11<00:12, 16.22it/s]
Loading 0:  44%|████▎     | 158/363 [00:11<00:10, 19.06it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:15, 13.06it/s]
Loading 0:  45%|████▍     | 163/363 [00:12<00:16, 12.28it/s]
Loading 0:  45%|████▌     | 165/363 [00:12<00:15, 12.97it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:19, 10.09it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:12, 15.09it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:10, 18.01it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:14, 12.62it/s]
Loading 0:  50%|████▉     | 181/363 [00:13<00:15, 12.01it/s]
Loading 0:  50%|█████     | 183/363 [00:13<00:13, 12.87it/s]
Loading 0:  51%|█████     | 185/363 [00:13<00:16, 10.55it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:10, 15.81it/s]
Loading 0:  53%|█████▎    | 194/363 [00:14<00:08, 19.02it/s]
Loading 0:  54%|█████▍    | 197/363 [00:14<00:12, 13.33it/s]
Loading 0:  55%|█████▍    | 199/363 [00:14<00:13, 12.34it/s]
Loading 0:  55%|█████▌    | 200/363 [00:30<00:13, 12.34it/s]
Loading 0:  55%|█████▌    | 201/363 [00:30<04:56,  1.83s/it]
Loading 0:  56%|█████▌    | 203/363 [00:30<03:47,  1.42s/it]
Loading 0:  57%|█████▋    | 207/363 [00:30<02:12,  1.18it/s]
Loading 0:  58%|█████▊    | 210/363 [00:30<01:31,  1.66it/s]
Loading 0:  59%|█████▊    | 213/363 [00:31<01:06,  2.25it/s]
Loading 0:  59%|█████▉    | 215/363 [00:31<00:54,  2.73it/s]
Loading 0:  60%|█████▉    | 217/363 [00:31<00:43,  3.38it/s]
Loading 0:  60%|██████    | 219/363 [00:31<00:33,  4.28it/s]
Loading 0:  61%|██████    | 221/363 [00:31<00:29,  4.83it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:15,  8.60it/s]
Loading 0:  63%|██████▎   | 230/363 [00:32<00:11, 11.79it/s]
Loading 0:  64%|██████▍   | 233/363 [00:32<00:12, 10.53it/s]
Loading 0:  65%|██████▌   | 236/363 [00:32<00:10, 11.75it/s]
Loading 0:  66%|██████▌   | 238/363 [00:32<00:11, 10.99it/s]
Loading 0:  66%|██████▌   | 240/363 [00:32<00:11, 10.82it/s]
Loading 0:  67%|██████▋   | 244/363 [00:33<00:08, 14.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:33<00:06, 17.42it/s]
Loading 0:  69%|██████▉   | 251/363 [00:33<00:08, 12.85it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:08, 12.43it/s]
Loading 0:  70%|███████   | 255/363 [00:33<00:08, 13.29it/s]
Loading 0:  71%|███████   | 257/363 [00:34<00:09, 10.87it/s]
Loading 0:  72%|███████▏  | 262/363 [00:34<00:06, 15.94it/s]
Loading 0:  73%|███████▎  | 266/363 [00:34<00:05, 18.60it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 13.53it/s]
Loading 0:  75%|███████▍  | 271/363 [00:35<00:07, 12.84it/s]
Loading 0:  75%|███████▌  | 273/363 [00:35<00:06, 13.77it/s]
Loading 0:  76%|███████▌  | 275/363 [00:35<00:07, 11.28it/s]
Loading 0:  77%|███████▋  | 280/363 [00:35<00:04, 16.88it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:03, 20.28it/s]
Loading 0:  79%|███████▉  | 287/363 [00:36<00:05, 14.55it/s]
Loading 0:  80%|███████▉  | 289/363 [00:36<00:05, 13.76it/s]
Loading 0:  80%|████████  | 291/363 [00:36<00:04, 14.53it/s]
Loading 0:  81%|████████  | 293/363 [00:36<00:05, 11.77it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:03, 17.62it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:02, 21.07it/s]
Loading 0:  84%|████████▍ | 305/363 [00:37<00:03, 14.87it/s]
Loading 0:  85%|████████▍ | 308/363 [00:37<00:03, 15.40it/s]
Loading 0:  85%|████████▌ | 310/363 [00:37<00:03, 13.49it/s]
Loading 0:  86%|████████▌ | 312/363 [00:37<00:04, 12.64it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 16.66it/s]
Loading 0:  88%|████████▊ | 320/363 [00:38<00:02, 20.07it/s]
Loading 0:  89%|████████▉ | 323/363 [00:38<00:02, 13.81it/s]
Loading 0:  90%|████████▉ | 325/363 [00:38<00:02, 13.21it/s]
Loading 0:  90%|█████████ | 327/363 [00:38<00:02, 13.89it/s]
Loading 0:  91%|█████████ | 329/363 [00:39<00:03, 11.30it/s]
Loading 0:  92%|█████████▏| 334/363 [00:39<00:01, 16.99it/s]
Loading 0:  93%|█████████▎| 338/363 [00:39<00:01, 20.04it/s]
Loading 0:  94%|█████████▍| 341/363 [00:39<00:01, 13.99it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 13.15it/s]
Loading 0:  95%|█████████▌| 345/363 [00:40<00:01, 13.89it/s]
Loading 0:  96%|█████████▌| 347/363 [00:40<00:01, 10.94it/s]
Loading 0:  97%|█████████▋| 352/363 [00:40<00:00, 16.38it/s]
Loading 0:  98%|█████████▊| 356/363 [00:40<00:00, 19.44it/s]
Loading 0:  99%|█████████▉| 359/363 [00:47<00:02,  1.44it/s]
Loading 0:  99%|█████████▉| 361/363 [00:48<00:01,  1.73it/s]
                                                            
Job rirv938-100p-0ff-rirv93-34479-v1-mkmlizer completed after 298.91s with status: succeeded
Stopping job with name rirv938-100p-0ff-rirv93-34479-v1-mkmlizer
Pipeline stage MKMLizer completed in 299.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-100p-0ff-rirv93-34479-v1
Waiting for inference service rirv938-100p-0ff-rirv93-34479-v1 to be ready
Inference service rirv938-100p-0ff-rirv93-34479-v1 ready after 130.46616411209106s
Pipeline stage MKMLDeployer completed in 130.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8488168716430664s
Received healthy response to inference request in 2.6332709789276123s
Received healthy response to inference request in 2.479527473449707s
Received healthy response to inference request in 2.6568126678466797s
Received healthy response to inference request in 2.5102181434631348s
5 requests
0 failed requests
5th percentile: 2.4856656074523924
10th percentile: 2.491803741455078
20th percentile: 2.5040800094604494
30th percentile: 2.53482871055603
40th percentile: 2.584049844741821
50th percentile: 2.6332709789276123
60th percentile: 2.6426876544952393
70th percentile: 2.6521043300628664
80th percentile: 2.695213508605957
90th percentile: 2.772015190124512
95th percentile: 2.810416030883789
99th percentile: 2.8411367034912107
mean time: 2.62572922706604
Pipeline stage StressChecker completed in 14.44s
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 0.71s
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
rirv938-100p-0ff-rirv93_34479_v1 status is now deployed due to DeploymentManager action
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 3073.36s
Shutdown handler de-registered
rirv938-100p-0ff-rirv93_34479_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-100p-0ff-rirv93_34479_v1 status is now torndown due to DeploymentManager action