rirv938-98p-2ff-rirv938_33106

developer_uid: rirv938

submission_id: rirv938-98p-2ff-rirv938_33106_v1

model_name: rirv938-98p-2ff-rirv938_33106_v1

model_group: rirv938/98p_2ff_rirv938_

status: torndown

timestamp: 2025-04-21T23:16:12+00:00

num_battles: 6402

num_wins: 3290

celo_rating: 1303.47

family_friendly_score: 0.5227999999999999

family_friendly_standard_error: 0.007063712338423756

submission_type: basic

model_repo: rirv938/98p_2ff_rirv938_1000_sim_100p_0_17599_v1_cp1060_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.53398634578368, 'latency_mean': 1.8726411640644074, 'latency_p50': 1.8532062768936157, 'latency_p90': 2.077303671836853}, {'batch_size': 3, 'throughput': 1.0864128028815403, 'latency_mean': 2.7518797063827516, 'latency_p50': 2.7450366020202637, 'latency_p90': 3.031430220603943}, {'batch_size': 5, 'throughput': 1.3932738345549374, 'latency_mean': 3.5623637521266938, 'latency_p50': 3.5644627809524536, 'latency_p90': 4.0273113489151005}, {'batch_size': 6, 'throughput': 1.5139463561812532, 'latency_mean': 3.94184766292572, 'latency_p50': 3.9698725938796997, 'latency_p90': 4.431387877464294}, {'batch_size': 8, 'throughput': 1.6419751250342527, 'latency_mean': 4.830393220186234, 'latency_p50': 4.8262070417404175, 'latency_p90': 5.400958776473999}, {'batch_size': 10, 'throughput': 1.7449770063314027, 'latency_mean': 5.678575754165649, 'latency_p50': 5.7132850885391235, 'latency_p90': 6.399179673194885}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-98p-2ff-rirv938_33106_v1

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: rirv938/98p_2ff_rirv938_1000_sim_100p_0_17599_v1_cp1060_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.45

us_pacific_date: 2025-04-21

win_ratio: 0.513901905654483

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['</s>', 'You:', '\n', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 rirv938-98p-2ff-rirv938-33106-v1-mkmlizer
Waiting for job on rirv938-98p-2ff-rirv938-33106-v1-mkmlizer to finish
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║       /___/                                                         ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║                                                                     ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║                                                                     ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║                                                                     ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ║                                                                     ║
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-sam-montgom_38443_v1: HTTPConnectionPool(host='jellywibble-sam-montgom-38443-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: Downloaded to shared memory in 163.277s
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgbamdmm2, device:0
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-sam-montgom_38443_v1: HTTPConnectionPool(host='jellywibble-sam-montgom-38443-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: quantized model in 70.758s
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: Processed model rirv938/98p_2ff_rirv938_1000_sim_100p_0_17599_v1_cp1060_merged in 234.036s
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1/config.json
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1/special_tokens_map.json
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1/tokenizer_config.json
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1/tokenizer.json
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1/flywheel_model.1.safetensors
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-98p-2ff-rirv938-33106-v1/flywheel_model.0.safetensors
rirv938-98p-2ff-rirv938-33106-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.21it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.03it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.61it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:24, 14.18it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:30, 11.37it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.21it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 15.61it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:23, 14.41it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.59it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.95it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.16it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:22, 14.25it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:21, 15.10it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:26, 11.99it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.86it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 20.92it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 14.87it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.73it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 14.64it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 11.73it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.44it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.11it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 13.93it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:23, 12.37it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:22, 12.88it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:28,  9.94it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:19, 14.62it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:16, 17.13it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:23, 11.74it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:24, 11.13it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:18, 14.26it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:15, 16.87it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:17, 15.28it/s]
Loading 0:  29%|██▊       | 104/363 [00:07<00:19, 13.36it/s]
Loading 0:  29%|██▉       | 106/363 [00:07<00:24, 10.52it/s]
Loading 0:  30%|██▉       | 108/363 [00:07<00:28,  8.80it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:22, 11.03it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:28,  8.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:18, 13.35it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:15, 15.92it/s]
Loading 0:  34%|███▍      | 124/363 [00:08<00:20, 11.67it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:24,  9.51it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:20, 11.68it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:24,  9.39it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:16, 13.80it/s]
Loading 0:  39%|███▊      | 140/363 [00:10<00:13, 16.37it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:19, 11.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:20, 10.85it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:18, 11.53it/s]
Loading 0:  41%|████      | 149/363 [00:11<00:23,  9.24it/s]
Loading 0:  42%|████▏     | 154/363 [00:11<00:15, 13.74it/s]
Loading 0:  44%|████▎     | 158/363 [00:11<00:12, 16.20it/s]
Loading 0:  44%|████▍     | 160/363 [00:11<00:17, 11.82it/s]
Loading 0:  45%|████▍     | 162/363 [00:12<00:21,  9.45it/s]
Loading 0:  45%|████▌     | 165/363 [00:12<00:17, 11.56it/s]
Loading 0:  46%|████▌     | 167/363 [00:12<00:20,  9.34it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:13, 13.71it/s]
Loading 0:  48%|████▊     | 176/363 [00:13<00:11, 16.26it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:16, 11.32it/s]
Loading 0:  50%|████▉     | 181/363 [00:13<00:16, 10.72it/s]
Loading 0:  50%|█████     | 183/363 [00:13<00:15, 11.42it/s]
Loading 0:  51%|█████     | 185/363 [00:14<00:19,  9.06it/s]
Loading 0:  52%|█████▏    | 190/363 [00:14<00:12, 13.74it/s]
Loading 0:  53%|█████▎    | 194/363 [00:14<00:10, 16.36it/s]
Loading 0:  54%|█████▍    | 197/363 [00:15<00:14, 11.61it/s]
Loading 0:  55%|█████▍    | 199/363 [00:15<00:14, 11.13it/s]
Loading 0:  55%|█████▌    | 200/363 [00:30<00:14, 11.13it/s]
Loading 0:  55%|█████▌    | 201/363 [00:30<04:52,  1.80s/it]
Loading 0:  56%|█████▌    | 202/363 [00:30<04:12,  1.57s/it]
Loading 0:  56%|█████▌    | 204/363 [00:30<03:04,  1.16s/it]
Loading 0:  57%|█████▋    | 207/363 [00:31<01:54,  1.36it/s]
Loading 0:  58%|█████▊    | 209/363 [00:31<01:25,  1.81it/s]
Loading 0:  58%|█████▊    | 212/363 [00:31<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 214/363 [00:31<00:47,  3.14it/s]
Loading 0:  60%|█████▉    | 216/363 [00:31<00:40,  3.59it/s]
Loading 0:  60%|██████    | 219/363 [00:32<00:27,  5.20it/s]
Loading 0:  61%|██████    | 221/363 [00:32<00:26,  5.45it/s]
Loading 0:  62%|██████▏   | 226/363 [00:32<00:14,  9.20it/s]
Loading 0:  63%|██████▎   | 230/363 [00:32<00:11, 12.04it/s]
Loading 0:  64%|██████▍   | 233/363 [00:33<00:13,  9.90it/s]
Loading 0:  65%|██████▍   | 235/363 [00:33<00:12,  9.91it/s]
Loading 0:  65%|██████▌   | 237/363 [00:33<00:11, 10.78it/s]
Loading 0:  66%|██████▌   | 239/363 [00:33<00:13,  9.14it/s]
Loading 0:  67%|██████▋   | 244/363 [00:33<00:08, 14.09it/s]
Loading 0:  68%|██████▊   | 248/363 [00:34<00:06, 17.11it/s]
Loading 0:  69%|██████▉   | 251/363 [00:34<00:09, 12.12it/s]
Loading 0:  70%|██████▉   | 253/363 [00:34<00:09, 11.59it/s]
Loading 0:  70%|███████   | 255/363 [00:34<00:08, 12.30it/s]
Loading 0:  71%|███████   | 257/363 [00:35<00:10,  9.92it/s]
Loading 0:  72%|███████▏  | 262/363 [00:35<00:06, 15.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:35<00:05, 18.27it/s]
Loading 0:  74%|███████▍  | 269/363 [00:35<00:07, 12.62it/s]
Loading 0:  75%|███████▍  | 271/363 [00:36<00:07, 11.86it/s]
Loading 0:  75%|███████▌  | 273/363 [00:36<00:07, 12.42it/s]
Loading 0:  76%|███████▌  | 275/363 [00:36<00:08,  9.95it/s]
Loading 0:  77%|███████▋  | 280/363 [00:36<00:05, 15.03it/s]
Loading 0:  78%|███████▊  | 284/363 [00:36<00:04, 17.95it/s]
Loading 0:  79%|███████▉  | 287/363 [00:37<00:06, 12.22it/s]
Loading 0:  80%|███████▉  | 289/363 [00:37<00:06, 11.45it/s]
Loading 0:  80%|████████  | 291/363 [00:37<00:05, 12.16it/s]
Loading 0:  81%|████████  | 293/363 [00:37<00:07,  9.87it/s]
Loading 0:  82%|████████▏ | 298/363 [00:38<00:04, 14.91it/s]
Loading 0:  83%|████████▎ | 302/363 [00:38<00:03, 17.82it/s]
Loading 0:  84%|████████▍ | 305/363 [00:38<00:04, 12.07it/s]
Loading 0:  85%|████████▍ | 307/363 [00:38<00:04, 11.60it/s]
Loading 0:  85%|████████▌ | 309/363 [00:39<00:04, 12.09it/s]
Loading 0:  86%|████████▌ | 311/363 [00:39<00:05,  9.79it/s]
Loading 0:  87%|████████▋ | 316/363 [00:39<00:03, 14.72it/s]
Loading 0:  88%|████████▊ | 320/363 [00:39<00:02, 18.06it/s]
Loading 0:  89%|████████▉ | 323/363 [00:40<00:03, 12.48it/s]
Loading 0:  90%|████████▉ | 325/363 [00:40<00:03, 11.35it/s]
Loading 0:  90%|█████████ | 327/363 [00:40<00:02, 12.02it/s]
Loading 0:  91%|█████████ | 329/363 [00:40<00:03,  9.77it/s]
Loading 0:  92%|█████████▏| 334/363 [00:40<00:01, 15.09it/s]
Loading 0:  93%|█████████▎| 338/363 [00:41<00:01, 18.49it/s]
Loading 0:  94%|█████████▍| 341/363 [00:41<00:01, 12.57it/s]
Loading 0:  94%|█████████▍| 343/363 [00:41<00:01, 12.05it/s]
Loading 0:  95%|█████████▌| 345/363 [00:41<00:01, 12.63it/s]
Loading 0:  96%|█████████▌| 347/363 [00:42<00:01, 10.06it/s]
Loading 0:  97%|█████████▋| 352/363 [00:42<00:00, 15.32it/s]
Loading 0:  98%|█████████▊| 356/363 [00:42<00:00, 18.73it/s]
Loading 0:  99%|█████████▉| 359/363 [00:50<00:02,  1.35it/s]
Loading 0:  99%|█████████▉| 361/363 [00:50<00:01,  1.62it/s]
                                                            
Job rirv938-98p-2ff-rirv938-33106-v1-mkmlizer completed after 269.46s with status: succeeded
Stopping job with name rirv938-98p-2ff-rirv938-33106-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.99s
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 rirv938-98p-2ff-rirv938-33106-v1
Waiting for inference service rirv938-98p-2ff-rirv938-33106-v1 to be ready
Failed to get response for submission jellywibble-sam-montgom_38443_v1: HTTPConnectionPool(host='jellywibble-sam-montgom-38443-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-98p-2ff-rirv938-33106-v1 ready after 130.53849935531616s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6424553394317627s
Received healthy response to inference request in 2.156217098236084s
Received healthy response to inference request in 2.2344868183135986s
Received healthy response to inference request in 1.7962453365325928s
Received healthy response to inference request in 1.9294838905334473s
5 requests
0 failed requests
5th percentile: 1.8228930473327636
10th percentile: 1.8495407581329346
20th percentile: 1.9028361797332765
30th percentile: 1.9748305320739745
40th percentile: 2.0655238151550295
50th percentile: 2.156217098236084
60th percentile: 2.18752498626709
70th percentile: 2.2188328742980956
80th percentile: 2.3160805225372316
90th percentile: 2.479267930984497
95th percentile: 2.5608616352081297
99th percentile: 2.626136598587036
mean time: 2.1517776966094972
Pipeline stage StressChecker completed in 12.07s
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 0.64s
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 0.66s
Shutdown handler de-registered
rirv938-98p-2ff-rirv938_33106_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 2812.17s
Shutdown handler de-registered
rirv938-98p-2ff-rirv938_33106_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-98p-2ff-rirv938_33106_v1 status is now torndown due to DeploymentManager action