rirv938-dotc-grpo-20250_21051

developer_uid: rirv938

submission_id: rirv938-dotc-grpo-20250_21051_v3

model_name: rirv938-dotc-grpo-20250_21051_v3

model_group: rirv938/dotc_grpo_202509

status: torndown

timestamp: 2025-10-06T16:58:17+00:00

num_battles: 5755

num_wins: 2894

celo_rating: 1288.92

family_friendly_score: 0.5614

family_friendly_standard_error: 0.007017549999821875

submission_type: basic

model_repo: rirv938/dotc_grpo_20250929_cp624_sid_mn24b_v2preferwin1sy_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': 0.4396086253760796, 'latency_mean': 2.2746244764328, 'latency_p50': 2.2746152877807617, 'latency_p90': 2.543464469909668}, {'batch_size': 3, 'throughput': 0.919100826963922, 'latency_mean': 3.250446741580963, 'latency_p50': 3.2203919887542725, 'latency_p90': 3.593358874320984}, {'batch_size': 5, 'throughput': 1.2156889930651695, 'latency_mean': 4.087016454935074, 'latency_p50': 4.071468710899353, 'latency_p90': 4.5975508213043215}, {'batch_size': 6, 'throughput': 1.3056140840011465, 'latency_mean': 4.560134155750275, 'latency_p50': 4.552913069725037, 'latency_p90': 5.097602605819702}, {'batch_size': 8, 'throughput': 1.473858531425118, 'latency_mean': 5.400739945173264, 'latency_p50': 5.378684639930725, 'latency_p90': 6.1650962114334105}, {'batch_size': 10, 'throughput': 1.537367729935487, 'latency_mean': 6.43247292637825, 'latency_p50': 6.531918287277222, 'latency_p90': 7.213845872879029}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: rirv938-dotc-grpo-20250_21051_v3

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: rirv938/dotc_grpo_20250929_cp624_sid_mn24b_v2preferwin1sy_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.1

us_pacific_date: 2025-10-06

win_ratio: 0.5028670721112076

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, '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-dotc-grpo-20250-21051-v3-mkmlizer
Waiting for job on rirv938-dotc-grpo-20250-21051-v3-mkmlizer to finish
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║                                                                     ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║                                                                     ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  Version: 0.30.2                                                    ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║                                                                     ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  belonging to:                                                      ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║                                                                     ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ║                                                                     ║
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: Downloaded to shared memory in 96.634s
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: Checking if rirv938/dotc_grpo_20250929_cp624_sid_mn24b_v2preferwin1sy_merged already exists in ChaiML
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp796h8o2b, device:0
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: quantized model in 49.806s
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: Processed model rirv938/dotc_grpo_20250929_cp624_sid_mn24b_v2preferwin1sy_merged in 146.464s
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia/config.json
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia/special_tokens_map.json
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia/tokenizer_config.json
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia/tokenizer.json
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia/flywheel_model.1.safetensors
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dotc-grpo-20250-21051-v3/nvidia/flywheel_model.0.safetensors
rirv938-dotc-grpo-20250-21051-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:14, 24.04it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:17, 19.95it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:13, 25.38it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:21, 16.35it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:20, 17.21it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:17, 19.82it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:19, 16.99it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:13, 24.92it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 21.21it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.47it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:17, 18.10it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 18.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:12, 26.13it/s]
Loading 0:  15%|█▍        | 53/363 [00:02<00:15, 19.50it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:15, 19.99it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:19, 15.68it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:12, 24.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:14, 20.85it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:15, 18.51it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:15, 18.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:15, 18.41it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:11, 24.24it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:12, 21.50it/s]
Loading 0:  25%|██▍       | 90/363 [00:04<00:16, 16.32it/s]
Loading 0:  26%|██▋       | 96/363 [00:04<00:11, 23.48it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:10, 25.27it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:13, 18.60it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.34it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:14, 17.05it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:14, 17.65it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:09, 24.52it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:12, 19.06it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:12, 19.44it/s]
Loading 0:  36%|███▌      | 131/363 [00:06<00:15, 15.38it/s]
Loading 0:  38%|███▊      | 137/363 [00:06<00:10, 22.23it/s]
Loading 0:  39%|███▉      | 141/363 [00:07<00:10, 21.78it/s]
Loading 0:  40%|███▉      | 144/363 [00:07<00:12, 16.90it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:11, 18.34it/s]
Loading 0:  42%|████▏     | 151/363 [00:07<00:11, 18.47it/s]
Loading 0:  43%|████▎     | 156/363 [00:07<00:08, 24.07it/s]
Loading 0:  44%|████▍     | 159/363 [00:08<00:09, 21.64it/s]
Loading 0:  45%|████▍     | 162/363 [00:08<00:12, 16.48it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:10, 18.11it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:10, 18.41it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:07, 25.70it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:09, 19.00it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:09, 19.42it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:11, 15.41it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:07, 23.47it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 20.56it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:09, 18.20it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:08, 18.20it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:15,  1.20s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:38,  1.01it/s]
Loading 0:  57%|█████▋    | 207/363 [00:23<01:39,  1.56it/s]
Loading 0:  58%|█████▊    | 212/363 [00:23<01:00,  2.52it/s]
Loading 0:  59%|█████▉    | 215/363 [00:24<00:47,  3.11it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:36,  4.02it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.78it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.56it/s]
Loading 0:  64%|██████▍   | 232/363 [00:24<00:13,  9.79it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:12, 10.39it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:10, 11.43it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:09, 12.74it/s]
Loading 0:  68%|██████▊   | 247/363 [00:25<00:06, 19.00it/s]
Loading 0:  69%|██████▉   | 251/363 [00:25<00:06, 16.27it/s]
Loading 0:  70%|██████▉   | 254/363 [00:26<00:06, 17.18it/s]
Loading 0:  71%|███████   | 257/363 [00:26<00:07, 14.16it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:04, 22.03it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 19.68it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:05, 17.72it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:05, 17.54it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:04, 17.91it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:03, 25.12it/s]
Loading 0:  79%|███████▉  | 287/363 [00:27<00:03, 19.10it/s]
Loading 0:  80%|███████▉  | 290/363 [00:27<00:03, 19.44it/s]
Loading 0:  81%|████████  | 293/363 [00:28<00:04, 15.28it/s]
Loading 0:  83%|████████▎ | 300/363 [00:28<00:02, 23.34it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 20.50it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:03, 18.28it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 17.98it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 18.33it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:01, 25.62it/s]
Loading 0:  89%|████████▉ | 323/363 [00:29<00:02, 19.31it/s]
Loading 0:  90%|████████▉ | 326/363 [00:29<00:01, 19.12it/s]
Loading 0:  91%|█████████ | 329/363 [00:30<00:02, 15.27it/s]
Loading 0:  92%|█████████▏| 335/363 [00:30<00:01, 22.17it/s]
Loading 0:  93%|█████████▎| 339/363 [00:30<00:01, 21.68it/s]
Loading 0:  94%|█████████▍| 342/363 [00:30<00:01, 16.87it/s]
Loading 0:  95%|█████████▌| 346/363 [00:30<00:00, 18.34it/s]
Loading 0:  96%|█████████▌| 349/363 [00:31<00:00, 18.78it/s]
Loading 0:  98%|█████████▊| 355/363 [00:31<00:00, 25.90it/s]
Loading 0:  99%|█████████▉| 359/363 [00:31<00:00, 14.62it/s]
Loading 0: 100%|█████████▉| 362/363 [00:31<00:00, 14.25it/s]
                                                            
Job rirv938-dotc-grpo-20250-21051-v3-mkmlizer completed after 269.97s with status: succeeded
Stopping job with name rirv938-dotc-grpo-20250-21051-v3-mkmlizer
Pipeline stage MKMLizer completed in 271.68s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.27s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-dotc-grpo-20250-21051-v3
Waiting for inference service rirv938-dotc-grpo-20250-21051-v3 to be ready
Inference service rirv938-dotc-grpo-20250-21051-v3 ready after 70.48161387443542s
Pipeline stage MKMLDeployer completed in 70.97s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.830500841140747s
Received healthy response to inference request in 2.820171594619751s
Received healthy response to inference request in 2.427555799484253s
Received healthy response to inference request in 2.178415536880493s
5 requests
1 failed requests
5th percentile: 2.228243589401245
10th percentile: 2.278071641921997
20th percentile: 2.377727746963501
30th percentile: 2.5060789585113525
40th percentile: 2.6631252765655518
50th percentile: 2.820171594619751
60th percentile: 2.8243032932281493
70th percentile: 2.8284349918365477
80th percentile: 6.2953407287597685
90th percentile: 13.225020503997804
95th percentile: 16.68986039161682
99th percentile: 19.461732301712036
mean time: 6.082268810272216
%s, retrying in %s seconds...
Received healthy response to inference request in 2.2511637210845947s
Received healthy response to inference request in 2.4953200817108154s
Received healthy response to inference request in 2.785278797149658s
Received healthy response to inference request in 2.553739309310913s
Received healthy response to inference request in 2.068364143371582s
5 requests
0 failed requests
5th percentile: 2.1049240589141847
10th percentile: 2.1414839744567873
20th percentile: 2.214603805541992
30th percentile: 2.2999949932098387
40th percentile: 2.397657537460327
50th percentile: 2.4953200817108154
60th percentile: 2.5186877727508543
70th percentile: 2.5420554637908936
80th percentile: 2.600047206878662
90th percentile: 2.69266300201416
95th percentile: 2.738970899581909
99th percentile: 2.776017217636108
mean time: 2.430773210525513
Pipeline stage StressChecker completed in 45.17s
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 0.68s
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 1.67s
Shutdown handler de-registered
rirv938-dotc-grpo-20250_21051_v3 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-dotc-grpo-20250-21051-v3-profiler
Waiting for inference service rirv938-dotc-grpo-20250-21051-v3-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 3010.03s
Shutdown handler de-registered
rirv938-dotc-grpo-20250_21051_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-dotc-grpo-20250_21051_v3 status is now torndown due to DeploymentManager action