rirv938-dotc-r2-grpo-20_50271

developer_uid: rirv938

submission_id: rirv938-dotc-r2-grpo-20_50271_v2

model_name: rirv938-dotc-r2-grpo-20_50271_v2

model_group: rirv938/dotc_r2_grpo_202

status: torndown

timestamp: 2025-10-06T16:58:21+00:00

num_battles: 5894

num_wins: 3059

celo_rating: 1300.02

family_friendly_score: 0.5472

family_friendly_standard_error: 0.0070394908906823645

submission_type: basic

model_repo: rirv938/dotc_r2_grpo_20250929_cp468_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': 0.4375599076011812, 'latency_mean': 2.2852756440639497, 'latency_p50': 2.2958394289016724, 'latency_p90': 2.538358449935913}, {'batch_size': 3, 'throughput': 0.9200551125714149, 'latency_mean': 3.2435858881473543, 'latency_p50': 3.243560552597046, 'latency_p90': 3.603393483161926}, {'batch_size': 5, 'throughput': 1.215604971880746, 'latency_mean': 4.084377474784851, 'latency_p50': 4.088942885398865, 'latency_p90': 4.577005434036255}, {'batch_size': 6, 'throughput': 1.3289860873068091, 'latency_mean': 4.486704406738281, 'latency_p50': 4.463705658912659, 'latency_p90': 5.111554718017578}, {'batch_size': 8, 'throughput': 1.4808075156288496, 'latency_mean': 5.362927708625794, 'latency_p50': 5.322932720184326, 'latency_p90': 6.086224603652954}, {'batch_size': 10, 'throughput': 1.591218074946907, 'latency_mean': 6.214945892095566, 'latency_p50': 6.207841634750366, 'latency_p90': 7.326030445098877}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: rirv938-dotc-r2-grpo-20_50271_v2

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: rirv938/dotc_r2_grpo_20250929_cp468_sid_mn24b_v2preferwin1sy_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.1

us_pacific_date: 2025-10-06

win_ratio: 0.5190023752969121

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': ['\n', 'You:', '</s>', '###'], '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-r2-grpo-20-50271-v2-mkmlizer
Waiting for job on rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer to finish
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ║                                                                     ║
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: Downloaded to shared memory in 99.091s
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: Checking if rirv938/dotc_r2_grpo_20250929_cp468_sid_mn24b_v2preferwin1sy_merged already exists in ChaiML
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpidxuy3s7, device:0
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: quantized model in 49.604s
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: Processed model rirv938/dotc_r2_grpo_20250929_cp468_sid_mn24b_v2preferwin1sy_merged in 148.717s
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia/config.json
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia/special_tokens_map.json
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia/tokenizer_config.json
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia/tokenizer.json
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia/flywheel_model.1.safetensors
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-dotc-r2-grpo-20-50271-v2/nvidia/flywheel_model.0.safetensors
rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:14, 23.94it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 19.29it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.36it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:21, 16.41it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:22, 15.68it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:16, 20.32it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:18, 18.09it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:15, 22.33it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:14, 23.16it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:19, 17.17it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:17, 18.58it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 18.66it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:12, 25.89it/s]
Loading 0:  15%|█▍        | 53/363 [00:02<00:15, 19.49it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:15, 19.74it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:19, 15.59it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:12, 23.75it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:14, 20.48it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:16, 18.11it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:16, 17.66it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:15, 18.05it/s]
Loading 0:  23%|██▎       | 85/363 [00:04<00:11, 25.21it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:14, 19.02it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 19.21it/s]
Loading 0:  27%|██▋       | 98/363 [00:04<00:10, 25.99it/s]
Loading 0:  28%|██▊       | 102/363 [00:05<00:11, 23.65it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:13, 19.47it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.26it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:14, 16.98it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:14, 17.18it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:09, 24.24it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:12, 18.76it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:12, 19.26it/s]
Loading 0:  36%|███▌      | 131/363 [00:06<00:15, 15.14it/s]
Loading 0:  38%|███▊      | 138/363 [00:06<00:09, 23.23it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:11, 19.98it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:12, 17.64it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:12, 17.39it/s]
Loading 0:  42%|████▏     | 151/363 [00:07<00:12, 17.58it/s]
Loading 0:  43%|████▎     | 156/363 [00:07<00:09, 22.79it/s]
Loading 0:  44%|████▍     | 159/363 [00:08<00:09, 20.68it/s]
Loading 0:  45%|████▍     | 162/363 [00:08<00:12, 16.04it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:11, 17.74it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:10, 18.25it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:07, 25.61it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:09, 19.25it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:09, 19.65it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:12, 14.72it/s]
Loading 0:  53%|█████▎    | 191/363 [00:09<00:08, 21.42it/s]
Loading 0:  54%|█████▎    | 195/363 [00:09<00:08, 20.60it/s]
Loading 0:  55%|█████▍    | 198/363 [00:10<00:09, 16.52it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:09, 16.52it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:08,  1.16s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:35,  1.03it/s]
Loading 0:  57%|█████▋    | 207/363 [00:24<01:38,  1.58it/s]
Loading 0:  58%|█████▊    | 212/363 [00:24<01:00,  2.51it/s]
Loading 0:  59%|█████▉    | 215/363 [00:24<00:47,  3.10it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:36,  4.00it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.73it/s]
Loading 0:  62%|██████▏   | 226/363 [00:25<00:18,  7.34it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13,  9.74it/s]
Loading 0:  64%|██████▍   | 234/363 [00:25<00:13,  9.68it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:10, 11.76it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:09, 12.95it/s]
Loading 0:  68%|██████▊   | 246/363 [00:26<00:06, 17.63it/s]
Loading 0:  69%|██████▊   | 249/363 [00:26<00:06, 17.20it/s]
Loading 0:  69%|██████▉   | 252/363 [00:26<00:07, 14.34it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:06, 16.20it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:06, 16.69it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:04, 22.29it/s]
Loading 0:  74%|███████▎  | 267/363 [00:27<00:04, 20.42it/s]
Loading 0:  74%|███████▍  | 270/363 [00:27<00:05, 15.86it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:05, 17.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:04, 18.02it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 23.89it/s]
Loading 0:  79%|███████▊  | 285/363 [00:28<00:03, 21.33it/s]
Loading 0:  79%|███████▉  | 288/363 [00:28<00:04, 16.01it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:03, 17.75it/s]
Loading 0:  81%|████████▏ | 295/363 [00:28<00:03, 17.81it/s]
Loading 0:  83%|████████▎ | 300/363 [00:28<00:02, 23.58it/s]
Loading 0:  83%|████████▎ | 303/363 [00:29<00:02, 21.08it/s]
Loading 0:  84%|████████▍ | 306/363 [00:29<00:03, 16.15it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 17.79it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 18.28it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:01, 25.56it/s]
Loading 0:  89%|████████▉ | 323/363 [00:30<00:02, 19.17it/s]
Loading 0:  90%|████████▉ | 326/363 [00:30<00:01, 19.60it/s]
Loading 0:  91%|█████████ | 329/363 [00:30<00:02, 15.47it/s]
Loading 0:  92%|█████████▏| 334/363 [00:30<00:01, 20.70it/s]
Loading 0:  93%|█████████▎| 339/363 [00:30<00:01, 21.48it/s]
Loading 0:  94%|█████████▍| 342/363 [00:31<00:01, 16.69it/s]
Loading 0:  95%|█████████▌| 346/363 [00:31<00:00, 18.01it/s]
Loading 0:  96%|█████████▌| 349/363 [00:31<00:00, 18.43it/s]
Loading 0:  98%|█████████▊| 355/363 [00:31<00:00, 25.45it/s]
Loading 0:  99%|█████████▉| 359/363 [00:32<00:00, 14.31it/s]
Loading 0: 100%|█████████▉| 362/363 [00:32<00:00, 13.94it/s]
                                                            
Job rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer completed after 269.51s with status: succeeded
Stopping job with name rirv938-dotc-r2-grpo-20-50271-v2-mkmlizer
Pipeline stage MKMLizer completed in 270.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-dotc-r2-grpo-20-50271-v2
Waiting for inference service rirv938-dotc-r2-grpo-20-50271-v2 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rirv938-dotc-r2-grpo-20-50271-v2 ready after 60.878666162490845s
Pipeline stage MKMLDeployer completed in 62.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2800183296203613s
Received healthy response to inference request in 2.0970256328582764s
Received healthy response to inference request in 1.84128999710083s
Received healthy response to inference request in 2.7656054496765137s
Received healthy response to inference request in 2.2410876750946045s
5 requests
0 failed requests
5th percentile: 1.8924371242523192
10th percentile: 1.9435842514038086
20th percentile: 2.045878505706787
30th percentile: 2.125838041305542
40th percentile: 2.1834628582000732
50th percentile: 2.2410876750946045
60th percentile: 2.2566599369049074
70th percentile: 2.27223219871521
80th percentile: 2.377135753631592
90th percentile: 2.5713706016540527
95th percentile: 2.668488025665283
99th percentile: 2.7461819648742676
mean time: 2.245005416870117
Pipeline stage StressChecker completed in 12.69s
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 1.02s
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 0.71s
Shutdown handler de-registered
rirv938-dotc-r2-grpo-20_50271_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 0.09s
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-dotc-r2-grpo-20-50271-v2-profiler
Waiting for inference service rirv938-dotc-r2-grpo-20-50271-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 2969.31s
Shutdown handler de-registered
rirv938-dotc-r2-grpo-20_50271_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-dotc-r2-grpo-20_50271_v2 status is now torndown due to DeploymentManager action