developer_uid: rirv938
submission_id: chaiml-dotc-r2-grpo-202_36226_v1
model_name: chaiml-dotc-r2-grpo-202_36226_v1
model_group: ChaiML/dotc_r2_grpo_2025
status: torndown
timestamp: 2025-10-21T23:57:18+00:00
num_battles: 5490
num_wins: 2970
celo_rating: 1296.09
family_friendly_score: 0.5492
family_friendly_standard_error: 0.007036751523252757
submission_type: basic
model_repo: ChaiML/dotc_r2_grpo_20250929_hars_base_model
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': 0.4446287269023836, 'latency_mean': 2.24893865942955, 'latency_p50': 2.2329061031341553, 'latency_p90': 2.5059216260910033}, {'batch_size': 3, 'throughput': 0.9327809650932782, 'latency_mean': 3.203958423137665, 'latency_p50': 3.211747407913208, 'latency_p90': 3.597802019119263}, {'batch_size': 5, 'throughput': 1.2344815246041554, 'latency_mean': 4.027036201953888, 'latency_p50': 4.064178109169006, 'latency_p90': 4.498672223091125}, {'batch_size': 6, 'throughput': 1.3387543592802134, 'latency_mean': 4.43342185139656, 'latency_p50': 4.471303224563599, 'latency_p90': 4.944507050514221}, {'batch_size': 8, 'throughput': 1.5047608731305022, 'latency_mean': 5.266416382789612, 'latency_p50': 5.331494927406311, 'latency_p90': 5.937021636962891}, {'batch_size': 10, 'throughput': 1.6001058389098883, 'latency_mean': 6.199500181674957, 'latency_p50': 6.20123028755188, 'latency_p90': 7.073600721359253}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-dotc-r2-grpo-202_36226_v1
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/dotc_r2_grpo_20250929_hars_base_model
model_size: 24B
ranking_group: single
throughput_3p7s: 1.14
us_pacific_date: 2025-10-21
win_ratio: 0.5409836065573771
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, '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 chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer
Waiting for job on chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer to finish
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║                                                                     ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║                                                                     ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║                                                                     ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║                                                                     ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ║                                                                     ║
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: Downloaded to shared memory in 107.646s
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: Checking if ChaiML/dotc_r2_grpo_20250929_hars_base_model already exists in ChaiML
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr4whc5p9, device:0
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: quantized model in 50.308s
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: Processed model ChaiML/dotc_r2_grpo_20250929_hars_base_model in 157.955s
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-dotc-r2-grpo-202-36226-v1/nvidia
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-dotc-r2-grpo-202-36226-v1/nvidia/config.json
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-dotc-r2-grpo-202-36226-v1/nvidia/special_tokens_map.json
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-dotc-r2-grpo-202-36226-v1/nvidia/tokenizer_config.json
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-dotc-r2-grpo-202-36226-v1/nvidia/flywheel_model.1.safetensors
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-dotc-r2-grpo-202-36226-v1/nvidia/flywheel_model.0.safetensors
chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:14, 24.12it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 19.08it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.53it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:22, 15.32it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:23, 14.84it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:17, 19.32it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:20, 16.83it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:14, 22.63it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:15, 20.80it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:20, 16.03it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:18, 17.61it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 17.84it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:13, 23.25it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:15, 20.37it/s]
Loading 0:  15%|█▍        | 54/363 [00:02<00:19, 15.83it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:17, 17.53it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:17, 17.58it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:12, 23.00it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:14, 20.29it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:18, 15.70it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:16, 17.49it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:16, 17.74it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:11, 23.49it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:13, 20.93it/s]
Loading 0:  25%|██▍       | 90/363 [00:04<00:17, 16.03it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:10, 25.04it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:14, 18.14it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.01it/s]
Loading 0:  31%|███       | 112/363 [00:06<00:14, 16.73it/s]
Loading 0:  32%|███▏      | 115/363 [00:06<00:14, 16.94it/s]
Loading 0:  33%|███▎      | 120/363 [00:06<00:10, 22.13it/s]
Loading 0:  34%|███▍      | 123/363 [00:06<00:11, 20.33it/s]
Loading 0:  35%|███▍      | 126/363 [00:06<00:14, 15.82it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:13, 17.57it/s]
Loading 0:  37%|███▋      | 133/363 [00:07<00:13, 17.44it/s]
Loading 0:  38%|███▊      | 139/363 [00:07<00:09, 24.56it/s]
Loading 0:  39%|███▉      | 143/363 [00:07<00:11, 18.82it/s]
Loading 0:  40%|████      | 146/363 [00:07<00:11, 19.11it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:14, 15.16it/s]
Loading 0:  43%|████▎     | 156/363 [00:08<00:08, 23.28it/s]
Loading 0:  44%|████▍     | 160/363 [00:08<00:09, 20.45it/s]
Loading 0:  45%|████▍     | 163/363 [00:08<00:10, 18.22it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:11, 17.85it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:10, 18.15it/s]
Loading 0:  48%|████▊     | 175/363 [00:09<00:07, 25.45it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:09, 18.93it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:09, 19.36it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:11, 15.08it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:07, 21.74it/s]
Loading 0:  54%|█████▎    | 195/363 [00:10<00:08, 20.96it/s]
Loading 0:  55%|█████▍    | 198/363 [00:10<00:10, 15.40it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:10, 15.40it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:04,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 207/363 [00:24<01:36,  1.61it/s]
Loading 0:  58%|█████▊    | 212/363 [00:24<00:58,  2.56it/s]
Loading 0:  59%|█████▉    | 215/363 [00:24<00:46,  3.16it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:35,  4.06it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.80it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:15,  8.58it/s]
Loading 0:  64%|██████▍   | 232/363 [00:25<00:13,  9.80it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:12, 10.40it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:10, 11.50it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:09, 12.90it/s]
Loading 0:  68%|██████▊   | 247/363 [00:25<00:06, 19.23it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:06, 16.34it/s]
Loading 0:  70%|██████▉   | 254/363 [00:26<00:06, 17.29it/s]
Loading 0:  71%|███████   | 257/363 [00:26<00:07, 14.31it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:04, 22.25it/s]
Loading 0:  74%|███████▍  | 268/363 [00:27<00:04, 19.96it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:05, 17.84it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:05, 17.68it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:04, 18.04it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:03, 25.31it/s]
Loading 0:  79%|███████▉  | 287/363 [00:28<00:04, 18.87it/s]
Loading 0:  80%|███████▉  | 290/363 [00:28<00:03, 19.13it/s]
Loading 0:  81%|████████  | 293/363 [00:28<00:04, 14.81it/s]
Loading 0:  83%|████████▎ | 300/363 [00:28<00:02, 22.68it/s]
Loading 0:  84%|████████▎ | 304/363 [00:29<00:02, 19.88it/s]
Loading 0:  85%|████████▍ | 307/363 [00:29<00:03, 17.52it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:03, 17.13it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 17.68it/s]
Loading 0:  88%|████████▊ | 318/363 [00:29<00:01, 23.41it/s]
Loading 0:  88%|████████▊ | 321/363 [00:29<00:01, 21.30it/s]
Loading 0:  89%|████████▉ | 324/363 [00:30<00:02, 16.03it/s]
Loading 0:  90%|█████████ | 328/363 [00:30<00:01, 17.79it/s]
Loading 0:  91%|█████████ | 331/363 [00:30<00:01, 18.33it/s]
Loading 0:  93%|█████████▎| 337/363 [00:30<00:01, 25.76it/s]
Loading 0:  94%|█████████▍| 341/363 [00:30<00:01, 19.48it/s]
Loading 0:  95%|█████████▍| 344/363 [00:31<00:01, 18.95it/s]
Loading 0:  96%|█████████▌| 347/363 [00:31<00:01, 14.97it/s]
Loading 0:  98%|█████████▊| 354/363 [00:31<00:00, 22.98it/s]
Loading 0:  99%|█████████▊| 358/363 [00:32<00:00, 15.09it/s]
Loading 0:  99%|█████████▉| 361/363 [00:32<00:00, 13.38it/s]
                                                            

Job chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer completed after 255.78s with status: succeeded
Stopping job with name chaiml-dotc-r2-grpo-202-36226-v1-mkmlizer
Pipeline stage MKMLizer completed in 256.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.50s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-dotc-r2-grpo-202-36226-v1
Waiting for inference service chaiml-dotc-r2-grpo-202-36226-v1 to be ready
Inference service chaiml-dotc-r2-grpo-202-36226-v1 ready after 512.5350966453552s
Pipeline stage MKMLDeployer completed in 513.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6481173038482666s
Received healthy response to inference request in 3.023005962371826s
Received healthy response to inference request in 2.1441650390625s
Received healthy response to inference request in 2.0371241569519043s
Received healthy response to inference request in 2.1686594486236572s
5 requests
0 failed requests
5th percentile: 2.0585323333740235
10th percentile: 2.0799405097961428
20th percentile: 2.1227568626403808
30th percentile: 2.1490639209747315
40th percentile: 2.158861684799194
50th percentile: 2.1686594486236572
60th percentile: 2.360442590713501
70th percentile: 2.5522257328033446
80th percentile: 2.7230950355529786
90th percentile: 2.873050498962402
95th percentile: 2.948028230667114
99th percentile: 3.0080104160308836
mean time: 2.404214382171631
Pipeline stage StressChecker completed in 13.41s
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 0.63s
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
chaiml-dotc-r2-grpo-202_36226_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 2929.15s
Shutdown handler de-registered
chaiml-dotc-r2-grpo-202_36226_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-dotc-r2-grpo-202_36226_v1 status is now torndown due to DeploymentManager action