chaiml-exp-grpo-cp312-_36146

developer_uid: NischayDnk

submission_id: chaiml-exp-grpo-cp312-_36146_v31

model_name: chaiml-exp-grpo-cp312-_36146_v31

model_group: ChaiML/exp_grpo_cp312_96

status: torndown

timestamp: 2025-09-11T22:16:36+00:00

num_battles: 5416

num_wins: 3015

celo_rating: 1302.93

family_friendly_score: 0.5186

family_friendly_standard_error: 0.007066173504804421

submission_type: basic

model_repo: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 7

max_input_tokens: 1280

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.42809244282246073, 'latency_mean': 2.3358388340473173, 'latency_p50': 2.337301254272461, 'latency_p90': 2.594454455375671}, {'batch_size': 3, 'throughput': 0.8599488721384466, 'latency_mean': 3.4798843812942506, 'latency_p50': 3.484443187713623, 'latency_p90': 3.8194077014923096}, {'batch_size': 5, 'throughput': 1.1293957276823048, 'latency_mean': 4.40700854420662, 'latency_p50': 4.356012344360352, 'latency_p90': 5.106326651573181}, {'batch_size': 6, 'throughput': 1.201390975291532, 'latency_mean': 4.953342760801315, 'latency_p50': 4.9495790004730225, 'latency_p90': 5.633728098869324}, {'batch_size': 8, 'throughput': 1.324208673006665, 'latency_mean': 5.989614638090134, 'latency_p50': 6.027601957321167, 'latency_p90': 6.832726001739502}, {'batch_size': 10, 'throughput': 1.4012362959443112, 'latency_mean': 7.076765556335449, 'latency_p50': 7.068050980567932, 'latency_p90': 8.11681809425354}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-exp-grpo-cp312-_36146_v31

is_internal_developer: False

language_model: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 0.94

us_pacific_date: 2025-09-11

win_ratio: 0.5566838995568686

generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1280, 'best_of': 7, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", '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-exp-grpo-cp312-36146-v31-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v31-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: Downloaded to shared memory in 110.605s
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpub8640_w, device:0
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: quantized model in 49.743s
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 160.348s
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia/config.json
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia/tokenizer.json
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v31/nvidia/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v31-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:15, 23.93it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:17, 19.80it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.43it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:21, 16.04it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:22, 15.38it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:17, 20.11it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:19, 17.39it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:13, 25.18it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 20.91it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.23it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:17, 18.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:02<00:17, 18.26it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:13, 24.23it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.73it/s]
Loading 0:  15%|█▍        | 54/363 [00:02<00:19, 16.16it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:16, 18.09it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:16, 18.23it/s]
Loading 0:  18%|█▊        | 66/363 [00:03<00:12, 24.08it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 21.78it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:17, 16.32it/s]
Loading 0:  21%|██        | 76/363 [00:03<00:15, 18.00it/s]
Loading 0:  22%|██▏       | 79/363 [00:04<00:15, 18.28it/s]
Loading 0:  23%|██▎       | 85/363 [00:04<00:10, 25.63it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:14, 19.28it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 19.22it/s]
Loading 0:  27%|██▋       | 98/363 [00:04<00:10, 26.22it/s]
Loading 0:  28%|██▊       | 102/363 [00:05<00:10, 23.79it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:13, 18.93it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.19it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:14, 17.03it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:14, 17.49it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:09, 24.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:12, 18.80it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:12, 19.18it/s]
Loading 0:  36%|███▌      | 131/363 [00:06<00:15, 14.86it/s]
Loading 0:  38%|███▊      | 137/363 [00:06<00:10, 21.40it/s]
Loading 0:  39%|███▉      | 141/363 [00:07<00:10, 21.08it/s]
Loading 0:  40%|███▉      | 144/363 [00:07<00:13, 16.48it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:11, 18.10it/s]
Loading 0:  42%|████▏     | 151/363 [00:07<00:11, 18.28it/s]
Loading 0:  43%|████▎     | 156/363 [00:07<00:08, 23.91it/s]
Loading 0:  44%|████▍     | 159/363 [00:08<00:09, 21.62it/s]
Loading 0:  45%|████▍     | 162/363 [00:08<00:12, 16.25it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:10, 17.96it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:10, 18.09it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:07, 25.37it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:09, 18.95it/s]
Loading 0:  50%|█████     | 182/363 [00:09<00:09, 19.33it/s]
Loading 0:  51%|█████     | 185/363 [00:09<00:11, 15.23it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:07, 23.31it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:08, 20.35it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:09, 17.89it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:09, 17.89it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:14,  1.20s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:38,  1.01it/s]
Loading 0:  57%|█████▋    | 207/363 [00:23<01:39,  1.57it/s]
Loading 0:  58%|█████▊    | 212/363 [00:23<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,  4.76it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.54it/s]
Loading 0:  64%|██████▍   | 232/363 [00:25<00:13,  9.76it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:12, 10.32it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:10, 11.49it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:09, 12.71it/s]
Loading 0:  67%|██████▋   | 245/363 [00:25<00:07, 16.28it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:06, 17.45it/s]
Loading 0:  69%|██████▉   | 252/363 [00:26<00:07, 14.44it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:06, 16.46it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:06, 16.76it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:04, 22.03it/s]
Loading 0:  74%|███████▎  | 267/363 [00:26<00:04, 20.35it/s]
Loading 0:  74%|███████▍  | 270/363 [00:27<00:05, 15.75it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:05, 17.56it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:04, 17.93it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 23.59it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 21.04it/s]
Loading 0:  79%|███████▉  | 288/363 [00:28<00:04, 16.00it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:03, 17.76it/s]
Loading 0:  81%|████████▏ | 295/363 [00:28<00:03, 17.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:28<00:02, 21.54it/s]
Loading 0:  83%|████████▎ | 303/363 [00:28<00:02, 20.28it/s]
Loading 0:  84%|████████▍ | 306/363 [00:29<00:03, 15.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 17.75it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 18.22it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:01, 25.73it/s]
Loading 0:  89%|████████▉ | 323/363 [00:29<00:02, 19.40it/s]
Loading 0:  90%|████████▉ | 326/363 [00:30<00:01, 19.64it/s]
Loading 0:  91%|█████████ | 329/363 [00:30<00:02, 15.59it/s]
Loading 0:  92%|█████████▏| 335/363 [00:30<00:01, 22.29it/s]
Loading 0:  93%|█████████▎| 339/363 [00:30<00:01, 21.66it/s]
Loading 0:  94%|█████████▍| 342/363 [00:30<00:01, 16.70it/s]
Loading 0:  95%|█████████▌| 346/363 [00:31<00:00, 18.30it/s]
Loading 0:  96%|█████████▌| 349/363 [00:31<00:00, 18.50it/s]
Loading 0:  98%|█████████▊| 354/363 [00:31<00:00, 24.04it/s]
Loading 0:  98%|█████████▊| 357/363 [00:31<00:00, 13.77it/s]
Loading 0:  99%|█████████▉| 360/363 [00:32<00:00, 14.72it/s]
Loading 0: 100%|██████████| 363/363 [00:32<00:00, 16.02it/s]
                                                            
Job chaiml-exp-grpo-cp312-36146-v31-mkmlizer completed after 235.85s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v31-mkmlizer
Pipeline stage MKMLizer completed in 236.39s
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 chaiml-exp-grpo-cp312-36146-v31
Waiting for inference service chaiml-exp-grpo-cp312-36146-v31 to be ready
Inference service chaiml-exp-grpo-cp312-36146-v31 ready after 60.2599880695343s
Pipeline stage MKMLDeployer completed in 60.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.60866117477417s
Received healthy response to inference request in 2.573361873626709s
Received healthy response to inference request in 2.0973033905029297s
Received healthy response to inference request in 2.182931900024414s
Received healthy response to inference request in 2.1611273288726807s
5 requests
0 failed requests
5th percentile: 2.11006817817688
10th percentile: 2.1228329658508303
20th percentile: 2.1483625411987304
30th percentile: 2.1654882431030273
40th percentile: 2.1742100715637207
50th percentile: 2.182931900024414
60th percentile: 2.339103889465332
70th percentile: 2.49527587890625
80th percentile: 2.580421733856201
90th percentile: 2.5945414543151855
95th percentile: 2.601601314544678
99th percentile: 2.6072492027282714
mean time: 2.3246771335601806
Pipeline stage StressChecker completed in 12.91s
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 0.65s
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
chaiml-exp-grpo-cp312-_36146_v31 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v31-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v31-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 2893.05s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v31 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-_36146_v31 status is now torndown due to DeploymentManager action