chaiml-exp-grpo-cp312-_36146

developer_uid: chai_backend_admin

submission_id: chaiml-exp-grpo-cp312-_36146_v10

model_name: chaiml-exp-grpo-cp312-_36146_v10

model_group: ChaiML/exp_grpo_cp312_96

status: torndown

timestamp: 2025-07-01T17:29:06+00:00

num_battles: 8295

num_wins: 4375

celo_rating: 1310.61

family_friendly_score: 0.5326

family_friendly_standard_error: 0.0070560221088089

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: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.516788973396942, 'latency_mean': 1.9349047589302062, 'latency_p50': 1.9533189535140991, 'latency_p90': 2.1276721239089964}, {'batch_size': 3, 'throughput': 1.0478185241302673, 'latency_mean': 2.855246720314026, 'latency_p50': 2.855763554573059, 'latency_p90': 3.1301820516586303}, {'batch_size': 5, 'throughput': 1.3329093522734563, 'latency_mean': 3.7407590663433075, 'latency_p50': 3.7480621337890625, 'latency_p90': 4.15589849948883}, {'batch_size': 6, 'throughput': 1.4401151074670668, 'latency_mean': 4.132072026729584, 'latency_p50': 4.154402136802673, 'latency_p90': 4.600254964828491}, {'batch_size': 8, 'throughput': 1.5746231492996081, 'latency_mean': 5.036430459022522, 'latency_p50': 4.991874814033508, 'latency_p90': 5.659867286682129}, {'batch_size': 10, 'throughput': 1.6754267110693402, 'latency_mean': 5.913742733001709, 'latency_p50': 5.828285336494446, 'latency_p90': 6.716793465614319}]

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

display_name: chaiml-exp-grpo-cp312-_36146_v10

is_internal_developer: True

language_model: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-01

win_ratio: 0.5274261603375527

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': ['###', '</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-exp-grpo-cp312-36146-v10-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v10-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: Downloaded to shared memory in 127.883s
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5cvzoy6f, device:0
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: quantized model in 55.001s
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 182.885s
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10/config.json
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10/tokenizer.json
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v10/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-36146-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.32it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.37it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.72it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.20it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:24, 13.90it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.65it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 14.12it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:16, 20.27it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 23.69it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:19, 16.44it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.88it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:23, 13.42it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.76it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.28it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.94it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.79it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:22, 13.33it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.66it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 22.06it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:20, 14.35it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.25it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:19, 14.88it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.39it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.78it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.86it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.33it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 20.19it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.40it/s]
Loading 0:  29%|██▊       | 104/363 [00:05<00:14, 18.20it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 14.13it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.60it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.53it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.27it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.43it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.22it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.47it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.34it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 13.07it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:12, 18.30it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.63it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 15.75it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.67it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:16, 13.02it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.83it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.84it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.35it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.29it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.18it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.35it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.83it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 16.13it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.94it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.46it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.65it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.34it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.61it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.47it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:36,  1.35s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:20,  1.11it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:42,  1.49it/s]
Loading 0:  59%|█████▊    | 213/363 [00:26<01:16,  1.96it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:58,  2.52it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:42,  3.42it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:32,  4.32it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:21,  6.32it/s]
Loading 0:  63%|██████▎   | 230/363 [00:27<00:15,  8.72it/s]
Loading 0:  64%|██████▍   | 233/363 [00:27<00:14,  8.72it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.23it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:12,  9.71it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:08, 14.13it/s]
Loading 0:  68%|██████▊   | 248/363 [00:28<00:06, 17.46it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:08, 13.94it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:07, 14.90it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.69it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:05, 17.95it/s]
Loading 0:  73%|███████▎  | 266/363 [00:29<00:04, 21.46it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:06, 14.14it/s]
Loading 0:  75%|███████▌  | 273/363 [00:30<00:05, 16.12it/s]
Loading 0:  76%|███████▌  | 276/363 [00:30<00:05, 14.62it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:04, 18.20it/s]
Loading 0:  78%|███████▊  | 284/363 [00:30<00:03, 21.72it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.78it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.54it/s]
Loading 0:  81%|████████  | 293/363 [00:31<00:05, 13.16it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:03, 18.31it/s]
Loading 0:  83%|████████▎ | 302/363 [00:31<00:02, 21.45it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 15.78it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.58it/s]
Loading 0:  86%|████████▌ | 311/363 [00:32<00:03, 13.43it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 18.58it/s]
Loading 0:  88%|████████▊ | 320/363 [00:32<00:01, 22.10it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 16.05it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 16.88it/s]
Loading 0:  91%|█████████ | 329/363 [00:33<00:02, 13.58it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 17.68it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 21.19it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 15.73it/s]
Loading 0:  95%|█████████▍| 344/363 [00:34<00:01, 16.57it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:01, 13.30it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.51it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.93it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 11.91it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 11.97it/s]
                                                            
Job chaiml-exp-grpo-cp312-36146-v10-mkmlizer completed after 219.68s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v10-mkmlizer
Pipeline stage MKMLizer completed in 220.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v10
Waiting for inference service chaiml-exp-grpo-cp312-36146-v10 to be ready
Failed to get response for submission chaiml-exp-grpo-cp312-9_36146_v9: ('http://guanaco-model-mesh.k2.chaiverse.com/models/chaiml-exp-grpo-cp312-9_36146_v9/predict', '')
Inference service chaiml-exp-grpo-cp312-36146-v10 ready after 301.0976972579956s
Pipeline stage MKMLDeployer completed in 301.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9265382289886475s
Received healthy response to inference request in 2.2961981296539307s
Received healthy response to inference request in 2.317763090133667s
Received healthy response to inference request in 2.4716217517852783s
Received healthy response to inference request in 2.093024730682373s
5 requests
0 failed requests
5th percentile: 2.1336594104766844
10th percentile: 2.174294090270996
20th percentile: 2.2555634498596193
30th percentile: 2.300511121749878
40th percentile: 2.3091371059417725
50th percentile: 2.317763090133667
60th percentile: 2.3793065547943115
70th percentile: 2.440850019454956
80th percentile: 2.562605047225952
90th percentile: 2.7445716381073
95th percentile: 2.8355549335479737
99th percentile: 2.9083415699005126
mean time: 2.4210291862487794
Pipeline stage StressChecker completed in 13.82s
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 0.69s
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 0.69s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v10 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v10-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v10-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5759.56s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v10 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-_36146_v10 status is now torndown due to DeploymentManager action