chaiml-exp-grpo-cp312-9_36146

developer_uid: richhx

submission_id: chaiml-exp-grpo-cp312-9_36146_v6

model_name: chaiml-exp-grpo-cp312-9_36146_v6

model_group: ChaiML/exp_grpo_cp312_96

status: torndown

timestamp: 2025-06-20T23:00:50+00:00

num_battles: 7515

num_wins: 3997

celo_rating: 1309.78

family_friendly_score: 0.527

family_friendly_standard_error: 0.00706075066830716

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': 0.5155938860693622, 'latency_mean': 1.939406569004059, 'latency_p50': 1.9496279954910278, 'latency_p90': 2.145363116264343}, {'batch_size': 3, 'throughput': 1.0592194902544083, 'latency_mean': 2.8187156760692598, 'latency_p50': 2.800226330757141, 'latency_p90': 3.1169842958450316}, {'batch_size': 5, 'throughput': 1.3323634532065398, 'latency_mean': 3.7333092069625855, 'latency_p50': 3.7252683639526367, 'latency_p90': 4.211689496040345}, {'batch_size': 6, 'throughput': 1.4046941623735283, 'latency_mean': 4.237655864953995, 'latency_p50': 4.272393465042114, 'latency_p90': 4.773106551170349}, {'batch_size': 8, 'throughput': 1.5516258946119776, 'latency_mean': 5.111622000932694, 'latency_p50': 5.105599045753479, 'latency_p90': 5.761911296844482}, {'batch_size': 10, 'throughput': 1.6616248880499969, 'latency_mean': 5.968604601621628, 'latency_p50': 5.938504457473755, 'latency_p90': 6.736632180213928}]

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

display_name: chaiml-exp-grpo-cp312-9_36146_v6

ineligible_reason: num_battles<10000

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: 2025-06-20

win_ratio: 0.5318695941450432

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': ['You:', '\n', '###', '</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 chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer to finish
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: Downloaded to shared memory in 117.509s
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9mhyl8w2, device:0
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: quantized model in 59.550s
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 177.059s
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-9-36146-v6/config.json
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-9-36146-v6/special_tokens_map.json
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-9-36146-v6/tokenizer_config.json
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-9-36146-v6/tokenizer.json
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-9-36146-v6/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.28it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.29it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.05it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 13.38it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.81it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.51it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.71it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.66it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.84it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.14it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 13.73it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:25, 12.67it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:24, 13.38it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:29, 10.78it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.38it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:23, 13.33it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:24, 12.76it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.53it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:28, 10.80it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 16.40it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 19.77it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.60it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 12.80it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:21, 13.57it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:26, 10.88it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:17, 16.31it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 19.45it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:20, 13.58it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:21, 12.74it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:16, 16.38it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:13, 19.48it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 17.60it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:19, 13.09it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:21, 12.06it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:22, 11.43it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:20, 12.34it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:24, 10.17it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:15, 15.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:12, 19.18it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.31it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:18, 12.71it/s]
Loading 0:  36%|███▌      | 129/363 [00:09<00:17, 13.40it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:21, 10.92it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.42it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.66it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:16, 13.51it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:16, 12.90it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:15, 13.63it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:19, 11.04it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.56it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 19.83it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:14, 13.68it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:15, 12.99it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:14, 13.76it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.13it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.67it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:09, 20.01it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:13, 13.89it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:13, 13.15it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 13.90it/s]
Loading 0:  51%|█████     | 185/363 [00:13<00:16, 11.11it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:10, 16.60it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:08, 19.93it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 13.91it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:12, 13.39it/s]
Loading 0:  55%|█████▌    | 201/363 [00:28<04:44,  1.76s/it]
Loading 0:  56%|█████▌    | 203/363 [00:29<03:38,  1.37s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<02:07,  1.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:28,  1.72it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:04,  2.31it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:52,  2.79it/s]
Loading 0:  60%|█████▉    | 217/363 [00:30<00:42,  3.43it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:33,  4.32it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:29,  4.86it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:15,  8.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:11, 11.83it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:12, 10.45it/s]
Loading 0:  65%|██████▌   | 236/363 [00:31<00:10, 11.82it/s]
Loading 0:  66%|██████▌   | 238/363 [00:31<00:11, 11.24it/s]
Loading 0:  66%|██████▌   | 240/363 [00:31<00:10, 11.44it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.85it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:05, 19.96it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:08, 14.00it/s]
Loading 0:  70%|██████▉   | 254/363 [00:32<00:07, 14.86it/s]
Loading 0:  71%|███████   | 256/363 [00:32<00:08, 13.32it/s]
Loading 0:  71%|███████   | 258/363 [00:32<00:08, 12.85it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:05, 17.17it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 21.11it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.82it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:05, 15.63it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 13.91it/s]
Loading 0:  76%|███████▌  | 276/363 [00:33<00:06, 13.42it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 18.02it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 22.03it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 14.67it/s]
Loading 0:  80%|███████▉  | 290/363 [00:34<00:04, 15.56it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:05, 13.76it/s]
Loading 0:  81%|████████  | 294/363 [00:35<00:05, 13.29it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 18.12it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 22.36it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:03, 15.11it/s]
Loading 0:  85%|████████▍ | 308/363 [00:35<00:03, 15.87it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 12.42it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 17.78it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 21.43it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 15.31it/s]
Loading 0:  90%|████████▉ | 326/363 [00:36<00:02, 15.89it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:02, 12.30it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 16.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 19.65it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 14.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:38<00:01, 15.28it/s]
Loading 0:  95%|█████████▌| 346/363 [00:38<00:01, 13.60it/s]
Loading 0:  96%|█████████▌| 348/363 [00:38<00:01, 12.95it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.16it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 20.71it/s]
Loading 0:  99%|█████████▉| 359/363 [00:39<00:00, 10.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:39<00:00,  9.63it/s]
                                                            
Job chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer completed after 206.63s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-9-36146-v6-mkmlizer
Pipeline stage MKMLizer completed in 207.12s
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-cp312-9-36146-v6
Waiting for inference service chaiml-exp-grpo-cp312-9-36146-v6 to be ready
Inference service chaiml-exp-grpo-cp312-9-36146-v6 ready after 120.42926263809204s
Pipeline stage MKMLDeployer completed in 120.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7155630588531494s
Received healthy response to inference request in 2.101397752761841s
Received healthy response to inference request in 2.0868947505950928s
Received healthy response to inference request in 1.8521440029144287s
Received healthy response to inference request in 2.275484800338745s
5 requests
0 failed requests
5th percentile: 1.8990941524505616
10th percentile: 1.9460443019866944
20th percentile: 2.03994460105896
30th percentile: 2.0897953510284424
40th percentile: 2.0955965518951416
50th percentile: 2.101397752761841
60th percentile: 2.1710325717926025
70th percentile: 2.240667390823364
80th percentile: 2.363500452041626
90th percentile: 2.5395317554473875
95th percentile: 2.6275474071502685
99th percentile: 2.697959928512573
mean time: 2.2062968730926515
Pipeline stage StressChecker completed in 12.27s
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 0.73s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-9_36146_v6 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 0.13s
run pipeline stage %s
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 3462.70s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-9_36146_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-9_36146_v6 status is now torndown due to DeploymentManager action