chaiml-exp-grpo-cp312-_36146

developer_uid: NischayDnk

submission_id: chaiml-exp-grpo-cp312-_36146_v25

model_name: chaiml-exp-grpo-cp312-_36146_v25

model_group: ChaiML/exp_grpo_cp312_96

status: torndown

timestamp: 2025-09-10T04:02:14+00:00

num_battles: 5676

num_wins: 3239

celo_rating: 1301.77

family_friendly_score: 0.5178

family_friendly_standard_error: 0.007066585597019256

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': 0.42481487501412984, 'latency_mean': 2.3538416278362275, 'latency_p50': 2.339539051055908, 'latency_p90': 2.6119213342666625}, {'batch_size': 3, 'throughput': 0.8640435773039855, 'latency_mean': 3.459709358215332, 'latency_p50': 3.462730646133423, 'latency_p90': 3.7753525018692016}, {'batch_size': 5, 'throughput': 1.1244838161603288, 'latency_mean': 4.418815559148788, 'latency_p50': 4.40323793888092, 'latency_p90': 4.911617994308472}, {'batch_size': 6, 'throughput': 1.2015389113964716, 'latency_mean': 4.966340017318726, 'latency_p50': 4.947826385498047, 'latency_p90': 5.64973030090332}, {'batch_size': 8, 'throughput': 1.3232665392866223, 'latency_mean': 6.0052908527851105, 'latency_p50': 6.008383750915527, 'latency_p90': 6.754736042022705}, {'batch_size': 10, 'throughput': 1.4075125321659705, 'latency_mean': 7.038004975318909, 'latency_p50': 7.059073448181152, 'latency_p90': 8.066915559768677}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-exp-grpo-cp312-_36146_v25

is_internal_developer: False

language_model: ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 0.95

us_pacific_date: 2025-09-09

win_ratio: 0.5706483439041579

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': '', '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-v25-mkmlizer
Waiting for job on chaiml-exp-grpo-cp312-36146-v25-mkmlizer to finish
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  belonging to:                                                      ║
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', '')
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ║                                                                     ║
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-ocean-life25051_60844_v21: HTTPConnectionPool(host='chaiml-ocean-life25051-60844-v21-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7ede74315290>, 'Connection to chaiml-ocean-life25051-60844-v21-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04.chaiverse.com timed out. (connect timeout=12.0)'))
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: Downloaded to shared memory in 161.793s
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: Checking if ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged already exists in ChaiML
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkry4h2j4, device:0
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-ocean-life25051_60844_v21: HTTPConnectionPool(host='chaiml-ocean-life25051-60844-v21-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7ede2064cd90>, 'Connection to chaiml-ocean-life25051-60844-v21-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04.chaiverse.com timed out. (connect timeout=12.0)'))
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: quantized model in 49.634s
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: Processed model ChaiML/exp_grpo_cp312_96ff_b6_r2_less_ff_merged in 211.428s
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', '')
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia/config.json
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia/special_tokens_map.json
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia/tokenizer_config.json
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia/tokenizer.json
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia/flywheel_model.0.safetensors
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp-grpo-cp312-36146-v25/nvidia/flywheel_model.1.safetensors
chaiml-exp-grpo-cp312-36146-v25-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:15, 22.64it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:18, 19.19it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.65it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:22, 15.32it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:23, 14.87it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:17, 19.48it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:19, 17.08it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:13, 24.83it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:16, 20.34it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:19, 16.37it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:19, 16.35it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:21, 15.13it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 19.38it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 20.80it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:19, 16.05it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:17, 17.67it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:16, 18.05it/s]
Loading 0:  18%|█▊        | 67/363 [00:03<00:11, 25.18it/s]
Loading 0:  20%|█▉        | 71/363 [00:03<00:15, 18.84it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:15, 19.21it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:18, 15.33it/s]
Loading 0:  23%|██▎       | 83/363 [00:04<00:12, 22.16it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:12, 21.82it/s]
Loading 0:  25%|██▍       | 90/363 [00:04<00:16, 16.70it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.73it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:10, 25.54it/s]
Loading 0:  29%|██▉       | 105/363 [00:05<00:13, 18.81it/s]
Loading 0:  30%|██▉       | 108/363 [00:05<00:16, 15.33it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:14, 16.94it/s]
Loading 0:  32%|███▏      | 115/363 [00:06<00:14, 17.42it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:09, 24.20it/s]
Loading 0:  34%|███▍      | 125/363 [00:06<00:12, 18.45it/s]
Loading 0:  35%|███▌      | 128/363 [00:06<00:12, 18.61it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:15, 14.77it/s]
Loading 0:  38%|███▊      | 138/363 [00:07<00:09, 22.62it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:11, 19.71it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:12, 17.67it/s]
Loading 0:  41%|████      | 148/363 [00:07<00:12, 17.56it/s]
Loading 0:  42%|████▏     | 151/363 [00:08<00:11, 18.00it/s]
Loading 0:  43%|████▎     | 157/363 [00:08<00:08, 25.24it/s]
Loading 0:  44%|████▍     | 161/363 [00:08<00:10, 19.21it/s]
Loading 0:  45%|████▌     | 164/363 [00:08<00:10, 19.49it/s]
Loading 0:  46%|████▌     | 167/363 [00:08<00:12, 15.34it/s]
Loading 0:  48%|████▊     | 173/363 [00:09<00:08, 21.92it/s]
Loading 0:  49%|████▉     | 177/363 [00:09<00:08, 21.65it/s]
Loading 0:  50%|████▉     | 180/363 [00:09<00:10, 16.88it/s]
Loading 0:  51%|█████     | 184/363 [00:09<00:09, 18.36it/s]
Loading 0:  52%|█████▏    | 187/363 [00:09<00:09, 18.60it/s]
Loading 0:  53%|█████▎    | 192/363 [00:09<00:07, 23.93it/s]
Loading 0:  54%|█████▎    | 195/363 [00:10<00:07, 21.99it/s]
Loading 0:  55%|█████▍    | 198/363 [00:10<00:09, 16.52it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:16,  1.21s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:39,  1.01it/s]
Loading 0:  57%|█████▋    | 207/363 [00:23<01:39,  1.56it/s]
Loading 0:  58%|█████▊    | 212/363 [00:24<00:59,  2.52it/s]
Loading 0:  59%|█████▉    | 215/363 [00:24<00:47,  3.12it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:36,  4.03it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.74it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:25<00:13,  9.74it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:12, 10.36it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:10, 11.50it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:09, 12.88it/s]
Loading 0:  68%|██████▊   | 247/363 [00:25<00:06, 19.14it/s]
Loading 0:  69%|██████▉   | 251/363 [00:26<00:06, 16.31it/s]
Loading 0:  70%|██████▉   | 254/363 [00:26<00:06, 17.16it/s]
Loading 0:  71%|███████   | 257/363 [00:26<00:07, 14.16it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:04, 21.96it/s]
Loading 0:  74%|███████▍  | 268/363 [00:27<00:04, 19.77it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:05, 17.88it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:04, 17.88it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:04, 17.92it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 23.51it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 21.80it/s]
Loading 0:  79%|███████▉  | 288/363 [00:28<00:04, 16.38it/s]
Loading 0:  80%|████████  | 292/363 [00:28<00:03, 18.12it/s]
Loading 0:  81%|████████▏ | 295/363 [00:28<00:03, 18.46it/s]
Loading 0:  83%|████████▎ | 301/363 [00:28<00:02, 25.86it/s]
Loading 0:  84%|████████▍ | 305/363 [00:28<00:03, 19.30it/s]
Loading 0:  85%|████████▍ | 308/363 [00:29<00:02, 19.61it/s]
Loading 0:  86%|████████▌ | 311/363 [00:29<00:03, 15.38it/s]
Loading 0:  88%|████████▊ | 318/363 [00:29<00:01, 23.60it/s]
Loading 0:  89%|████████▊ | 322/363 [00:29<00:01, 20.65it/s]
Loading 0:  90%|████████▉ | 325/363 [00:30<00:02, 18.25it/s]
Loading 0:  90%|█████████ | 328/363 [00:30<00:01, 17.95it/s]
Loading 0:  91%|█████████ | 331/363 [00:30<00:01, 18.22it/s]
Loading 0:  93%|█████████▎| 337/363 [00:30<00:01, 25.45it/s]
Loading 0:  94%|█████████▍| 341/363 [00:30<00:01, 19.24it/s]
Loading 0:  95%|█████████▍| 344/363 [00:30<00:00, 19.52it/s]
Loading 0:  96%|█████████▌| 347/363 [00:31<00:01, 15.33it/s]
Loading 0:  98%|█████████▊| 354/363 [00:31<00:00, 23.51it/s]
Loading 0:  99%|█████████▊| 358/363 [00:31<00:00, 15.21it/s]
Loading 0:  99%|█████████▉| 361/363 [00:32<00:00, 13.39it/s]
                                                            
Job chaiml-exp-grpo-cp312-36146-v25-mkmlizer completed after 267.32s with status: succeeded
Stopping job with name chaiml-exp-grpo-cp312-36146-v25-mkmlizer
Pipeline stage MKMLizer completed in 267.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp-grpo-cp312-36146-v25
Waiting for inference service chaiml-exp-grpo-cp312-36146-v25 to be ready
Failed to get response for submission chaiml-ocean-life25051_60844_v21: HTTPConnectionPool(host='chaiml-ocean-life25051-60844-v21-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7ede3c54ae50>, 'Connection to chaiml-ocean-life25051-60844-v21-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-exp-grpo-cp312-36146-v25 ready after 80.14939951896667s
Pipeline stage MKMLDeployer completed in 80.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2079763412475586s
Received healthy response to inference request in 1.7295050621032715s
Received healthy response to inference request in 1.6978461742401123s
Received healthy response to inference request in 1.6757147312164307s
Received healthy response to inference request in 1.8122823238372803s
5 requests
0 failed requests
5th percentile: 1.680141019821167
10th percentile: 1.6845673084259034
20th percentile: 1.693419885635376
30th percentile: 1.7041779518127442
40th percentile: 1.7168415069580079
50th percentile: 1.7295050621032715
60th percentile: 1.762615966796875
70th percentile: 1.7957268714904786
80th percentile: 1.891421127319336
90th percentile: 2.049698734283447
95th percentile: 2.1288375377655027
99th percentile: 2.1921485805511476
mean time: 1.8246649265289308
Pipeline stage StressChecker completed in 10.50s
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 0.72s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v25 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 0.16s
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-v25-profiler
Waiting for inference service chaiml-exp-grpo-cp312-36146-v25-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 2874.55s
Shutdown handler de-registered
chaiml-exp-grpo-cp312-_36146_v25 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp-grpo-cp312-_36146_v25 status is now torndown due to DeploymentManager action