developer_uid: NischayDnk
submission_id: chaiml-llama31-rhflow-e_30509_v1
model_name: chaiml-llama31-rhflow-e_30509_v1
model_group: ChaiML/llama31-rhflow-ex
status: torndown
timestamp: 2025-06-22T07:17:22+00:00
num_battles: 8726
num_wins: 4268
celo_rating: 1281.95
family_friendly_score: 0.5347999999999999
family_friendly_standard_error: 0.007053920328441483
submission_type: basic
model_repo: ChaiML/llama31-rhflow-exp3-data-dynamicv1-500k-full-1e-2e-1
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 1
reward_model: default
display_name: chaiml-llama31-rhflow-e_30509_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama31-rhflow-exp3-data-dynamicv1-500k-full-1e-2e-1
model_size: 8B
ranking_group: single
us_pacific_date: 2025-06-22
win_ratio: 0.4891129956451983
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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-llama31-rhflow-e-30509-v1-mkmlizer
Waiting for job on chaiml-llama31-rhflow-e-30509-v1-mkmlizer to finish
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ belonging to: ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ║ ║
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: Downloaded to shared memory in 27.093s
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: Checking if ChaiML/llama31-rhflow-exp3-data-dynamicv1-500k-full-1e-2e-1 already exists in ChaiML
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmppbrzjp7i, device:0
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: quantized model in 21.007s
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: Processed model ChaiML/llama31-rhflow-exp3-data-dynamicv1-500k-full-1e-2e-1 in 48.101s
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama31-rhflow-e-30509-v1
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama31-rhflow-e-30509-v1/special_tokens_map.json
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama31-rhflow-e-30509-v1/config.json
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama31-rhflow-e-30509-v1/tokenizer_config.json
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama31-rhflow-e-30509-v1/tokenizer.json
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama31-rhflow-e-30509-v1/flywheel_model.0.safetensors
chaiml-llama31-rhflow-e-30509-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 32.46it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:05, 49.88it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:05, 45.82it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:07, 35.43it/s] Loading 0: 10%|█ | 30/291 [00:00<00:05, 44.30it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:05, 43.75it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 43.52it/s] Loading 0: 15%|█▌ | 45/291 [00:01<00:05, 44.61it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:06, 36.19it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:05, 43.14it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:05, 42.95it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:05, 42.94it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 43.95it/s] Loading 0: 26%|██▋ | 77/291 [00:01<00:06, 34.77it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:07, 27.13it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 26.97it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:06, 32.23it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:05, 32.94it/s] Loading 0: 35%|███▌ | 102/291 [00:02<00:05, 35.86it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 35.50it/s] Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 38.51it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 39.40it/s] Loading 0: 42%|████▏ | 121/291 [00:03<00:04, 39.31it/s] Loading 0: 43%|████▎ | 126/291 [00:03<00:04, 40.88it/s] Loading 0: 45%|████▌ | 131/291 [00:03<00:04, 32.98it/s] Loading 0: 47%|████▋ | 138/291 [00:03<00:03, 39.46it/s] Loading 0: 49%|████▉ | 143/291 [00:03<00:03, 39.84it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:03, 40.81it/s] Loading 0: 53%|█████▎ | 153/291 [00:03<00:03, 42.45it/s] Loading 0: 54%|█████▍ | 158/291 [00:04<00:03, 34.67it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:02, 42.02it/s] Loading 0: 58%|█████▊ | 170/291 [00:04<00:02, 41.81it/s] Loading 0: 60%|██████ | 175/291 [00:04<00:02, 42.37it/s] Loading 0: 62%|██████▏ | 180/291 [00:04<00:02, 42.00it/s] Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 43.32it/s] Loading 0: 65%|██████▌ | 190/291 [00:05<00:04, 24.94it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.25it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 33.43it/s] Loading 0: 71%|███████ | 206/291 [00:05<00:02, 35.30it/s] Loading 0: 73%|███████▎ | 211/291 [00:05<00:02, 36.97it/s] Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 39.52it/s] Loading 0: 76%|███████▌ | 221/291 [00:05<00:02, 32.91it/s] Loading 0: 78%|███████▊ | 228/291 [00:06<00:01, 40.30it/s] Loading 0: 80%|████████ | 233/291 [00:06<00:01, 41.43it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:01, 41.64it/s] Loading 0: 84%|████████▎ | 243/291 [00:06<00:01, 43.30it/s] Loading 0: 85%|████████▌ | 248/291 [00:06<00:01, 35.70it/s] Loading 0: 88%|████████▊ | 255/291 [00:06<00:00, 42.90it/s] Loading 0: 89%|████████▉ | 260/291 [00:06<00:00, 41.86it/s] Loading 0: 91%|█████████ | 265/291 [00:07<00:00, 30.81it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 34.34it/s] Loading 0: 95%|█████████▍| 275/291 [00:07<00:00, 29.92it/s] Loading 0: 97%|█████████▋| 281/291 [00:07<00:00, 35.66it/s] Loading 0: 98%|█████████▊| 286/291 [00:07<00:00, 33.58it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 27.90it/s]
Job chaiml-llama31-rhflow-e-30509-v1-mkmlizer completed after 83.8s with status: succeeded
Stopping job with name chaiml-llama31-rhflow-e-30509-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.50s
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-llama31-rhflow-e-30509-v1
Waiting for inference service chaiml-llama31-rhflow-e-30509-v1 to be ready
Failed to get response for submission chaiml-llama8b-rmflow-r_13988_v2: HTTPConnectionPool(host='chaiml-llama8b-rmflow-r-13988-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama31-rhflow-e-30509-v1 ready after 120.48153352737427s
Pipeline stage MKMLDeployer completed in 120.89s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 6.037167549133301s
Received healthy response to inference request in 4.090647220611572s
Received healthy response to inference request in 2.565195322036743s
Received healthy response to inference request in 4.077832937240601s
5 requests
1 failed requests
5th percentile: 2.8677228450775147
10th percentile: 3.1702503681182863
20th percentile: 3.775305414199829
30th percentile: 4.080395793914795
40th percentile: 4.085521507263183
50th percentile: 4.090647220611572
60th percentile: 4.8692553520202635
70th percentile: 5.647863483428955
80th percentile: 8.85451002120972
90th percentile: 14.48919496536255
95th percentile: 17.306537437438962
99th percentile: 19.5604114151001
mean time: 7.37894458770752
%s, retrying in %s seconds...
Received healthy response to inference request in 4.557852029800415s
Received healthy response to inference request in 5.216639518737793s
Received healthy response to inference request in 4.136138439178467s
Received healthy response to inference request in 5.628305196762085s
Received healthy response to inference request in 2.7629923820495605s
5 requests
0 failed requests
5th percentile: 3.037621593475342
10th percentile: 3.3122508049011232
20th percentile: 3.8615092277526855
30th percentile: 4.2204811573028564
40th percentile: 4.389166593551636
50th percentile: 4.557852029800415
60th percentile: 4.821367025375366
70th percentile: 5.084882020950317
80th percentile: 5.298972654342651
90th percentile: 5.4636389255523685
95th percentile: 5.545972061157227
99th percentile: 5.6118385696411135
mean time: 4.460385513305664
%s, retrying in %s seconds...
Received healthy response to inference request in 5.011765003204346s
Received healthy response to inference request in 3.080601930618286s
Received healthy response to inference request in 2.5547685623168945s
Received healthy response to inference request in 3.8500473499298096s
Received healthy response to inference request in 2.6805307865142822s
5 requests
0 failed requests
5th percentile: 2.579921007156372
10th percentile: 2.6050734519958496
20th percentile: 2.6553783416748047
30th percentile: 2.760545015335083
40th percentile: 2.9205734729766846
50th percentile: 3.080601930618286
60th percentile: 3.3883800983428953
70th percentile: 3.6961582660675045
80th percentile: 4.082390880584717
90th percentile: 4.547077941894531
95th percentile: 4.779421472549438
99th percentile: 4.9652962970733645
mean time: 3.4355427265167235
Pipeline stage StressChecker completed in 80.16s
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 0.73s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
Failed to get response for submission chaiml-llama8b-rmflow-r_13988_v2: HTTPConnectionPool(host='chaiml-llama8b-rmflow-r-13988-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.97s
Shutdown handler de-registered
chaiml-llama31-rhflow-e_30509_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 4338.59s
Shutdown handler de-registered
chaiml-llama31-rhflow-e_30509_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama31-rhflow-e_30509_v1 status is now torndown due to DeploymentManager action