chaiml-llama8b-rmflow-r_54267

developer_uid: richhx
submission_id: chaiml-llama8b-rmflow-r_54267_v3
model_name: chaiml-llama8b-rmflow-r_54267_v3
model_group: ChaiML/llama8b-rmflow-rm
status: torndown
timestamp: 2025-06-20T17:55:37+00:00
num_battles: 16982
num_wins: 7279
celo_rating: 1237.0
family_friendly_score: 0.5512
family_friendly_standard_error: 0.007033897354951947
submission_type: basic
model_repo: ChaiML/llama8b-rmflow-rm-pointwise-datav1-500k-2e-64mckpt-resetlin-ckpt40pfix
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-llama8b-rmflow-r_54267_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama8b-rmflow-rm-pointwise-datav1-500k-2e-64mckpt-resetlin-ckpt40pfix
model_size: 8B
ranking_group: single
us_pacific_date: 2025-06-20
win_ratio: 0.42863031445059474
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': '{bot_name}:', 'truncate_by_message': True}
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-llama8b-rmflow-r-54267-v3-mkmlizer
Waiting for job on chaiml-llama8b-rmflow-r-54267-v3-mkmlizer to finish
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║                                                                     ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║                                                                     ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  Version: 0.29.1                                                    ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║                                                                     ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║                                                                     ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ║                                                                     ║
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: Downloaded to shared memory in 26.923s
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: Checking if ChaiML/llama8b-rmflow-rm-pointwise-datav1-500k-2e-64mckpt-resetlin-ckpt40pfix already exists in ChaiML
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpqsoymafh, device:0
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: quantized model in 18.917s
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: Processed model ChaiML/llama8b-rmflow-rm-pointwise-datav1-500k-2e-64mckpt-resetlin-ckpt40pfix in 45.840s
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama8b-rmflow-r-54267-v3
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8b-rmflow-r-54267-v3/config.json
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8b-rmflow-r-54267-v3/special_tokens_map.json
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8b-rmflow-r-54267-v3/tokenizer_config.json
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8b-rmflow-r-54267-v3/tokenizer.json
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama8b-rmflow-r-54267-v3/flywheel_model.0.safetensors
chaiml-llama8b-rmflow-r-54267-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 37.23it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.58it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 46.30it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 45.61it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 51.11it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.95it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.90it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 51.07it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 45.87it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 42.83it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 48.18it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 45.18it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 45.30it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.74it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 31.63it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 39.01it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.37it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.78it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.40it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 45.51it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 44.54it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:03, 48.34it/s]
Loading 0:  46%|████▋     | 135/291 [00:03<00:03, 48.61it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:03, 40.31it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 49.18it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 45.22it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 44.90it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 50.43it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 46.86it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 50.83it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 52.37it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 33.77it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 35.50it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.02it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:01, 41.71it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 42.64it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 45.91it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 46.51it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 42.96it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 51.35it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 48.82it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 50.59it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 52.25it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 48.68it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 50.39it/s]
Loading 0:  95%|█████████▍| 275/291 [00:06<00:00, 47.29it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 46.29it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 35.83it/s]
                                                            
Job chaiml-llama8b-rmflow-r-54267-v3-mkmlizer completed after 125.16s with status: succeeded
Stopping job with name chaiml-llama8b-rmflow-r-54267-v3-mkmlizer
Pipeline stage MKMLizer completed in 125.69s
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-llama8b-rmflow-r-54267-v3
Waiting for inference service chaiml-llama8b-rmflow-r-54267-v3 to be ready
Inference service chaiml-llama8b-rmflow-r-54267-v3 ready after 120.51402306556702s
Pipeline stage MKMLDeployer completed in 121.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9381654262542725s
Received healthy response to inference request in 2.472797393798828s
Received healthy response to inference request in 3.164788246154785s
Received healthy response to inference request in 1.8029699325561523s
Received healthy response to inference request in 5.481261968612671s
5 requests
0 failed requests
5th percentile: 1.9369354248046875
10th percentile: 2.0709009170532227
20th percentile: 2.338831901550293
30th percentile: 2.6111955642700195
40th percentile: 2.8879919052124023
50th percentile: 3.164788246154785
60th percentile: 3.47413911819458
70th percentile: 3.783489990234375
80th percentile: 4.246784734725953
90th percentile: 4.864023351669312
95th percentile: 5.1726426601409905
99th percentile: 5.419538106918335
mean time: 3.371996593475342
Pipeline stage StressChecker completed in 18.20s
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 0.76s
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 0.82s
Shutdown handler de-registered
chaiml-llama8b-rmflow-r_54267_v3 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama8b-rmflow-r-54267-v3-profiler
Waiting for inference service chaiml-llama8b-rmflow-r-54267-v3-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 7316.79s
Shutdown handler de-registered
chaiml-llama8b-rmflow-r_54267_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8b-rmflow-r_54267_v3 status is now torndown due to DeploymentManager action