chaiml-20250611-retune-u_1558

developer_uid: rirv938
submission_id: chaiml-20250611-retune-u_1558_v1
model_name: chaiml-20250611-retune-u_1558_v1
model_group: ChaiML/20250611_retune_U
status: torndown
timestamp: 2025-06-12T00:10:31+00:00
num_battles: 8424
num_wins: 4462
celo_rating: 1301.95
family_friendly_score: 0.5262
family_friendly_standard_error: 0.007061353411351113
submission_type: basic
model_repo: ChaiML/20250611_retune_US_7_to_13_seconds
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-20250611-retune-u_1558_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/20250611_retune_US_7_to_13_seconds
model_size: 8B
ranking_group: single
us_pacific_date: 2025-06-11
win_ratio: 0.5296771130104464
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-20250611-retune-u-1558-v1-mkmlizer
Waiting for job on chaiml-20250611-retune-u-1558-v1-mkmlizer to finish
chaiml-20250611-retune-u-1558-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║                                                                     ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║                                                                     ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  Version: 0.27.1+vampire_v3                                         ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║                                                                     ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║                                                                     ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ║                                                                     ║
chaiml-20250611-retune-u-1558-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-20250611-retune-u-1558-v1-mkmlizer: Downloaded to shared memory in 148.521s
chaiml-20250611-retune-u-1558-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpmmue3s4o, device:0
chaiml-20250611-retune-u-1558-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-20250611-retune-u-1558-v1-mkmlizer: quantized model in 19.511s
chaiml-20250611-retune-u-1558-v1-mkmlizer: Processed model ChaiML/20250611_retune_US_7_to_13_seconds in 168.033s
chaiml-20250611-retune-u-1558-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-20250611-retune-u-1558-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-20250611-retune-u-1558-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-20250611-retune-u-1558-v1
chaiml-20250611-retune-u-1558-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-20250611-retune-u-1558-v1/config.json
chaiml-20250611-retune-u-1558-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-20250611-retune-u-1558-v1/special_tokens_map.json
chaiml-20250611-retune-u-1558-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-20250611-retune-u-1558-v1/tokenizer_config.json
chaiml-20250611-retune-u-1558-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-20250611-retune-u-1558-v1/flywheel_model.0.safetensors
chaiml-20250611-retune-u-1558-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.42it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 50.44it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 43.22it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 42.41it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 50.06it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 44.34it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 44.05it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 49.36it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 47.37it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.93it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 49.80it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.62it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 46.45it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.40it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 32.41it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 40.20it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.72it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.63it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 46.37it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 43.83it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 41.76it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 47.81it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 46.78it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 46.36it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 51.12it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 47.27it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 47.25it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 46.09it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 53.84it/s]
Loading 0:  62%|██████▏   | 181/291 [00:04<00:02, 47.40it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:02, 36.94it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 37.28it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 40.12it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:02, 41.36it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 46.55it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 44.99it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 45.27it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 50.85it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 48.69it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 49.46it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 51.46it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 48.60it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 46.56it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 51.05it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 43.15it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 42.69it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 39.67it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 31.58it/s]
                                                            
Job chaiml-20250611-retune-u-1558-v1-mkmlizer completed after 206.63s with status: succeeded
Stopping job with name chaiml-20250611-retune-u-1558-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-20250611-retune-u-1558-v1
Waiting for inference service chaiml-20250611-retune-u-1558-v1 to be ready
Inference service chaiml-20250611-retune-u-1558-v1 ready after 110.4866464138031s
Pipeline stage MKMLDeployer completed in 111.04s
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 4.483850717544556s
Received healthy response to inference request in 3.391965866088867s
Received healthy response to inference request in 5.982511043548584s
Received healthy response to inference request in 3.0831024646759033s
5 requests
1 failed requests
5th percentile: 3.144875144958496
10th percentile: 3.206647825241089
20th percentile: 3.3301931858062743
30th percentile: 3.610342836380005
40th percentile: 4.04709677696228
50th percentile: 4.483850717544556
60th percentile: 5.083314847946167
70th percentile: 5.682778978347778
80th percentile: 8.814995765686039
90th percentile: 14.479965209960938
95th percentile: 17.312449932098385
99th percentile: 19.578437709808348
mean time: 7.41727294921875
%s, retrying in %s seconds...
Received healthy response to inference request in 2.519826889038086s
Received healthy response to inference request in 2.288041114807129s
Received healthy response to inference request in 3.3301894664764404s
Received healthy response to inference request in 4.102996587753296s
Received healthy response to inference request in 1.860804557800293s
5 requests
0 failed requests
5th percentile: 1.9462518692016602
10th percentile: 2.0316991806030273
20th percentile: 2.2025938034057617
30th percentile: 2.3343982696533203
40th percentile: 2.427112579345703
50th percentile: 2.519826889038086
60th percentile: 2.843971920013428
70th percentile: 3.1681169509887694
80th percentile: 3.484750890731812
90th percentile: 3.793873739242554
95th percentile: 3.9484351634979244
99th percentile: 4.072084302902222
mean time: 2.820371723175049
Pipeline stage StressChecker completed in 54.35s
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 0.70s
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 0.70s
Shutdown handler de-registered
chaiml-20250611-retune-u_1558_v1 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 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-20250611-retune-u-1558-v1-profiler
Waiting for inference service chaiml-20250611-retune-u-1558-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 9645.56s
Shutdown handler de-registered
chaiml-20250611-retune-u_1558_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-20250611-retune-u_1558_v1 status is now torndown due to DeploymentManager action