developer_uid: chai_backend_admin
submission_id: alexdaoud-trainer-humof_84701_v1
model_name: alexdaoud-trainer-humof_84701_v1
model_group: alexdaoud/trainer_humof_
status: torndown
timestamp: 2025-01-29T17:42:08+00:00
num_battles: 8240
num_wins: 4073
celo_rating: 1266.58
family_friendly_score: 0.6046
family_friendly_standard_error: 0.006914605411735365
submission_type: basic
model_repo: alexdaoud/trainer_humof_2025-01-27-checkpoint-46
model_architecture: MultiHeadLlamaClassifier
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: alexdaoud-trainer-humof_84701_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: alexdaoud/trainer_humof_2025-01-27-checkpoint-46
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-29
win_ratio: 0.4942961165048544
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': 256, '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': 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 alexdaoud-trainer-humof-84701-v1-mkmlizer
Waiting for job on alexdaoud-trainer-humof-84701-v1-mkmlizer to finish
alexdaoud-trainer-humof-84701-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║     _____            __           __                                ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║       /___/                                                         ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  Version: 0.11.37                                                   ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  https://mk1.ai                                                     ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  belonging to:                                                      ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  Chai Research Corp.                                                ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ║                                                                     ║
alexdaoud-trainer-humof-84701-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexdaoud-trainer-humof-84701-v1-mkmlizer: Downloaded to shared memory in 32.694s
alexdaoud-trainer-humof-84701-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpozo1f9e8, device:0
alexdaoud-trainer-humof-84701-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexdaoud-trainer-humof-84701-v1-mkmlizer: quantized model in 16.042s
alexdaoud-trainer-humof-84701-v1-mkmlizer: Processed model alexdaoud/trainer_humof_2025-01-27-checkpoint-46 in 48.737s
alexdaoud-trainer-humof-84701-v1-mkmlizer: creating bucket guanaco-mkml-models
alexdaoud-trainer-humof-84701-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexdaoud-trainer-humof-84701-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexdaoud-trainer-humof-84701-v1
alexdaoud-trainer-humof-84701-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexdaoud-trainer-humof-84701-v1/tokenizer.json
alexdaoud-trainer-humof-84701-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexdaoud-trainer-humof-84701-v1/flywheel_model.0.safetensors
alexdaoud-trainer-humof-84701-v1-mkmlizer: 
Loading 0:   0%|          | 0/292 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/292 [00:00<00:08, 33.76it/s]
Loading 0:   4%|▍         | 13/292 [00:00<00:05, 53.26it/s]
Loading 0:   7%|▋         | 19/292 [00:00<00:05, 46.35it/s]
Loading 0:   8%|▊         | 24/292 [00:00<00:05, 46.04it/s]
Loading 0:  11%|█         | 31/292 [00:00<00:04, 52.97it/s]
Loading 0:  13%|█▎        | 37/292 [00:00<00:05, 49.43it/s]
Loading 0:  15%|█▍        | 43/292 [00:00<00:05, 49.79it/s]
Loading 0:  17%|█▋        | 49/292 [00:00<00:04, 51.87it/s]
Loading 0:  19%|█▉        | 55/292 [00:01<00:04, 47.68it/s]
Loading 0:  21%|██        | 60/292 [00:01<00:04, 47.03it/s]
Loading 0:  23%|██▎       | 67/292 [00:01<00:04, 52.54it/s]
Loading 0:  25%|██▌       | 73/292 [00:01<00:04, 49.85it/s]
Loading 0:  27%|██▋       | 79/292 [00:01<00:04, 50.44it/s]
Loading 0:  29%|██▉       | 85/292 [00:01<00:06, 34.03it/s]
Loading 0:  31%|███       | 90/292 [00:02<00:05, 36.03it/s]
Loading 0:  33%|███▎      | 95/292 [00:02<00:05, 33.00it/s]
Loading 0:  35%|███▌      | 103/292 [00:02<00:04, 42.17it/s]
Loading 0:  37%|███▋      | 109/292 [00:02<00:04, 43.04it/s]
Loading 0:  39%|███▉      | 114/292 [00:02<00:04, 43.31it/s]
Loading 0:  41%|████▏     | 121/292 [00:02<00:03, 49.60it/s]
Loading 0:  43%|████▎     | 127/292 [00:02<00:03, 48.67it/s]
Loading 0:  46%|████▌     | 133/292 [00:02<00:03, 50.60it/s]
Loading 0:  48%|████▊     | 139/292 [00:03<00:02, 52.17it/s]
Loading 0:  50%|████▉     | 145/292 [00:03<00:02, 50.02it/s]
Loading 0:  52%|█████▏    | 151/292 [00:03<00:02, 50.31it/s]
Loading 0:  54%|█████▍    | 157/292 [00:03<00:02, 52.36it/s]
Loading 0:  56%|█████▌    | 163/292 [00:03<00:02, 47.01it/s]
Loading 0:  58%|█████▊    | 168/292 [00:03<00:02, 46.82it/s]
Loading 0:  61%|██████    | 177/292 [00:03<00:02, 52.42it/s]
Loading 0:  63%|██████▎   | 183/292 [00:03<00:02, 53.12it/s]
Loading 0:  65%|██████▍   | 189/292 [00:04<00:03, 31.46it/s]
Loading 0:  66%|██████▋   | 194/292 [00:04<00:02, 34.44it/s]
Loading 0:  69%|██████▉   | 202/292 [00:04<00:02, 42.82it/s]
Loading 0:  71%|███████   | 208/292 [00:04<00:01, 43.58it/s]
Loading 0:  73%|███████▎  | 214/292 [00:04<00:01, 46.41it/s]
Loading 0:  75%|███████▌  | 220/292 [00:04<00:01, 49.26it/s]
Loading 0:  77%|███████▋  | 226/292 [00:04<00:01, 48.25it/s]
Loading 0:  79%|███████▉  | 232/292 [00:05<00:01, 49.68it/s]
Loading 0:  82%|████████▏ | 238/292 [00:05<00:01, 51.92it/s]
Loading 0:  84%|████████▎ | 244/292 [00:05<00:00, 49.97it/s]
Loading 0:  86%|████████▌ | 250/292 [00:05<00:00, 52.29it/s]
Loading 0:  88%|████████▊ | 257/292 [00:05<00:00, 48.58it/s]
Loading 0:  91%|█████████ | 265/292 [00:05<00:00, 56.35it/s]
Loading 0:  93%|█████████▎| 271/292 [00:05<00:00, 53.50it/s]
Loading 0:  95%|█████████▍| 277/292 [00:05<00:00, 54.78it/s]
Loading 0:  97%|█████████▋| 283/292 [00:06<00:00, 49.18it/s]
Loading 0:  99%|█████████▉| 289/292 [00:06<00:00, 35.32it/s]
                                                            

Job alexdaoud-trainer-humof-84701-v1-mkmlizer completed after 73.24s with status: succeeded
Stopping job with name alexdaoud-trainer-humof-84701-v1-mkmlizer
Pipeline stage MKMLizer completed in 73.79s
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 alexdaoud-trainer-humof-84701-v1
Waiting for inference service alexdaoud-trainer-humof-84701-v1 to be ready
Inference service alexdaoud-trainer-humof-84701-v1 ready after 201.26591968536377s
Pipeline stage MKMLDeployer completed in 201.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.369318723678589s
Received healthy response to inference request in 2.161705493927002s
Received healthy response to inference request in 2.895775556564331s
Received healthy response to inference request in 3.660945177078247s
Received healthy response to inference request in 5.2338385581970215s
5 requests
0 failed requests
5th percentile: 2.3085195064544677
10th percentile: 2.4553335189819334
20th percentile: 2.7489615440368653
30th percentile: 3.0488094806671144
40th percentile: 3.3548773288726808
50th percentile: 3.660945177078247
60th percentile: 3.9442945957183837
70th percentile: 4.22764401435852
80th percentile: 4.542222690582276
90th percentile: 4.888030624389648
95th percentile: 5.060934591293335
99th percentile: 5.199257764816284
mean time: 3.664316701889038
%s, retrying in %s seconds...
Received healthy response to inference request in 5.343457937240601s
Received healthy response to inference request in 2.2106130123138428s
Received healthy response to inference request in 2.657560110092163s
Received healthy response to inference request in 6.06089973449707s
Received healthy response to inference request in 3.9492383003234863s
5 requests
0 failed requests
5th percentile: 2.300002431869507
10th percentile: 2.389391851425171
20th percentile: 2.568170690536499
30th percentile: 2.9158957481384276
40th percentile: 3.4325670242309574
50th percentile: 3.9492383003234863
60th percentile: 4.506926155090332
70th percentile: 5.064614009857177
80th percentile: 5.486946296691895
90th percentile: 5.773923015594482
95th percentile: 5.917411375045776
99th percentile: 6.032202062606811
mean time: 4.044353818893432
%s, retrying in %s seconds...
Received healthy response to inference request in 2.000129222869873s
Received healthy response to inference request in 3.13555908203125s
Received healthy response to inference request in 3.1768898963928223s
Received healthy response to inference request in 2.8232624530792236s
Received healthy response to inference request in 2.9412901401519775s
5 requests
0 failed requests
5th percentile: 2.164755868911743
10th percentile: 2.3293825149536134
20th percentile: 2.6586358070373537
30th percentile: 2.8468679904937746
40th percentile: 2.894079065322876
50th percentile: 2.9412901401519775
60th percentile: 3.0189977169036863
70th percentile: 3.0967052936553956
80th percentile: 3.1438252449035646
90th percentile: 3.1603575706481934
95th percentile: 3.1686237335205076
99th percentile: 3.1752366638183593
mean time: 2.815426158905029
Pipeline stage StressChecker completed in 56.14s
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
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.78s
Shutdown handler de-registered
alexdaoud-trainer-humof_84701_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 0.13s
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 alexdaoud-trainer-humof-84701-v1-profiler
Waiting for inference service alexdaoud-trainer-humof-84701-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3497.29s
Shutdown handler de-registered
alexdaoud-trainer-humof_84701_v1 status is now inactive due to auto deactivation removed underperforming models
alexdaoud-trainer-humof_84701_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1