chaiml-exp503-cogito14b_43656

developer_uid: NischayDnk

submission_id: chaiml-exp503-cogito14b_43656_v1

model_name: chaiml-exp503-cogito14b_43656_v1

model_group: ChaiML/exp503-cogito14b-

status: torndown

timestamp: 2025-04-15T23:59:58+00:00

num_battles: 5700

num_wins: 2921

celo_rating: 1298.48

family_friendly_score: 0.5372

family_friendly_standard_error: 0.007051470201312631

submission_type: basic

model_repo: ChaiML/exp503-cogito14b-simpo-stage1pub-datav1sft1285-9k-1

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14765603840.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4732332369626201, 'latency_mean': 2.113029651641846, 'latency_p50': 2.1211588382720947, 'latency_p90': 2.33399658203125}, {'batch_size': 3, 'throughput': 0.8676544464116553, 'latency_mean': 3.4418276393413545, 'latency_p50': 3.468093156814575, 'latency_p90': 3.7878984451293944}, {'batch_size': 5, 'throughput': 1.0653917085811233, 'latency_mean': 4.673693162202835, 'latency_p50': 4.673291325569153, 'latency_p90': 5.195717167854308}, {'batch_size': 6, 'throughput': 1.1159544104788741, 'latency_mean': 5.341293761730194, 'latency_p50': 5.3504451513290405, 'latency_p90': 5.948348569869995}, {'batch_size': 10, 'throughput': 1.2019059861569321, 'latency_mean': 8.272520604133605, 'latency_p50': 8.336909294128418, 'latency_p90': 9.293782210350036}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp503-cogito14b_43656_v1

is_internal_developer: False

language_model: ChaiML/exp503-cogito14b-simpo-stage1pub-datav1sft1285-9k-1

model_size: 15B

ranking_group: single

throughput_3p7s: 0.92

us_pacific_date: 2025-04-15

win_ratio: 0.5124561403508772

generation_params: {'temperature': 0.75, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-exp503-cogito14b-43656-v1-mkmlizer
Waiting for job on chaiml-exp503-cogito14b-43656-v1-mkmlizer to finish
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║                                                                     ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║                                                                     ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║                                                                     ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ║                                                                     ║
chaiml-exp503-cogito14b-43656-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp503-cogito14b-43656-v1-mkmlizer: Downloaded to shared memory in 53.375s
chaiml-exp503-cogito14b-43656-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpip7hhh0m, device:0
chaiml-exp503-cogito14b-43656-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
chaiml-exp503-cogito14b-43656-v1-mkmlizer: quantized model in 36.644s
chaiml-exp503-cogito14b-43656-v1-mkmlizer: Processed model ChaiML/exp503-cogito14b-simpo-stage1pub-datav1sft1285-9k-1 in 90.020s
chaiml-exp503-cogito14b-43656-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp503-cogito14b-43656-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp503-cogito14b-43656-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/config.json
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/added_tokens.json
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/special_tokens_map.json
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/tokenizer_config.json
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/merges.txt
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/vocab.json
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/tokenizer.json
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/flywheel_model.1.safetensors
chaiml-exp503-cogito14b-43656-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp503-cogito14b-43656-v1/flywheel_model.0.safetensors
chaiml-exp503-cogito14b-43656-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 132.02it/s]
Loading 0:   5%|▌         | 29/579 [00:00<00:04, 116.37it/s]
Loading 0:   8%|▊         | 47/579 [00:00<00:03, 139.40it/s]
Loading 0:  11%|█         | 63/579 [00:00<00:03, 143.01it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 86.92it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:05, 94.68it/s]
Loading 0:  18%|█▊        | 107/579 [00:01<00:04, 101.72it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 108.36it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 126.68it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 133.38it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 129.33it/s]
Loading 0:  33%|███▎      | 189/579 [00:01<00:04, 96.29it/s] 
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 93.64it/s]
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 109.31it/s]
Loading 0:  40%|████      | 232/579 [00:02<00:03, 113.54it/s]
Loading 0:  42%|████▏     | 245/579 [00:02<00:02, 117.49it/s]
Loading 0:  46%|████▌     | 264/579 [00:02<00:02, 136.16it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 138.97it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 100.81it/s]
Loading 0:  54%|█████▎    | 310/579 [00:02<00:02, 97.68it/s] 
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 111.84it/s]
Loading 0:  59%|█████▉    | 341/579 [00:03<00:02, 113.55it/s]
Loading 0:  63%|██████▎   | 363/579 [00:03<00:01, 133.71it/s]
Loading 0:  65%|██████▌   | 378/579 [00:03<00:01, 130.83it/s]
Loading 0:  69%|██████▉   | 400/579 [00:03<00:01, 150.85it/s]
Loading 0:  72%|███████▏  | 416/579 [00:03<00:01, 94.18it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 109.32it/s]
Loading 0:  78%|███████▊  | 449/579 [00:03<00:01, 111.56it/s]
Loading 0:  81%|████████▏ | 471/579 [00:04<00:00, 129.58it/s]
Loading 0:  84%|████████▍ | 486/579 [00:04<00:00, 128.63it/s]
Loading 0:  88%|████████▊ | 508/579 [00:04<00:00, 148.38it/s]
Loading 0:  88%|████████▊ | 512/579 [00:25<00:00, 148.38it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:29,  2.22it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:21,  2.73it/s]
Loading 0:  93%|█████████▎| 537/579 [00:26<00:10,  4.17it/s]
Loading 0:  96%|█████████▌| 556/579 [00:26<00:03,  6.55it/s]
Loading 0:  99%|█████████▊| 571/579 [00:26<00:00,  9.12it/s]
                                                            
Job chaiml-exp503-cogito14b-43656-v1-mkmlizer completed after 114.82s with status: succeeded
Stopping job with name chaiml-exp503-cogito14b-43656-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp503-cogito14b-43656-v1
Waiting for inference service chaiml-exp503-cogito14b-43656-v1 to be ready
Inference service chaiml-exp503-cogito14b-43656-v1 ready after 120.49618816375732s
Pipeline stage MKMLDeployer completed in 120.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4658734798431396s
Received healthy response to inference request in 1.9689323902130127s
Received healthy response to inference request in 2.230402708053589s
Received healthy response to inference request in 1.852217435836792s
Received healthy response to inference request in 2.043581485748291s
5 requests
0 failed requests
5th percentile: 1.875560426712036
10th percentile: 1.8989034175872803
20th percentile: 1.9455893993377686
30th percentile: 1.9838622093200684
40th percentile: 2.0137218475341796
50th percentile: 2.043581485748291
60th percentile: 2.11830997467041
70th percentile: 2.1930384635925293
80th percentile: 2.277496862411499
90th percentile: 2.3716851711273192
95th percentile: 2.4187793254852297
99th percentile: 2.4564546489715577
mean time: 2.1122014999389647
Pipeline stage StressChecker completed in 11.82s
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 0.71s
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 0.64s
Shutdown handler de-registered
chaiml-exp503-cogito14b_43656_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 0.12s
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-exp503-cogito14b-43656-v1-profiler
Waiting for inference service chaiml-exp503-cogito14b-43656-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 2786.59s
Shutdown handler de-registered
chaiml-exp503-cogito14b_43656_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp503-cogito14b_43656_v1 status is now torndown due to DeploymentManager action