chaiml-exp504-cogito14b_21955

developer_uid: NischayDnk

submission_id: chaiml-exp504-cogito14b_21955_v2

model_name: chaiml-exp504-cogito14b_21955_v2

model_group: ChaiML/exp504-cogito14b-

status: torndown

timestamp: 2025-04-16T02:55:41+00:00

num_battles: 5824

num_wins: 2954

celo_rating: 1292.38

family_friendly_score: 0.5478000000000001

family_friendly_standard_error: 0.007038681126461122

submission_type: basic

model_repo: ChaiML/exp504-cogito14b-simpo-stage1pub-datav1sft1285-9k

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': 0.47837068616574724, 'latency_mean': 2.0903327894210815, 'latency_p50': 2.0757700204849243, 'latency_p90': 2.320152831077576}, {'batch_size': 3, 'throughput': 0.8751928843787723, 'latency_mean': 3.418384875059128, 'latency_p50': 3.4055325984954834, 'latency_p90': 3.8094301223754883}, {'batch_size': 5, 'throughput': 1.04862637076772, 'latency_mean': 4.74037809252739, 'latency_p50': 4.831303238868713, 'latency_p90': 5.3339506626129145}, {'batch_size': 6, 'throughput': 1.1133974719533233, 'latency_mean': 5.348640615940094, 'latency_p50': 5.383849501609802, 'latency_p90': 5.925815463066101}, {'batch_size': 10, 'throughput': 1.202019061098743, 'latency_mean': 8.256317121982574, 'latency_p50': 8.212692618370056, 'latency_p90': 9.372756266593933}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp504-cogito14b_21955_v2

is_internal_developer: False

language_model: ChaiML/exp504-cogito14b-simpo-stage1pub-datav1sft1285-9k

model_size: 15B

ranking_group: single

throughput_3p7s: 0.93

us_pacific_date: 2025-04-15

win_ratio: 0.5072115384615384

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': ['\n', '<|im_end|>'], '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-exp504-cogito14b-21955-v2-mkmlizer
Waiting for job on chaiml-exp504-cogito14b-21955-v2-mkmlizer to finish
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║                                                                     ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║                                                                     ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║                                                                     ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ║                                                                     ║
chaiml-exp504-cogito14b-21955-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp504-cogito14b-21955-v2-mkmlizer: Downloaded to shared memory in 58.661s
chaiml-exp504-cogito14b-21955-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj1rr4y_y, device:0
chaiml-exp504-cogito14b-21955-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp504-cogito14b-21955-v2-mkmlizer: quantized model in 36.350s
chaiml-exp504-cogito14b-21955-v2-mkmlizer: Processed model ChaiML/exp504-cogito14b-simpo-stage1pub-datav1sft1285-9k in 95.011s
chaiml-exp504-cogito14b-21955-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp504-cogito14b-21955-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp504-cogito14b-21955-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/config.json
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/added_tokens.json
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/special_tokens_map.json
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/tokenizer_config.json
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/merges.txt
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/vocab.json
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/flywheel_model.1.safetensors
chaiml-exp504-cogito14b-21955-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp504-cogito14b-21955-v2/flywheel_model.0.safetensors
chaiml-exp504-cogito14b-21955-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 142.63it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 130.88it/s]
Loading 0:   9%|▉         | 51/579 [00:00<00:03, 153.07it/s]
Loading 0:  12%|█▏        | 67/579 [00:00<00:03, 145.36it/s]
Loading 0:  14%|█▍        | 82/579 [00:00<00:05, 93.71it/s] 
Loading 0:  17%|█▋        | 96/579 [00:00<00:04, 100.21it/s]
Loading 0:  20%|██        | 118/579 [00:00<00:03, 123.09it/s]
Loading 0:  23%|██▎       | 132/579 [00:01<00:03, 119.64it/s]
Loading 0:  26%|██▌       | 151/579 [00:01<00:03, 137.01it/s]
Loading 0:  29%|██▊       | 166/579 [00:01<00:03, 133.52it/s]
Loading 0:  31%|███▏      | 181/579 [00:01<00:03, 130.22it/s]
Loading 0:  34%|███▎      | 195/579 [00:01<00:04, 87.18it/s] 
Loading 0:  36%|███▌      | 208/579 [00:01<00:03, 95.55it/s]
Loading 0:  39%|███▊      | 224/579 [00:01<00:03, 109.68it/s]
Loading 0:  41%|████      | 237/579 [00:02<00:03, 106.98it/s]
Loading 0:  44%|████▍     | 255/579 [00:02<00:02, 121.23it/s]
Loading 0:  46%|████▋     | 269/579 [00:02<00:02, 120.80it/s]
Loading 0:  50%|████▉     | 289/579 [00:02<00:02, 140.76it/s]
Loading 0:  53%|█████▎    | 304/579 [00:02<00:02, 91.98it/s] 
Loading 0:  55%|█████▌    | 320/579 [00:02<00:02, 105.18it/s]
Loading 0:  58%|█████▊    | 338/579 [00:02<00:01, 121.58it/s]
Loading 0:  61%|██████    | 353/579 [00:03<00:01, 116.50it/s]
Loading 0:  65%|██████▍   | 375/579 [00:03<00:01, 136.17it/s]
Loading 0:  68%|██████▊   | 391/579 [00:03<00:01, 134.49it/s]
Loading 0:  70%|███████   | 406/579 [00:03<00:01, 102.46it/s]
Loading 0:  72%|███████▏  | 419/579 [00:03<00:01, 102.71it/s]
Loading 0:  75%|███████▌  | 436/579 [00:03<00:01, 113.67it/s]
Loading 0:  78%|███████▊  | 453/579 [00:03<00:01, 124.86it/s]
Loading 0:  81%|████████▏ | 471/579 [00:03<00:00, 137.14it/s]
Loading 0:  84%|████████▍ | 486/579 [00:04<00:00, 128.06it/s]
Loading 0:  88%|████████▊ | 508/579 [00:04<00:00, 150.74it/s]
Loading 0:  88%|████████▊ | 512/579 [00:25<00:00, 150.74it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:30,  2.15it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:25<00:21,  2.66it/s]
Loading 0:  93%|█████████▎| 537/579 [00:25<00:10,  4.11it/s]
Loading 0:  96%|█████████▌| 556/579 [00:26<00:03,  6.51it/s]
Loading 0:  99%|█████████▊| 571/579 [00:26<00:00,  9.10it/s]
                                                            
Job chaiml-exp504-cogito14b-21955-v2-mkmlizer completed after 115.29s with status: succeeded
Stopping job with name chaiml-exp504-cogito14b-21955-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.74s
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-exp504-cogito14b-21955-v2
Waiting for inference service chaiml-exp504-cogito14b-21955-v2 to be ready
Inference service chaiml-exp504-cogito14b-21955-v2 ready after 131.07447409629822s
Pipeline stage MKMLDeployer completed in 131.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5365943908691406s
Received healthy response to inference request in 1.929840087890625s
Received healthy response to inference request in 1.8882360458374023s
Received healthy response to inference request in 1.8871345520019531s
Received healthy response to inference request in 1.9162085056304932s
5 requests
0 failed requests
5th percentile: 1.887354850769043
10th percentile: 1.8875751495361328
20th percentile: 1.8880157470703125
30th percentile: 1.8938305377960205
40th percentile: 1.9050195217132568
50th percentile: 1.9162085056304932
60th percentile: 1.921661138534546
70th percentile: 1.9271137714385986
80th percentile: 2.051190948486328
90th percentile: 2.293892669677734
95th percentile: 2.4152435302734374
99th percentile: 2.51232421875
mean time: 2.031602716445923
Pipeline stage StressChecker completed in 11.44s
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 1.37s
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 0.94s
Shutdown handler de-registered
chaiml-exp504-cogito14b_21955_v2 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 2720.35s
Shutdown handler de-registered
chaiml-exp504-cogito14b_21955_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp504-cogito14b_21955_v2 status is now torndown due to DeploymentManager action