chaiml-cogito14b-dpoexp_10161

developer_uid: NischayDnk

submission_id: chaiml-cogito14b-dpoexp_10161_v2

model_name: chaiml-cogito14b-dpoexp_10161_v2

model_group: ChaiML/cogito14b-dpoexp2

status: torndown

timestamp: 2025-05-02T10:10:22+00:00

num_battles: 7003

num_wins: 3738

celo_rating: 1308.11

family_friendly_score: 0.4988

family_friendly_standard_error: 0.007071047447160852

submission_type: basic

model_repo: ChaiML/cogito14b-dpoexp2-s1-datav1-1284prefsft-mgpu

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': 0.47367073552128225, 'latency_mean': 2.1111093628406525, 'latency_p50': 2.107001781463623, 'latency_p90': 2.332503890991211}, {'batch_size': 3, 'throughput': 0.8726576219395709, 'latency_mean': 3.4197057628631593, 'latency_p50': 3.432263970375061, 'latency_p90': 3.7878289461135863}, {'batch_size': 5, 'throughput': 1.0652612143636853, 'latency_mean': 4.669933919906616, 'latency_p50': 4.718017578125, 'latency_p90': 5.190479397773743}, {'batch_size': 6, 'throughput': 1.1225153929757703, 'latency_mean': 5.325576021671295, 'latency_p50': 5.296399235725403, 'latency_p90': 5.902623033523559}, {'batch_size': 10, 'throughput': 1.2162024732340857, 'latency_mean': 8.15816178202629, 'latency_p50': 8.111783742904663, 'latency_p90': 9.274491047859192}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-cogito14b-dpoexp_10161_v2

is_internal_developer: False

language_model: ChaiML/cogito14b-dpoexp2-s1-datav1-1284prefsft-mgpu

model_size: 15B

ranking_group: single

throughput_3p7s: 0.93

us_pacific_date: 2025-05-02

win_ratio: 0.5337712408967585

generation_params: {'temperature': 0.8, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|im_start|>', '<|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-cogito14b-dpoexp-10161-v2-mkmlizer
Waiting for job on chaiml-cogito14b-dpoexp-10161-v2-mkmlizer to finish
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║       /___/                                                         ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║                                                                     ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║                                                                     ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║                                                                     ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ║                                                                     ║
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: Downloaded to shared memory in 52.596s
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwm98twq9, device:0
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: quantized model in 36.688s
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: Processed model ChaiML/cogito14b-dpoexp2-s1-datav1-1284prefsft-mgpu in 89.284s
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/config.json
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/added_tokens.json
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/tokenizer_config.json
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/special_tokens_map.json
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/merges.txt
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/vocab.json
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/tokenizer.json
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/flywheel_model.1.safetensors
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito14b-dpoexp-10161-v2/flywheel_model.0.safetensors
chaiml-cogito14b-dpoexp-10161-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 143.89it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 131.23it/s]
Loading 0:   9%|▉         | 51/579 [00:00<00:03, 153.84it/s]
Loading 0:  12%|█▏        | 67/579 [00:00<00:03, 144.61it/s]
Loading 0:  14%|█▍        | 82/579 [00:00<00:05, 94.36it/s] 
Loading 0:  16%|█▋        | 95/579 [00:00<00:04, 101.44it/s]
Loading 0:  19%|█▉        | 109/579 [00:00<00:04, 110.88it/s]
Loading 0:  22%|██▏       | 130/579 [00:01<00:03, 130.34it/s]
Loading 0:  26%|██▌       | 150/579 [00:01<00:03, 141.63it/s]
Loading 0:  28%|██▊       | 165/579 [00:01<00:02, 143.43it/s]
Loading 0:  31%|███       | 180/579 [00:01<00:03, 130.56it/s]
Loading 0:  34%|███▎      | 194/579 [00:01<00:04, 93.81it/s] 
Loading 0:  36%|███▌      | 208/579 [00:01<00:03, 99.26it/s]
Loading 0:  38%|███▊      | 221/579 [00:01<00:03, 105.65it/s]
Loading 0:  42%|████▏     | 241/579 [00:02<00:02, 127.78it/s]
Loading 0:  44%|████▍     | 256/579 [00:02<00:02, 126.30it/s]
Loading 0:  47%|████▋     | 270/579 [00:02<00:02, 128.43it/s]
Loading 0:  50%|█████     | 291/579 [00:02<00:01, 149.71it/s]
Loading 0:  53%|█████▎    | 307/579 [00:02<00:02, 94.99it/s] 
Loading 0:  56%|█████▌    | 323/579 [00:02<00:02, 107.56it/s]
Loading 0:  59%|█████▊    | 339/579 [00:02<00:02, 118.36it/s]
Loading 0:  61%|██████    | 354/579 [00:02<00:01, 119.58it/s]
Loading 0:  65%|██████▍   | 375/579 [00:03<00:01, 135.67it/s]
Loading 0:  67%|██████▋   | 390/579 [00:03<00:01, 128.91it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 103.67it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 99.16it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 113.70it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 117.14it/s]
Loading 0:  80%|███████▉  | 461/579 [00:03<00:00, 119.94it/s]
Loading 0:  83%|████████▎ | 483/579 [00:04<00:00, 138.83it/s]
Loading 0:  86%|████████▌ | 498/579 [00:04<00:00, 134.20it/s]
Loading 0:  88%|████████▊ | 512/579 [00:21<00:00, 134.20it/s]
Loading 0:  89%|████████▊ | 513/579 [00:26<00:27,  2.38it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:20,  2.88it/s]
Loading 0:  92%|█████████▏| 535/579 [00:26<00:10,  4.12it/s]
Loading 0:  96%|█████████▌| 556/579 [00:26<00:03,  6.74it/s]
Loading 0:  99%|█████████▊| 571/579 [00:26<00:00,  9.27it/s]
                                                            
Job chaiml-cogito14b-dpoexp-10161-v2-mkmlizer completed after 115.09s with status: succeeded
Stopping job with name chaiml-cogito14b-dpoexp-10161-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.57s
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-cogito14b-dpoexp-10161-v2
Waiting for inference service chaiml-cogito14b-dpoexp-10161-v2 to be ready
Inference service chaiml-cogito14b-dpoexp-10161-v2 ready after 160.76980924606323s
Pipeline stage MKMLDeployer completed in 161.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6964807510375977s
Received healthy response to inference request in 1.9514715671539307s
Received healthy response to inference request in 2.291525363922119s
Received healthy response to inference request in 2.09944748878479s
Received healthy response to inference request in 1.9691259860992432s
5 requests
0 failed requests
5th percentile: 1.955002450942993
10th percentile: 1.9585333347320557
20th percentile: 1.9655951023101808
30th percentile: 1.9951902866363525
40th percentile: 2.0473188877105715
50th percentile: 2.09944748878479
60th percentile: 2.1762786388397215
70th percentile: 2.2531097888946534
80th percentile: 2.372516441345215
90th percentile: 2.534498596191406
95th percentile: 2.6154896736145017
99th percentile: 2.6802825355529785
mean time: 2.201610231399536
Pipeline stage StressChecker completed in 12.70s
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 0.69s
Shutdown handler de-registered
chaiml-cogito14b-dpoexp_10161_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
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 0.10s
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-cogito14b-dpoexp-10161-v2-profiler
Waiting for inference service chaiml-cogito14b-dpoexp-10161-v2-profiler to be ready
Inference service chaiml-cogito14b-dpoexp-10161-v2-profiler ready after 160.58880853652954s
Pipeline stage MKMLProfilerDeployer completed in 160.99s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cogito14b-dpo159eaf56a9471806071c9386b8d9cea2-deplop5bz6:/code/chaiverse_profiler_1746181133 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-cogito14b-dpo159eaf56a9471806071c9386b8d9cea2-deplop5bz6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1746181133 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1746181133/summary.json'
kubectl exec -it chaiml-cogito14b-dpo159eaf56a9471806071c9386b8d9cea2-deplop5bz6 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1746181133/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1191.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cogito14b-dpoexp-10161-v2-profiler is running
Tearing down inference service chaiml-cogito14b-dpoexp-10161-v2-profiler
Service chaiml-cogito14b-dpoexp-10161-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.69s
Shutdown handler de-registered
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 3225.73s
Shutdown handler de-registered
chaiml-cogito14b-dpoexp_10161_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito14b-dpoexp_10161_v2 status is now torndown due to DeploymentManager action