developer_uid: NischayDnk
submission_id: chaiml-cogito14b-sftexp_21695_v1
model_name: chaiml-cogito14b-sftexp_21695_v1
model_group: ChaiML/cogito14b-sftexp1
status: torndown
timestamp: 2025-05-05T15:45:34+00:00
num_battles: 8619
num_wins: 4156
celo_rating: 1273.87
family_friendly_score: 0.5813999999999999
family_friendly_standard_error: 0.006976733333014814
submission_type: basic
model_repo: ChaiML/cogito14b-sftexp1-s1-retryv1-toplex50perc
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': 0.48179329673824794, 'latency_mean': 2.075512661933899, 'latency_p50': 2.0652334690093994, 'latency_p90': 2.2939013719558714}, {'batch_size': 3, 'throughput': 0.8789880964895725, 'latency_mean': 3.3951522028446197, 'latency_p50': 3.400989532470703, 'latency_p90': 3.7492352962493896}, {'batch_size': 5, 'throughput': 1.071495579754761, 'latency_mean': 4.638914369344711, 'latency_p50': 4.649352312088013, 'latency_p90': 5.240677237510681}, {'batch_size': 6, 'throughput': 1.1351037131119588, 'latency_mean': 5.253473193645477, 'latency_p50': 5.290542244911194, 'latency_p90': 5.846518635749817}, {'batch_size': 10, 'throughput': 1.2153352291913155, 'latency_mean': 8.166130722761155, 'latency_p50': 8.19392728805542, 'latency_p90': 9.167839956283569}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-cogito14b-sftexp_21695_v1
is_internal_developer: False
language_model: ChaiML/cogito14b-sftexp1-s1-retryv1-toplex50perc
model_size: 15B
ranking_group: single
throughput_3p7s: 0.94
us_pacific_date: 2025-05-05
win_ratio: 0.4821905093398306
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': ['<|im_start|>', '<|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-cogito14b-sftexp-21695-v1-mkmlizer
Waiting for job on chaiml-cogito14b-sftexp-21695-v1-mkmlizer to finish
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ _____ __ __ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ /___/ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ belonging to: ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ║ ║
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: Downloaded to shared memory in 50.341s
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwuhy2omy, device:0
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/config.json
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/added_tokens.json
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/special_tokens_map.json
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/tokenizer_config.json
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/merges.txt
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/vocab.json
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/tokenizer.json
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/flywheel_model.1.safetensors
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito14b-sftexp-21695-v1/flywheel_model.0.safetensors
chaiml-cogito14b-sftexp-21695-v1-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 16/579 [00:00<00:04, 136.37it/s] Loading 0: 6%|▌ | 33/579 [00:00<00:03, 150.54it/s] Loading 0: 9%|▉ | 51/579 [00:00<00:03, 161.01it/s] Loading 0: 12%|█▏ | 68/579 [00:00<00:03, 153.61it/s] Loading 0: 15%|█▍ | 84/579 [00:00<00:05, 96.07it/s] Loading 0: 18%|█▊ | 106/579 [00:00<00:03, 120.18it/s] Loading 0: 21%|██ | 121/579 [00:00<00:03, 123.24it/s] Loading 0: 25%|██▍ | 143/579 [00:01<00:02, 146.27it/s] Loading 0: 28%|██▊ | 160/579 [00:01<00:03, 136.34it/s] Loading 0: 31%|███ | 178/579 [00:01<00:02, 145.25it/s] Loading 0: 34%|███▎ | 194/579 [00:01<00:03, 100.51it/s] Loading 0: 36%|███▌ | 207/579 [00:01<00:03, 106.16it/s] Loading 0: 38%|███▊ | 221/579 [00:01<00:03, 110.06it/s] Loading 0: 42%|████▏ | 243/579 [00:01<00:02, 130.26it/s] Loading 0: 45%|████▍ | 258/579 [00:02<00:02, 130.70it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 146.51it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 112.50it/s] Loading 0: 54%|█████▎ | 311/579 [00:02<00:02, 109.92it/s] Loading 0: 57%|█████▋ | 328/579 [00:02<00:02, 119.18it/s] Loading 0: 60%|█████▉ | 345/579 [00:02<00:01, 129.83it/s] Loading 0: 63%|██████▎ | 363/579 [00:02<00:01, 141.08it/s] Loading 0: 65%|██████▌ | 379/579 [00:02<00:01, 140.53it/s] Loading 0: 69%|██████▉ | 400/579 [00:03<00:01, 157.96it/s] Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 103.37it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 117.74it/s] Loading 0: 78%|███████▊ | 450/579 [00:03<00:01, 120.65it/s] Loading 0: 81%|████████▏ | 471/579 [00:03<00:00, 135.97it/s] Loading 0: 84%|████████▍ | 487/579 [00:03<00:00, 136.81it/s] Loading 0: 88%|████████▊ | 508/579 [00:03<00:00, 154.01it/s] Loading 0: 88%|████████▊ | 512/579 [00:25<00:00, 154.01it/s] Loading 0: 89%|████████▊ | 513/579 [00:25<00:29, 2.22it/s] Loading 0: 90%|█████████ | 522/579 [00:25<00:20, 2.79it/s] Loading 0: 94%|█████████▍| 544/579 [00:25<00:07, 4.78it/s] Loading 0: 97%|█████████▋| 560/579 [00:25<00:02, 6.78it/s]
Job chaiml-cogito14b-sftexp-21695-v1-mkmlizer completed after 114.86s with status: succeeded
Stopping job with name chaiml-cogito14b-sftexp-21695-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito14b-sftexp-21695-v1
Waiting for inference service chaiml-cogito14b-sftexp-21695-v1 to be ready
Inference service chaiml-cogito14b-sftexp-21695-v1 ready after 150.50934219360352s
Pipeline stage MKMLDeployer completed in 151.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6689364910125732s
Received healthy response to inference request in 2.01257586479187s
Received healthy response to inference request in 2.0774600505828857s
Received healthy response to inference request in 2.287412643432617s
Received healthy response to inference request in 2.055217742919922s
5 requests
0 failed requests
5th percentile: 2.0211042404174804
10th percentile: 2.0296326160430906
20th percentile: 2.0466893672943116
30th percentile: 2.0596662044525145
40th percentile: 2.0685631275177
50th percentile: 2.0774600505828857
60th percentile: 2.1614410877227783
70th percentile: 2.245422124862671
80th percentile: 2.3637174129486085
90th percentile: 2.5163269519805906
95th percentile: 2.592631721496582
99th percentile: 2.653675537109375
mean time: 2.2203205585479737
Pipeline stage StressChecker completed in 12.33s
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 0.87s
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 0.72s
Shutdown handler de-registered
chaiml-cogito14b-sftexp_21695_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cogito14b-sftexp-21695-v1-profiler
Waiting for inference service chaiml-cogito14b-sftexp-21695-v1-profiler to be ready
Inference service chaiml-cogito14b-sftexp-21695-v1-profiler ready after 150.5679953098297s
Pipeline stage MKMLProfilerDeployer completed in 150.98s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cogito14b-sftacc25d6d27a4c813d0e0c197fc3154a0-deplog87gv:/code/chaiverse_profiler_1746460407 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-cogito14b-sftacc25d6d27a4c813d0e0c197fc3154a0-deplog87gv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1746460407 && 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_1746460407/summary.json'
kubectl exec -it chaiml-cogito14b-sftacc25d6d27a4c813d0e0c197fc3154a0-deplog87gv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1746460407/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1179.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cogito14b-sftexp-21695-v1-profiler is running
Tearing down inference service chaiml-cogito14b-sftexp-21695-v1-profiler
Service chaiml-cogito14b-sftexp-21695-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
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 3997.42s
Shutdown handler de-registered
chaiml-cogito14b-sftexp_21695_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito14b-sftexp_21695_v1 status is now torndown due to DeploymentManager action