developer_uid: NischayDnk
submission_id: chaiml-cogito12b-sft-ne_75354_v1
model_name: chaiml-cogito12b-sft-ne_75354_v1
model_group: ChaiML/cogito12b-sft-new
status: torndown
timestamp: 2025-04-22T07:03:24+00:00
num_battles: 9343
num_wins: 4543
celo_rating: 1284.15
family_friendly_score: 0.5418000000000001
family_friendly_standard_error: 0.007046314781501037
submission_type: basic
model_repo: ChaiML/cogito12b-sft-new-noeos
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': 0.47602060815555436, 'latency_mean': 2.100680434703827, 'latency_p50': 2.100730538368225, 'latency_p90': 2.3223658084869383}, {'batch_size': 3, 'throughput': 0.8858572800462988, 'latency_mean': 3.3783719885349273, 'latency_p50': 3.3839778900146484, 'latency_p90': 3.7577433586120605}, {'batch_size': 5, 'throughput': 1.0738937224010163, 'latency_mean': 4.634793442487717, 'latency_p50': 4.59000039100647, 'latency_p90': 5.223374199867249}, {'batch_size': 6, 'throughput': 1.1285759862534017, 'latency_mean': 5.2833581638336184, 'latency_p50': 5.331639051437378, 'latency_p90': 5.908719992637634}, {'batch_size': 10, 'throughput': 1.2124847016566047, 'latency_mean': 8.166541500091553, 'latency_p50': 8.253077387809753, 'latency_p90': 9.242114925384522}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-cogito12b-sft-ne_75354_v1
is_internal_developer: False
language_model: ChaiML/cogito12b-sft-new-noeos
model_size: 15B
ranking_group: single
throughput_3p7s: 0.95
us_pacific_date: 2025-04-22
win_ratio: 0.4862463876699133
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-cogito12b-sft-ne-75354-v1-mkmlizer
Waiting for job on chaiml-cogito12b-sft-ne-75354-v1-mkmlizer to finish
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ _____ __ __ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ /___/ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ belonging to: ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ║ ║
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: Downloaded to shared memory in 53.494s
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnm5tv2g3, device:0
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: quantized model in 37.081s
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: Processed model ChaiML/cogito12b-sft-new-noeos in 90.576s
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/config.json
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/special_tokens_map.json
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/added_tokens.json
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/tokenizer_config.json
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/merges.txt
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/flywheel_model.1.safetensors
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v1/flywheel_model.0.safetensors
chaiml-cogito12b-sft-ne-75354-v1-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 137.55it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:04, 120.49it/s] Loading 0: 8%|▊ | 47/579 [00:00<00:03, 143.26it/s] Loading 0: 11%|█ | 63/579 [00:00<00:03, 145.58it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 91.44it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 98.94it/s] Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 105.30it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 110.68it/s] Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 126.73it/s] Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 132.94it/s] Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 128.92it/s] Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 138.42it/s] Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 86.12it/s] Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 101.13it/s] Loading 0: 40%|████ | 232/579 [00:02<00:03, 106.59it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:03, 110.09it/s] Loading 0: 45%|████▌ | 263/579 [00:02<00:02, 126.49it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 133.23it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 98.37it/s] Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 94.32it/s] Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 109.35it/s] Loading 0: 59%|█████▊ | 340/579 [00:03<00:02, 112.94it/s] Loading 0: 61%|██████ | 353/579 [00:03<00:01, 114.80it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 129.26it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 134.32it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 99.70it/s] Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 95.22it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 110.78it/s] Loading 0: 77%|███████▋ | 448/579 [00:03<00:01, 113.52it/s] Loading 0: 80%|███████▉ | 461/579 [00:04<00:01, 116.32it/s] Loading 0: 83%|████████▎ | 481/579 [00:04<00:00, 137.67it/s] Loading 0: 86%|████████▌ | 496/579 [00:04<00:00, 133.07it/s] Loading 0: 88%|████████▊ | 512/579 [00:22<00:00, 133.07it/s] Loading 0: 89%|████████▊ | 513/579 [00:26<00:27, 2.41it/s] Loading 0: 90%|████████▉ | 521/579 [00:26<00:19, 2.90it/s] Loading 0: 92%|█████████▏| 534/579 [00:26<00:11, 4.05it/s] Loading 0: 96%|█████████▌| 554/579 [00:26<00:03, 6.54it/s] Loading 0: 98%|█████████▊| 569/579 [00:26<00:01, 9.06it/s]
Job chaiml-cogito12b-sft-ne-75354-v1-mkmlizer completed after 114.37s with status: succeeded
Stopping job with name chaiml-cogito12b-sft-ne-75354-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.86s
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-cogito12b-sft-ne-75354-v1
Waiting for inference service chaiml-cogito12b-sft-ne-75354-v1 to be ready
Inference service chaiml-cogito12b-sft-ne-75354-v1 ready after 130.45480632781982s
Pipeline stage MKMLDeployer completed in 131.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.622314453125s
Received healthy response to inference request in 2.1410176753997803s
Received healthy response to inference request in 1.9209043979644775s
Received healthy response to inference request in 2.077221155166626s
Received healthy response to inference request in 1.9363353252410889s
5 requests
0 failed requests
5th percentile: 1.9239905834198
10th percentile: 1.927076768875122
20th percentile: 1.9332491397857665
30th percentile: 1.9645124912261962
40th percentile: 2.0208668231964113
50th percentile: 2.077221155166626
60th percentile: 2.102739763259888
70th percentile: 2.1282583713531493
80th percentile: 2.237277030944824
90th percentile: 2.429795742034912
95th percentile: 2.526055097579956
99th percentile: 2.6030625820159914
mean time: 2.1395586013793944
Pipeline stage StressChecker completed in 12.15s
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 0.68s
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 0.88s
Shutdown handler de-registered
chaiml-cogito12b-sft-ne_75354_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cogito12b-sft-ne-75354-v1-profiler
Waiting for inference service chaiml-cogito12b-sft-ne-75354-v1-profiler to be ready
Inference service chaiml-cogito12b-sft-ne-75354-v1-profiler ready after 130.59525990486145s
Pipeline stage MKMLProfilerDeployer completed in 130.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cogito12b-sft2a5dd0f84fafee11411169155372d3c0-deplojp6np:/code/chaiverse_profiler_1745305837 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-cogito12b-sft2a5dd0f84fafee11411169155372d3c0-deplojp6np --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1745305837 && 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_1745305837/summary.json'
kubectl exec -it chaiml-cogito12b-sft2a5dd0f84fafee11411169155372d3c0-deplojp6np --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1745305837/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1181.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cogito12b-sft-ne-75354-v1-profiler is running
Tearing down inference service chaiml-cogito12b-sft-ne-75354-v1-profiler
Service chaiml-cogito12b-sft-ne-75354-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.45s
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4718.00s
Shutdown handler de-registered
chaiml-cogito12b-sft-ne_75354_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito12b-sft-ne_75354_v1 status is now torndown due to DeploymentManager action