developer_uid: NischayDnk
submission_id: chaiml-cogito32b-sft-ex_77245_v2
model_name: chaiml-cogito32b-sft-ex_77245_v2
model_group: ChaiML/cogito32b-sft-exp
status: torndown
timestamp: 2025-04-18T21:47:58+00:00
num_battles: 8689
num_wins: 4348
celo_rating: 1287.58
family_friendly_score: 0.5674
family_friendly_standard_error: 0.007006528955196004
submission_type: basic
model_repo: ChaiML/cogito32b-sft-exp1-top5kdel
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32759331840.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.27056224293476794, 'latency_mean': 3.69591086268425, 'latency_p50': 3.7102088928222656, 'latency_p90': 4.117567682266236}, {'batch_size': 2, 'throughput': 0.43897081948891475, 'latency_mean': 4.553821865320206, 'latency_p50': 4.558265686035156, 'latency_p90': 5.045520997047424}, {'batch_size': 3, 'throughput': 0.5772972486060429, 'latency_mean': 5.169687997102738, 'latency_p50': 5.135049939155579, 'latency_p90': 5.735102367401123}, {'batch_size': 5, 'throughput': 0.7752792322338878, 'latency_mean': 6.430789473056794, 'latency_p50': 6.485261559486389, 'latency_p90': 7.098634672164917}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-cogito32b-sft-ex_77245_v2
is_internal_developer: False
language_model: ChaiML/cogito32b-sft-exp1-top5kdel
model_size: 33B
ranking_group: single
throughput_3p7s: 0.27
us_pacific_date: 2025-04-18
win_ratio: 0.5004028081482333
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 768, 'best_of': 5, '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-cogito32b-sft-ex-77245-v2-mkmlizer
Waiting for job on chaiml-cogito32b-sft-ex-77245-v2-mkmlizer to finish
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ _____ __ __ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ /___/ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ belonging to: ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ║ ║
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: Downloaded to shared memory in 98.331s
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn7q664iv, device:0
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: quantized model in 62.335s
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: Processed model ChaiML/cogito32b-sft-exp1-top5kdel in 160.666s
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/config.json
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/added_tokens.json
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/special_tokens_map.json
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/tokenizer_config.json
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/merges.txt
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/vocab.json
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/tokenizer.json
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/flywheel_model.2.safetensors
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/flywheel_model.1.safetensors
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sft-ex-77245-v2/flywheel_model.0.safetensors
chaiml-cogito32b-sft-ex-77245-v2-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:18, 41.71it/s] Loading 0: 2%|▏ | 17/771 [00:00<00:10, 70.49it/s] Loading 0: 4%|▍ | 29/771 [00:00<00:09, 77.75it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:10, 66.36it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:13, 54.93it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:11, 63.74it/s] Loading 0: 10%|▉ | 77/771 [00:01<00:09, 70.69it/s] Loading 0: 12%|█▏ | 89/771 [00:01<00:09, 75.26it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:09, 70.25it/s] Loading 0: 15%|█▍ | 114/771 [00:01<00:09, 68.32it/s] Loading 0: 16%|█▌ | 122/771 [00:01<00:09, 67.07it/s] Loading 0: 17%|█▋ | 133/771 [00:01<00:08, 70.95it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 92.17it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 80.89it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 59.18it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 58.33it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:09, 60.15it/s] Loading 0: 26%|██▌ | 197/771 [00:02<00:08, 68.29it/s] Loading 0: 27%|██▋ | 209/771 [00:03<00:07, 73.82it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:07, 70.67it/s] Loading 0: 30%|███ | 234/771 [00:03<00:08, 60.46it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 65.37it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 70.72it/s] Loading 0: 35%|███▍ | 269/771 [00:03<00:06, 75.28it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:06, 70.80it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:07, 60.62it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:11, 2.44it/s] Loading 0: 41%|████ | 315/771 [00:18<02:08, 3.55it/s] Loading 0: 42%|████▏ | 325/771 [00:18<01:31, 4.85it/s] Loading 0: 43%|████▎ | 333/771 [00:19<01:10, 6.23it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:47, 9.04it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:40, 10.34it/s] Loading 0: 47%|████▋ | 365/771 [00:19<00:27, 14.88it/s] Loading 0: 49%|████▉ | 377/771 [00:19<00:19, 20.52it/s] Loading 0: 50%|█████ | 388/771 [00:20<00:14, 27.19it/s] Loading 0: 52%|█████▏ | 400/771 [00:20<00:10, 36.14it/s] Loading 0: 53%|█████▎ | 410/771 [00:20<00:10, 36.09it/s] Loading 0: 54%|█████▍ | 418/771 [00:20<00:08, 40.13it/s] Loading 0: 55%|█████▌ | 426/771 [00:20<00:07, 43.92it/s] Loading 0: 57%|█████▋ | 437/771 [00:20<00:06, 51.96it/s] Loading 0: 58%|█████▊ | 449/771 [00:20<00:05, 60.21it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:04, 62.05it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 55.46it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 60.90it/s] Loading 0: 64%|██████▍ | 497/771 [00:21<00:04, 67.88it/s] Loading 0: 66%|██████▌ | 509/771 [00:21<00:03, 72.87it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 70.66it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:03, 60.97it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 65.69it/s] Loading 0: 72%|███████▏ | 557/771 [00:22<00:03, 71.26it/s] Loading 0: 74%|███████▍ | 569/771 [00:22<00:02, 75.58it/s] Loading 0: 76%|███████▌ | 586/771 [00:22<00:02, 70.91it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:02, 61.18it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 66.05it/s] Loading 0: 80%|███████▉ | 616/771 [00:23<00:02, 74.65it/s] Loading 0: 81%|████████▏ | 627/771 [00:37<00:54, 2.63it/s] Loading 0: 83%|████████▎ | 638/771 [00:37<00:36, 3.68it/s] Loading 0: 84%|████████▍ | 647/771 [00:37<00:26, 4.69it/s] Loading 0: 85%|████████▍ | 654/771 [00:38<00:20, 5.83it/s] Loading 0: 86%|████████▋ | 665/771 [00:38<00:12, 8.43it/s] Loading 0: 88%|████████▊ | 676/771 [00:38<00:07, 12.00it/s] Loading 0: 89%|████████▉ | 688/771 [00:38<00:04, 16.87it/s] Loading 0: 91%|█████████ | 700/771 [00:38<00:03, 23.35it/s] Loading 0: 92%|█████████▏| 710/771 [00:38<00:02, 25.64it/s] Loading 0: 93%|█████████▎| 718/771 [00:38<00:01, 29.90it/s] Loading 0: 94%|█████████▍| 726/771 [00:39<00:01, 34.62it/s] Loading 0: 96%|█████████▌| 737/771 [00:39<00:00, 42.88it/s] Loading 0: 97%|█████████▋| 749/771 [00:39<00:00, 52.05it/s] Loading 0: 99%|█████████▉| 766/771 [00:47<00:00, 5.00it/s]
Job chaiml-cogito32b-sft-ex-77245-v2-mkmlizer completed after 198.04s with status: succeeded
Stopping job with name chaiml-cogito32b-sft-ex-77245-v2-mkmlizer
Pipeline stage MKMLizer completed in 198.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito32b-sft-ex-77245-v2
Waiting for inference service chaiml-cogito32b-sft-ex-77245-v2 to be ready
Inference service chaiml-cogito32b-sft-ex-77245-v2 ready after 130.4769127368927s
Pipeline stage MKMLDeployer completed in 131.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7855515480041504s
Received healthy response to inference request in 3.4801671504974365s
Received healthy response to inference request in 3.247591018676758s
Received healthy response to inference request in 3.6296536922454834s
Received healthy response to inference request in 3.4602301120758057s
5 requests
0 failed requests
5th percentile: 3.2901188373565673
10th percentile: 3.3326466560363768
20th percentile: 3.417702293395996
30th percentile: 3.464217519760132
40th percentile: 3.472192335128784
50th percentile: 3.4801671504974365
60th percentile: 3.5399617671966555
70th percentile: 3.599756383895874
80th percentile: 3.6608332633972167
90th percentile: 3.7231924057006838
95th percentile: 3.754371976852417
99th percentile: 3.7793156337738036
mean time: 3.5206387042999268
Pipeline stage StressChecker completed in 18.98s
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 0.73s
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 0.67s
Shutdown handler de-registered
chaiml-cogito32b-sft-ex_77245_v2 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-cogito32b-sft-ex-77245-v2-profiler
Waiting for inference service chaiml-cogito32b-sft-ex-77245-v2-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 3509.28s
Shutdown handler de-registered
chaiml-cogito32b-sft-ex_77245_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-sft-ex_77245_v2 status is now torndown due to DeploymentManager action