chaiml-cogito32b-sftmor_54936

developer_uid: NischayDnk

submission_id: chaiml-cogito32b-sftmor_54936_v1

model_name: chaiml-cogito32b-sftmor_54936_v1

model_group: ChaiML/cogito32b-sftmore

status: torndown

timestamp: 2025-05-11T04:51:46+00:00

num_battles: 12356

num_wins: 6088

celo_rating: 1281.77

family_friendly_score: 0.5806

family_friendly_standard_error: 0.0069785906886705995

submission_type: basic

model_repo: ChaiML/cogito32b-sftmorelora-retryv2-top20k-maskprompt-2e

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': 0.38850015193432375, 'latency_mean': 2.573946807384491, 'latency_p50': 2.583465337753296, 'latency_p90': 2.8597001314163206}, {'batch_size': 3, 'throughput': 0.8675038450318902, 'latency_mean': 3.4494953656196596, 'latency_p50': 3.452643632888794, 'latency_p90': 3.788697862625122}, {'batch_size': 5, 'throughput': 1.1892024815932651, 'latency_mean': 4.163318574428558, 'latency_p50': 4.142158269882202, 'latency_p90': 4.6748947381973265}, {'batch_size': 6, 'throughput': 1.2965091135156215, 'latency_mean': 4.600184500217438, 'latency_p50': 4.59426736831665, 'latency_p90': 5.160507583618164}, {'batch_size': 8, 'throughput': 1.4580030230339265, 'latency_mean': 5.41757279753685, 'latency_p50': 5.421815752983093, 'latency_p90': 6.066693949699402}, {'batch_size': 10, 'throughput': 1.6062510207202718, 'latency_mean': 6.176395114660263, 'latency_p50': 6.180604577064514, 'latency_p90': 7.091788935661316}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-cogito32b-sftmor_54936_v1

is_internal_developer: False

language_model: ChaiML/cogito32b-sftmorelora-retryv2-top20k-maskprompt-2e

model_size: 33B

ranking_group: single

throughput_3p7s: 1.0

us_pacific_date: 2025-05-10

win_ratio: 0.492716089349304

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, '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-sftmor-54936-v1-mkmlizer
Waiting for job on chaiml-cogito32b-sftmor-54936-v1-mkmlizer to finish
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║       /___/                                                         ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ║                                                                     ║
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: Downloaded to shared memory in 110.126s
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf3gslwwq, device:0
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: quantized model in 63.500s
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: Processed model ChaiML/cogito32b-sftmorelora-retryv2-top20k-maskprompt-2e in 173.626s
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/config.json
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/added_tokens.json
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/tokenizer_config.json
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/special_tokens_map.json
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/vocab.json
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/tokenizer.json
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/merges.txt
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/flywheel_model.2.safetensors
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/flywheel_model.1.safetensors
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sftmor-54936-v1/flywheel_model.0.safetensors
chaiml-cogito32b-sftmor-54936-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.61it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:09, 76.48it/s]
Loading 0:   4%|▎         | 28/771 [00:00<00:09, 81.53it/s]
Loading 0:   5%|▍         | 38/771 [00:00<00:08, 87.78it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 54.84it/s]
Loading 0:   7%|▋         | 54/771 [00:00<00:14, 50.47it/s]
Loading 0:   8%|▊         | 65/771 [00:01<00:11, 58.99it/s]
Loading 0:  10%|▉         | 77/771 [00:01<00:10, 67.12it/s]
Loading 0:  12%|█▏        | 89/771 [00:01<00:09, 72.70it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:09, 68.42it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:09, 66.28it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:10, 63.30it/s]
Loading 0:  17%|█▋        | 133/771 [00:01<00:09, 70.31it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:06, 91.53it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 79.92it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 59.09it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 57.64it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 58.57it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 69.36it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 78.72it/s]
Loading 0:  28%|██▊       | 218/771 [00:03<00:06, 79.16it/s]
Loading 0:  29%|██▉       | 227/771 [00:03<00:09, 58.88it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:09, 54.08it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 60.78it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 68.16it/s]
Loading 0:  35%|███▍      | 269/771 [00:03<00:06, 74.15it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 68.60it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 59.20it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:18,  2.36it/s]
Loading 0:  41%|████      | 314/771 [00:19<02:15,  3.37it/s]
Loading 0:  42%|████▏     | 322/771 [00:19<01:42,  4.37it/s]
Loading 0:  43%|████▎     | 330/771 [00:19<01:16,  5.75it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:45,  9.26it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:39, 10.53it/s]
Loading 0:  47%|████▋     | 365/771 [00:20<00:27, 14.99it/s]
Loading 0:  49%|████▉     | 377/771 [00:20<00:19, 20.51it/s]
Loading 0:  50%|█████     | 388/771 [00:20<00:14, 27.04it/s]
Loading 0:  52%|█████▏    | 398/771 [00:20<00:10, 33.97it/s]
Loading 0:  53%|█████▎    | 407/771 [00:20<00:10, 33.93it/s]
Loading 0:  54%|█████▍    | 415/771 [00:20<00:09, 36.72it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:07, 43.32it/s]
Loading 0:  57%|█████▋    | 437/771 [00:21<00:06, 52.40it/s]
Loading 0:  58%|█████▊    | 449/771 [00:21<00:05, 60.31it/s]
Loading 0:  60%|██████    | 466/771 [00:21<00:04, 62.93it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 55.87it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 61.38it/s]
Loading 0:  64%|██████▍   | 496/771 [00:22<00:03, 69.39it/s]
Loading 0:  66%|██████▌   | 508/771 [00:22<00:03, 74.17it/s]
Loading 0:  67%|██████▋   | 518/771 [00:22<00:03, 79.69it/s]
Loading 0:  68%|██████▊   | 527/771 [00:22<00:04, 60.96it/s]
Loading 0:  69%|██████▉   | 535/771 [00:22<00:04, 57.34it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 61.58it/s]
Loading 0:  72%|███████▏  | 557/771 [00:22<00:03, 68.58it/s]
Loading 0:  74%|███████▍  | 569/771 [00:23<00:02, 75.05it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 73.28it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 62.09it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 67.66it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 73.64it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<00:58,  2.46it/s]
Loading 0:  83%|████████▎ | 638/771 [00:38<00:38,  3.47it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:28,  4.41it/s]
Loading 0:  85%|████████▍ | 653/771 [00:39<00:21,  5.39it/s]
Loading 0:  86%|████████▋ | 665/771 [00:39<00:13,  8.13it/s]
Loading 0:  88%|████████▊ | 677/771 [00:39<00:08, 11.73it/s]
Loading 0:  89%|████████▉ | 689/771 [00:39<00:05, 16.37it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 23.43it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 25.60it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 32.18it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 40.35it/s]
Loading 0:  97%|█████████▋| 749/771 [00:40<00:00, 48.57it/s]
Loading 0:  99%|█████████▉| 766/771 [00:48<00:00,  5.30it/s]
                                                            
Job chaiml-cogito32b-sftmor-54936-v1-mkmlizer completed after 206.2s with status: succeeded
Stopping job with name chaiml-cogito32b-sftmor-54936-v1-mkmlizer
Pipeline stage MKMLizer completed in 206.67s
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-cogito32b-sftmor-54936-v1
Waiting for inference service chaiml-cogito32b-sftmor-54936-v1 to be ready
Inference service chaiml-cogito32b-sftmor-54936-v1 ready after 120.58855295181274s
Pipeline stage MKMLDeployer completed in 121.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.061194658279419s
Received healthy response to inference request in 2.838783025741577s
Received healthy response to inference request in 2.509225606918335s
Received healthy response to inference request in 2.548708438873291s
Received healthy response to inference request in 2.928199291229248s
5 requests
0 failed requests
5th percentile: 2.517122173309326
10th percentile: 2.525018739700317
20th percentile: 2.5408118724823
30th percentile: 2.606723356246948
40th percentile: 2.7227531909942626
50th percentile: 2.838783025741577
60th percentile: 2.8745495319366454
70th percentile: 2.9103160381317137
80th percentile: 2.954798364639282
90th percentile: 3.0079965114593508
95th percentile: 3.034595584869385
99th percentile: 3.055874843597412
mean time: 2.777222204208374
Pipeline stage StressChecker completed in 14.99s
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 0.60s
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 0.62s
Shutdown handler de-registered
chaiml-cogito32b-sftmor_54936_v1 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 3232.00s
Shutdown handler de-registered
chaiml-cogito32b-sftmor_54936_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-sftmor_54936_v1 status is now torndown due to DeploymentManager action