chaiml-cogito32b-sft-ne_19811

developer_uid: NischayDnk

submission_id: chaiml-cogito32b-sft-ne_19811_v1

model_name: chaiml-cogito32b-sft-ne_19811_v1

model_group: ChaiML/cogito32b-sft-new

status: torndown

timestamp: 2025-04-21T11:23:41+00:00

num_battles: 6850

num_wins: 3317

celo_rating: 1275.25

family_friendly_score: 0.5766

family_friendly_standard_error: 0.00698759529452014

submission_type: basic

model_repo: ChaiML/cogito32b-sft-newparam-datav1

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': 0.2758981807769656, 'latency_mean': 3.6244325256347656, 'latency_p50': 3.5984679460525513, 'latency_p90': 4.008121538162231}, {'batch_size': 2, 'throughput': 0.44471188015196433, 'latency_mean': 4.488240550756455, 'latency_p50': 4.4754098653793335, 'latency_p90': 4.957122278213501}, {'batch_size': 3, 'throughput': 0.5898506449821784, 'latency_mean': 5.061619802713394, 'latency_p50': 5.089579224586487, 'latency_p90': 5.589176368713379}, {'batch_size': 5, 'throughput': 0.7885346164660386, 'latency_mean': 6.317297813892364, 'latency_p50': 6.3028223514556885, 'latency_p90': 7.070372939109802}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-cogito32b-sft-ne_19811_v1

is_internal_developer: False

language_model: ChaiML/cogito32b-sft-newparam-datav1

model_size: 33B

ranking_group: single

throughput_3p7s: 0.29

us_pacific_date: 2025-04-21

win_ratio: 0.48423357664233574

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], '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-ne-19811-v1-mkmlizer
Waiting for job on chaiml-cogito32b-sft-ne-19811-v1-mkmlizer to finish
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: Downloaded to shared memory in 105.407s
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppbn6tpl0, device:0
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: quantized model in 63.153s
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: Processed model ChaiML/cogito32b-sft-newparam-datav1 in 168.560s
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/config.json
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/added_tokens.json
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/special_tokens_map.json
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/tokenizer_config.json
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/merges.txt
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/vocab.json
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/tokenizer.json
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/flywheel_model.2.safetensors
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/flywheel_model.1.safetensors
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito32b-sft-ne-19811-v1/flywheel_model.0.safetensors
chaiml-cogito32b-sft-ne-19811-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 39.51it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:09, 75.73it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:08, 89.27it/s]
Loading 0:   5%|▍         | 37/771 [00:00<00:08, 91.01it/s]
Loading 0:   6%|▌         | 47/771 [00:00<00:13, 52.31it/s]
Loading 0:   7%|▋         | 55/771 [00:00<00:14, 50.82it/s]
Loading 0:   8%|▊         | 65/771 [00:01<00:12, 56.52it/s]
Loading 0:  10%|▉         | 76/771 [00:01<00:10, 68.10it/s]
Loading 0:  11%|█▏        | 87/771 [00:01<00:08, 77.53it/s]
Loading 0:  12%|█▏        | 96/771 [00:01<00:08, 79.90it/s]
Loading 0:  14%|█▎        | 106/771 [00:01<00:10, 60.61it/s]
Loading 0:  15%|█▍        | 114/771 [00:01<00:10, 60.58it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:11, 58.67it/s]
Loading 0:  17%|█▋        | 133/771 [00:02<00:09, 66.54it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:06, 88.79it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:07, 77.61it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 56.11it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 55.45it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 56.84it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 67.52it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 77.23it/s]
Loading 0:  28%|██▊       | 216/771 [00:03<00:06, 80.32it/s]
Loading 0:  29%|██▉       | 226/771 [00:03<00:09, 60.20it/s]
Loading 0:  30%|███       | 234/771 [00:03<00:10, 52.28it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 59.29it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 66.24it/s]
Loading 0:  35%|███▍      | 269/771 [00:04<00:06, 71.97it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:07, 68.67it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:08, 59.26it/s]
Loading 0:  39%|███▉      | 303/771 [00:18<03:16,  2.39it/s]
Loading 0:  41%|████      | 315/771 [00:19<02:10,  3.50it/s]
Loading 0:  42%|████▏     | 326/771 [00:19<01:30,  4.92it/s]
Loading 0:  43%|████▎     | 335/771 [00:19<01:07,  6.48it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:48,  8.68it/s]
Loading 0:  46%|████▌     | 353/771 [00:19<00:41, 10.11it/s]
Loading 0:  47%|████▋     | 365/771 [00:20<00:27, 14.65it/s]
Loading 0:  49%|████▉     | 377/771 [00:20<00:19, 20.26it/s]
Loading 0:  50%|█████     | 389/771 [00:20<00:14, 26.93it/s]
Loading 0:  53%|█████▎    | 406/771 [00:20<00:10, 34.47it/s]
Loading 0:  54%|█████▎    | 414/771 [00:20<00:10, 34.98it/s]
Loading 0:  55%|█████▍    | 424/771 [00:20<00:08, 42.49it/s]
Loading 0:  56%|█████▋    | 435/771 [00:21<00:06, 52.02it/s]
Loading 0:  58%|█████▊    | 447/771 [00:21<00:05, 59.71it/s]
Loading 0:  59%|█████▉    | 458/771 [00:21<00:04, 64.43it/s]
Loading 0:  61%|██████    | 467/771 [00:21<00:05, 53.38it/s]
Loading 0:  61%|██████▏   | 474/771 [00:21<00:05, 50.54it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 57.65it/s]
Loading 0:  64%|██████▍   | 496/771 [00:21<00:04, 67.72it/s]
Loading 0:  66%|██████▌   | 507/771 [00:22<00:03, 77.01it/s]
Loading 0:  67%|██████▋   | 517/771 [00:22<00:03, 82.51it/s]
Loading 0:  68%|██████▊   | 527/771 [00:22<00:04, 59.35it/s]
Loading 0:  69%|██████▉   | 535/771 [00:22<00:04, 56.55it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 60.63it/s]
Loading 0:  72%|███████▏  | 557/771 [00:22<00:03, 67.77it/s]
Loading 0:  74%|███████▍  | 569/771 [00:23<00:02, 73.42it/s]
Loading 0:  76%|███████▌  | 586/771 [00:23<00:02, 69.55it/s]
Loading 0:  77%|███████▋  | 594/771 [00:23<00:02, 60.07it/s]
Loading 0:  78%|███████▊  | 604/771 [00:23<00:02, 66.22it/s]
Loading 0:  80%|███████▉  | 616/771 [00:23<00:02, 72.26it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<00:57,  2.52it/s]
Loading 0:  83%|████████▎ | 637/771 [00:38<00:38,  3.45it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:27,  4.48it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:21,  5.50it/s]
Loading 0:  86%|████████▋ | 665/771 [00:39<00:12,  8.26it/s]
Loading 0:  88%|████████▊ | 677/771 [00:39<00:07, 11.89it/s]
Loading 0:  89%|████████▉ | 689/771 [00:39<00:04, 16.55it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 23.34it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 25.49it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 32.00it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 39.86it/s]
Loading 0:  97%|█████████▋| 749/771 [00:40<00:00, 47.94it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:00,  5.28it/s]
                                                            
Job chaiml-cogito32b-sft-ne-19811-v1-mkmlizer completed after 206.99s with status: succeeded
Stopping job with name chaiml-cogito32b-sft-ne-19811-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cogito32b-sft-ne-19811-v1
Waiting for inference service chaiml-cogito32b-sft-ne-19811-v1 to be ready
Inference service chaiml-cogito32b-sft-ne-19811-v1 ready after 130.4558925628662s
Pipeline stage MKMLDeployer completed in 130.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7751872539520264s
Received healthy response to inference request in 4.135544776916504s
Received healthy response to inference request in 3.3595430850982666s
Received healthy response to inference request in 4.019669055938721s
Received healthy response to inference request in 3.264342784881592s
5 requests
0 failed requests
5th percentile: 3.283382844924927
10th percentile: 3.3024229049682616
20th percentile: 3.3405030250549315
30th percentile: 3.4426719188690185
40th percentile: 3.6089295864105226
50th percentile: 3.7751872539520264
60th percentile: 3.872979974746704
70th percentile: 3.970772695541382
80th percentile: 4.042844200134278
90th percentile: 4.089194488525391
95th percentile: 4.112369632720947
99th percentile: 4.130909748077393
mean time: 3.710857391357422
%s, retrying in %s seconds...
Received healthy response to inference request in 3.200251340866089s
Received healthy response to inference request in 3.223917007446289s
Received healthy response to inference request in 3.615410327911377s
Received healthy response to inference request in 3.3798227310180664s
Received healthy response to inference request in 3.227552890777588s
5 requests
0 failed requests
5th percentile: 3.2049844741821287
10th percentile: 3.209717607498169
20th percentile: 3.219183874130249
30th percentile: 3.224644184112549
40th percentile: 3.2260985374450684
50th percentile: 3.227552890777588
60th percentile: 3.2884608268737794
70th percentile: 3.349368762969971
80th percentile: 3.4269402503967283
90th percentile: 3.5211752891540526
95th percentile: 3.568292808532715
99th percentile: 3.6059868240356447
mean time: 3.329390859603882
Pipeline stage StressChecker completed in 37.39s
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 0.67s
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 1.05s
Shutdown handler de-registered
chaiml-cogito32b-sft-ne_19811_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6014.34s
Shutdown handler de-registered
chaiml-cogito32b-sft-ne_19811_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito32b-sft-ne_19811_v1 status is now torndown due to DeploymentManager action