chaiml-cogito12b-sft-ne_75354

developer_uid: NischayDnk

submission_id: chaiml-cogito12b-sft-ne_75354_v2

model_name: chaiml-cogito12b-sft-ne_75354_v2

model_group: ChaiML/cogito12b-sft-new

status: torndown

timestamp: 2025-04-22T08:05:47+00:00

num_battles: 9216

num_wins: 4538

celo_rating: 1283.86

family_friendly_score: 0.5324

family_friendly_standard_error: 0.007056206346189147

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': 0.4797682923248718, 'latency_mean': 2.084266220331192, 'latency_p50': 2.0693607330322266, 'latency_p90': 2.3150755405426025}, {'batch_size': 3, 'throughput': 0.8831294093571271, 'latency_mean': 3.3885922372341155, 'latency_p50': 3.397439479827881, 'latency_p90': 3.764077877998352}, {'batch_size': 5, 'throughput': 1.0835182878101368, 'latency_mean': 4.601809833049774, 'latency_p50': 4.624069094657898, 'latency_p90': 5.165721774101257}, {'batch_size': 6, 'throughput': 1.1515504922231896, 'latency_mean': 5.19489540219307, 'latency_p50': 5.18575644493103, 'latency_p90': 5.844387173652649}, {'batch_size': 10, 'throughput': 1.240393830920488, 'latency_mean': 7.978381776809693, 'latency_p50': 8.007421612739563, 'latency_p90': 8.916084551811219}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-cogito12b-sft-ne_75354_v2

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: 0.4924045138888889

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': ['\n', '<|im_end|>'], '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-v2-mkmlizer
Waiting for job on chaiml-cogito12b-sft-ne-75354-v2-mkmlizer to finish
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║       /___/                                                         ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║                                                                     ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║                                                                     ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║                                                                     ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ║                                                                     ║
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: Downloaded to shared memory in 39.594s
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplas6u45q, device:0
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: quantized model in 36.303s
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: Processed model ChaiML/cogito12b-sft-new-noeos in 75.898s
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/config.json
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/special_tokens_map.json
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/added_tokens.json
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/tokenizer_config.json
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/merges.txt
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/vocab.json
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/tokenizer.json
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/flywheel_model.1.safetensors
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cogito12b-sft-ne-75354-v2/flywheel_model.0.safetensors
chaiml-cogito12b-sft-ne-75354-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 142.26it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 130.69it/s]
Loading 0:   9%|▉         | 51/579 [00:00<00:03, 152.44it/s]
Loading 0:  12%|█▏        | 67/579 [00:00<00:03, 144.11it/s]
Loading 0:  14%|█▍        | 82/579 [00:00<00:05, 91.95it/s] 
Loading 0:  16%|█▋        | 95/579 [00:00<00:04, 100.33it/s]
Loading 0:  19%|█▉        | 111/579 [00:00<00:04, 114.47it/s]
Loading 0:  22%|██▏       | 130/579 [00:01<00:03, 128.22it/s]
Loading 0:  26%|██▌       | 149/579 [00:01<00:02, 144.12it/s]
Loading 0:  28%|██▊       | 165/579 [00:01<00:02, 140.83it/s]
Loading 0:  31%|███       | 180/579 [00:01<00:03, 130.53it/s]
Loading 0:  34%|███▎      | 194/579 [00:01<00:04, 91.57it/s] 
Loading 0:  36%|███▌      | 208/579 [00:01<00:03, 98.00it/s]
Loading 0:  39%|███▊      | 224/579 [00:01<00:03, 111.50it/s]
Loading 0:  42%|████▏     | 243/579 [00:02<00:02, 125.69it/s]
Loading 0:  44%|████▍     | 257/579 [00:02<00:02, 122.56it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 140.38it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 104.86it/s]
Loading 0:  54%|█████▎    | 310/579 [00:02<00:02, 101.97it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 114.83it/s]
Loading 0:  59%|█████▉    | 341/579 [00:02<00:02, 116.12it/s]
Loading 0:  63%|██████▎   | 363/579 [00:03<00:01, 135.37it/s]
Loading 0:  65%|██████▌   | 378/579 [00:03<00:01, 131.99it/s]
Loading 0:  69%|██████▉   | 400/579 [00:03<00:01, 151.54it/s]
Loading 0:  72%|███████▏  | 416/579 [00:03<00:01, 97.60it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 111.67it/s]
Loading 0:  78%|███████▊  | 449/579 [00:03<00:01, 113.46it/s]
Loading 0:  81%|████████▏ | 471/579 [00:03<00:00, 132.35it/s]
Loading 0:  84%|████████▍ | 486/579 [00:04<00:00, 129.96it/s]
Loading 0:  88%|████████▊ | 507/579 [00:04<00:00, 149.15it/s]
Loading 0:  88%|████████▊ | 512/579 [00:25<00:00, 149.15it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:29,  2.25it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:25<00:21,  2.76it/s]
Loading 0:  92%|█████████▏| 535/579 [00:25<00:10,  4.02it/s]
Loading 0:  96%|█████████▌| 556/579 [00:25<00:03,  6.68it/s]
Loading 0:  99%|█████████▊| 571/579 [00:26<00:00,  9.26it/s]
                                                            
Job chaiml-cogito12b-sft-ne-75354-v2-mkmlizer completed after 104.86s with status: succeeded
Stopping job with name chaiml-cogito12b-sft-ne-75354-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.40s
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-cogito12b-sft-ne-75354-v2
Waiting for inference service chaiml-cogito12b-sft-ne-75354-v2 to be ready
Inference service chaiml-cogito12b-sft-ne-75354-v2 ready after 130.4381160736084s
Pipeline stage MKMLDeployer completed in 130.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.951007127761841s
Received healthy response to inference request in 2.1416239738464355s
Received healthy response to inference request in 2.028590679168701s
Received healthy response to inference request in 2.1502928733825684s
Received healthy response to inference request in 2.1775500774383545s
5 requests
0 failed requests
5th percentile: 2.051197338104248
10th percentile: 2.073803997039795
20th percentile: 2.119017314910889
30th percentile: 2.143357753753662
40th percentile: 2.1468253135681152
50th percentile: 2.1502928733825684
60th percentile: 2.161195755004883
70th percentile: 2.1720986366271973
80th percentile: 2.332241487503052
90th percentile: 2.6416243076324464
95th percentile: 2.7963157176971434
99th percentile: 2.9200688457489012
mean time: 2.28981294631958
Pipeline stage StressChecker completed in 13.13s
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 0.70s
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 0.74s
Shutdown handler de-registered
chaiml-cogito12b-sft-ne_75354_v2 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 4753.37s
Shutdown handler de-registered
chaiml-cogito12b-sft-ne_75354_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-cogito12b-sft-ne_75354_v2 status is now torndown due to DeploymentManager action