chaiml-exp501-cogito14b_37332

developer_uid: NischayDnk

submission_id: chaiml-exp501-cogito14b_37332_v1

model_name: chaiml-exp501-cogito14b_37332_v1

model_group: ChaiML/exp501-cogito14b-

status: torndown

timestamp: 2025-04-15T21:51:59+00:00

num_battles: 7632

num_wins: 3869

celo_rating: 1294.83

family_friendly_score: 0.5352

family_friendly_standard_error: 0.007053523374881521

submission_type: basic

model_repo: ChaiML/exp501-cogito14b-dpo-stage1pub-datav1sft1285-9k

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': 0.4733425197258533, 'latency_mean': 2.1125634241104128, 'latency_p50': 2.13678240776062, 'latency_p90': 2.321560835838318}, {'batch_size': 3, 'throughput': 0.8814175882102429, 'latency_mean': 3.397568354606628, 'latency_p50': 3.3862162828445435, 'latency_p90': 3.73673620223999}, {'batch_size': 5, 'throughput': 1.0824054708188209, 'latency_mean': 4.5978029239177705, 'latency_p50': 4.591367721557617, 'latency_p90': 5.119006538391113}, {'batch_size': 6, 'throughput': 1.138119195012206, 'latency_mean': 5.245485240221024, 'latency_p50': 5.302243947982788, 'latency_p90': 5.827844142913818}, {'batch_size': 10, 'throughput': 1.2340830946637646, 'latency_mean': 8.050280920267106, 'latency_p50': 7.982016921043396, 'latency_p90': 9.165141677856445}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-exp501-cogito14b_37332_v1

is_internal_developer: False

language_model: ChaiML/exp501-cogito14b-dpo-stage1pub-datav1sft1285-9k

model_size: 15B

ranking_group: single

throughput_3p7s: 0.95

us_pacific_date: 2025-04-15

win_ratio: 0.5069444444444444

generation_params: {'temperature': 0.85, 'top_p': 0.94, 'min_p': 0.02, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, '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-exp501-cogito14b-37332-v1-mkmlizer
Waiting for job on chaiml-exp501-cogito14b-37332-v1-mkmlizer to finish
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║                                                                     ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║                                                                     ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║                                                                     ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ║                                                                     ║
chaiml-exp501-cogito14b-37332-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp501-cogito14b-37332-v1-mkmlizer: Downloaded to shared memory in 54.781s
chaiml-exp501-cogito14b-37332-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcmc7yxo_, device:0
chaiml-exp501-cogito14b-37332-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp501-cogito14b-37332-v1-mkmlizer: quantized model in 36.411s
chaiml-exp501-cogito14b-37332-v1-mkmlizer: Processed model ChaiML/exp501-cogito14b-dpo-stage1pub-datav1sft1285-9k in 91.192s
chaiml-exp501-cogito14b-37332-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp501-cogito14b-37332-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp501-cogito14b-37332-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/config.json
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/added_tokens.json
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/special_tokens_map.json
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/tokenizer_config.json
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/merges.txt
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/vocab.json
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/tokenizer.json
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/flywheel_model.1.safetensors
chaiml-exp501-cogito14b-37332-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp501-cogito14b-37332-v1/flywheel_model.0.safetensors
chaiml-exp501-cogito14b-37332-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:03, 142.80it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 128.41it/s]
Loading 0:   8%|▊         | 48/579 [00:00<00:03, 149.75it/s]
Loading 0:  11%|█         | 64/579 [00:00<00:03, 141.39it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:04, 101.24it/s]
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 107.28it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 112.91it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:03, 116.76it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 133.90it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 139.67it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 132.33it/s]
Loading 0:  32%|███▏      | 186/579 [00:01<00:02, 141.51it/s]
Loading 0:  35%|███▍      | 201/579 [00:01<00:04, 89.45it/s] 
Loading 0:  38%|███▊      | 219/579 [00:01<00:03, 104.52it/s]
Loading 0:  40%|████      | 233/579 [00:01<00:03, 107.96it/s]
Loading 0:  44%|████▎     | 252/579 [00:02<00:02, 126.74it/s]
Loading 0:  46%|████▌     | 267/579 [00:02<00:02, 131.89it/s]
Loading 0:  49%|████▊     | 282/579 [00:02<00:02, 127.97it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 104.77it/s]
Loading 0:  53%|█████▎    | 309/579 [00:02<00:02, 100.08it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 115.56it/s]
Loading 0:  59%|█████▊    | 340/579 [00:02<00:02, 117.68it/s]
Loading 0:  61%|██████    | 353/579 [00:02<00:01, 120.69it/s]
Loading 0:  65%|██████▍   | 375/579 [00:03<00:01, 139.98it/s]
Loading 0:  67%|██████▋   | 390/579 [00:03<00:01, 134.44it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 104.95it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 100.59it/s]
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 116.29it/s]
Loading 0:  77%|███████▋  | 448/579 [00:03<00:01, 118.96it/s]
Loading 0:  80%|███████▉  | 461/579 [00:03<00:00, 120.62it/s]
Loading 0:  83%|████████▎ | 483/579 [00:04<00:00, 140.42it/s]
Loading 0:  86%|████████▌ | 498/579 [00:04<00:00, 135.28it/s]
Loading 0:  88%|████████▊ | 512/579 [00:21<00:00, 135.28it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:27,  2.40it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:25<00:19,  2.91it/s]
Loading 0:  92%|█████████▏| 535/579 [00:25<00:10,  4.16it/s]
Loading 0:  96%|█████████▌| 556/579 [00:26<00:03,  6.81it/s]
Loading 0:  99%|█████████▊| 571/579 [00:26<00:00,  9.36it/s]
                                                            
Job chaiml-exp501-cogito14b-37332-v1-mkmlizer completed after 117.19s with status: succeeded
Stopping job with name chaiml-exp501-cogito14b-37332-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp501-cogito14b-37332-v1
Waiting for inference service chaiml-exp501-cogito14b-37332-v1 to be ready
Inference service chaiml-exp501-cogito14b-37332-v1 ready after 130.7048671245575s
Pipeline stage MKMLDeployer completed in 131.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6805713176727295s
Received healthy response to inference request in 2.147284984588623s
Received healthy response to inference request in 2.138842821121216s
Received healthy response to inference request in 2.2508320808410645s
Received healthy response to inference request in 2.206568717956543s
5 requests
0 failed requests
5th percentile: 2.1405312538146974
10th percentile: 2.1422196865081786
20th percentile: 2.1455965518951414
30th percentile: 2.159141731262207
40th percentile: 2.182855224609375
50th percentile: 2.206568717956543
60th percentile: 2.2242740631103515
70th percentile: 2.24197940826416
80th percentile: 2.3367799282073975
90th percentile: 2.5086756229400633
95th percentile: 2.5946234703063964
99th percentile: 2.663381748199463
mean time: 2.284819984436035
Pipeline stage StressChecker completed in 12.63s
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 0.63s
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 0.63s
Shutdown handler de-registered
chaiml-exp501-cogito14b_37332_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp501-cogito14b-37332-v1-profiler
Waiting for inference service chaiml-exp501-cogito14b-37332-v1-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 2905.73s
Shutdown handler de-registered
chaiml-exp501-cogito14b_37332_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp501-cogito14b_37332_v1 status is now torndown due to DeploymentManager action