developer_uid: NischayDnk
submission_id: chaiml-exp502-cogito14b_11869_v2
model_name: chaiml-exp502-cogito14b_11869_v2
model_group: ChaiML/exp502-cogito14b-
status: torndown
timestamp: 2025-04-16T03:01:49+00:00
num_battles: 7751
num_wins: 3945
celo_rating: 1293.07
family_friendly_score: 0.5428
family_friendly_standard_error: 0.007045114051596325
submission_type: basic
model_repo: ChaiML/exp502-cogito14b-dpotype2-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': 0.47700058270996587, 'latency_mean': 2.096354693174362, 'latency_p50': 2.101957321166992, 'latency_p90': 2.3087825775146484}, {'batch_size': 3, 'throughput': 0.8869336766926216, 'latency_mean': 3.374823936223984, 'latency_p50': 3.3855570554733276, 'latency_p90': 3.7487114906311034}, {'batch_size': 5, 'throughput': 1.069350578452512, 'latency_mean': 4.644357495307922, 'latency_p50': 4.6640318632125854, 'latency_p90': 5.210073828697205}, {'batch_size': 6, 'throughput': 1.1382930341603672, 'latency_mean': 5.254888108968735, 'latency_p50': 5.3063894510269165, 'latency_p90': 5.924021744728089}, {'batch_size': 10, 'throughput': 1.2192390961138608, 'latency_mean': 8.13060490489006, 'latency_p50': 8.145082592964172, 'latency_p90': 9.152729868888855}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-exp502-cogito14b_11869_v2
is_internal_developer: False
language_model: ChaiML/exp502-cogito14b-dpotype2-stage1pub-datav1sft1285-9k
model_size: 15B
ranking_group: single
throughput_3p7s: 0.95
us_pacific_date: 2025-04-15
win_ratio: 0.5089665849567798
generation_params: {'temperature': 0.75, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, '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-exp502-cogito14b-11869-v2-mkmlizer
Waiting for job on chaiml-exp502-cogito14b-11869-v2-mkmlizer to finish
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║                                                                     ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║                                                                     ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║                                                                     ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ║                                                                     ║
chaiml-exp502-cogito14b-11869-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp502-cogito14b-11869-v2-mkmlizer: Downloaded to shared memory in 52.752s
chaiml-exp502-cogito14b-11869-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk2ahvh1j, device:0
chaiml-exp502-cogito14b-11869-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp502-cogito14b-11869-v2-mkmlizer: quantized model in 36.900s
chaiml-exp502-cogito14b-11869-v2-mkmlizer: Processed model ChaiML/exp502-cogito14b-dpotype2-stage1pub-datav1sft1285-9k in 89.652s
chaiml-exp502-cogito14b-11869-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp502-cogito14b-11869-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp502-cogito14b-11869-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/config.json
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/added_tokens.json
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/special_tokens_map.json
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/tokenizer_config.json
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/merges.txt
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/vocab.json
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/tokenizer.json
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/flywheel_model.1.safetensors
chaiml-exp502-cogito14b-11869-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp502-cogito14b-11869-v2/flywheel_model.0.safetensors
chaiml-exp502-cogito14b-11869-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 140.51it/s]
Loading 0:   5%|▌         | 30/579 [00:00<00:04, 129.60it/s]
Loading 0:   9%|▉         | 51/579 [00:00<00:03, 151.61it/s]
Loading 0:  12%|█▏        | 67/579 [00:00<00:03, 143.52it/s]
Loading 0:  14%|█▍        | 82/579 [00:00<00:05, 90.93it/s] 
Loading 0:  16%|█▋        | 95/579 [00:00<00:04, 99.31it/s]
Loading 0:  19%|█▊        | 108/579 [00:00<00:04, 105.87it/s]
Loading 0:  22%|██▏       | 128/579 [00:01<00:03, 129.57it/s]
Loading 0:  26%|██▌       | 149/579 [00:01<00:02, 143.69it/s]
Loading 0:  28%|██▊       | 165/579 [00:01<00:02, 139.78it/s]
Loading 0:  31%|███       | 180/579 [00:01<00:03, 127.09it/s]
Loading 0:  34%|███▎      | 194/579 [00:01<00:04, 89.92it/s] 
Loading 0:  36%|███▌      | 208/579 [00:01<00:03, 96.27it/s]
Loading 0:  38%|███▊      | 221/579 [00:01<00:03, 103.10it/s]
Loading 0:  41%|████▏     | 239/579 [00:02<00:02, 120.92it/s]
Loading 0:  44%|████▍     | 255/579 [00:02<00:02, 129.49it/s]
Loading 0:  47%|████▋     | 270/579 [00:02<00:02, 128.05it/s]
Loading 0:  50%|█████     | 291/579 [00:02<00:01, 149.20it/s]
Loading 0:  53%|█████▎    | 307/579 [00:02<00:03, 90.58it/s] 
Loading 0:  56%|█████▌    | 325/579 [00:02<00:02, 107.37it/s]
Loading 0:  59%|█████▊    | 340/579 [00:02<00:02, 110.55it/s]
Loading 0:  61%|██████    | 354/579 [00:03<00:01, 116.02it/s]
Loading 0:  64%|██████▍   | 373/579 [00:03<00:01, 133.31it/s]
Loading 0:  67%|██████▋   | 389/579 [00:03<00:01, 127.99it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 102.02it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 97.34it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 113.19it/s]
Loading 0:  78%|███████▊  | 449/579 [00:03<00:01, 114.72it/s]
Loading 0:  81%|████████  | 469/579 [00:03<00:00, 135.04it/s]
Loading 0:  84%|████████▎ | 484/579 [00:04<00:00, 131.09it/s]
Loading 0:  86%|████████▋ | 500/579 [00:04<00:00, 138.23it/s]
Loading 0:  88%|████████▊ | 512/579 [00:22<00:00, 138.23it/s]
Loading 0:  89%|████████▊ | 513/579 [00:26<00:28,  2.29it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:26<00:20,  2.79it/s]
Loading 0:  92%|█████████▏| 535/579 [00:26<00:10,  4.04it/s]
Loading 0:  96%|█████████▌| 556/579 [00:26<00:03,  6.66it/s]
Loading 0:  99%|█████████▊| 571/579 [00:26<00:00,  9.20it/s]
                                                            

Job chaiml-exp502-cogito14b-11869-v2-mkmlizer completed after 115.65s with status: succeeded
Stopping job with name chaiml-exp502-cogito14b-11869-v2-mkmlizer
Pipeline stage MKMLizer completed in 116.33s
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-exp502-cogito14b-11869-v2
Waiting for inference service chaiml-exp502-cogito14b-11869-v2 to be ready
Inference service chaiml-exp502-cogito14b-11869-v2 ready after 130.56995725631714s
Pipeline stage MKMLDeployer completed in 131.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4071855545043945s
Received healthy response to inference request in 1.9400575160980225s
Received healthy response to inference request in 2.007859230041504s
Received healthy response to inference request in 2.0999879837036133s
Received healthy response to inference request in 2.008070230484009s
5 requests
0 failed requests
5th percentile: 1.9536178588867188
10th percentile: 1.9671782016754151
20th percentile: 1.9942988872528076
30th percentile: 2.007901430130005
40th percentile: 2.007985830307007
50th percentile: 2.008070230484009
60th percentile: 2.0448373317718507
70th percentile: 2.0816044330596926
80th percentile: 2.1614274978637695
90th percentile: 2.284306526184082
95th percentile: 2.3457460403442383
99th percentile: 2.3948976516723635
mean time: 2.0926321029663084
Pipeline stage StressChecker completed in 11.74s
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 0.69s
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 0.69s
Shutdown handler de-registered
chaiml-exp502-cogito14b_11869_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 0.10s
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-exp502-cogito14b-11869-v2-profiler
Waiting for inference service chaiml-exp502-cogito14b-11869-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 2799.61s
Shutdown handler de-registered
chaiml-exp502-cogito14b_11869_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp502-cogito14b_11869_v2 status is now torndown due to DeploymentManager action