chaiml-nemo-espresso-gi_20459

developer_uid: azuruce

submission_id: chaiml-nemo-espresso-gi_20459_v1

model_name: giraffe

model_group: ChaiML/nemo_espresso_gir

status: torndown

timestamp: 2025-04-11T10:03:43+00:00

num_battles: 7325

num_wins: 3324

celo_rating: 1250.2

family_friendly_score: 0.6115999999999999

family_friendly_standard_error: 0.006892683657328254

submission_type: basic

model_repo: ChaiML/nemo_espresso_giraffe_250411_albert_sft-2e128a

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6024792288937426, 'latency_mean': 1.6597141408920288, 'latency_p50': 1.653221845626831, 'latency_p90': 1.847502303123474}, {'batch_size': 3, 'throughput': 1.1061089417163728, 'latency_mean': 2.7080914211273193, 'latency_p50': 2.691998600959778, 'latency_p90': 2.9856266260147093}, {'batch_size': 5, 'throughput': 1.328669763824621, 'latency_mean': 3.7415000808238985, 'latency_p50': 3.7406811714172363, 'latency_p90': 4.124588489532471}, {'batch_size': 6, 'throughput': 1.391701919108265, 'latency_mean': 4.291323010921478, 'latency_p50': 4.301611304283142, 'latency_p90': 4.780189824104309}, {'batch_size': 8, 'throughput': 1.469829170798064, 'latency_mean': 5.410825412273407, 'latency_p50': 5.394392251968384, 'latency_p90': 6.093137931823731}, {'batch_size': 10, 'throughput': 1.4916456489622028, 'latency_mean': 6.6519563555717465, 'latency_p50': 6.670977711677551, 'latency_p90': 7.537637495994568}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: giraffe

is_internal_developer: False

language_model: ChaiML/nemo_espresso_giraffe_250411_albert_sft-2e128a

model_size: 13B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-04-11

win_ratio: 0.45378839590443687

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 99, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_of_text|>', '<|eot_id|>', 'You:', 'Bot:', 'Me:', '\n', '###', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', '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-nemo-espresso-gi-20459-v1-mkmlizer
Waiting for job on chaiml-nemo-espresso-gi-20459-v1-mkmlizer to finish
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: Downloaded to shared memory in 39.208s
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprwvfbbs9, device:0
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: quantized model in 36.458s
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: Processed model ChaiML/nemo_espresso_giraffe_250411_albert_sft-2e128a in 75.666s
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-gi-20459-v1
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-gi-20459-v1/config.json
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-gi-20459-v1/special_tokens_map.json
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-gi-20459-v1/tokenizer_config.json
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-gi-20459-v1/tokenizer.json
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-gi-20459-v1/flywheel_model.0.safetensors
chaiml-nemo-espresso-gi-20459-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.77it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.67it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.30it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.71it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.50it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.82it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.76it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.99it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.56it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.64it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.71it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.02it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.58it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 37.79it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.15it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:12, 21.19it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:10, 23.73it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:08, 29.05it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:08, 30.07it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:08, 29.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 37.37it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.01it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.34it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.66it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 27.67it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 28.36it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.54it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.92it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.69it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 39.34it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.25it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 44.74it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 45.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:04, 41.10it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 47.94it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 49.34it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 43.55it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 44.55it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.96it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 34.39it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 33.59it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 40.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:02, 40.43it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.73it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.54it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.29it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.85it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 41.15it/s]
Loading 0:  76%|███████▌  | 276/363 [00:07<00:02, 40.66it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 45.62it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 44.83it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 43.84it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 47.86it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:22,  2.62it/s]
Loading 0:  85%|████████▌ | 309/363 [00:14<00:16,  3.35it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:11,  4.32it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.77it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  9.21it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.70it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.47it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.11it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.00it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 27.97it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 30.85it/s]
                                                            
Job chaiml-nemo-espresso-gi-20459-v1-mkmlizer completed after 104.77s with status: succeeded
Stopping job with name chaiml-nemo-espresso-gi-20459-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.28s
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-nemo-espresso-gi-20459-v1
Waiting for inference service chaiml-nemo-espresso-gi-20459-v1 to be ready
Inference service chaiml-nemo-espresso-gi-20459-v1 ready after 110.41682696342468s
Pipeline stage MKMLDeployer completed in 110.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9574344158172607s
Received healthy response to inference request in 1.6622495651245117s
Received healthy response to inference request in 1.5120174884796143s
Received healthy response to inference request in 1.45228910446167s
Received healthy response to inference request in 1.4773685932159424s
5 requests
0 failed requests
5th percentile: 1.4573050022125245
10th percentile: 1.462320899963379
20th percentile: 1.4723526954650878
30th percentile: 1.4842983722686767
40th percentile: 1.4981579303741455
50th percentile: 1.5120174884796143
60th percentile: 1.5721103191375732
70th percentile: 1.6322031497955323
80th percentile: 1.7212865352630615
90th percentile: 1.8393604755401611
95th percentile: 1.898397445678711
99th percentile: 1.9456270217895508
mean time: 1.6122718334197998
Pipeline stage StressChecker completed in 9.23s
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 0.64s
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 0.72s
Shutdown handler de-registered
chaiml-nemo-espresso-gi_20459_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-nemo-espresso-gi-20459-v1-profiler
Waiting for inference service chaiml-nemo-espresso-gi-20459-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4423.66s
Shutdown handler de-registered
chaiml-nemo-espresso-gi_20459_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-espresso-gi_20459_v1 status is now torndown due to DeploymentManager action