chaiml-nemo-20241017-ti_8098

developer_uid: Jellywibble

submission_id: chaiml-nemo-20241017-ti_8098_v11

model_name: chaiml-nemo-20241017-ti_8098_v11

model_group: ChaiML/nemo-20241017-tie

status: inactive

timestamp: 2024-11-30T18:02:37+00:00

num_battles: 13836

num_wins: 6406

celo_rating: 1239.31

family_friendly_score: 0.5976

family_friendly_standard_error: 0.006935044916941779

submission_type: basic

model_repo: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 768

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6784897017407296, 'latency_mean': 1.4738058567047119, 'latency_p50': 1.4487977027893066, 'latency_p90': 1.6434290647506713}, {'batch_size': 4, 'throughput': 1.6609594464107398, 'latency_mean': 2.3978163969516753, 'latency_p50': 2.3903998136520386, 'latency_p90': 2.7487540245056152}, {'batch_size': 5, 'throughput': 1.8264392835027004, 'latency_mean': 2.717057431936264, 'latency_p50': 2.727040648460388, 'latency_p90': 2.986604833602905}, {'batch_size': 8, 'throughput': 2.1997256756995776, 'latency_mean': 3.61170556306839, 'latency_p50': 3.626213312149048, 'latency_p90': 4.049780011177063}, {'batch_size': 10, 'throughput': 2.3020907168600084, 'latency_mean': 4.285889111757278, 'latency_p50': 4.290968060493469, 'latency_p90': 4.831053113937378}, {'batch_size': 12, 'throughput': 2.384925798119422, 'latency_mean': 4.9817523097991945, 'latency_p50': 5.047474980354309, 'latency_p90': 5.7130062818527225}, {'batch_size': 15, 'throughput': 2.4666123390666437, 'latency_mean': 6.002158412933349, 'latency_p50': 6.019604682922363, 'latency_p90': 6.8013831615448}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-nemo-20241017-ti_8098_v11

is_internal_developer: True

language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

model_size: 13B

ranking_group: single

throughput_3p7s: 2.23

us_pacific_date: 2024-11-30

win_ratio: 0.4629950852847644

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 4, '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-20241017-ti-8098-v11-mkmlizer
Waiting for job on chaiml-nemo-20241017-ti-8098-v11-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: Downloaded to shared memory in 50.655s
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw6vlhnpp, device:0
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: quantized model in 40.067s
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 90.723s
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v11
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v11/config.json
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v11/special_tokens_map.json
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v11/tokenizer_config.json
chaiml-nemo-20241017-ti-8098-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-ti-8098-v11/tokenizer.json
Job chaiml-nemo-20241017-ti-8098-v11-mkmlizer completed after 146.97s with status: succeeded
Stopping job with name chaiml-nemo-20241017-ti-8098-v11-mkmlizer
Pipeline stage MKMLizer completed in 147.51s
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-nemo-20241017-ti-8098-v11
Waiting for inference service chaiml-nemo-20241017-ti-8098-v11 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-20241017-ti-8098-v11 ready after 120.41686654090881s
Pipeline stage MKMLDeployer completed in 121.06s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.7228665351867676s
Received healthy response to inference request in 1.7796401977539062s
Received healthy response to inference request in 2.042618989944458s
Received healthy response to inference request in 1.4644107818603516s
5 requests
1 failed requests
5th percentile: 1.5161019325256349
10th percentile: 1.567793083190918
20th percentile: 1.6711753845214843
30th percentile: 1.7342212677001954
40th percentile: 1.7569307327270507
50th percentile: 1.7796401977539062
60th percentile: 1.884831714630127
70th percentile: 1.9900232315063475
80th percentile: 5.659042978286746
90th percentile: 12.891890954971316
95th percentile: 16.508314943313597
99th percentile: 19.401454133987425
mean time: 5.426855087280273
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9915366172790527s
Received healthy response to inference request in 1.6367418766021729s
Received healthy response to inference request in 1.7100083827972412s
Received healthy response to inference request in 1.4370758533477783s
Received healthy response to inference request in 1.5061602592468262s
5 requests
0 failed requests
5th percentile: 1.450892734527588
10th percentile: 1.4647096157073975
20th percentile: 1.4923433780670166
30th percentile: 1.5322765827178955
40th percentile: 1.5845092296600343
50th percentile: 1.6367418766021729
60th percentile: 1.6660484790802002
70th percentile: 1.6953550815582275
80th percentile: 1.7663140296936035
90th percentile: 1.8789253234863281
95th percentile: 1.9352309703826904
99th percentile: 1.9802754878997804
mean time: 1.6563045978546143
Pipeline stage StressChecker completed in 38.34s
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 2.49s
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 2.41s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v11 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2709.66s
Shutdown handler de-registered
chaiml-nemo-20241017-ti_8098_v11 status is now inactive due to auto deactivation removed underperforming models