submission_id: chaiml-nemo-20241017-tie_8098_v8
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1265.23
display_name: chaiml-nemo-20241017-tie_8098_v8
family_friendly_score: 0.5866
family_friendly_standard_error: 0.0069642004566209895
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}
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert
latencies: [{'batch_size': 1, 'throughput': 0.6150370166317337, 'latency_mean': 1.625851068496704, 'latency_p50': 1.618636965751648, 'latency_p90': 1.7992146492004395}, {'batch_size': 3, 'throughput': 1.1315260365712356, 'latency_mean': 2.637871034145355, 'latency_p50': 2.6347548961639404, 'latency_p90': 2.958636236190796}, {'batch_size': 5, 'throughput': 1.380072210285505, 'latency_mean': 3.6121048271656035, 'latency_p50': 3.6081610918045044, 'latency_p90': 4.070677852630615}, {'batch_size': 6, 'throughput': 1.4489160708350601, 'latency_mean': 4.118265240192414, 'latency_p50': 4.081860423088074, 'latency_p90': 4.616992402076721}, {'batch_size': 8, 'throughput': 1.5056307162559703, 'latency_mean': 5.277897847890854, 'latency_p50': 5.30113685131073, 'latency_p90': 5.922278904914855}, {'batch_size': 10, 'throughput': 1.5382675438121967, 'latency_mean': 6.438643809556961, 'latency_p50': 6.4818642139434814, 'latency_p90': 7.2305192947387695}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/nemo-20241017-tie
model_name: chaiml-nemo-20241017-tie_8098_v8
model_num_parameters: 12772070400.0
model_repo: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert
model_size: 13B
num_battles: 13052
num_wins: 6949
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.4
timestamp: 2024-11-12T01:27:28+00:00
us_pacific_date: 2024-11-11
win_ratio: 0.5324088262335275
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-tie-8098-v8-mkmlizer
Waiting for job on chaiml-nemo-20241017-tie-8098-v8-mkmlizer to finish
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  Version: 0.11.33                                                   ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-tie-8098-v8-mkmlizer: Downloaded to shared memory in 60.467s
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq8kkgu_i, device:0
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: quantized model in 37.624s
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 98.091s
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v8
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v8/config.json
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v8/special_tokens_map.json
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v8/tokenizer_config.json
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v8/tokenizer.json
chaiml-nemo-20241017-tie-8098-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v8/flywheel_model.0.safetensors
Job chaiml-nemo-20241017-tie-8098-v8-mkmlizer completed after 124.74s with status: succeeded
Stopping job with name chaiml-nemo-20241017-tie-8098-v8-mkmlizer
Pipeline stage MKMLizer completed in 125.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-tie-8098-v8
Waiting for inference service chaiml-nemo-20241017-tie-8098-v8 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
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-tie-8098-v8 ready after 180.7448980808258s
Pipeline stage MKMLDeployer completed in 181.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.44755482673645s
Received healthy response to inference request in 1.7527940273284912s
Received healthy response to inference request in 1.5136642456054688s
Received healthy response to inference request in 1.4918675422668457s
Received healthy response to inference request in 1.621030569076538s
5 requests
0 failed requests
5th percentile: 1.4962268829345704
10th percentile: 1.5005862236022949
20th percentile: 1.509304904937744
30th percentile: 1.5351375102996827
40th percentile: 1.5780840396881104
50th percentile: 1.621030569076538
60th percentile: 1.6737359523773194
70th percentile: 1.7264413356781005
80th percentile: 1.8917461872100831
90th percentile: 2.169650506973267
95th percentile: 2.308602666854858
99th percentile: 2.419764394760132
mean time: 1.7653822422027587
Pipeline stage StressChecker completed in 10.26s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.73s
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 2.38s
Shutdown handler de-registered
chaiml-nemo-20241017-tie_8098_v8 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 2763.57s
Shutdown handler de-registered
chaiml-nemo-20241017-tie_8098_v8 status is now inactive due to auto deactivation removed underperforming models