developer_uid: azuruce
submission_id: chaiml-nemo-espresso-an_5543_v11
model_name: chaiml-nemo-espresso-an_5543_v11
model_group: ChaiML/nemo_espresso_ant
status: inactive
timestamp: 2024-12-07T02:25:36+00:00
num_battles: 10387
num_wins: 5337
celo_rating: 1274.23
family_friendly_score: 0.5842
family_friendly_standard_error: 0.006970084074098389
submission_type: basic
model_repo: ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6333205445024321, 'latency_mean': 1.5789202082157134, 'latency_p50': 1.5977742671966553, 'latency_p90': 1.728541898727417}, {'batch_size': 3, 'throughput': 1.2510861647511302, 'latency_mean': 2.387041701078415, 'latency_p50': 2.3886191844940186, 'latency_p90': 2.603682518005371}, {'batch_size': 5, 'throughput': 1.6033006578616176, 'latency_mean': 3.1141424095630645, 'latency_p50': 3.1198651790618896, 'latency_p90': 3.4971446990966797}, {'batch_size': 6, 'throughput': 1.6911010742223183, 'latency_mean': 3.5192952871322634, 'latency_p50': 3.5090768337249756, 'latency_p90': 3.9114184617996215}, {'batch_size': 8, 'throughput': 1.8423216906756077, 'latency_mean': 4.318116987943649, 'latency_p50': 4.3215025663375854, 'latency_p90': 4.878628826141357}, {'batch_size': 10, 'throughput': 1.9333510418341655, 'latency_mean': 5.130530546903611, 'latency_p50': 5.138705849647522, 'latency_p90': 5.821836924552917}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-an_5543_v11
is_internal_developer: True
language_model: ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_size: 13B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2024-12-06
win_ratio: 0.5138153461057091
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, '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': '{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-an-5543-v11-mkmlizer
Waiting for job on chaiml-nemo-espresso-an-5543-v11-mkmlizer to finish
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-an-5543-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-an-5543-v11-mkmlizer: Downloaded to shared memory in 31.435s
chaiml-nemo-espresso-an-5543-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpikdx_4t7, device:0
chaiml-nemo-espresso-an-5543-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-espresso-an-5543-v11-mkmlizer: quantized model in 35.646s
chaiml-nemo-espresso-an-5543-v11-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 67.082s
chaiml-nemo-espresso-an-5543-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-an-5543-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-an-5543-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v11
chaiml-nemo-espresso-an-5543-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v11/config.json
chaiml-nemo-espresso-an-5543-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v11/special_tokens_map.json
chaiml-nemo-espresso-an-5543-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v11/tokenizer_config.json
chaiml-nemo-espresso-an-5543-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v11/tokenizer.json
chaiml-nemo-espresso-an-5543-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-an-5543-v11/flywheel_model.0.safetensors
Job chaiml-nemo-espresso-an-5543-v11-mkmlizer completed after 94.05s with status: succeeded
Stopping job with name chaiml-nemo-espresso-an-5543-v11-mkmlizer
Pipeline stage MKMLizer completed in 94.56s
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-nemo-espresso-an-5543-v11
Waiting for inference service chaiml-nemo-espresso-an-5543-v11 to be ready
Inference service chaiml-nemo-espresso-an-5543-v11 ready after 170.6388726234436s
Retrying (%r) after connection broken by '%r': %s
Pipeline stage MKMLDeployer completed in 171.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8210687637329102s
Received healthy response to inference request in 1.488363265991211s
Received healthy response to inference request in 1.4236574172973633s
Received healthy response to inference request in 1.747880458831787s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.413254976272583s
5 requests
0 failed requests
5th percentile: 1.415335464477539
10th percentile: 1.4174159526824952
20th percentile: 1.4215769290924072
30th percentile: 1.4365985870361329
40th percentile: 1.4624809265136718
50th percentile: 1.488363265991211
60th percentile: 1.5921701431274413
70th percentile: 1.695977020263672
80th percentile: 1.7625181198120117
90th percentile: 1.791793441772461
95th percentile: 1.8064311027526856
99th percentile: 1.8181412315368652
mean time: 1.5788449764251709
Pipeline stage StressChecker completed in 9.18s
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 2.15s
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 2.05s
Shutdown handler de-registered
chaiml-nemo-espresso-an_5543_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 2406.48s
Shutdown handler de-registered
chaiml-nemo-espresso-an_5543_v11 status is now inactive due to auto deactivation removed underperforming models