developer_uid: azuruce
submission_id: chaiml-nemo-espresso-ant_1376_v4
model_name: chaiml-nemo-espresso-ant_1376_v4
model_group: ChaiML/nemo_espresso_ant
status: inactive
timestamp: 2024-12-06T22:43:02+00:00
num_battles: 6444
num_wins: 3507
celo_rating: 1273.29
family_friendly_score: 0.5718
family_friendly_standard_error: 0.006997781934298896
submission_type: basic
model_repo: ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6050106105024797, 'latency_mean': 1.652790012359619, 'latency_p50': 1.6665891408920288, 'latency_p90': 1.8187295198440552}, {'batch_size': 3, 'throughput': 1.1254233561827445, 'latency_mean': 2.6584449720382692, 'latency_p50': 2.63966965675354, 'latency_p90': 2.943519854545593}, {'batch_size': 5, 'throughput': 1.3879267040587413, 'latency_mean': 3.58195561170578, 'latency_p50': 3.579925298690796, 'latency_p90': 3.961029624938965}, {'batch_size': 6, 'throughput': 1.4327620293986447, 'latency_mean': 4.160714344978333, 'latency_p50': 4.16169285774231, 'latency_p90': 4.717983746528626}, {'batch_size': 8, 'throughput': 1.501566349730787, 'latency_mean': 5.30349588394165, 'latency_p50': 5.278266549110413, 'latency_p90': 6.05651273727417}, {'batch_size': 10, 'throughput': 1.545602411572293, 'latency_mean': 6.4190797364711765, 'latency_p50': 6.407688736915588, 'latency_p90': 7.275645542144775}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-ant_1376_v4
is_internal_developer: True
language_model: ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a
model_size: 13B
ranking_group: single
throughput_3p7s: 1.41
us_pacific_date: 2024-12-06
win_ratio: 0.5442271880819367
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', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '{memory}\n', 'prompt_template': '{prompt}\n', '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-ant-1376-v4-mkmlizer
Waiting for job on chaiml-nemo-espresso-ant-1376-v4-mkmlizer to finish
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: Downloaded to shared memory in 31.303s
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbm87831o, device:0
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: quantized model in 37.736s
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_ez_v1_sft-3e128a in 69.040s
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v4
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v4/special_tokens_map.json
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v4/config.json
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v4/tokenizer_config.json
chaiml-nemo-espresso-ant-1376-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-1376-v4/tokenizer.json
Job chaiml-nemo-espresso-ant-1376-v4-mkmlizer completed after 95.12s with status: succeeded
Stopping job with name chaiml-nemo-espresso-ant-1376-v4-mkmlizer
Pipeline stage MKMLizer completed in 95.65s
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-espresso-ant-1376-v4
Waiting for inference service chaiml-nemo-espresso-ant-1376-v4 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
Inference service chaiml-nemo-espresso-ant-1376-v4 ready after 170.64765977859497s
Pipeline stage MKMLDeployer completed in 171.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.58125638961792s
Received healthy response to inference request in 1.8810193538665771s
Received healthy response to inference request in 1.9499969482421875s
Received healthy response to inference request in 1.9659719467163086s
Received healthy response to inference request in 1.714665174484253s
5 requests
0 failed requests
5th percentile: 1.7479360103607178
10th percentile: 1.7812068462371826
20th percentile: 1.8477485179901123
30th percentile: 1.8948148727416991
40th percentile: 1.9224059104919433
50th percentile: 1.9499969482421875
60th percentile: 1.9563869476318358
70th percentile: 1.9627769470214844
80th percentile: 2.089028835296631
90th percentile: 2.3351426124572754
95th percentile: 2.4581995010375977
99th percentile: 2.5566450119018556
mean time: 2.0185819625854493
Pipeline stage StressChecker completed in 11.37s
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 2.13s
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 2.07s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_1376_v4 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 2644.95s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_1376_v4 status is now inactive due to auto deactivation removed underperforming models