developer_uid: azuruce
submission_id: chaiml-nemo-espresso-ant_5543_v8
model_name: chaiml-nemo-espresso-ant_5543_v8
model_group: ChaiML/nemo_espresso_ant
status: inactive
timestamp: 2024-12-06T16:05:46+00:00
num_battles: 7086
num_wins: 3726
celo_rating: 1282.89
family_friendly_score: 0.5840000000000001
family_friendly_standard_error: 0.006970566691453429
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': 0.6254285656137727, 'latency_mean': 1.5988388776779174, 'latency_p50': 1.6023868322372437, 'latency_p90': 1.7575559616088867}, {'batch_size': 3, 'throughput': 1.2443617480193183, 'latency_mean': 2.405854980945587, 'latency_p50': 2.413886070251465, 'latency_p90': 2.5989789962768555}, {'batch_size': 5, 'throughput': 1.563498517821183, 'latency_mean': 3.1862959921360017, 'latency_p50': 3.1920526027679443, 'latency_p90': 3.5725114583969115}, {'batch_size': 6, 'throughput': 1.6626963089396127, 'latency_mean': 3.5899096608161924, 'latency_p50': 3.601210117340088, 'latency_p90': 4.035549569129944}, {'batch_size': 8, 'throughput': 1.8070898076246744, 'latency_mean': 4.393259996175766, 'latency_p50': 4.404839634895325, 'latency_p90': 4.915502643585205}, {'batch_size': 10, 'throughput': 1.8946992285632138, 'latency_mean': 5.2385887372493745, 'latency_p50': 5.270009875297546, 'latency_p90': 5.9035862445831295}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-nemo-espresso-ant_5543_v8
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: 1.7
us_pacific_date: 2024-12-06
win_ratio: 0.5258255715495342
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-ant-5543-v8-mkmlizer
Waiting for job on chaiml-nemo-espresso-ant-5543-v8-mkmlizer to finish
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ║                                                                     ║
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: Downloaded to shared memory in 24.473s
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxnzhu_pk, device:0
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: quantized model in 37.747s
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: Processed model ChaiML/nemo_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 62.220s
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v8
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v8/special_tokens_map.json
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v8/config.json
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v8/tokenizer_config.json
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v8/tokenizer.json
chaiml-nemo-espresso-ant-5543-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-espresso-ant-5543-v8/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-nemo-espresso-ant-5543-v8-mkmlizer completed after 96.58s with status: succeeded
Stopping job with name chaiml-nemo-espresso-ant-5543-v8-mkmlizer
Pipeline stage MKMLizer completed in 98.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-espresso-ant-5543-v8
Waiting for inference service chaiml-nemo-espresso-ant-5543-v8 to be ready
Inference service chaiml-nemo-espresso-ant-5543-v8 ready after 201.29410600662231s
Pipeline stage MKMLDeployer completed in 202.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2036542892456055s
Received healthy response to inference request in 1.9194715023040771s
Received healthy response to inference request in 1.827232837677002s
Received healthy response to inference request in 1.3734605312347412s
Received healthy response to inference request in 1.3454432487487793s
5 requests
0 failed requests
5th percentile: 1.3510467052459716
10th percentile: 1.356650161743164
20th percentile: 1.367857074737549
30th percentile: 1.4642149925231933
40th percentile: 1.6457239151000977
50th percentile: 1.827232837677002
60th percentile: 1.864128303527832
70th percentile: 1.901023769378662
80th percentile: 1.9763080596923828
90th percentile: 2.0899811744689942
95th percentile: 2.1468177318572996
99th percentile: 2.192286977767944
mean time: 1.733852481842041
Pipeline stage StressChecker completed in 9.83s
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 2.47s
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 2.25s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_5543_v8 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 2304.73s
Shutdown handler de-registered
chaiml-nemo-espresso-ant_5543_v8 status is now inactive due to auto deactivation removed underperforming models