chaiml-espresso-ant-lla_1666

developer_uid: azuruce

submission_id: chaiml-espresso-ant-lla_1666_v15

model_name: chaiml-espresso-ant-lla_1666_v15

model_group: ChaiML/espresso_ant_llam

status: inactive

timestamp: 2024-12-05T16:30:05+00:00

num_battles: 19170

num_wins: 9508

celo_rating: 1259.47

family_friendly_score: 0.5833999999999999

family_friendly_standard_error: 0.006972007458401059

submission_type: basic

model_repo: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.38709690399650615, 'latency_mean': 2.5832625782489775, 'latency_p50': 2.588773488998413, 'latency_p90': 2.8485098838806153}, {'batch_size': 3, 'throughput': 0.8214414731234724, 'latency_mean': 3.6446912491321566, 'latency_p50': 3.6286779642105103, 'latency_p90': 3.993558073043823}, {'batch_size': 5, 'throughput': 1.0921034896256014, 'latency_mean': 4.553416728973389, 'latency_p50': 4.572546482086182, 'latency_p90': 5.08454315662384}, {'batch_size': 6, 'throughput': 1.1799851776301722, 'latency_mean': 5.050583699941635, 'latency_p50': 5.022781133651733, 'latency_p90': 5.747643542289734}, {'batch_size': 10, 'throughput': 1.393241259660366, 'latency_mean': 7.102843043804168, 'latency_p50': 7.12735652923584, 'latency_p90': 7.995365381240845}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-espresso-ant-lla_1666_v15

is_internal_developer: True

language_model: ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha

model_size: 22B

ranking_group: single

throughput_3p7s: 0.84

us_pacific_date: 2024-12-05

win_ratio: 0.4959833072509129

generation_params: {'temperature': 0.85, '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-espresso-ant-lla-1666-v15-mkmlizer
Waiting for job on chaiml-espresso-ant-lla-1666-v15-mkmlizer to finish
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║     _____            __           __                                ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║       /___/                                                         ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  belonging to:                                                      ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ║                                                                     ║
chaiml-espresso-ant-lla-1666-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-espresso-ant-lla-1666-v15-mkmlizer: Downloaded to shared memory in 41.313s
chaiml-espresso-ant-lla-1666-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyzjg4ki8, device:0
chaiml-espresso-ant-lla-1666-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-espresso-ant-lla-1666-v15-mkmlizer: quantized model in 43.145s
chaiml-espresso-ant-lla-1666-v15-mkmlizer: Processed model ChaiML/espresso_ant_llama_241204_albert_v2_sft_2epoch_128alpha in 84.458s
chaiml-espresso-ant-lla-1666-v15-mkmlizer: creating bucket guanaco-mkml-models
chaiml-espresso-ant-lla-1666-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-espresso-ant-lla-1666-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v15
chaiml-espresso-ant-lla-1666-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v15/special_tokens_map.json
chaiml-espresso-ant-lla-1666-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v15/config.json
chaiml-espresso-ant-lla-1666-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v15/tokenizer_config.json
chaiml-espresso-ant-lla-1666-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v15/flywheel_model.1.safetensors
chaiml-espresso-ant-lla-1666-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-espresso-ant-lla-1666-v15/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-espresso-ant-lla-1666-v15-mkmlizer completed after 120.18s with status: succeeded
Stopping job with name chaiml-espresso-ant-lla-1666-v15-mkmlizer
Pipeline stage MKMLizer completed in 122.12s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Creating inference service chaiml-espresso-ant-lla-1666-v15
Waiting for inference service chaiml-espresso-ant-lla-1666-v15 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
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-espresso-ant-lla-1666-v15 ready after 184.5274782180786s
Pipeline stage MKMLDeployer completed in 186.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6629037857055664s
Received healthy response to inference request in 2.255195140838623s
Received healthy response to inference request in 2.6913304328918457s
Received healthy response to inference request in 2.2286622524261475s
Received healthy response to inference request in 2.2516019344329834s
5 requests
0 failed requests
5th percentile: 2.2332501888275145
10th percentile: 2.237838125228882
20th percentile: 2.2470139980316164
30th percentile: 2.252320575714111
40th percentile: 2.253757858276367
50th percentile: 2.255195140838623
60th percentile: 2.4182785987854003
70th percentile: 2.5813620567321776
80th percentile: 2.6685891151428223
90th percentile: 2.679959774017334
95th percentile: 2.68564510345459
99th percentile: 2.6901933670043947
mean time: 2.417938709259033
Pipeline stage StressChecker completed in 13.56s
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 2.44s
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 2.53s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v15 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 4223.36s
Shutdown handler de-registered
chaiml-espresso-ant-lla_1666_v15 status is now inactive due to auto deactivation removed underperforming models