developer_uid: azuruce
submission_id: chaiml-small-espresso-an_6112_v6
model_name: chaiml-small-espresso-an_6112_v6
model_group: ChaiML/small_espresso_an
status: inactive
timestamp: 2024-12-06T16:03:21+00:00
num_battles: 10620
num_wins: 5524
celo_rating: 1273.14
family_friendly_score: 0.5806
family_friendly_standard_error: 0.0069785906886705995
submission_type: basic
model_repo: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.37817514094567434, 'latency_mean': 2.644206465482712, 'latency_p50': 2.644735813140869, 'latency_p90': 2.910560941696167}, {'batch_size': 2, 'throughput': 0.596652057242752, 'latency_mean': 3.3457377231121064, 'latency_p50': 3.324328064918518, 'latency_p90': 3.695701789855957}, {'batch_size': 3, 'throughput': 0.7488488272436961, 'latency_mean': 3.9862829518318175, 'latency_p50': 3.97929584980011, 'latency_p90': 4.489296221733094}, {'batch_size': 4, 'throughput': 0.8577037362672418, 'latency_mean': 4.651923294067383, 'latency_p50': 4.674438834190369, 'latency_p90': 5.167126154899597}, {'batch_size': 5, 'throughput': 0.951703264383103, 'latency_mean': 5.224178005456924, 'latency_p50': 5.243801951408386, 'latency_p90': 5.89670467376709}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-small-espresso-an_6112_v6
is_internal_developer: True
language_model: ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a
model_size: 22B
ranking_group: single
throughput_3p7s: 0.69
us_pacific_date: 2024-12-06
win_ratio: 0.52015065913371
generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\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-small-espresso-an-6112-v6-mkmlizer
Waiting for job on chaiml-small-espresso-an-6112-v6-mkmlizer to finish
Failed to get response for submission chaiml-lexical-viral-v5a_3966_v4: ('http://chaiml-lexical-viral-v5a-3966-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48036->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-small-espresso-an-6112-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-espresso-an-6112-v6-mkmlizer: ║     _____            __           __                                ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║       /___/                                                         ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ║                                                                     ║
chaiml-small-espresso-an-6112-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-small-espresso-an-6112-v6-mkmlizer: Downloaded to shared memory in 38.376s
chaiml-small-espresso-an-6112-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpugnehefw, device:0
chaiml-small-espresso-an-6112-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-espresso-an-6112-v6-mkmlizer: quantized model in 46.455s
chaiml-small-espresso-an-6112-v6-mkmlizer: Processed model ChaiML/small_espresso_ant_llama_story_241205_albert_v1_sft-3e128a in 84.832s
chaiml-small-espresso-an-6112-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-espresso-an-6112-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-espresso-an-6112-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v6
chaiml-small-espresso-an-6112-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v6/special_tokens_map.json
chaiml-small-espresso-an-6112-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v6/config.json
chaiml-small-espresso-an-6112-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v6/tokenizer_config.json
chaiml-small-espresso-an-6112-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-espresso-an-6112-v6/tokenizer.json
Job chaiml-small-espresso-an-6112-v6-mkmlizer completed after 152.73s with status: succeeded
Stopping job with name chaiml-small-espresso-an-6112-v6-mkmlizer
Pipeline stage MKMLizer completed in 154.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-espresso-an-6112-v6
Waiting for inference service chaiml-small-espresso-an-6112-v6 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
Inference service chaiml-small-espresso-an-6112-v6 ready after 200.13675498962402s
Pipeline stage MKMLDeployer completed in 202.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.564095973968506s
Received healthy response to inference request in 2.909137487411499s
Received healthy response to inference request in 2.904357433319092s
Received healthy response to inference request in 2.7761430740356445s
Received healthy response to inference request in 2.9530889987945557s
5 requests
0 failed requests
5th percentile: 2.801785945892334
10th percentile: 2.8274288177490234
20th percentile: 2.8787145614624023
30th percentile: 2.9053134441375734
40th percentile: 2.907225465774536
50th percentile: 2.909137487411499
60th percentile: 2.9267180919647218
70th percentile: 2.9442986965179445
80th percentile: 3.075290393829346
90th percentile: 3.319693183898926
95th percentile: 3.4418945789337156
99th percentile: 3.5396556949615476
mean time: 3.0213645935058593
Pipeline stage StressChecker completed in 16.31s
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 2.25s
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 2.03s
Shutdown handler de-registered
chaiml-small-espresso-an_6112_v6 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 3341.42s
Shutdown handler de-registered
chaiml-small-espresso-an_6112_v6 status is now inactive due to auto deactivation removed underperforming models