developer_uid: ebony59
submission_id: chaiml-ezstorytellingedi_3596_v1
model_name: chaiml-ezstorytellingedi_3596_v1
model_group: ChaiML/EZStorytellingEdi
status: inactive
timestamp: 2024-11-30T23:41:59+00:00
num_battles: 16848
num_wins: 8017
celo_rating: 1246.83
family_friendly_score: 0.5708
family_friendly_standard_error: 0.006999819426242366
submission_type: basic
model_repo: ChaiML/EZStorytellingEditsSFT_Qi6_71convos_reward_8epoch
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3902131338513373, 'latency_mean': 2.562640258073807, 'latency_p50': 2.55664324760437, 'latency_p90': 2.8402642965316773}, {'batch_size': 3, 'throughput': 0.8253715058681451, 'latency_mean': 3.6304714524745942, 'latency_p50': 3.6331684589385986, 'latency_p90': 4.005609154701233}, {'batch_size': 5, 'throughput': 1.0916729941392953, 'latency_mean': 4.554381772279739, 'latency_p50': 4.578869462013245, 'latency_p90': 5.050980019569397}, {'batch_size': 6, 'throughput': 1.1827414652921622, 'latency_mean': 5.046576124429703, 'latency_p50': 5.013116359710693, 'latency_p90': 5.607031917572021}, {'batch_size': 10, 'throughput': 1.3989740693167358, 'latency_mean': 7.092078609466553, 'latency_p50': 7.111538529396057, 'latency_p90': 8.134689688682556}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-ezstorytellingedi_3596_v1
is_internal_developer: True
language_model: ChaiML/EZStorytellingEditsSFT_Qi6_71convos_reward_8epoch
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2024-11-30
win_ratio: 0.4758428300094967
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, '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-ezstorytellingedi-3596-v1-mkmlizer
Waiting for job on chaiml-ezstorytellingedi-3596-v1-mkmlizer to finish
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║       /___/                                                         ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-ezstorytellingedi-3596-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingedi-3596-v1-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-ezstorytellingedi-3596-v1-mkmlizer: Downloaded to shared memory in 86.214s
chaiml-ezstorytellingedi-3596-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5a1qa_dw, device:0
chaiml-ezstorytellingedi-3596-v1-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-ezstorytellingedi-3596-v1-mkmlizer: quantized model in 44.724s
chaiml-ezstorytellingedi-3596-v1-mkmlizer: Processed model ChaiML/EZStorytellingEditsSFT_Qi6_71convos_reward_8epoch in 130.938s
chaiml-ezstorytellingedi-3596-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingedi-3596-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingedi-3596-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingedi-3596-v1
chaiml-ezstorytellingedi-3596-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-3596-v1/config.json
chaiml-ezstorytellingedi-3596-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-3596-v1/special_tokens_map.json
chaiml-ezstorytellingedi-3596-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingedi-3596-v1/flywheel_model.1.safetensors
chaiml-ezstorytellingedi-3596-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingedi-3596-v1/flywheel_model.0.safetensors
Job chaiml-ezstorytellingedi-3596-v1-mkmlizer completed after 165.25s with status: succeeded
Stopping job with name chaiml-ezstorytellingedi-3596-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.81s
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-ezstorytellingedi-3596-v1
Waiting for inference service chaiml-ezstorytellingedi-3596-v1 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-ezstorytellingedi-3596-v1 ready after 140.55818367004395s
Pipeline stage MKMLDeployer completed in 141.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1896207332611084s
Received healthy response to inference request in 3.1677348613739014s
Received healthy response to inference request in 2.5652875900268555s
Received healthy response to inference request in 2.638192892074585s
Received healthy response to inference request in 2.9490602016448975s
5 requests
0 failed requests
5th percentile: 2.5798686504364015
10th percentile: 2.5944497108459474
20th percentile: 2.623611831665039
30th percentile: 2.7003663539886475
40th percentile: 2.8247132778167723
50th percentile: 2.9490602016448975
60th percentile: 3.036530065536499
70th percentile: 3.1239999294281007
80th percentile: 3.1721120357513426
90th percentile: 3.1808663845062255
95th percentile: 3.185243558883667
99th percentile: 3.18874529838562
mean time: 2.9019792556762694
Pipeline stage StressChecker completed in 15.85s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %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 2.10s
Shutdown handler de-registered
chaiml-ezstorytellingedi_3596_v1 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 3688.32s
Shutdown handler de-registered
chaiml-ezstorytellingedi_3596_v1 status is now inactive due to auto deactivation removed underperforming models