developer_uid: chai_backend_admin
submission_id: chaiml-ezstorytellingedi_9240_v2
model_name: chaiml-ezstorytellingedi_9240_v2
model_group: ChaiML/EZStorytellingEdi
status: torndown
timestamp: 2024-11-26T08:26:25+00:00
num_battles: 26263
num_wins: 12872
celo_rating: 1257.11
family_friendly_score: 0.5704
family_friendly_standard_error: 0.007000626257700092
submission_type: basic
model_repo: ChaiML/EZStorytellingEditsSFT_Qi6_65convos_reward
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3911107123906939, 'latency_mean': 2.5567614424228666, 'latency_p50': 2.5419816970825195, 'latency_p90': 2.850979709625244}, {'batch_size': 3, 'throughput': 0.8212145459428527, 'latency_mean': 3.637252835035324, 'latency_p50': 3.6331628561019897, 'latency_p90': 3.937829923629761}, {'batch_size': 5, 'throughput': 1.0956352199762174, 'latency_mean': 4.552560524940491, 'latency_p50': 4.518997550010681, 'latency_p90': 5.142461252212525}, {'batch_size': 6, 'throughput': 1.177306250305989, 'latency_mean': 5.066455938816071, 'latency_p50': 5.065533638000488, 'latency_p90': 5.760034394264221}, {'batch_size': 10, 'throughput': 1.3925617944639817, 'latency_mean': 7.123489508628845, 'latency_p50': 7.094146132469177, 'latency_p90': 8.067437148094177}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-ezstorytellingedi_9240_v2
is_internal_developer: True
language_model: ChaiML/EZStorytellingEditsSFT_Qi6_65convos_reward
model_size: 22B
ranking_group: single
throughput_3p7s: 0.85
us_pacific_date: 2024-11-26
win_ratio: 0.4901191790732209
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': '', '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-ezstorytellingedi-9240-v2-mkmlizer
Waiting for job on chaiml-ezstorytellingedi-9240-v2-mkmlizer to finish
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ _____ __ __ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ /___/ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ belonging to: ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-9240-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ezstorytellingedi-9240-v2-mkmlizer: Downloaded to shared memory in 58.163s
chaiml-ezstorytellingedi-9240-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1rex35f3, device:0
chaiml-ezstorytellingedi-9240-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ezstorytellingedi-9240-v2-mkmlizer: quantized model in 43.213s
chaiml-ezstorytellingedi-9240-v2-mkmlizer: Processed model ChaiML/EZStorytellingEditsSFT_Qi6_65convos_reward in 101.376s
chaiml-ezstorytellingedi-9240-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingedi-9240-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingedi-9240-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2
chaiml-ezstorytellingedi-9240-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2/config.json
chaiml-ezstorytellingedi-9240-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2/special_tokens_map.json
chaiml-ezstorytellingedi-9240-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2/tokenizer_config.json
chaiml-ezstorytellingedi-9240-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-ezstorytellingedi-9240-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2/flywheel_model.1.safetensors
chaiml-ezstorytellingedi-9240-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingedi-9240-v2/flywheel_model.0.safetensors
Job chaiml-ezstorytellingedi-9240-v2-mkmlizer completed after 134.66s with status: succeeded
Stopping job with name chaiml-ezstorytellingedi-9240-v2-mkmlizer
Pipeline stage MKMLizer completed in 135.14s
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-9240-v2
Waiting for inference service chaiml-ezstorytellingedi-9240-v2 to be ready
Inference service chaiml-ezstorytellingedi-9240-v2 ready after 120.65265893936157s
Pipeline stage MKMLDeployer completed in 121.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7898149490356445s
Received healthy response to inference request in 2.290794849395752s
Received healthy response to inference request in 2.520317554473877s
Received healthy response to inference request in 2.2970805168151855s
Received healthy response to inference request in 2.2543997764587402s
5 requests
0 failed requests
5th percentile: 2.2616787910461427
10th percentile: 2.268957805633545
20th percentile: 2.2835158348083495
30th percentile: 2.292051982879639
40th percentile: 2.294566249847412
50th percentile: 2.2970805168151855
60th percentile: 2.386375331878662
70th percentile: 2.4756701469421385
80th percentile: 2.5742170333862306
90th percentile: 2.6820159912109376
95th percentile: 2.735915470123291
99th percentile: 2.779035053253174
mean time: 2.43048152923584
Pipeline stage StressChecker completed in 13.61s
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 2.27s
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 1.96s
Shutdown handler de-registered
chaiml-ezstorytellingedi_9240_v2 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 3304.37s
Shutdown handler de-registered
chaiml-ezstorytellingedi_9240_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-ezstorytellingedi_9240_v2 status is now torndown due to DeploymentManager action
chaiml-ezstorytellingedi_9240_v2 status is now torndown due to DeploymentManager action
chaiml-ezstorytellingedi_9240_v2 status is now torndown due to DeploymentManager action