developer_uid: stark2000s
submission_id: stark2000s-10-14-dpo-re_56392_v1
model_name: stark2000s-10-14-dpo-re_56392_v1
model_group: stark2000s/10_14_dpo_rep
status: torndown
timestamp: 2025-01-04T02:24:54+00:00
num_battles: 11571
num_wins: 6099
celo_rating: 1280.8
family_friendly_score: 0.593
family_friendly_standard_error: 0.00694767587039004
submission_type: basic
model_repo: stark2000s/10_14_dpo_reproduction8
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6167067078782642, 'latency_mean': 1.6214500224590302, 'latency_p50': 1.611435890197754, 'latency_p90': 1.7895408153533936}, {'batch_size': 3, 'throughput': 1.1508686669142703, 'latency_mean': 2.598607176542282, 'latency_p50': 2.5808387994766235, 'latency_p90': 2.8461421251297}, {'batch_size': 5, 'throughput': 1.3953053483854623, 'latency_mean': 3.562385057210922, 'latency_p50': 3.5478217601776123, 'latency_p90': 4.005225944519043}, {'batch_size': 6, 'throughput': 1.4819950528202313, 'latency_mean': 4.029650422334671, 'latency_p50': 4.044284224510193, 'latency_p90': 4.578938126564026}, {'batch_size': 8, 'throughput': 1.5438804543323372, 'latency_mean': 5.147313940525055, 'latency_p50': 5.154489755630493, 'latency_p90': 5.834531474113464}, {'batch_size': 10, 'throughput': 1.5897830856512172, 'latency_mean': 6.248913522958755, 'latency_p50': 6.19364070892334, 'latency_p90': 7.141624808311462}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: stark2000s-10-14-dpo-re_56392_v1
is_internal_developer: False
language_model: stark2000s/10_14_dpo_reproduction8
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2025-01-03
win_ratio: 0.5270935960591133
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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 stark2000s-10-14-dpo-re-56392-v1-mkmlizer
Waiting for job on stark2000s-10-14-dpo-re-56392-v1-mkmlizer to finish
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ _____ __ __ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ /___/ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ Version: 0.11.12 ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ https://mk1.ai ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ The license key for the current software has been verified as ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ belonging to: ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ Chai Research Corp. ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ║ ║
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: Downloaded to shared memory in 96.201s
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjzi_nei7, device:0
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: quantized model in 40.798s
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: Processed model stark2000s/10_14_dpo_reproduction8 in 136.999s
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: creating bucket guanaco-mkml-models
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/stark2000s-10-14-dpo-re-56392-v1
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/stark2000s-10-14-dpo-re-56392-v1/config.json
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/stark2000s-10-14-dpo-re-56392-v1/special_tokens_map.json
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/stark2000s-10-14-dpo-re-56392-v1/tokenizer_config.json
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/stark2000s-10-14-dpo-re-56392-v1/tokenizer.json
stark2000s-10-14-dpo-re-56392-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/stark2000s-10-14-dpo-re-56392-v1/flywheel_model.0.safetensors
Job stark2000s-10-14-dpo-re-56392-v1-mkmlizer completed after 166.58s with status: succeeded
Stopping job with name stark2000s-10-14-dpo-re-56392-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.11s
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 stark2000s-10-14-dpo-re-56392-v1
Waiting for inference service stark2000s-10-14-dpo-re-56392-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
Inference service stark2000s-10-14-dpo-re-56392-v1 ready after 331.2849805355072s
Pipeline stage MKMLDeployer completed in 331.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0025949478149414s
Received healthy response to inference request in 1.701019287109375s
Received healthy response to inference request in 1.6609978675842285s
Received healthy response to inference request in 1.274935245513916s
Received healthy response to inference request in 1.8974964618682861s
5 requests
0 failed requests
5th percentile: 1.3521477699279785
10th percentile: 1.429360294342041
20th percentile: 1.583785343170166
30th percentile: 1.669002151489258
40th percentile: 1.6850107192993165
50th percentile: 1.701019287109375
60th percentile: 1.7796101570129395
70th percentile: 1.858201026916504
80th percentile: 1.9185161590576172
90th percentile: 1.9605555534362793
95th percentile: 1.9815752506256104
99th percentile: 1.9983910083770753
mean time: 1.7074087619781495
Pipeline stage StressChecker completed in 10.43s
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 0.72s
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 0.75s
Shutdown handler de-registered
stark2000s-10-14-dpo-re_56392_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service stark2000s-10-14-dpo-re-56392-v1-profiler
Waiting for inference service stark2000s-10-14-dpo-re-56392-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 7036.15s
Shutdown handler de-registered
stark2000s-10-14-dpo-re_56392_v1 status is now inactive due to auto deactivation removed underperforming models
stark2000s-10-14-dpo-re_56392_v1 status is now torndown due to DeploymentManager action
stark2000s-10-14-dpo-re_56392_v1 status is now torndown due to DeploymentManager action
stark2000s-10-14-dpo-re_56392_v1 status is now torndown due to DeploymentManager action