submission_id: rinen0721-mistral12b-exp6_v1
developer_uid: rinen0721
best_of: 8
celo_rating: 1242.42
display_name: rinen0721-mistral12b-exp6_v1
family_friendly_score: 0.5640000000000001
family_friendly_standard_error: 0.007012902394871898
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rinen0721/Mistral12b-exp6
latencies: [{'batch_size': 1, 'throughput': 0.6027102052849364, 'latency_mean': 1.6591154742240906, 'latency_p50': 1.6542747020721436, 'latency_p90': 1.8353351354599}, {'batch_size': 3, 'throughput': 1.0834752959169172, 'latency_mean': 2.754355283975601, 'latency_p50': 2.7569133043289185, 'latency_p90': 3.054333710670471}, {'batch_size': 5, 'throughput': 1.293250985938748, 'latency_mean': 3.855130971670151, 'latency_p50': 3.859785318374634, 'latency_p90': 4.275857830047608}, {'batch_size': 6, 'throughput': 1.3664949452254025, 'latency_mean': 4.351033116579056, 'latency_p50': 4.354986548423767, 'latency_p90': 4.931137418746948}, {'batch_size': 8, 'throughput': 1.430702447164861, 'latency_mean': 5.562985821962356, 'latency_p50': 5.5357266664505005, 'latency_p90': 6.309940242767334}, {'batch_size': 10, 'throughput': 1.4663646295666268, 'latency_mean': 6.770626026391983, 'latency_p50': 6.737765073776245, 'latency_p90': 7.688602495193481}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/Mistral12b-exp
model_name: rinen0721-mistral12b-exp6_v1
model_num_parameters: 12772070400.0
model_repo: rinen0721/Mistral12b-exp6
model_size: 13B
num_battles: 14173
num_wins: 7003
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.28
timestamp: 2024-11-12T12:13:21+00:00
us_pacific_date: 2024-11-12
win_ratio: 0.49410851619276086
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 rinen0721-mistral12b-exp6-v1-mkmlizer
Waiting for job on rinen0721-mistral12b-exp6-v1-mkmlizer to finish
rinen0721-mistral12b-exp6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ /___/ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ Version: 0.11.33 ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ belonging to: ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral12b-exp6-v1-mkmlizer: Downloaded to shared memory in 48.416s
rinen0721-mistral12b-exp6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwmk8khhb, device:0
rinen0721-mistral12b-exp6-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
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
rinen0721-mistral12b-exp6-v1-mkmlizer: quantized model in 37.384s
rinen0721-mistral12b-exp6-v1-mkmlizer: Processed model rinen0721/Mistral12b-exp6 in 85.800s
rinen0721-mistral12b-exp6-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral12b-exp6-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral12b-exp6-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral12b-exp6-v1
rinen0721-mistral12b-exp6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp6-v1/config.json
rinen0721-mistral12b-exp6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp6-v1/special_tokens_map.json
rinen0721-mistral12b-exp6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp6-v1/tokenizer_config.json
rinen0721-mistral12b-exp6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp6-v1/tokenizer.json
rinen0721-mistral12b-exp6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral12b-exp6-v1/flywheel_model.0.safetensors
Job rinen0721-mistral12b-exp6-v1-mkmlizer completed after 116.32s with status: succeeded
Stopping job with name rinen0721-mistral12b-exp6-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-mistral12b-exp6-v1
Waiting for inference service rinen0721-mistral12b-exp6-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
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 rinen0721-mistral12b-exp6-v1 ready after 180.87842655181885s
Pipeline stage MKMLDeployer completed in 181.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.056988000869751s
Received healthy response to inference request in 1.58465576171875s
Received healthy response to inference request in 1.6862273216247559s
Received healthy response to inference request in 1.6402266025543213s
Received healthy response to inference request in 1.0320148468017578s
5 requests
0 failed requests
5th percentile: 1.1425430297851562
10th percentile: 1.2530712127685546
20th percentile: 1.4741275787353516
30th percentile: 1.5957699298858643
40th percentile: 1.6179982662200927
50th percentile: 1.6402266025543213
60th percentile: 1.6586268901824952
70th percentile: 1.677027177810669
80th percentile: 1.760379457473755
90th percentile: 1.9086837291717529
95th percentile: 1.9828358650207518
99th percentile: 2.042157573699951
mean time: 1.6000225067138671
Pipeline stage StressChecker completed in 9.58s
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 3.12s
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 2.72s
Shutdown handler de-registered
rinen0721-mistral12b-exp6_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 2739.60s
Shutdown handler de-registered
rinen0721-mistral12b-exp6_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral12b-exp6_v1 status is now torndown due to DeploymentManager action