developer_uid: rirv938
submission_id: rirv938-mistral-24b-rou_70379_v1
model_name: rirv938-mistral-24b-rou_70379_v1
model_group: rirv938/mistral_24b_roun
status: torndown
timestamp: 2025-03-08T17:33:13+00:00
num_battles: 11301
num_wins: 6014
celo_rating: 1305.92
family_friendly_score: 0.575
family_friendly_standard_error: 0.006991065727054781
submission_type: basic
model_repo: rirv938/mistral_24b_round_3_dpo_40k_65w_pref_10w_swear_2500_v2
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3850012393245358, 'latency_mean': 2.597307184934616, 'latency_p50': 2.6223108768463135, 'latency_p90': 2.85613317489624}, {'batch_size': 3, 'throughput': 0.7925684171306938, 'latency_mean': 3.7749269330501556, 'latency_p50': 3.75805926322937, 'latency_p90': 4.214222717285156}, {'batch_size': 5, 'throughput': 1.0476309556865717, 'latency_mean': 4.756425067186355, 'latency_p50': 4.7481595277786255, 'latency_p90': 5.208951306343079}, {'batch_size': 6, 'throughput': 1.1151918543867496, 'latency_mean': 5.349468884468078, 'latency_p50': 5.381174445152283, 'latency_p90': 5.9810107231140135}, {'batch_size': 10, 'throughput': 1.2840236456970358, 'latency_mean': 7.6990964674949645, 'latency_p50': 7.6659791469573975, 'latency_p90': 8.731128716468811}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-rou_70379_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_round_3_dpo_40k_65w_pref_10w_swear_2500_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-03-08
win_ratio: 0.5321652951066277
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '###', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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 rirv938-mistral-24b-rou-70379-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-rou-70379-v1-mkmlizer to finish
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ║ ║
rirv938-mistral-24b-rou-70379-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_mobok_2025-03-01: HTTPConnectionPool(host='blend-tusat-2025-03-01-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-mistral-24b-rou-70379-v1-mkmlizer: Downloaded to shared memory in 162.448s
rirv938-mistral-24b-rou-70379-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpecukauw5, device:0
rirv938-mistral-24b-rou-70379-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-rou-70379-v1-mkmlizer: quantized model in 66.681s
rirv938-mistral-24b-rou-70379-v1-mkmlizer: Processed model rirv938/mistral_24b_round_3_dpo_40k_65w_pref_10w_swear_2500_v2 in 229.130s
rirv938-mistral-24b-rou-70379-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-rou-70379-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-rou-70379-v1
rirv938-mistral-24b-rou-70379-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-70379-v1/config.json
rirv938-mistral-24b-rou-70379-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-70379-v1/special_tokens_map.json
rirv938-mistral-24b-rou-70379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-70379-v1/tokenizer_config.json
rirv938-mistral-24b-rou-70379-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-rou-70379-v1/tokenizer.json
Job rirv938-mistral-24b-rou-70379-v1-mkmlizer completed after 272.81s with status: succeeded
Stopping job with name rirv938-mistral-24b-rou-70379-v1-mkmlizer
Pipeline stage MKMLizer completed in 273.31s
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 rirv938-mistral-24b-rou-70379-v1
Waiting for inference service rirv938-mistral-24b-rou-70379-v1 to be ready
Inference service rirv938-mistral-24b-rou-70379-v1 ready after 90.31960415840149s
Pipeline stage MKMLDeployer completed in 90.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0877110958099365s
Received healthy response to inference request in 2.9399397373199463s
Received healthy response to inference request in 2.786836624145508s
Received healthy response to inference request in 2.4474308490753174s
Received healthy response to inference request in 2.620995044708252s
5 requests
0 failed requests
5th percentile: 2.482143688201904
10th percentile: 2.5168565273284913
20th percentile: 2.586282205581665
30th percentile: 2.654163360595703
40th percentile: 2.7204999923706055
50th percentile: 2.786836624145508
60th percentile: 2.8480778694152833
70th percentile: 2.9093191146850588
80th percentile: 2.9694940090179442
90th percentile: 3.0286025524139406
95th percentile: 3.0581568241119386
99th percentile: 3.081800241470337
mean time: 2.776582670211792
Pipeline stage StressChecker completed in 15.21s
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 0.65s
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 0.93s
Shutdown handler de-registered
rirv938-mistral-24b-rou_70379_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-rou-70379-v1-profiler
Waiting for inference service rirv938-mistral-24b-rou-70379-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 5363.22s
Shutdown handler de-registered
rirv938-mistral-24b-rou_70379_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-rou_70379_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1