developer_uid: rirv938
submission_id: rirv938-mistral-24b-dpo_48957_v1
model_name: rirv938-mistral-24b-dpo_48957_v1
model_group: rirv938/mistral_24b_dpo_
status: torndown
timestamp: 2025-02-23T16:02:06+00:00
num_battles: 8210
num_wins: 4042
celo_rating: 1272.44
family_friendly_score: 0.6377999999999999
family_friendly_standard_error: 0.0067972223738818486
submission_type: basic
model_repo: rirv938/mistral_24b_dpo_96k_3000_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': 0.3862112576354579, 'latency_mean': 2.5891687273979187, 'latency_p50': 2.6121954917907715, 'latency_p90': 2.8620254039764403}, {'batch_size': 3, 'throughput': 0.7950576708605204, 'latency_mean': 3.7591555511951444, 'latency_p50': 3.8043066263198853, 'latency_p90': 4.113805890083313}, {'batch_size': 5, 'throughput': 1.0511149168397742, 'latency_mean': 4.729025807380676, 'latency_p50': 4.680017113685608, 'latency_p90': 5.3082146644592285}, {'batch_size': 6, 'throughput': 1.134976898081817, 'latency_mean': 5.245246994495392, 'latency_p50': 5.2618248462677, 'latency_p90': 5.8258641242980955}, {'batch_size': 10, 'throughput': 1.2931804062349574, 'latency_mean': 7.654966194629669, 'latency_p50': 7.657963871955872, 'latency_p90': 8.727495145797729}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: rirv938-mistral-24b-dpo_48957_v1
is_internal_developer: True
language_model: rirv938/mistral_24b_dpo_96k_3000_v2
model_size: 24B
ranking_group: single
throughput_3p7s: 0.78
us_pacific_date: 2025-02-23
win_ratio: 0.492326431181486
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-dpo-48957-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-48957-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ║ ║
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: Downloaded to shared memory in 166.616s
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3q7e4rfg, device:0
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: quantized model in 64.672s
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_96k_3000_v2 in 231.288s
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1/config.json
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1/tokenizer.json
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-48957-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-48957-v1/flywheel_model.1.safetensors
Job rirv938-mistral-24b-dpo-48957-v1-mkmlizer completed after 268.29s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-48957-v1-mkmlizer
Pipeline stage MKMLizer completed in 268.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-48957-v1
Waiting for inference service rirv938-mistral-24b-dpo-48957-v1 to be ready
Inference service rirv938-mistral-24b-dpo-48957-v1 ready after 231.36358904838562s
Pipeline stage MKMLDeployer completed in 231.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2396628856658936s
Received healthy response to inference request in 2.010118007659912s
Received healthy response to inference request in 1.8015272617340088s
Received healthy response to inference request in 1.5946521759033203s
Received healthy response to inference request in 1.7279012203216553s
5 requests
0 failed requests
5th percentile: 1.6213019847869874
10th percentile: 1.6479517936706543
20th percentile: 1.7012514114379882
30th percentile: 1.742626428604126
40th percentile: 1.7720768451690674
50th percentile: 1.8015272617340088
60th percentile: 1.8849635601043702
70th percentile: 1.9683998584747313
80th percentile: 2.056026983261108
90th percentile: 2.147844934463501
95th percentile: 2.1937539100646974
99th percentile: 2.2304810905456542
mean time: 1.874772310256958
Pipeline stage StressChecker completed in 10.64s
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 0.70s
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 1.08s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_48957_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 0.08s
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-dpo-48957-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-48957-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 4818.44s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_48957_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_48957_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1