developer_uid: rirv938
submission_id: rirv938-mistral-12b-w60_75581_v1
model_name: rirv938-mistral-12b-w60_75581_v1
model_group: rirv938/mistral_12b_w60_
status: torndown
timestamp: 2025-02-21T01:32:47+00:00
num_battles: 6405
num_wins: 3120
celo_rating: 1264.68
family_friendly_score: 0.5660000000000001
family_friendly_standard_error: 0.007009193962218481
submission_type: basic
model_repo: rirv938/mistral_12b_w60_oai_inputs_bon_outputs_300_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6068467194825848, 'latency_mean': 1.6477893483638764, 'latency_p50': 1.6392366886138916, 'latency_p90': 1.8272725105285645}, {'batch_size': 3, 'throughput': 1.1014852968693263, 'latency_mean': 2.7120256090164183, 'latency_p50': 2.70051109790802, 'latency_p90': 2.9709261894226073}, {'batch_size': 5, 'throughput': 1.3336010325876975, 'latency_mean': 3.727448288202286, 'latency_p50': 3.7240917682647705, 'latency_p90': 4.189597177505493}, {'batch_size': 6, 'throughput': 1.4059692615147212, 'latency_mean': 4.2467197573184965, 'latency_p50': 4.2544790506362915, 'latency_p90': 4.80334849357605}, {'batch_size': 8, 'throughput': 1.4588488041435455, 'latency_mean': 5.4399815213680265, 'latency_p50': 5.497500658035278, 'latency_p90': 6.115249872207642}, {'batch_size': 10, 'throughput': 1.4970203405941278, 'latency_mean': 6.635226527452469, 'latency_p50': 6.6608651876449585, 'latency_p90': 7.480742120742797}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-w60_75581_v1
is_internal_developer: True
language_model: rirv938/mistral_12b_w60_oai_inputs_bon_outputs_300_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.34
us_pacific_date: 2025-02-20
win_ratio: 0.48711943793911006
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': 1024, 'best_of': 8, '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 rirv938-mistral-12b-w60-75581-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-w60-75581-v1-mkmlizer to finish
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ _____ __ __ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ /___/ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ belonging to: ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ║ ║
rirv938-mistral-12b-w60-75581-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-mistral-12b-w60-75581-v1-mkmlizer: Downloaded to shared memory in 105.629s
rirv938-mistral-12b-w60-75581-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfv6w99eo, device:0
rirv938-mistral-12b-w60-75581-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-w60-75581-v1-mkmlizer: quantized model in 43.541s
rirv938-mistral-12b-w60-75581-v1-mkmlizer: Processed model rirv938/mistral_12b_w60_oai_inputs_bon_outputs_300_v2 in 149.171s
rirv938-mistral-12b-w60-75581-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-w60-75581-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-w60-75581-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-w60-75581-v1
rirv938-mistral-12b-w60-75581-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-w60-75581-v1/config.json
rirv938-mistral-12b-w60-75581-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-w60-75581-v1/special_tokens_map.json
Job rirv938-mistral-12b-w60-75581-v1-mkmlizer completed after 195.25s with status: succeeded
Stopping job with name rirv938-mistral-12b-w60-75581-v1-mkmlizer
Pipeline stage MKMLizer completed in 195.75s
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-12b-w60-75581-v1
Waiting for inference service rirv938-mistral-12b-w60-75581-v1 to be ready
Inference service rirv938-mistral-12b-w60-75581-v1 ready after 201.10202717781067s
Pipeline stage MKMLDeployer completed in 201.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.213043212890625s
Received healthy response to inference request in 1.6037580966949463s
Received healthy response to inference request in 1.5941729545593262s
Received healthy response to inference request in 1.4805371761322021s
Received healthy response to inference request in 1.6035125255584717s
5 requests
0 failed requests
5th percentile: 1.5032643318176269
10th percentile: 1.5259914875030518
20th percentile: 1.5714457988739015
30th percentile: 1.5960408687591552
40th percentile: 1.5997766971588134
50th percentile: 1.6035125255584717
60th percentile: 1.6036107540130615
70th percentile: 1.6037089824676514
80th percentile: 1.7256151199340821
90th percentile: 1.9693291664123536
95th percentile: 2.091186189651489
99th percentile: 2.188671808242798
mean time: 1.6990047931671142
Pipeline stage StressChecker completed in 9.80s
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 0.67s
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 0.63s
Shutdown handler de-registered
rirv938-mistral-12b-w60_75581_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 0.11s
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 rirv938-mistral-12b-w60-75581-v1-profiler
Waiting for inference service rirv938-mistral-12b-w60-75581-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2652.66s
Shutdown handler de-registered
rirv938-mistral-12b-w60_75581_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-w60_75581_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1