developer_uid: rirv938
submission_id: rirv938-mistral-12b-vir_43998_v1
model_name: rirv938-mistral-12b-vir_43998_v1
model_group: rirv938/mistral_12b_vira
status: torndown
timestamp: 2025-02-21T07:26:23+00:00
num_battles: 6074
num_wins: 2951
celo_rating: 1256.05
family_friendly_score: 0.6018
family_friendly_standard_error: 0.006922958327189324
submission_type: basic
model_repo: rirv938/mistral_12b_viral_ss_1_600_samples_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': 0.595390611452494, 'latency_mean': 1.6795031213760376, 'latency_p50': 1.6894594430923462, 'latency_p90': 1.8390166759490967}, {'batch_size': 3, 'throughput': 1.0729013312934712, 'latency_mean': 2.7915645241737366, 'latency_p50': 2.788703680038452, 'latency_p90': 3.0513255119323732}, {'batch_size': 5, 'throughput': 1.3039936888170902, 'latency_mean': 3.814501482248306, 'latency_p50': 3.84408175945282, 'latency_p90': 4.257529950141906}, {'batch_size': 6, 'throughput': 1.3467036760292355, 'latency_mean': 4.424700525999069, 'latency_p50': 4.459667086601257, 'latency_p90': 4.951239609718323}, {'batch_size': 8, 'throughput': 1.4209928363775284, 'latency_mean': 5.598263413906097, 'latency_p50': 5.5826133489608765, 'latency_p90': 6.321742510795593}, {'batch_size': 10, 'throughput': 1.4545178908850418, 'latency_mean': 6.825649042129516, 'latency_p50': 6.75278103351593, 'latency_p90': 7.75679042339325}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-mistral-12b-vir_43998_v1
is_internal_developer: True
language_model: rirv938/mistral_12b_viral_ss_1_600_samples_300_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.29
us_pacific_date: 2025-02-20
win_ratio: 0.48584129074744814
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-vir-43998-v1-mkmlizer
Waiting for job on rirv938-mistral-12b-vir-43998-v1-mkmlizer to finish
rirv938-mistral-12b-vir-43998-v1-mkmlizer: Downloaded to shared memory in 92.016s
rirv938-mistral-12b-vir-43998-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc7rle7i8, device:0
rirv938-mistral-12b-vir-43998-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-12b-vir-43998-v1-mkmlizer: quantized model in 44.996s
rirv938-mistral-12b-vir-43998-v1-mkmlizer: Processed model rirv938/mistral_12b_viral_ss_1_600_samples_300_v2 in 137.013s
rirv938-mistral-12b-vir-43998-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-12b-vir-43998-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-12b-vir-43998-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-12b-vir-43998-v1
rirv938-mistral-12b-vir-43998-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-12b-vir-43998-v1/config.json
rirv938-mistral-12b-vir-43998-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-12b-vir-43998-v1/special_tokens_map.json
rirv938-mistral-12b-vir-43998-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-12b-vir-43998-v1/tokenizer_config.json
rirv938-mistral-12b-vir-43998-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-12b-vir-43998-v1/tokenizer.json
Job rirv938-mistral-12b-vir-43998-v1-mkmlizer completed after 200.73s with status: succeeded
Stopping job with name rirv938-mistral-12b-vir-43998-v1-mkmlizer
Pipeline stage MKMLizer completed in 201.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-12b-vir-43998-v1
Waiting for inference service rirv938-mistral-12b-vir-43998-v1 to be ready
Inference service rirv938-mistral-12b-vir-43998-v1 ready after 230.76826167106628s
Pipeline stage MKMLDeployer completed in 231.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.542149543762207s
Received healthy response to inference request in 1.2571442127227783s
Received healthy response to inference request in 1.4520022869110107s
Received healthy response to inference request in 1.571594476699829s
Received healthy response to inference request in 1.12087082862854s
5 requests
0 failed requests
5th percentile: 1.1481255054473878
10th percentile: 1.1753801822662353
20th percentile: 1.2298895359039306
30th percentile: 1.2961158275604248
40th percentile: 1.3740590572357179
50th percentile: 1.4520022869110107
60th percentile: 1.4880611896514893
70th percentile: 1.5241200923919678
80th percentile: 1.5480385303497315
90th percentile: 1.5598165035247802
95th percentile: 1.5657054901123046
99th percentile: 1.5704166793823242
mean time: 1.388752269744873
Pipeline stage StressChecker completed in 8.21s
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 0.63s
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 0.65s
Shutdown handler de-registered
rirv938-mistral-12b-vir_43998_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-12b-vir-43998-v1-profiler
Waiting for inference service rirv938-mistral-12b-vir-43998-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 2635.04s
Shutdown handler de-registered
rirv938-mistral-12b-vir_43998_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-12b-vir_43998_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1