submission_id: mistralai-mistral-nemo_9330_v208
developer_uid: alex-au-chai-research
best_of: 8
celo_rating: 1238.98
display_name: mistralai-mistral-nemo_9330_v208
family_friendly_score: 0.5813999999999999
family_friendly_standard_error: 0.006976733333014814
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: mistralai/Mistral-Nemo-Instruct-2407
latencies: [{'batch_size': 1, 'throughput': 0.6155210045557368, 'latency_mean': 1.6245444810390473, 'latency_p50': 1.625504493713379, 'latency_p90': 1.780696415901184}, {'batch_size': 3, 'throughput': 1.1293063230342721, 'latency_mean': 2.652982405424118, 'latency_p50': 2.6434361934661865, 'latency_p90': 2.992136216163635}, {'batch_size': 5, 'throughput': 1.3725234484312627, 'latency_mean': 3.6316377007961274, 'latency_p50': 3.623907208442688, 'latency_p90': 4.083717322349548}, {'batch_size': 6, 'throughput': 1.4285000792932074, 'latency_mean': 4.173345178365707, 'latency_p50': 4.181983828544617, 'latency_p90': 4.682158708572388}, {'batch_size': 8, 'throughput': 1.5034550434285638, 'latency_mean': 5.279673131704331, 'latency_p50': 5.329104542732239, 'latency_p90': 5.917613768577575}, {'batch_size': 10, 'throughput': 1.54481785501448, 'latency_mean': 6.4148672413825985, 'latency_p50': 6.405645489692688, 'latency_p90': 7.283167314529419}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: mistralai/Mistral-Nemo-I
model_name: mistralai-mistral-nemo_9330_v208
model_num_parameters: 12772070400.0
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
num_battles: 12289
num_wins: 5791
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.39
timestamp: 2024-11-28T20:42:57+00:00
us_pacific_date: 2024-11-28
win_ratio: 0.4712344373016519
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 mistralai-mistral-nemo-9330-v208-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v208-mkmlizer to finish
mistralai-mistral-nemo-9330-v208-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ _____ __ __ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ /___/ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ Version: 0.11.12 ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ https://mk1.ai ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ The license key for the current software has been verified as ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ belonging to: ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ Chai Research Corp. ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ║ ║
mistralai-mistral-nemo-9330-v208-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-mistral-nemo-9330-v208-mkmlizer: Downloaded to shared memory in 54.696s
mistralai-mistral-nemo-9330-v208-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeinrabav, device:0
mistralai-mistral-nemo-9330-v208-mkmlizer: Saving flywheel model at /dev/shm/model_cache
mistralai-mistral-nemo-9330-v208-mkmlizer: quantized model in 36.284s
mistralai-mistral-nemo-9330-v208-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 90.981s
mistralai-mistral-nemo-9330-v208-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v208-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v208
mistralai-mistral-nemo-9330-v208-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v208/special_tokens_map.json
mistralai-mistral-nemo-9330-v208-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v208/config.json
mistralai-mistral-nemo-9330-v208-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v208/tokenizer_config.json
mistralai-mistral-nemo-9330-v208-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v208/tokenizer.json
mistralai-mistral-nemo-9330-v208-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v208/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job mistralai-mistral-nemo-9330-v208-mkmlizer completed after 124.74s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v208-mkmlizer
Pipeline stage MKMLizer completed in 125.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v208
Waiting for inference service mistralai-mistral-nemo-9330-v208 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
Inference service mistralai-mistral-nemo-9330-v208 ready after 130.81842255592346s
Pipeline stage MKMLDeployer completed in 131.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.289151668548584s
Received healthy response to inference request in 2.339294910430908s
Received healthy response to inference request in 1.604579210281372s
Received healthy response to inference request in 1.9065814018249512s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.6557996273040771s
5 requests
0 failed requests
5th percentile: 1.614823293685913
10th percentile: 1.625067377090454
20th percentile: 1.6455555438995362
30th percentile: 1.705955982208252
40th percentile: 1.8062686920166016
50th percentile: 1.9065814018249512
60th percentile: 2.0596095085144044
70th percentile: 2.212637615203857
80th percentile: 2.2991803169250487
90th percentile: 2.3192376136779784
95th percentile: 2.3292662620544435
99th percentile: 2.337289180755615
mean time: 1.9590813636779785
Pipeline stage StressChecker completed in 11.41s
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 2.49s
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 2.35s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v208 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 2737.25s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v208 status is now inactive due to auto deactivation removed underperforming models