developer_uid: robert_irvine
submission_id: mistralai-mistral-nemo_9330_v109
model_name: mistralai-mistral-nemo_9330_v109
model_group: mistralai/Mistral-Nemo-I
status: torndown
timestamp: 2024-09-24T19:26:42+00:00
num_battles: 5707
num_wins: 2736
celo_rating: 1238.85
family_friendly_score: 0.0
submission_type: basic
model_repo: mistralai/Mistral-Nemo-Instruct-2407
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6173632533326499, 'latency_mean': 1.6197321653366088, 'latency_p50': 1.6280728578567505, 'latency_p90': 1.7757274150848388}, {'batch_size': 3, 'throughput': 1.0853117192549175, 'latency_mean': 2.7575769889354707, 'latency_p50': 2.745757818222046, 'latency_p90': 3.0233444213867187}, {'batch_size': 5, 'throughput': 1.2366964207753732, 'latency_mean': 4.019458125829697, 'latency_p50': 4.019347429275513, 'latency_p90': 4.575237703323364}, {'batch_size': 6, 'throughput': 1.2626866120967086, 'latency_mean': 4.738929365873337, 'latency_p50': 4.7456361055374146, 'latency_p90': 5.337195611000061}, {'batch_size': 8, 'throughput': 1.2435590813754247, 'latency_mean': 6.393421548604965, 'latency_p50': 6.400758385658264, 'latency_p90': 7.2582491636276245}, {'batch_size': 10, 'throughput': 1.2115064750486562, 'latency_mean': 8.217003868818283, 'latency_p50': 8.24162220954895, 'latency_p90': 9.320314216613768}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: mistralai-mistral-nemo_9330_v109
is_internal_developer: True
language_model: mistralai/Mistral-Nemo-Instruct-2407
model_size: 13B
ranking_group: single
throughput_3p7s: 1.21
us_pacific_date: 2024-09-24
win_ratio: 0.47941124934291224
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', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], '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 mistralai-mistral-nemo-9330-v109-mkmlizer
Waiting for job on mistralai-mistral-nemo-9330-v109-mkmlizer to finish
mistralai-mistral-nemo-9330-v109-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-mistral-nemo-9330-v109-mkmlizer: ║     _____            __           __                                ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║       /___/                                                         ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  Version: 0.10.1                                                    ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  belonging to:                                                      ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ║                                                                     ║
mistralai-mistral-nemo-9330-v109-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_batat_2024-09-20: ('http://zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:56348->127.0.0.1:8080: write tcp 127.0.0.1:56348->127.0.0.1:8080: use of closed network connection\n')
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
mistralai-mistral-nemo-9330-v109-mkmlizer: Downloaded to shared memory in 48.445s
mistralai-mistral-nemo-9330-v109-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyukzenxn, device:0
mistralai-mistral-nemo-9330-v109-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38056->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
LLM-Router throws exception AssertionError('LLM-Router predict returns error 504') for josephson
mistralai-mistral-nemo-9330-v109-mkmlizer: quantized model in 35.065s
mistralai-mistral-nemo-9330-v109-mkmlizer: Processed model mistralai/Mistral-Nemo-Instruct-2407 in 83.510s
mistralai-mistral-nemo-9330-v109-mkmlizer: creating bucket guanaco-mkml-models
mistralai-mistral-nemo-9330-v109-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-mistral-nemo-9330-v109-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v109
mistralai-mistral-nemo-9330-v109-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v109/config.json
mistralai-mistral-nemo-9330-v109-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v109/special_tokens_map.json
mistralai-mistral-nemo-9330-v109-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v109/tokenizer_config.json
mistralai-mistral-nemo-9330-v109-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v109/tokenizer.json
mistralai-mistral-nemo-9330-v109-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v109/flywheel_model.0.safetensors
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Job mistralai-mistral-nemo-9330-v109-mkmlizer completed after 109.48s with status: succeeded
Stopping job with name mistralai-mistral-nemo-9330-v109-mkmlizer
Pipeline stage MKMLizer completed in 110.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service mistralai-mistral-nemo-9330-v109
Waiting for inference service mistralai-mistral-nemo-9330-v109 to be ready
Failed to get response for submission chaiml-chaiml-sft-horror_v2: ('http://chaiml-chaiml-sft-horror-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43010->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
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
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission mistralai-mistral-nemo_9330_v108: ('http://mistralai-mistral-nemo-9330-v108-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service mistralai-mistral-nemo-9330-v109 ready after 212.1510591506958s
Pipeline stage MKMLDeployer completed in 213.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6560986042022705s
Received healthy response to inference request in 1.4207074642181396s
Received healthy response to inference request in 1.7648253440856934s
Received healthy response to inference request in 1.6508510112762451s
Received healthy response to inference request in 0.938957691192627s
5 requests
0 failed requests
5th percentile: 1.0353076457977295
10th percentile: 1.131657600402832
20th percentile: 1.324357509613037
30th percentile: 1.4667361736297608
40th percentile: 1.558793592453003
50th percentile: 1.6508510112762451
60th percentile: 1.6964407444000245
70th percentile: 1.7420304775238038
80th percentile: 2.1430799961090092
90th percentile: 2.8995893001556396
95th percentile: 3.2778439521789546
99th percentile: 3.5804476737976074
mean time: 1.8862880229949952
Pipeline stage StressChecker completed in 10.54s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.83s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v109 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 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service mistralai-mistral-nemo-9330-v109-profiler
Waiting for inference service mistralai-mistral-nemo-9330-v109-profiler to be ready
Inference service mistralai-mistral-nemo-9330-v109-profiler ready after 220.50513315200806s
Pipeline stage MKMLProfilerDeployer completed in 220.93s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/mistralai-mistral-nec115d23c40c80cf7a46c109622a2ff65-deplox9lxd:/code/chaiverse_profiler_1727206627 --namespace tenant-chaiml-guanaco
kubectl exec -it mistralai-mistral-nec115d23c40c80cf7a46c109622a2ff65-deplox9lxd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727206627 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727206627/summary.json'
kubectl exec -it mistralai-mistral-nec115d23c40c80cf7a46c109622a2ff65-deplox9lxd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727206627/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1159.49s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service mistralai-mistral-nemo-9330-v109-profiler is running
Tearing down inference service mistralai-mistral-nemo-9330-v109-profiler
Service mistralai-mistral-nemo-9330-v109-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.46s
Shutdown handler de-registered
mistralai-mistral-nemo_9330_v109 status is now inactive due to auto deactivation removed underperforming models
mistralai-mistral-nemo_9330_v109 status is now torndown due to DeploymentManager action