nitral-ai-nera-noctis-1_10343

developer_uid: azuruce

submission_id: nitral-ai-nera-noctis-1_10343_v3

model_name: nitral-ai-nera-noctis-1_10343_v3

model_group: Nitral-AI/Nera_Noctis-12

status: torndown

timestamp: 2025-01-09T01:06:22+00:00

num_battles: 5557

num_wins: 2598

celo_rating: 1237.96

family_friendly_score: 0.587

family_friendly_standard_error: 0.0069632032858448125

submission_type: basic

model_repo: Nitral-AI/Nera_Noctis-12B-v0.420

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6330235680540945, 'latency_mean': 1.579664180278778, 'latency_p50': 1.5832953453063965, 'latency_p90': 1.7421048164367676}, {'batch_size': 3, 'throughput': 1.2467717150771307, 'latency_mean': 2.39936986207962, 'latency_p50': 2.384803533554077, 'latency_p90': 2.6077935218811037}, {'batch_size': 5, 'throughput': 1.5602572491727464, 'latency_mean': 3.1828184616565705, 'latency_p50': 3.172266721725464, 'latency_p90': 3.6042354822158815}, {'batch_size': 6, 'throughput': 1.6714981377277685, 'latency_mean': 3.573636897802353, 'latency_p50': 3.5943124294281006, 'latency_p90': 4.021764302253723}, {'batch_size': 8, 'throughput': 1.836083629429972, 'latency_mean': 4.334799828529358, 'latency_p50': 4.329536080360413, 'latency_p90': 4.995322966575623}, {'batch_size': 10, 'throughput': 1.8968588859943762, 'latency_mean': 5.233211364746094, 'latency_p50': 5.22193455696106, 'latency_p90': 5.878463196754455}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: nitral-ai-nera-noctis-1_10343_v3

is_internal_developer: True

language_model: Nitral-AI/Nera_Noctis-12B-v0.420

model_size: 13B

ranking_group: single

throughput_3p7s: 1.71

us_pacific_date: 2025-01-08

win_ratio: 0.4675184452042469

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>', 'Me:'], 'max_input_tokens': 1024, 'best_of': 4, '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 nitral-ai-nera-noctis-1-10343-v3-mkmlizer
Waiting for job on nitral-ai-nera-noctis-1-10343-v3-mkmlizer to finish
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║     _____            __           __                                ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║       /___/                                                         ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║                                                                     ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  https://mk1.ai                                                     ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║                                                                     ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  belonging to:                                                      ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║                                                                     ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  Chai Research Corp.                                                ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ║                                                                     ║
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: Downloaded to shared memory in 38.225s
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb2sfugsg, device:0
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: quantized model in 36.891s
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: Processed model Nitral-AI/Nera_Noctis-12B-v0.420 in 75.117s
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-nera-noctis-1-10343-v3
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-nera-noctis-1-10343-v3/special_tokens_map.json
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-nera-noctis-1-10343-v3/config.json
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-nera-noctis-1-10343-v3/tokenizer_config.json
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-nera-noctis-1-10343-v3/tokenizer.json
nitral-ai-nera-noctis-1-10343-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-nera-noctis-1-10343-v3/flywheel_model.0.safetensors
Job nitral-ai-nera-noctis-1-10343-v3-mkmlizer completed after 104.87s with status: succeeded
Stopping job with name nitral-ai-nera-noctis-1-10343-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.40s
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 nitral-ai-nera-noctis-1-10343-v3
Waiting for inference service nitral-ai-nera-noctis-1-10343-v3 to be ready
Inference service nitral-ai-nera-noctis-1-10343-v3 ready after 411.65869784355164s
Pipeline stage MKMLDeployer completed in 412.33s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.2272651195526123s
Received healthy response to inference request in 1.268303632736206s
Received healthy response to inference request in 0.8021225929260254s
Received healthy response to inference request in 1.328728437423706s
5 requests
1 failed requests
5th percentile: 0.8871510982513428
10th percentile: 0.9721796035766601
20th percentile: 1.1422366142272948
30th percentile: 1.235472822189331
40th percentile: 1.2518882274627685
50th percentile: 1.268303632736206
60th percentile: 1.292473554611206
70th percentile: 1.316643476486206
80th percentile: 5.090349197387699
90th percentile: 12.613590717315676
95th percentile: 16.37521147727966
99th percentile: 19.384508085250854
mean time: 4.95265040397644
%s, retrying in %s seconds...
Received healthy response to inference request in 1.408454418182373s
Received healthy response to inference request in 1.0981895923614502s
Received healthy response to inference request in 0.6324653625488281s
Received healthy response to inference request in 0.635134220123291s
Received healthy response to inference request in 0.8282961845397949s
5 requests
0 failed requests
5th percentile: 0.6329991340637207
10th percentile: 0.6335329055786133
20th percentile: 0.6346004486083985
30th percentile: 0.6737666130065918
40th percentile: 0.7510313987731934
50th percentile: 0.8282961845397949
60th percentile: 0.936253547668457
70th percentile: 1.0442109107971191
80th percentile: 1.1602425575256348
90th percentile: 1.284348487854004
95th percentile: 1.3464014530181885
99th percentile: 1.3960438251495362
mean time: 0.9205079555511475
Pipeline stage StressChecker completed in 31.90s
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 0.81s
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
nitral-ai-nera-noctis-1_10343_v3 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 2333.85s
Shutdown handler de-registered
nitral-ai-nera-noctis-1_10343_v3 status is now inactive due to auto deactivation removed underperforming models
nitral-ai-nera-noctis-1_10343_v3 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message