cgato-nemo-12b-thespice_1853

developer_uid: c.gato

submission_id: cgato-nemo-12b-thespice_1853_v15

model_name: cgato-nemo-12b-thespice_1853_v15

model_group: cgato/Nemo-12b-TheSpice-

status: inactive

timestamp: 2024-11-18T05:41:55+00:00

num_battles: 10927

num_wins: 5643

celo_rating: 1260.39

family_friendly_score: 0.5720000000000001

family_friendly_standard_error: 0.00699737093485832

submission_type: basic

model_repo: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k

model_architecture: MistralForCausalLM

model_num_parameters: 12772121600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6223553710310497, 'latency_mean': 1.6067028617858887, 'latency_p50': 1.602844476699829, 'latency_p90': 1.7761103868484498}, {'batch_size': 3, 'throughput': 1.150473666958209, 'latency_mean': 2.595200138092041, 'latency_p50': 2.599632740020752, 'latency_p90': 2.861869788169861}, {'batch_size': 5, 'throughput': 1.4068450346662211, 'latency_mean': 3.537263103723526, 'latency_p50': 3.507136344909668, 'latency_p90': 3.9154595375061034}, {'batch_size': 6, 'throughput': 1.483177630801583, 'latency_mean': 4.0214212238788605, 'latency_p50': 4.0563132762908936, 'latency_p90': 4.487084269523621}, {'batch_size': 8, 'throughput': 1.5422291051495052, 'latency_mean': 5.143332198858261, 'latency_p50': 5.168980956077576, 'latency_p90': 5.849752712249756}, {'batch_size': 10, 'throughput': 1.5935014986614084, 'latency_mean': 6.231094080209732, 'latency_p50': 6.21247935295105, 'latency_p90': 7.093318223953247}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-thespice_1853_v15

is_internal_developer: False

language_model: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k

model_size: 13B

ranking_group: single

throughput_3p7s: 1.44

us_pacific_date: 2024-11-17

win_ratio: 0.5164271986821635

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}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

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 cgato-nemo-12b-thespice-1853-v15-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-1853-v15-mkmlizer to finish
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v15-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
cgato-nemo-12b-thespice-1853-v15-mkmlizer: Downloaded to shared memory in 50.157s
cgato-nemo-12b-thespice-1853-v15-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_q6ugrnx, device:0
cgato-nemo-12b-thespice-1853-v15-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-thespice-1853-v15-mkmlizer: quantized model in 36.352s
cgato-nemo-12b-thespice-1853-v15-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k in 86.509s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cgato-nemo-12b-thespice-1853-v15-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-1853-v15-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v15
cgato-nemo-12b-thespice-1853-v15-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v15/config.json
cgato-nemo-12b-thespice-1853-v15-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v15/special_tokens_map.json
cgato-nemo-12b-thespice-1853-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v15/tokenizer_config.json
cgato-nemo-12b-thespice-1853-v15-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v15/tokenizer.json
cgato-nemo-12b-thespice-1853-v15-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v15/flywheel_model.0.safetensors
Job cgato-nemo-12b-thespice-1853-v15-mkmlizer completed after 115.0s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-1853-v15-mkmlizer
Pipeline stage MKMLizer completed in 115.58s
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 cgato-nemo-12b-thespice-1853-v15
Waiting for inference service cgato-nemo-12b-thespice-1853-v15 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
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 zonemercy-virgo-edit-v1-1e5_v13: ('http://zonemercy-virgo-edit-v1-1e5-v13-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40742->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cgato-nemo-12b-thespice-1853-v15 ready after 210.70824313163757s
Pipeline stage MKMLDeployer completed in 211.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7072644233703613s
Received healthy response to inference request in 1.8017668724060059s
Received healthy response to inference request in 1.813938856124878s
Received healthy response to inference request in 1.7068819999694824s
Received healthy response to inference request in 2.4645588397979736s
5 requests
0 failed requests
5th percentile: 1.7258589744567872
10th percentile: 1.7448359489440919
20th percentile: 1.7827898979187011
30th percentile: 1.8042012691497802
40th percentile: 1.809070062637329
50th percentile: 1.813938856124878
60th percentile: 2.074186849594116
70th percentile: 2.3344348430633546
80th percentile: 2.513099956512451
90th percentile: 2.610182189941406
95th percentile: 2.658723306655884
99th percentile: 2.6975562000274658
mean time: 2.0988821983337402
Pipeline stage StressChecker completed in 11.78s
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 2.80s
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 2.24s
Shutdown handler de-registered
cgato-nemo-12b-thespice_1853_v15 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 2605.85s
Shutdown handler de-registered
cgato-nemo-12b-thespice_1853_v15 status is now inactive due to auto deactivation removed underperforming models