developer_uid: c.gato
submission_id: cgato-nemo-12b-thespice_1853_v17
model_name: cgato-nemo-12b-thespice_1853_v17
model_group: cgato/Nemo-12b-TheSpice-
status: inactive
timestamp: 2024-11-18T14:27:25+00:00
num_battles: 15292
num_wins: 7868
celo_rating: 1261.46
family_friendly_score: 0.5688
family_friendly_standard_error: 0.00700380696478708
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': 0.6176175225129051, 'latency_mean': 1.6190649259090424, 'latency_p50': 1.6316299438476562, 'latency_p90': 1.7790443420410156}, {'batch_size': 3, 'throughput': 1.1393071192595896, 'latency_mean': 2.6230457890033723, 'latency_p50': 2.6212939023971558, 'latency_p90': 2.93538122177124}, {'batch_size': 5, 'throughput': 1.3916888948023822, 'latency_mean': 3.5749255633354187, 'latency_p50': 3.6042191982269287, 'latency_p90': 3.975060963630676}, {'batch_size': 6, 'throughput': 1.4606976822908433, 'latency_mean': 4.083910554647446, 'latency_p50': 4.092570781707764, 'latency_p90': 4.5655019044876095}, {'batch_size': 8, 'throughput': 1.5237056548670629, 'latency_mean': 5.223196955919266, 'latency_p50': 5.192181944847107, 'latency_p90': 5.850901937484741}, {'batch_size': 10, 'throughput': 1.5562810203527138, 'latency_mean': 6.37779456615448, 'latency_p50': 6.401230454444885, 'latency_p90': 7.270134305953979}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cgato-nemo-12b-thespice_1853_v17
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: 1.42
us_pacific_date: 2024-11-18
win_ratio: 0.5145173947161915
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', 'You:', '\n\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-v17-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-1853-v17-mkmlizer to finish
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-thespice-1853-v17-mkmlizer: Downloaded to shared memory in 47.851s
cgato-nemo-12b-thespice-1853-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkk_tcljw, device:0
cgato-nemo-12b-thespice-1853-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-v17-mkmlizer: quantized model in 36.424s
cgato-nemo-12b-thespice-1853-v17-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k in 84.275s
cgato-nemo-12b-thespice-1853-v17-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-thespice-1853-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-1853-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v17
cgato-nemo-12b-thespice-1853-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v17/special_tokens_map.json
cgato-nemo-12b-thespice-1853-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v17/config.json
cgato-nemo-12b-thespice-1853-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v17/tokenizer_config.json
cgato-nemo-12b-thespice-1853-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v17/tokenizer.json
cgato-nemo-12b-thespice-1853-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v17/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job cgato-nemo-12b-thespice-1853-v17-mkmlizer completed after 114.77s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-1853-v17-mkmlizer
Pipeline stage MKMLizer completed in 115.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.29s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-thespice-1853-v17
Waiting for inference service cgato-nemo-12b-thespice-1853-v17 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
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
Inference service cgato-nemo-12b-thespice-1853-v17 ready after 210.92268562316895s
Pipeline stage MKMLDeployer completed in 211.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.306518316268921s
Received healthy response to inference request in 1.862560510635376s
Received healthy response to inference request in 1.6845791339874268s
Received healthy response to inference request in 1.900831699371338s
Received healthy response to inference request in 1.684770107269287s
5 requests
0 failed requests
5th percentile: 1.6846173286437989
10th percentile: 1.684655523300171
20th percentile: 1.684731912612915
30th percentile: 1.720328187942505
40th percentile: 1.7914443492889405
50th percentile: 1.862560510635376
60th percentile: 1.8778689861297608
70th percentile: 1.8931774616241455
80th percentile: 1.9819690227508546
90th percentile: 2.144243669509888
95th percentile: 2.2253809928894044
99th percentile: 2.2902908515930176
mean time: 1.8878519535064697
Pipeline stage StressChecker completed in 11.03s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.69s
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 2.58s
Shutdown handler de-registered
cgato-nemo-12b-thespice_1853_v17 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 2828.47s
Shutdown handler de-registered
cgato-nemo-12b-thespice_1853_v17 status is now inactive due to auto deactivation removed underperforming models