cgato-nemo-12b-humaniz_74135

developer_uid: cgato

submission_id: cgato-nemo-12b-humaniz_74135_v29

model_name: cgato-nemo-12b-humaniz_74135_v29

model_group: cgato/Nemo-12b-Humanize-

status: torndown

timestamp: 2025-01-08T15:23:23+00:00

num_battles: 13729

num_wins: 7018

celo_rating: 1270.62

family_friendly_score: 0.5848

family_friendly_standard_error: 0.006968629133480989

submission_type: basic

model_repo: cgato/Nemo-12b-Humanize-KTO-Experimental-Latest

model_architecture: MistralForCausalLM

model_num_parameters: 12772111360.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6188865798826386, 'latency_mean': 1.6157124745845795, 'latency_p50': 1.6033189296722412, 'latency_p90': 1.8021348476409913}, {'batch_size': 3, 'throughput': 1.1373440080273205, 'latency_mean': 2.626182882785797, 'latency_p50': 2.6147741079330444, 'latency_p90': 2.8842023611068726}, {'batch_size': 5, 'throughput': 1.3710828120022258, 'latency_mean': 3.630878665447235, 'latency_p50': 3.6069438457489014, 'latency_p90': 4.023665952682495}, {'batch_size': 6, 'throughput': 1.4325892774864482, 'latency_mean': 4.160707712173462, 'latency_p50': 4.163808703422546, 'latency_p90': 4.6975723028182985}, {'batch_size': 8, 'throughput': 1.4856131223784783, 'latency_mean': 5.350693130493164, 'latency_p50': 5.340584635734558, 'latency_p90': 6.042189574241638}, {'batch_size': 10, 'throughput': 1.5448191124545145, 'latency_mean': 6.426766549348831, 'latency_p50': 6.439594984054565, 'latency_p90': 7.340346884727478}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-humaniz_74135_v29

is_internal_developer: False

language_model: cgato/Nemo-12b-Humanize-KTO-Experimental-Latest

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2025-01-08

win_ratio: 0.5111807123606963

generation_params: {'temperature': 0.7, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.01, 'frequency_penalty': 0.01, '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-humaniz-74135-v29-mkmlizer
Waiting for job on cgato-nemo-12b-humaniz-74135-v29-mkmlizer to finish
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: Downloaded to shared memory in 48.331s
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5ssgeleo, device:0
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: quantized model in 35.689s
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: Processed model cgato/Nemo-12b-Humanize-KTO-Experimental-Latest in 84.020s
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-humaniz-74135-v29
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-humaniz-74135-v29/config.json
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-humaniz-74135-v29/special_tokens_map.json
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-humaniz-74135-v29/tokenizer_config.json
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-humaniz-74135-v29/tokenizer.json
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-humaniz-74135-v29/flywheel_model.0.safetensors
cgato-nemo-12b-humaniz-74135-v29-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.09it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.28it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 49.12it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.03it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.70it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.39it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:06, 47.84it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 55.09it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 38.98it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.36it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.91it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:08, 34.23it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 37.34it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:07, 37.09it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.09it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.45it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 43.59it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 36.54it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 36.04it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 43.71it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.40it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.90it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.26it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.94it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.44it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.44it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.05it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 39.76it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.63it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 46.09it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 46.79it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 38.05it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 45.92it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 44.64it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 44.78it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 52.86it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.66it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 36.05it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.67it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 41.84it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 36.91it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.22it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 43.95it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 43.93it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 49.28it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 48.01it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 46.86it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 51.27it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 46.78it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 45.53it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:21,  2.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.27it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.31it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  6.96it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.77it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.24it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.52it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.17it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 23.76it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 27.25it/s]
                                                            
Job cgato-nemo-12b-humaniz-74135-v29-mkmlizer completed after 114.6s with status: succeeded
Stopping job with name cgato-nemo-12b-humaniz-74135-v29-mkmlizer
Pipeline stage MKMLizer completed in 115.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-humaniz-74135-v29
Waiting for inference service cgato-nemo-12b-humaniz-74135-v29 to be ready
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cgato-nemo-12b-humaniz-74135-v29 ready after 353.77322220802307s
Pipeline stage MKMLDeployer completed in 354.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7552595138549805s
Received healthy response to inference request in 1.8611092567443848s
Received healthy response to inference request in 1.6693997383117676s
Received healthy response to inference request in 1.4519157409667969s
Received healthy response to inference request in 1.649885654449463s
5 requests
0 failed requests
5th percentile: 1.4915097236633301
10th percentile: 1.5311037063598634
20th percentile: 1.6102916717529296
30th percentile: 1.6537884712219237
40th percentile: 1.6615941047668457
50th percentile: 1.6693997383117676
60th percentile: 1.7037436485290527
70th percentile: 1.7380875587463378
80th percentile: 1.7764294624328614
90th percentile: 1.818769359588623
95th percentile: 1.8399393081665039
99th percentile: 1.8568752670288087
mean time: 1.6775139808654784
Pipeline stage StressChecker completed in 10.41s
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 0.66s
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
cgato-nemo-12b-humaniz_74135_v29 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cgato-nemo-12b-humaniz-74135-v29-profiler
Waiting for inference service cgato-nemo-12b-humaniz-74135-v29-profiler to be ready
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 2867.48s
Shutdown handler de-registered
cgato-nemo-12b-humaniz_74135_v29 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-humaniz_74135_v29 status is now torndown due to DeploymentManager action