cgato-nemo-12b-humanize_77076

developer_uid: cgato

submission_id: cgato-nemo-12b-humanize_77076_v2

model_name: cgato-nemo-12b-humanize_77076_v2

model_group: cgato/Nemo-12b-Humanize-

status: torndown

timestamp: 2025-01-05T02:54:48+00:00

num_battles: 15638

num_wins: 7913

celo_rating: 1261.86

family_friendly_score: 0.5826

family_friendly_standard_error: 0.006973911958148023

submission_type: basic

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

model_architecture: MistralForCausalLM

model_num_parameters: 12772111360.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6159383218987522, 'latency_mean': 1.623471348285675, 'latency_p50': 1.612458348274231, 'latency_p90': 1.8069117784500122}, {'batch_size': 3, 'throughput': 1.1372392642599596, 'latency_mean': 2.631539888381958, 'latency_p50': 2.6394126415252686, 'latency_p90': 2.889621615409851}, {'batch_size': 5, 'throughput': 1.374832769894341, 'latency_mean': 3.6176149642467497, 'latency_p50': 3.6384583711624146, 'latency_p90': 4.034048581123352}, {'batch_size': 6, 'throughput': 1.4359329984846083, 'latency_mean': 4.1521862959861755, 'latency_p50': 4.1734302043914795, 'latency_p90': 4.634289360046386}, {'batch_size': 8, 'throughput': 1.5063002051219219, 'latency_mean': 5.280616564750671, 'latency_p50': 5.256383657455444, 'latency_p90': 6.057443332672119}, {'batch_size': 10, 'throughput': 1.5634222011626548, 'latency_mean': 6.347381521463394, 'latency_p50': 6.426294684410095, 'latency_p90': 7.125415301322937}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-humanize_77076_v2

is_internal_developer: False

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

model_size: 13B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2025-01-04

win_ratio: 0.5060109988489576

generation_params: {'temperature': 0.9, '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-humanize-77076-v2-mkmlizer
Waiting for job on cgato-nemo-12b-humanize-77076-v2-mkmlizer to finish
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-77076-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-humanize-77076-v2-mkmlizer: Downloaded to shared memory in 50.694s
cgato-nemo-12b-humanize-77076-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp29k4ti59, device:0
cgato-nemo-12b-humanize-77076-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-humanize-77076-v2-mkmlizer: quantized model in 37.387s
cgato-nemo-12b-humanize-77076-v2-mkmlizer: Processed model cgato/Nemo-12b-Humanize-KTO-Experimental-Latest-B in 88.081s
cgato-nemo-12b-humanize-77076-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-humanize-77076-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-humanize-77076-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-humanize-77076-v2
cgato-nemo-12b-humanize-77076-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-77076-v2/config.json
cgato-nemo-12b-humanize-77076-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-77076-v2/special_tokens_map.json
cgato-nemo-12b-humanize-77076-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-77076-v2/tokenizer_config.json
cgato-nemo-12b-humanize-77076-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-77076-v2/tokenizer.json
cgato-nemo-12b-humanize-77076-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-humanize-77076-v2/flywheel_model.0.safetensors
cgato-nemo-12b-humanize-77076-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.60it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 46.06it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:07, 43.42it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 43.32it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 44.15it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.49it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 42.18it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 41.29it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 41.68it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 42.67it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 42.75it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 24.82it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 31.88it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.33it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.31it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:08, 34.16it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 34.65it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:08, 33.66it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 35.87it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:07, 34.16it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 33.96it/s]
Loading 0:  30%|███       | 110/363 [00:03<00:07, 35.46it/s]
Loading 0:  31%|███▏      | 114/363 [00:03<00:07, 32.40it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 31.11it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 39.49it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 38.07it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 37.09it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.67it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.53it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:07, 29.43it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 30.00it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.81it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 36.81it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 41.27it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 41.34it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.51it/s]
Loading 0:  51%|█████     | 184/363 [00:05<00:03, 46.16it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:03, 45.38it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:03, 44.76it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 48.99it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 49.08it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:03, 38.74it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 42.12it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 33.39it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 33.77it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 32.25it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 38.51it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 40.09it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.40it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.28it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.69it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 43.70it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 43.00it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 42.89it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.15it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.46it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 44.51it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 45.19it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 45.95it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.47it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:16,  3.19it/s]
Loading 0:  87%|████████▋ | 315/363 [00:15<00:11,  4.18it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:07,  5.83it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:05,  7.50it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 10.23it/s]
Loading 0:  92%|█████████▏| 335/363 [00:15<00:02, 13.91it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.20it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 22.80it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 25.65it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 28.39it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 31.39it/s]
                                                            
Job cgato-nemo-12b-humanize-77076-v2-mkmlizer completed after 125.1s with status: succeeded
Stopping job with name cgato-nemo-12b-humanize-77076-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.68s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-humanize-77076-v2
Waiting for inference service cgato-nemo-12b-humanize-77076-v2 to be ready
Inference service cgato-nemo-12b-humanize-77076-v2 ready after 321.99433302879333s
Pipeline stage MKMLDeployer completed in 322.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.083361864089966s
Received healthy response to inference request in 1.8712480068206787s
Received healthy response to inference request in 1.7159643173217773s
Received healthy response to inference request in 1.2870488166809082s
Received healthy response to inference request in 1.7487709522247314s
5 requests
0 failed requests
5th percentile: 1.3728319168090821
10th percentile: 1.4586150169372558
20th percentile: 1.6301812171936034
30th percentile: 1.7225256443023682
40th percentile: 1.7356482982635497
50th percentile: 1.7487709522247314
60th percentile: 1.7977617740631104
70th percentile: 1.8467525959014892
80th percentile: 1.9136707782745361
90th percentile: 1.998516321182251
95th percentile: 2.0409390926361084
99th percentile: 2.074877309799194
mean time: 1.7412787914276122
Pipeline stage StressChecker completed in 10.45s
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 0.72s
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 0.73s
Shutdown handler de-registered
cgato-nemo-12b-humanize_77076_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6537.92s
Shutdown handler de-registered
cgato-nemo-12b-humanize_77076_v2 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-humanize_77076_v2 status is now torndown due to DeploymentManager action
cgato-nemo-12b-humanize_77076_v2 status is now torndown due to DeploymentManager action
cgato-nemo-12b-humanize_77076_v2 status is now torndown due to DeploymentManager action