cgato-nemo-12b-thespice-_3053

developer_uid: c.gato

submission_id: cgato-nemo-12b-thespice-_3053_v3

model_name: cgato-nemo-12b-thespice-_3053_v3

model_group: cgato/Nemo-12b-TheSpice-

status: torndown

timestamp: 2024-11-07T19:59:15+00:00

num_battles: 18686

num_wins: 9759

celo_rating: 1257.45

family_friendly_score: 0.5704

family_friendly_standard_error: 0.007000626257700092

submission_type: basic

model_repo: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-BigBoy-20k

model_architecture: MistralForCausalLM

model_num_parameters: 12772121600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6105732362664746, 'latency_mean': 1.6377105689048768, 'latency_p50': 1.649829626083374, 'latency_p90': 1.8064409255981446}, {'batch_size': 3, 'throughput': 1.1166443921042233, 'latency_mean': 2.678014771938324, 'latency_p50': 2.669026732444763, 'latency_p90': 2.9629977703094483}, {'batch_size': 5, 'throughput': 1.3588481817293567, 'latency_mean': 3.667422823905945, 'latency_p50': 3.6529067754745483, 'latency_p90': 4.055878281593323}, {'batch_size': 6, 'throughput': 1.4089444500607224, 'latency_mean': 4.23148398399353, 'latency_p50': 4.258513569831848, 'latency_p90': 4.699710893630981}, {'batch_size': 8, 'throughput': 1.4829647053640662, 'latency_mean': 5.37398175239563, 'latency_p50': 5.352683782577515, 'latency_p90': 6.072238039970398}, {'batch_size': 10, 'throughput': 1.5139679827787182, 'latency_mean': 6.548132554292679, 'latency_p50': 6.496110916137695, 'latency_p90': 7.442607450485229}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-thespice-_3053_v3

is_internal_developer: False

language_model: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-BigBoy-20k

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2024-11-07

win_ratio: 0.5222626565343037

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{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-3053-v3-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-3053-v3-mkmlizer to finish
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-3053-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  Version: 0.11.33                                                   ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-3053-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-thespice-3053-v3-mkmlizer: Downloaded to shared memory in 32.875s
cgato-nemo-12b-thespice-3053-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpegfybov5, device:0
cgato-nemo-12b-thespice-3053-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-thespice-3053-v3-mkmlizer: quantized model in 36.717s
cgato-nemo-12b-thespice-3053-v3-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-BigBoy-20k in 69.591s
cgato-nemo-12b-thespice-3053-v3-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-thespice-3053-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-3053-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-3053-v3
cgato-nemo-12b-thespice-3053-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-3053-v3/config.json
cgato-nemo-12b-thespice-3053-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-3053-v3/special_tokens_map.json
cgato-nemo-12b-thespice-3053-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-3053-v3/tokenizer_config.json
cgato-nemo-12b-thespice-3053-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-3053-v3/tokenizer.json
cgato-nemo-12b-thespice-3053-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-3053-v3/flywheel_model.0.safetensors
cgato-nemo-12b-thespice-3053-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.63it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.64it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:06, 49.41it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.39it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.75it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.41it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 40.95it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 46.23it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 42.85it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.01it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.03it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.27it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 39.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.16it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 39.95it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.02it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 41.62it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 39.82it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 41.81it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.03it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 40.48it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.63it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.74it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.37it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.94it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.95it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.53it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.17it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.74it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.24it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:05, 36.63it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 32.70it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 39.07it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 39.46it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 40.65it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.00it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.69it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.07it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.28it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.73it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 28.37it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 30.11it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.97it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.81it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 38.34it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.33it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.08it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 40.07it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 40.71it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.82it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.24it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.31it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.28it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.00it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 41.07it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:23,  2.46it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:16,  3.14it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:12,  3.85it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:07,  5.89it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.55it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03, 10.90it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 14.18it/s]
Loading 0:  93%|█████████▎| 339/363 [00:15<00:01, 16.15it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 22.50it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 26.10it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.21it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 32.80it/s]
                                                            
Job cgato-nemo-12b-thespice-3053-v3-mkmlizer completed after 94.51s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-3053-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.06s
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-thespice-3053-v3
Waiting for inference service cgato-nemo-12b-thespice-3053-v3 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
Inference service cgato-nemo-12b-thespice-3053-v3 ready after 170.92607474327087s
Pipeline stage MKMLDeployer completed in 171.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6226186752319336s
Received healthy response to inference request in 1.4872679710388184s
Received healthy response to inference request in 1.8133940696716309s
Received healthy response to inference request in 1.6237797737121582s
Received healthy response to inference request in 1.750692367553711s
5 requests
0 failed requests
5th percentile: 1.5145703315734864
10th percentile: 1.5418726921081543
20th percentile: 1.5964774131774901
30th percentile: 1.6491622924804688
40th percentile: 1.6999273300170898
50th percentile: 1.750692367553711
60th percentile: 1.775773048400879
70th percentile: 1.8008537292480469
80th percentile: 1.9752389907836916
90th percentile: 2.2989288330078126
95th percentile: 2.460773754119873
99th percentile: 2.5902496910095216
mean time: 1.8595505714416505
Pipeline stage StressChecker completed in 10.78s
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 5.85s
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 3.05s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_3053_v3 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cgato-nemo-12b-thespice-3053-v3-profiler
Waiting for inference service cgato-nemo-12b-thespice-3053-v3-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 2744.51s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_3053_v3 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-thespice-_3053_v3 status is now torndown due to DeploymentManager action
cgato-nemo-12b-thespice-_3053_v3 status is now torndown due to DeploymentManager action