cgato-nemo-12b-thespice-_4292

developer_uid: c.gato

submission_id: cgato-nemo-12b-thespice-_4292_v1

model_name: cgato-nemo-12b-thespice-_4292_v1

model_group: cgato/Nemo-12b-TheSpice-

status: inactive

timestamp: 2024-11-18T18:12:57+00:00

num_battles: 9465

num_wins: 4859

celo_rating: 1262.59

family_friendly_score: 0.5718

family_friendly_standard_error: 0.006997781934298896

submission_type: basic

model_repo: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-Split-E3

model_architecture: MistralForCausalLM

model_num_parameters: 12772121600.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6146653280321877, 'latency_mean': 1.626806721687317, 'latency_p50': 1.6205276250839233, 'latency_p90': 1.7999192476272583}, {'batch_size': 3, 'throughput': 1.1441867522142428, 'latency_mean': 2.6092393791675565, 'latency_p50': 2.6140164136886597, 'latency_p90': 2.931670880317688}, {'batch_size': 5, 'throughput': 1.387005891857711, 'latency_mean': 3.5858659970760347, 'latency_p50': 3.6085158586502075, 'latency_p90': 3.8919298887252807}, {'batch_size': 6, 'throughput': 1.4645013152740705, 'latency_mean': 4.071532455682754, 'latency_p50': 4.049622178077698, 'latency_p90': 4.5727965354919435}, {'batch_size': 8, 'throughput': 1.5357670768889349, 'latency_mean': 5.179777787923813, 'latency_p50': 5.15822970867157, 'latency_p90': 5.883510613441468}, {'batch_size': 10, 'throughput': 1.5744698332723512, 'latency_mean': 6.308985555171967, 'latency_p50': 6.329917788505554, 'latency_p90': 7.031081867218017}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-thespice-_4292_v1

is_internal_developer: False

language_model: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-Split-E3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-11-18

win_ratio: 0.513365029054411

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-4292-v1-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-4292-v1-mkmlizer to finish
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cgato-nemo-12b-thespice-4292-v1-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-4292-v1-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
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: ('http://chaiml-nemo-20241010-tie-5991-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49964->127.0.0.1:8080: read: connection reset by peer\n')
cgato-nemo-12b-thespice-4292-v1-mkmlizer: Downloaded to shared memory in 49.893s
cgato-nemo-12b-thespice-4292-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpksese_e2, device:0
cgato-nemo-12b-thespice-4292-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
cgato-nemo-12b-thespice-4292-v1-mkmlizer: quantized model in 35.928s
cgato-nemo-12b-thespice-4292-v1-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-Split-E3 in 85.822s
cgato-nemo-12b-thespice-4292-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-thespice-4292-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-4292-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-4292-v1
cgato-nemo-12b-thespice-4292-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-4292-v1/tokenizer.json
cgato-nemo-12b-thespice-4292-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-thespice-4292-v1/flywheel_model.0.safetensors
cgato-nemo-12b-thespice-4292-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.72it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.51it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.67it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.46it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.41it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.22it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.66it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.32it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.79it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.24it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.55it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 42.20it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.82it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 47.71it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.26it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.68it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 53.93it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 49.26it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 47.48it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.46it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 45.44it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.93it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.12it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 33.08it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.18it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 38.39it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:04, 40.50it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 42.75it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 42.38it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 41.82it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 47.20it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 46.52it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 37.66it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 44.70it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 44.18it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 44.69it/s]
Loading 0:  60%|█████▉    | 216/363 [00:04<00:03, 45.88it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 43.74it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 30.97it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.22it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 35.62it/s]
Loading 0:  66%|██████▋   | 241/363 [00:05<00:03, 34.13it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:03, 38.43it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.02it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 39.35it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 45.32it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 44.10it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:01, 43.60it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 48.80it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 46.37it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 42.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 43.82it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:23,  2.52it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:16,  3.24it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.15it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.90it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  9.03it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:02, 11.09it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:01, 15.87it/s]
Loading 0:  94%|█████████▍| 342/363 [00:14<00:01, 19.17it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 23.00it/s]
Loading 0:  97%|█████████▋| 352/363 [00:14<00:00, 27.04it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 26.48it/s]
                                                            
Job cgato-nemo-12b-thespice-4292-v1-mkmlizer completed after 104.75s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-4292-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.31s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-thespice-4292-v1
Waiting for inference service cgato-nemo-12b-thespice-4292-v1 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
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: ('http://chaiml-nemo-20241010-tie-5991-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33732->127.0.0.1:8080: read: connection reset by peer\n')
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-4292-v1 ready after 211.65537643432617s
Pipeline stage MKMLDeployer completed in 212.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.153999090194702s
Received healthy response to inference request in 1.8167052268981934s
Received healthy response to inference request in 2.4514944553375244s
Received healthy response to inference request in 1.7010855674743652s
Received healthy response to inference request in 1.9637451171875s
5 requests
0 failed requests
5th percentile: 1.7242094993591308
10th percentile: 1.7473334312438964
20th percentile: 1.7935812950134278
30th percentile: 1.8461132049560547
40th percentile: 1.9049291610717773
50th percentile: 1.9637451171875
60th percentile: 2.0398467063903807
70th percentile: 2.115948295593262
80th percentile: 2.213498163223267
90th percentile: 2.3324963092803954
95th percentile: 2.3919953823089597
99th percentile: 2.4395946407318116
mean time: 2.017405891418457
Pipeline stage StressChecker completed in 11.76s
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 3.22s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Retrying (%r) after connection broken by '%r': %s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 17.94s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_4292_v1 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 2589.09s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_4292_v1 status is now inactive due to auto deactivation removed underperforming models