submission_id: cgato-nemo-12b-thespice-_1853_v7
developer_uid: c.gato
best_of: 8
celo_rating: 1276.39
display_name: cgato-nemo-12b-thespice-_1853_v7
family_friendly_score: 0.5738
family_friendly_standard_error: 0.006993619377689924
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k
latencies: [{'batch_size': 1, 'throughput': 0.6250252687343449, 'latency_mean': 1.5998342728614807, 'latency_p50': 1.5826841592788696, 'latency_p90': 1.784176731109619}, {'batch_size': 3, 'throughput': 1.1576479024369735, 'latency_mean': 2.585192371606827, 'latency_p50': 2.5936790704727173, 'latency_p90': 2.8176811218261717}, {'batch_size': 5, 'throughput': 1.4046948351021353, 'latency_mean': 3.54594061255455, 'latency_p50': 3.5252373218536377, 'latency_p90': 3.9906351566314697}, {'batch_size': 6, 'throughput': 1.4643956060730068, 'latency_mean': 4.077109252214432, 'latency_p50': 4.100901961326599, 'latency_p90': 4.615076112747192}, {'batch_size': 8, 'throughput': 1.5397953832211069, 'latency_mean': 5.1635485827922825, 'latency_p50': 5.20543909072876, 'latency_p90': 5.776011323928833}, {'batch_size': 10, 'throughput': 1.5887662834562863, 'latency_mean': 6.243197081089019, 'latency_p50': 6.2810670137405396, 'latency_p90': 7.067011380195618}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cgato/Nemo-12b-TheSpice-
model_name: cgato-nemo-12b-thespice-_1853_v7
model_num_parameters: 12772121600.0
model_repo: cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k
model_size: 13B
num_battles: 8125
num_wins: 4393
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.43
timestamp: 2024-11-15T19:13:27+00:00
us_pacific_date: 2024-11-15
win_ratio: 0.540676923076923
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %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
Running pipeline stage MKMLizer
Starting job with name cgato-nemo-12b-thespice-1853-v7-mkmlizer
Waiting for job on cgato-nemo-12b-thespice-1853-v7-mkmlizer to finish
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cgato-nemo-12b-thespice-1853-v7-mkmlizer: ║                                                                     ║
cgato-nemo-12b-thespice-1853-v7-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
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-1853-v7-mkmlizer: Downloaded to shared memory in 93.181s
cgato-nemo-12b-thespice-1853-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy5e8n_4a, device:0
cgato-nemo-12b-thespice-1853-v7-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
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-v7-mkmlizer: quantized model in 36.189s
cgato-nemo-12b-thespice-1853-v7-mkmlizer: Processed model cgato/Nemo-12b-TheSpice-V0.9-All-v2-KTO-v0.3-Small-2k in 129.370s
cgato-nemo-12b-thespice-1853-v7-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-thespice-1853-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-thespice-1853-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v7
cgato-nemo-12b-thespice-1853-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v7/config.json
cgato-nemo-12b-thespice-1853-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v7/special_tokens_map.json
cgato-nemo-12b-thespice-1853-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v7/tokenizer_config.json
cgato-nemo-12b-thespice-1853-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-thespice-1853-v7/tokenizer.json
cgato-nemo-12b-thespice-1853-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.13it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.57it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.35it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.81it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.21it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.54it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.57it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.66it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.43it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.80it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 33.32it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.55it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 41.62it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.60it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.44it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 41.53it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.44it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 43.16it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:05, 42.21it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:05, 41.75it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:04, 47.96it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 44.73it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.20it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.85it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.34it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.31it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.08it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.75it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.90it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.57it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.38it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.41it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.09it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.55it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.74it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 43.62it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 48.22it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.17it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.67it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.01it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 36.54it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.98it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.51it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.40it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 43.11it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.47it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.87it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 45.25it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 38.69it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.68it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 44.41it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 43.21it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 44.00it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:23,  2.54it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.27it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.18it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:06,  6.59it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:04,  8.70it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:02, 11.34it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:01, 14.65it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:01, 17.18it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 23.64it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 27.28it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 31.04it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.32it/s]
                                                            

Job cgato-nemo-12b-thespice-1853-v7-mkmlizer completed after 155.6s with status: succeeded
Stopping job with name cgato-nemo-12b-thespice-1853-v7-mkmlizer
Pipeline stage MKMLizer completed in 156.31s
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-1853-v7
Waiting for inference service cgato-nemo-12b-thespice-1853-v7 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
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-v7 ready after 190.82443761825562s
Pipeline stage MKMLDeployer completed in 191.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.315613269805908s
Received healthy response to inference request in 1.8031134605407715s
Received healthy response to inference request in 1.7602813243865967s
Received healthy response to inference request in 1.9307141304016113s
Received healthy response to inference request in 1.8646645545959473s
5 requests
0 failed requests
5th percentile: 1.7688477516174317
10th percentile: 1.7774141788482667
20th percentile: 1.7945470333099365
30th percentile: 1.8154236793518066
40th percentile: 1.840044116973877
50th percentile: 1.8646645545959473
60th percentile: 1.8910843849182128
70th percentile: 1.9175042152404784
80th percentile: 2.007693958282471
90th percentile: 2.1616536140441895
95th percentile: 2.2386334419250487
99th percentile: 2.3002173042297365
mean time: 1.934877347946167
Pipeline stage StressChecker completed in 11.04s
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 6.45s
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 2.54s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_1853_v7 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 2503.75s
Shutdown handler de-registered
cgato-nemo-12b-thespice-_1853_v7 status is now inactive due to auto deactivation removed underperforming models