sao10k-mn-backyardai-pa_13506

developer_uid: huohuo12

submission_id: sao10k-mn-backyardai-pa_13506_v3

model_name: sao10k-l3-8b-lunaris-v1_v6

model_group: Sao10K/MN-BackyardAI-Par

status: torndown

timestamp: 2025-02-20T06:27:10+00:00

num_battles: 5567

num_wins: 2793

celo_rating: 1251.8

family_friendly_score: 0.5726

family_friendly_standard_error: 0.006996130930735931

submission_type: basic

model_repo: Sao10K/MN-BackyardAI-Party-12B-v1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6088605161194464, 'latency_mean': 1.6423240876197815, 'latency_p50': 1.6311051845550537, 'latency_p90': 1.8255927562713623}, {'batch_size': 3, 'throughput': 1.106095746840302, 'latency_mean': 2.7035609674453736, 'latency_p50': 2.668197512626648, 'latency_p90': 3.00636305809021}, {'batch_size': 5, 'throughput': 1.3373226724557254, 'latency_mean': 3.71900049328804, 'latency_p50': 3.750742793083191, 'latency_p90': 4.104906821250916}, {'batch_size': 6, 'throughput': 1.41294203815652, 'latency_mean': 4.216978030204773, 'latency_p50': 4.221577048301697, 'latency_p90': 4.787851428985595}, {'batch_size': 8, 'throughput': 1.4811506133983974, 'latency_mean': 5.372371668815613, 'latency_p50': 5.355698823928833, 'latency_p90': 6.069031548500061}, {'batch_size': 10, 'throughput': 1.507954791894249, 'latency_mean': 6.586740063428879, 'latency_p50': 6.593684673309326, 'latency_p90': 7.470977330207825}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sao10k-l3-8b-lunaris-v1_v6

is_internal_developer: False

language_model: Sao10K/MN-BackyardAI-Party-12B-v1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-02-19

win_ratio: 0.5017064846416383

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{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': False}

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 sao10k-mn-backyardai-pa-13506-v3-mkmlizer
Waiting for job on sao10k-mn-backyardai-pa-13506-v3-mkmlizer to finish
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║       /___/                                                         ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║                                                                     ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║                                                                     ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║                                                                     ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ║                                                                     ║
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: Downloaded to shared memory in 48.646s
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmploor75yc, device:0
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
sao10k-mn-backyardai-pa-13506-v3-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: quantized model in 38.748s
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: Processed model Sao10K/MN-BackyardAI-Party-12B-v1 in 87.395s
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-backyardai-pa-13506-v3
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-backyardai-pa-13506-v3/config.json
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-backyardai-pa-13506-v3/special_tokens_map.json
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-backyardai-pa-13506-v3/tokenizer_config.json
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-backyardai-pa-13506-v3/tokenizer.json
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-backyardai-pa-13506-v3/flywheel_model.0.safetensors
sao10k-mn-backyardai-pa-13506-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.63it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.67it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:06, 52.89it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.43it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 53.20it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 51.55it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:05, 51.55it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:18, 16.52it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:14, 19.61it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.56it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:08, 30.95it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 36.22it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:06, 41.06it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:05, 44.28it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:05, 45.87it/s]
Loading 0:  37%|███▋      | 133/363 [00:03<00:04, 47.21it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 52.97it/s]
Loading 0:  40%|████      | 147/363 [00:04<00:12, 17.08it/s]
Loading 0:  42%|████▏     | 152/363 [00:04<00:11, 18.86it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 23.53it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 29.15it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.68it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 38.27it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:03, 42.05it/s]
Loading 0:  56%|█████▋    | 205/363 [00:06<00:03, 44.38it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:03, 47.19it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:07, 18.05it/s]
Loading 0:  64%|██████▍   | 232/363 [00:07<00:05, 22.99it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:04, 28.66it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 33.76it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 38.42it/s]
Loading 0:  74%|███████▍  | 268/363 [00:08<00:02, 41.78it/s]
Loading 0:  76%|███████▋  | 277/363 [00:08<00:01, 44.77it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:01, 47.97it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 49.11it/s]
Loading 0:  84%|████████▎ | 304/363 [00:09<00:03, 18.78it/s]
Loading 0:  86%|████████▌ | 313/363 [00:09<00:02, 23.38it/s]
Loading 0:  89%|████████▊ | 322/363 [00:10<00:01, 28.38it/s]
Loading 0:  91%|█████████ | 331/363 [00:10<00:00, 33.68it/s]
Loading 0:  94%|█████████▎| 340/363 [00:10<00:00, 37.55it/s]
Loading 0:  95%|█████████▌| 346/363 [00:10<00:00, 39.60it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 43.45it/s]
Loading 0: 100%|██████████| 363/363 [00:17<00:00,  3.96it/s]
                                                            
Job sao10k-mn-backyardai-pa-13506-v3-mkmlizer completed after 114.5s with status: succeeded
Stopping job with name sao10k-mn-backyardai-pa-13506-v3-mkmlizer
Pipeline stage MKMLizer completed in 114.98s
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 sao10k-mn-backyardai-pa-13506-v3
Waiting for inference service sao10k-mn-backyardai-pa-13506-v3 to be ready
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-20250219-c-4epoc_80755_v1: HTTPConnectionPool(host='chaiml-20250219-c-4epoc-80755-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service sao10k-mn-backyardai-pa-13506-v3 ready after 190.66306066513062s
Pipeline stage MKMLDeployer completed in 191.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.231567621231079s
Received healthy response to inference request in 1.5209698677062988s
Received healthy response to inference request in 1.5861594676971436s
Received healthy response to inference request in 1.6674010753631592s
Received healthy response to inference request in 1.7817728519439697s
5 requests
0 failed requests
5th percentile: 1.5340077877044678
10th percentile: 1.5470457077026367
20th percentile: 1.5731215476989746
30th percentile: 1.6024077892303468
40th percentile: 1.634904432296753
50th percentile: 1.6674010753631592
60th percentile: 1.7131497859954834
70th percentile: 1.7588984966278076
80th percentile: 1.8717318058013916
90th percentile: 2.0516497135162353
95th percentile: 2.141608667373657
99th percentile: 2.2135758304595945
mean time: 1.7575741767883302
Pipeline stage StressChecker completed in 10.40s
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 0.73s
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 0.70s
Shutdown handler de-registered
sao10k-mn-backyardai-pa_13506_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-mn-backyardai-pa-13506-v3-profiler
Waiting for inference service sao10k-mn-backyardai-pa-13506-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 2640.79s
Shutdown handler de-registered
sao10k-mn-backyardai-pa_13506_v3 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-backyardai-pa_13506_v3 status is now torndown due to DeploymentManager action
sao10k-mn-backyardai-pa_13506_v3 status is now torndown due to DeploymentManager action
sao10k-mn-backyardai-pa_13506_v3 status is now torndown due to DeploymentManager action