rica40325-linear-merge-1106

developer_uid: azuruce

submission_id: rica40325-linear-merge-1106_v4

model_name: rica40325-linear-merge-1106_v4

model_group: rica40325/linear_merge_1

status: torndown

timestamp: 2024-11-13T19:16:24+00:00

num_battles: 11757

num_wins: 6398

celo_rating: 1278.44

family_friendly_score: 0.5671999999999999

family_friendly_standard_error: 0.007006913157732155

submission_type: basic

model_repo: rica40325/linear_merge_1106

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6280582810096431, 'latency_mean': 1.5921507000923156, 'latency_p50': 1.6098482608795166, 'latency_p90': 1.745671796798706}, {'batch_size': 3, 'throughput': 1.2454137248318708, 'latency_mean': 2.4002370154857635, 'latency_p50': 2.4208120107650757, 'latency_p90': 2.6136669874191285}, {'batch_size': 5, 'throughput': 1.562676802490534, 'latency_mean': 3.1800005340576174, 'latency_p50': 3.1733133792877197, 'latency_p90': 3.5851998567581176}, {'batch_size': 6, 'throughput': 1.6744486456525698, 'latency_mean': 3.557980926036835, 'latency_p50': 3.55689013004303, 'latency_p90': 4.062950277328492}, {'batch_size': 8, 'throughput': 1.838690664116347, 'latency_mean': 4.326847249269486, 'latency_p50': 4.292397856712341, 'latency_p90': 4.91574501991272}, {'batch_size': 10, 'throughput': 1.8989481090252878, 'latency_mean': 5.227130434513092, 'latency_p50': 5.242952346801758, 'latency_p90': 5.857126235961914}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-linear-merge-1106_v4

is_internal_developer: True

language_model: rica40325/linear_merge_1106

model_size: 13B

ranking_group: single

throughput_3p7s: 1.72

us_pacific_date: 2024-11-13

win_ratio: 0.5441864421195883

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 rica40325-linear-merge-1106-v4-mkmlizer
Waiting for job on rica40325-linear-merge-1106-v4-mkmlizer to finish
rica40325-linear-merge-1106-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-linear-merge-1106-v4-mkmlizer: ║     _____            __           __                                ║
rica40325-linear-merge-1106-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-linear-merge-1106-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-linear-merge-1106-v4-mkmlizer: ║       /___/                                                         ║
rica40325-linear-merge-1106-v4-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-linear-merge-1106-v4-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  belonging to:                                                      ║
rica40325-linear-merge-1106-v4-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-linear-merge-1106-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rica40325-linear-merge-1106-v4-mkmlizer: ║                                                                     ║
rica40325-linear-merge-1106-v4-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
rica40325-linear-merge-1106-v4-mkmlizer: Downloaded to shared memory in 34.140s
rica40325-linear-merge-1106-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0k624t50, device:0
rica40325-linear-merge-1106-v4-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
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
rica40325-linear-merge-1106-v4-mkmlizer: quantized model in 35.595s
rica40325-linear-merge-1106-v4-mkmlizer: Processed model rica40325/linear_merge_1106 in 69.736s
rica40325-linear-merge-1106-v4-mkmlizer: creating bucket guanaco-mkml-models
rica40325-linear-merge-1106-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-linear-merge-1106-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-linear-merge-1106-v4
rica40325-linear-merge-1106-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v4/config.json
rica40325-linear-merge-1106-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v4/special_tokens_map.json
rica40325-linear-merge-1106-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v4/tokenizer_config.json
rica40325-linear-merge-1106-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v4/tokenizer.json
rica40325-linear-merge-1106-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-linear-merge-1106-v4/flywheel_model.0.safetensors
rica40325-linear-merge-1106-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:17,  3.04s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:52,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.36it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.91it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  8.05it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.69it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.23it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:18, 17.83it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 20.22it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 25.76it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 29.83it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 32.45it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:07, 38.93it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 40.48it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 40.51it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 45.84it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:05, 45.34it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:05, 44.42it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 49.44it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 47.49it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 45.87it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 36.12it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:06, 37.14it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 39.12it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 40.59it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 33.75it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 40.24it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:05, 39.82it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:05, 40.03it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:04, 40.30it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 41.62it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:04, 46.38it/s]
Loading 0:  50%|████▉     | 181/363 [00:10<00:03, 46.52it/s]
Loading 0:  51%|█████     | 186/363 [00:10<00:04, 39.52it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 48.21it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 47.07it/s]
Loading 0:  56%|█████▋    | 205/363 [00:10<00:04, 34.21it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 40.39it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 41.34it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 41.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:02, 47.58it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 45.56it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 43.51it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:02, 47.83it/s]
Loading 0:  70%|██████▉   | 254/363 [00:11<00:02, 46.87it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 46.07it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:01, 49.87it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:01, 47.96it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:01, 46.95it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 37.41it/s]
Loading 0:  79%|███████▉  | 288/363 [00:12<00:02, 37.20it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:01, 38.24it/s]
Loading 0:  82%|████████▏ | 298/363 [00:13<00:01, 40.27it/s]
Loading 0:  83%|████████▎ | 303/363 [00:13<00:01, 36.71it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 45.55it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 45.35it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 45.47it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 50.21it/s]
Loading 0:  92%|█████████▏| 335/363 [00:13<00:00, 48.37it/s]
Loading 0:  94%|█████████▎| 340/363 [00:13<00:00, 47.01it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 50.25it/s]
Loading 0:  97%|█████████▋| 352/363 [00:14<00:00, 49.24it/s]
Loading 0:  98%|█████████▊| 357/363 [00:14<00:00, 40.26it/s]
                                                            
Job rica40325-linear-merge-1106-v4-mkmlizer completed after 93.86s with status: succeeded
Stopping job with name rica40325-linear-merge-1106-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-linear-merge-1106-v4
Waiting for inference service rica40325-linear-merge-1106-v4 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
Inference service rica40325-linear-merge-1106-v4 ready after 200.88624024391174s
Pipeline stage MKMLDeployer completed in 201.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9520044326782227s
Received healthy response to inference request in 1.4416170120239258s
Received healthy response to inference request in 1.7571091651916504s
Received healthy response to inference request in 1.790266990661621s
Received healthy response to inference request in 1.3955202102661133s
5 requests
0 failed requests
5th percentile: 1.4047395706176757
10th percentile: 1.4139589309692382
20th percentile: 1.4323976516723633
30th percentile: 1.5047154426574707
40th percentile: 1.6309123039245605
50th percentile: 1.7571091651916504
60th percentile: 1.7703722953796386
70th percentile: 1.783635425567627
80th percentile: 1.8226144790649415
90th percentile: 1.887309455871582
95th percentile: 1.9196569442749023
99th percentile: 1.9455349349975586
mean time: 1.6673035621643066
Pipeline stage StressChecker completed in 9.82s
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 2.52s
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 3.13s
Shutdown handler de-registered
rica40325-linear-merge-1106_v4 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-linear-merge-1106-v4-profiler
Waiting for inference service rica40325-linear-merge-1106-v4-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 2442.02s
Shutdown handler de-registered
rica40325-linear-merge-1106_v4 status is now inactive due to auto deactivation removed underperforming models
rica40325-linear-merge-1106_v4 status is now torndown due to DeploymentManager action