submission_id: rica40325-linear-merge-1106_v3
developer_uid: Riverise
best_of: 8
celo_rating: 1299.66
display_name: rica40325-linear-merge-1106_v1
family_friendly_score: 0.5628
family_friendly_standard_error: 0.007015071774401171
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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: rica40325/linear_merge_1106
latencies: [{'batch_size': 1, 'throughput': 0.612820775822151, 'latency_mean': 1.63173188328743, 'latency_p50': 1.6218996047973633, 'latency_p90': 1.8096311330795287}, {'batch_size': 3, 'throughput': 1.1123113529282709, 'latency_mean': 2.693516627550125, 'latency_p50': 2.6795666217803955, 'latency_p90': 2.968614435195923}, {'batch_size': 5, 'throughput': 1.3608970702545091, 'latency_mean': 3.6552741396427155, 'latency_p50': 3.6693313121795654, 'latency_p90': 3.9919979333877564}, {'batch_size': 6, 'throughput': 1.4171473879788512, 'latency_mean': 4.211583940982819, 'latency_p50': 4.2054831981658936, 'latency_p90': 4.676572060585022}, {'batch_size': 8, 'throughput': 1.4816848631127952, 'latency_mean': 5.371929988861084, 'latency_p50': 5.374629497528076, 'latency_p90': 6.0308187246322635}, {'batch_size': 10, 'throughput': 1.5305879274084617, 'latency_mean': 6.491317527294159, 'latency_p50': 6.481206774711609, 'latency_p90': 7.346806812286377}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rica40325/linear_merge_1
model_name: rica40325-linear-merge-1106_v1
model_num_parameters: 12772070400.0
model_repo: rica40325/linear_merge_1106
model_size: 13B
num_battles: 14986
num_wins: 8706
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.37
timestamp: 2024-11-12T02:41:49+00:00
us_pacific_date: 2024-11-11
win_ratio: 0.5809422127318831
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-v3-mkmlizer
Waiting for job on rica40325-linear-merge-1106-v3-mkmlizer to finish
rica40325-linear-merge-1106-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-linear-merge-1106-v3-mkmlizer: ║ _____ __ __ ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ /___/ ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ Version: 0.11.33 ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ https://mk1.ai ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ belonging to: ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ Chai Research Corp. ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rica40325-linear-merge-1106-v3-mkmlizer: ║ ║
rica40325-linear-merge-1106-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-linear-merge-1106-v3-mkmlizer: Downloaded to shared memory in 103.781s
rica40325-linear-merge-1106-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy8kd4elw, device:0
rica40325-linear-merge-1106-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-linear-merge-1106-v3-mkmlizer: quantized model in 36.824s
rica40325-linear-merge-1106-v3-mkmlizer: Processed model rica40325/linear_merge_1106 in 140.605s
rica40325-linear-merge-1106-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-linear-merge-1106-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-linear-merge-1106-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-linear-merge-1106-v3
rica40325-linear-merge-1106-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v3/config.json
rica40325-linear-merge-1106-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v3/special_tokens_map.json
rica40325-linear-merge-1106-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v3/tokenizer_config.json
rica40325-linear-merge-1106-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-linear-merge-1106-v3/tokenizer.json
rica40325-linear-merge-1106-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-linear-merge-1106-v3/flywheel_model.0.safetensors
rica40325-linear-merge-1106-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:40, 3.11s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:59, 1.19it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:46, 3.28it/s] Loading 0: 5%|▍ | 17/363 [00:06<01:12, 4.80it/s] Loading 0: 6%|▋ | 23/363 [00:06<00:43, 7.86it/s] Loading 0: 8%|▊ | 28/363 [00:06<00:30, 10.90it/s] Loading 0: 9%|▉ | 33/363 [00:06<00:23, 13.77it/s] Loading 0: 11%|█ | 40/363 [00:07<00:19, 16.55it/s] Loading 0: 12%|█▏ | 44/363 [00:07<00:16, 18.98it/s] Loading 0: 14%|█▍ | 50/363 [00:07<00:12, 24.42it/s] Loading 0: 15%|█▌ | 56/363 [00:07<00:10, 28.32it/s] Loading 0: 17%|█▋ | 61/363 [00:07<00:09, 30.28it/s] Loading 0: 18%|█▊ | 67/363 [00:07<00:08, 35.96it/s] Loading 0: 20%|█▉ | 72/363 [00:08<00:07, 36.85it/s] Loading 0: 21%|██ | 77/363 [00:08<00:07, 38.29it/s] Loading 0: 23%|██▎ | 82/363 [00:08<00:06, 40.42it/s] Loading 0: 24%|██▍ | 87/363 [00:08<00:08, 33.92it/s] Loading 0: 26%|██▌ | 94/363 [00:08<00:06, 41.67it/s] Loading 0: 27%|██▋ | 99/363 [00:08<00:06, 42.51it/s] Loading 0: 29%|██▊ | 104/363 [00:08<00:06, 42.70it/s] Loading 0: 30%|███ | 109/363 [00:08<00:05, 44.00it/s] Loading 0: 31%|███▏ | 114/363 [00:09<00:06, 38.16it/s] Loading 0: 33%|███▎ | 121/363 [00:09<00:07, 32.07it/s] Loading 0: 34%|███▍ | 125/363 [00:09<00:07, 32.89it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 35.83it/s] Loading 0: 37%|███▋ | 134/363 [00:09<00:06, 35.61it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 39.85it/s] Loading 0: 40%|███▉ | 145/363 [00:09<00:05, 41.40it/s] Loading 0: 41%|████▏ | 150/363 [00:10<00:06, 35.33it/s] Loading 0: 44%|████▎ | 158/363 [00:10<00:04, 44.37it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:04, 43.51it/s] Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 42.03it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:04, 46.49it/s] Loading 0: 50%|█████ | 182/363 [00:10<00:03, 45.34it/s] Loading 0: 52%|█████▏ | 187/363 [00:10<00:04, 42.37it/s] Loading 0: 53%|█████▎ | 193/363 [00:10<00:03, 46.14it/s] Loading 0: 55%|█████▍ | 198/363 [00:11<00:03, 44.56it/s] Loading 0: 56%|█████▌ | 203/363 [00:11<00:05, 29.61it/s] Loading 0: 57%|█████▋ | 207/363 [00:11<00:04, 31.54it/s] Loading 0: 58%|█████▊ | 212/363 [00:11<00:04, 34.99it/s] Loading 0: 60%|█████▉ | 217/363 [00:11<00:03, 38.20it/s] Loading 0: 61%|██████ | 222/363 [00:11<00:04, 34.78it/s] Loading 0: 63%|██████▎ | 230/363 [00:12<00:03, 43.40it/s] Loading 0: 65%|██████▍ | 235/363 [00:12<00:02, 43.33it/s] Loading 0: 66%|██████▌ | 240/363 [00:12<00:03, 35.93it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 41.61it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 41.55it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 42.43it/s] Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 42.40it/s] Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 40.10it/s] Loading 0: 75%|███████▌ | 274/363 [00:13<00:02, 44.11it/s] Loading 0: 77%|███████▋ | 279/363 [00:13<00:01, 43.68it/s] Loading 0: 78%|███████▊ | 284/363 [00:13<00:02, 29.30it/s] Loading 0: 79%|███████▉ | 288/363 [00:13<00:02, 30.86it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:02, 33.26it/s] Loading 0: 82%|████████▏ | 298/363 [00:13<00:01, 36.95it/s] Loading 0: 83%|████████▎ | 303/363 [00:14<00:01, 32.32it/s] Loading 0: 86%|████████▌ | 311/363 [00:14<00:01, 40.91it/s] Loading 0: 87%|████████▋ | 316/363 [00:14<00:01, 41.11it/s] Loading 0: 88%|████████▊ | 321/363 [00:14<00:01, 34.46it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 42.78it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:00, 42.49it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 41.33it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 46.25it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 42.85it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 42.29it/s]
Job rica40325-linear-merge-1106-v3-mkmlizer completed after 165.87s with status: succeeded
Stopping job with name rica40325-linear-merge-1106-v3-mkmlizer
Pipeline stage MKMLizer completed in 166.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-linear-merge-1106-v3
Waiting for inference service rica40325-linear-merge-1106-v3 to be ready
Inference service rica40325-linear-merge-1106-v3 ready after 180.6362133026123s
Pipeline stage MKMLDeployer completed in 181.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0438761711120605s
Received healthy response to inference request in 1.432391881942749s
Received healthy response to inference request in 1.682713508605957s
Received healthy response to inference request in 1.684499740600586s
Received healthy response to inference request in 1.5922081470489502s
5 requests
0 failed requests
5th percentile: 1.4643551349639892
10th percentile: 1.4963183879852295
20th percentile: 1.56024489402771
30th percentile: 1.6103092193603517
40th percentile: 1.6465113639831543
50th percentile: 1.682713508605957
60th percentile: 1.6834280014038085
70th percentile: 1.68414249420166
80th percentile: 1.756375026702881
90th percentile: 1.9001255989074708
95th percentile: 1.9720008850097654
99th percentile: 2.0295011138916017
mean time: 1.6871378898620606
Pipeline stage StressChecker completed in 9.84s
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 2.81s
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 2.76s
Shutdown handler de-registered
rica40325-linear-merge-1106_v3 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 2804.39s
Shutdown handler de-registered
rica40325-linear-merge-1106_v3 status is now inactive due to auto deactivation removed underperforming models
rica40325-linear-merge-1106_v3 status is now torndown due to DeploymentManager action