developer_uid: zonemercy
submission_id: zonemercy-lihumai-v1-12b_6565_v1
model_name: zonemercy-lihumai-v1-12b_6565_v1
model_group: zonemercy/LihumAI-v1-12b
status: inactive
timestamp: 2024-11-28T17:54:37+00:00
num_battles: 13220
num_wins: 6151
celo_rating: 1237.74
family_friendly_score: 0.5840000000000001
family_friendly_standard_error: 0.006970566691453429
submission_type: basic
model_repo: zonemercy/LihumAI-v1-12b0-sft1e5
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6129514211545295, 'latency_mean': 1.6313523399829863, 'latency_p50': 1.6351757049560547, 'latency_p90': 1.800416111946106}, {'batch_size': 3, 'throughput': 1.1352398650497382, 'latency_mean': 2.6405199790000915, 'latency_p50': 2.653167247772217, 'latency_p90': 2.9537573575973513}, {'batch_size': 5, 'throughput': 1.3761240497004363, 'latency_mean': 3.617656590938568, 'latency_p50': 3.60433566570282, 'latency_p90': 4.107019758224487}, {'batch_size': 6, 'throughput': 1.4452997551521272, 'latency_mean': 4.126822996139526, 'latency_p50': 4.125332951545715, 'latency_p90': 4.571816420555114}, {'batch_size': 8, 'throughput': 1.491371049934796, 'latency_mean': 5.328996640443802, 'latency_p50': 5.328116416931152, 'latency_p90': 5.978062605857849}, {'batch_size': 10, 'throughput': 1.5402634867473854, 'latency_mean': 6.442514199018478, 'latency_p50': 6.468080759048462, 'latency_p90': 7.237766742706299}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: zonemercy-lihumai-v1-12b_6565_v1
is_internal_developer: True
language_model: zonemercy/LihumAI-v1-12b0-sft1e5
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2024-11-28
win_ratio: 0.46527987897125567
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': "{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}
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 zonemercy-lihumai-v1-12b-6565-v1-mkmlizer
Waiting for job on zonemercy-lihumai-v1-12b-6565-v1-mkmlizer to finish
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ _____ __ __ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ /___/ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ Version: 0.11.12 ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ https://mk1.ai ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ belonging to: ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ Chai Research Corp. ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ║ ║
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: Downloaded to shared memory in 56.161s
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5c1p84kd, device:0
zonemercy-lihumai-v1-12b-6565-v1-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
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-lihumai-v1-12b-6565-v1
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-lihumai-v1-12b-6565-v1/special_tokens_map.json
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-lihumai-v1-12b-6565-v1/config.json
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-lihumai-v1-12b-6565-v1/tokenizer_config.json
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-lihumai-v1-12b-6565-v1/tokenizer.json
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-lihumai-v1-12b-6565-v1/flywheel_model.0.safetensors
zonemercy-lihumai-v1-12b-6565-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 25.23it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 42.61it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 41.02it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 41.21it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:07, 42.60it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 34.11it/s] Loading 0: 11%|█ | 39/363 [00:00<00:07, 42.61it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:07, 41.51it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 41.66it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 42.06it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 42.70it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:11, 24.96it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:09, 32.31it/s] Loading 0: 21%|██ | 76/363 [00:02<00:08, 33.49it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 35.48it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:07, 37.34it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 32.10it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.54it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 38.20it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:06, 40.00it/s] Loading 0: 31%|███ | 113/363 [00:03<00:07, 34.15it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:07, 33.99it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:05, 40.66it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 40.05it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 40.73it/s] Loading 0: 39%|███▊ | 140/363 [00:03<00:05, 42.41it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 26.95it/s] Loading 0: 41%|████ | 149/363 [00:04<00:07, 26.89it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 34.15it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 35.50it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:05, 37.32it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 39.17it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 33.28it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 39.95it/s] Loading 0: 52%|█████▏ | 188/363 [00:05<00:04, 39.44it/s] Loading 0: 53%|█████▎ | 193/363 [00:05<00:04, 40.22it/s] Loading 0: 55%|█████▍ | 198/363 [00:05<00:04, 41.24it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 32.98it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 39.84it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 39.69it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 40.78it/s] Loading 0: 62%|██████▏ | 225/363 [00:06<00:05, 25.87it/s] Loading 0: 63%|██████▎ | 230/363 [00:06<00:04, 27.60it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.15it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 35.26it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 36.48it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 38.21it/s] Loading 0: 71%|███████ | 257/363 [00:07<00:03, 32.41it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 39.44it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 39.47it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 39.70it/s] Loading 0: 77%|███████▋ | 279/363 [00:07<00:02, 40.89it/s] Loading 0: 78%|███████▊ | 284/363 [00:07<00:02, 34.11it/s] Loading 0: 80%|███████▉ | 289/363 [00:07<00:01, 37.52it/s] Loading 0: 81%|████████ | 294/363 [00:08<00:01, 35.94it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 37.86it/s] Loading 0: 84%|████████▎ | 304/363 [00:15<00:25, 2.35it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:19, 2.88it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:12, 4.12it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:06, 6.53it/s] Loading 0: 89%|████████▉ | 324/363 [00:15<00:04, 8.60it/s] Loading 0: 91%|█████████ | 329/363 [00:15<00:03, 11.16it/s] Loading 0: 92%|█████████▏| 334/363 [00:15<00:02, 14.34it/s] Loading 0: 93%|█████████▎| 339/363 [00:15<00:01, 16.30it/s] Loading 0: 95%|█████████▌| 346/363 [00:16<00:00, 22.40it/s] Loading 0: 97%|█████████▋| 351/363 [00:16<00:00, 25.47it/s] Loading 0: 98%|█████████▊| 356/363 [00:16<00:00, 28.63it/s] Loading 0: 99%|█████████▉| 361/363 [00:16<00:00, 32.01it/s]
Job zonemercy-lihumai-v1-12b-6565-v1-mkmlizer completed after 125.13s with status: succeeded
Stopping job with name zonemercy-lihumai-v1-12b-6565-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.61s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-lihumai-v1-12b-6565-v1
Waiting for inference service zonemercy-lihumai-v1-12b-6565-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
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 zonemercy-lihumai-v1-12b-6565-v1 ready after 140.5066578388214s
Pipeline stage MKMLDeployer completed in 141.02s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.4887104034423828s
Received healthy response to inference request in 1.344712495803833s
Received healthy response to inference request in 1.499305248260498s
Received healthy response to inference request in 0.9710788726806641s
5 requests
1 failed requests
5th percentile: 1.0458055973052978
10th percentile: 1.1205323219299317
20th percentile: 1.2699857711791993
30th percentile: 1.373512077331543
40th percentile: 1.4311112403869628
50th percentile: 1.4887104034423828
60th percentile: 1.492948341369629
70th percentile: 1.497186279296875
80th percentile: 5.225359869003299
90th percentile: 12.677469110488893
95th percentile: 16.403523731231687
99th percentile: 19.38436742782593
mean time: 5.086677074432373
%s, retrying in %s seconds...
Received healthy response to inference request in 1.1123013496398926s
Received healthy response to inference request in 2.1398887634277344s
Received healthy response to inference request in 1.8640005588531494s
Received healthy response to inference request in 1.5053606033325195s
Received healthy response to inference request in 1.0710220336914062s
5 requests
0 failed requests
5th percentile: 1.0792778968811034
10th percentile: 1.0875337600708008
20th percentile: 1.1040454864501954
30th percentile: 1.190913200378418
40th percentile: 1.3481369018554688
50th percentile: 1.5053606033325195
60th percentile: 1.6488165855407715
70th percentile: 1.7922725677490234
80th percentile: 1.9191781997680664
90th percentile: 2.0295334815979005
95th percentile: 2.084711122512817
99th percentile: 2.128853235244751
mean time: 1.5385146617889405
Pipeline stage StressChecker completed in 35.99s
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 2.12s
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 2.34s
Shutdown handler de-registered
zonemercy-lihumai-v1-12b_6565_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 3030.68s
Shutdown handler de-registered
zonemercy-lihumai-v1-12b_6565_v1 status is now inactive due to auto deactivation removed underperforming models