developer_uid: zonemercy
submission_id: chaiml-wisemen1-12b0-l1e5r7_v3
model_name: tempv1-4
model_group: ChaiML/WiseMen1-12b0-l1e
status: torndown
timestamp: 2024-12-27T23:02:26+00:00
num_battles: 13424
num_wins: 6580
celo_rating: 1262.95
family_friendly_score: 0.6138
family_friendly_standard_error: 0.006885485603790048
submission_type: basic
model_repo: ChaiML/WiseMen1-12b0-l1e5r7
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6358216603545375, 'latency_mean': 1.5727111983299256, 'latency_p50': 1.5878572463989258, 'latency_p90': 1.7421737909317017}, {'batch_size': 3, 'throughput': 1.2544529665660864, 'latency_mean': 2.389659022092819, 'latency_p50': 2.401383876800537, 'latency_p90': 2.633335828781128}, {'batch_size': 5, 'throughput': 1.59138131497022, 'latency_mean': 3.1341069638729095, 'latency_p50': 3.129905581474304, 'latency_p90': 3.5025778293609617}, {'batch_size': 6, 'throughput': 1.6761486719155982, 'latency_mean': 3.551488984823227, 'latency_p50': 3.5337486267089844, 'latency_p90': 4.056862545013428}, {'batch_size': 8, 'throughput': 1.8525242916118145, 'latency_mean': 4.292846742868424, 'latency_p50': 4.291472792625427, 'latency_p90': 4.897651290893554}, {'batch_size': 10, 'throughput': 1.9304175861642998, 'latency_mean': 5.145072473287582, 'latency_p50': 5.174155592918396, 'latency_p90': 5.7510493993759155}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-4
is_internal_developer: True
language_model: ChaiML/WiseMen1-12b0-l1e5r7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-27
win_ratio: 0.4901668653158522
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': 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 chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer
Waiting for job on chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer to finish
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ _____ __ __ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ /___/ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ Version: 0.11.12 ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ belonging to: ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ║ ║
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: Downloaded to shared memory in 33.151s
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbpdowfo1, device:0
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: quantized model in 38.597s
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: Processed model ChaiML/WiseMen1-12b0-l1e5r7 in 71.748s
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-wisemen1-12b0-l1e5r7-v3
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-wisemen1-12b0-l1e5r7-v3/config.json
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-wisemen1-12b0-l1e5r7-v3/special_tokens_map.json
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-wisemen1-12b0-l1e5r7-v3/tokenizer_config.json
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-wisemen1-12b0-l1e5r7-v3/tokenizer.json
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-wisemen1-12b0-l1e5r7-v3/flywheel_model.0.safetensors
chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.62it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 40.94it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:08, 39.68it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:08, 39.79it/s] Loading 0: 7%|▋ | 27/363 [00:00<00:08, 40.89it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:10, 32.55it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 40.38it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:08, 39.27it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 39.32it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:07, 39.69it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:07, 40.83it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:12, 23.78it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:10, 28.02it/s] Loading 0: 20%|██ | 73/363 [00:02<00:10, 27.67it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:08, 34.84it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:07, 35.00it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 35.50it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 34.02it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:07, 35.71it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 33.88it/s] Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 33.52it/s] Loading 0: 30%|███ | 110/363 [00:03<00:07, 34.25it/s] Loading 0: 31%|███▏ | 114/363 [00:03<00:07, 32.41it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:08, 30.10it/s] Loading 0: 34%|███▍ | 125/363 [00:03<00:06, 37.58it/s] Loading 0: 36%|███▌ | 129/363 [00:03<00:06, 35.61it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:06, 38.07it/s] Loading 0: 38%|███▊ | 138/363 [00:03<00:06, 36.08it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:08, 24.77it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:09, 23.57it/s] Loading 0: 41%|████ | 149/363 [00:04<00:08, 24.32it/s] Loading 0: 43%|████▎ | 156/363 [00:04<00:06, 32.89it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.68it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 36.29it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:05, 34.80it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:04, 37.90it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 35.72it/s] Loading 0: 50%|█████ | 183/363 [00:05<00:04, 37.74it/s] Loading 0: 52%|█████▏ | 187/363 [00:05<00:04, 35.61it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:04, 38.49it/s] Loading 0: 54%|█████▍ | 196/363 [00:05<00:04, 36.40it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 38.33it/s] Loading 0: 56%|█████▋ | 205/363 [00:05<00:04, 36.38it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:03, 39.20it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 36.52it/s] Loading 0: 60%|██████ | 218/363 [00:06<00:04, 36.19it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:05, 27.98it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 29.00it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 27.71it/s] Loading 0: 65%|██████▍ | 235/363 [00:06<00:04, 29.95it/s] Loading 0: 66%|██████▌ | 239/363 [00:07<00:04, 28.34it/s] Loading 0: 68%|██████▊ | 246/363 [00:07<00:03, 36.42it/s] Loading 0: 69%|██████▉ | 250/363 [00:07<00:03, 35.60it/s] Loading 0: 70%|███████ | 255/363 [00:07<00:02, 38.36it/s] Loading 0: 71%|███████▏ | 259/363 [00:07<00:02, 36.71it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 39.73it/s] Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 40.09it/s] Loading 0: 75%|███████▌ | 274/363 [00:07<00:02, 40.75it/s] Loading 0: 77%|███████▋ | 279/363 [00:08<00:02, 41.58it/s] Loading 0: 78%|███████▊ | 284/363 [00:08<00:02, 34.36it/s] Loading 0: 80%|████████ | 291/363 [00:08<00:01, 41.36it/s] Loading 0: 82%|████████▏ | 296/363 [00:08<00:01, 40.76it/s] Loading 0: 83%|████████▎ | 301/363 [00:08<00:01, 42.33it/s] Loading 0: 84%|████████▍ | 306/363 [00:15<00:24, 2.37it/s] Loading 0: 85%|████████▌ | 310/363 [00:15<00:17, 3.07it/s] Loading 0: 87%|████████▋ | 314/363 [00:15<00:12, 4.03it/s] Loading 0: 88%|████████▊ | 319/363 [00:15<00:07, 5.70it/s] Loading 0: 89%|████████▉ | 323/363 [00:16<00:05, 7.35it/s] Loading 0: 90%|█████████ | 328/363 [00:16<00:03, 10.12it/s] Loading 0: 92%|█████████▏| 333/363 [00:16<00:02, 13.28it/s] Loading 0: 93%|█████████▎| 338/363 [00:16<00:01, 16.75it/s] Loading 0: 94%|█████████▍| 343/363 [00:16<00:00, 20.57it/s] Loading 0: 96%|█████████▌| 348/363 [00:16<00:00, 21.29it/s] Loading 0: 98%|█████████▊| 355/363 [00:16<00:00, 28.15it/s] Loading 0: 99%|█████████▉| 360/363 [00:17<00:00, 30.36it/s]
Job chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer completed after 104.22s with status: succeeded
Stopping job with name chaiml-wisemen1-12b0-l1e5r7-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-wisemen1-12b0-l1e5r7-v3
Waiting for inference service chaiml-wisemen1-12b0-l1e5r7-v3 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
Inference service chaiml-wisemen1-12b0-l1e5r7-v3 ready after 301.35896730422974s
Pipeline stage MKMLDeployer completed in 301.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8991756439208984s
Received healthy response to inference request in 2.017594814300537s
Received healthy response to inference request in 1.1744325160980225s
Received healthy response to inference request in 1.506218433380127s
Received healthy response to inference request in 1.791144609451294s
5 requests
0 failed requests
5th percentile: 1.2407896995544434
10th percentile: 1.3071468830108643
20th percentile: 1.439861249923706
30th percentile: 1.5632036685943604
40th percentile: 1.6771741390228272
50th percentile: 1.791144609451294
60th percentile: 1.8343570232391357
70th percentile: 1.8775694370269775
80th percentile: 1.9228594779968262
90th percentile: 1.9702271461486816
95th percentile: 1.9939109802246093
99th percentile: 2.0128580474853517
mean time: 1.6777132034301758
Pipeline stage StressChecker completed in 9.80s
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 0.64s
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 0.71s
Shutdown handler de-registered
chaiml-wisemen1-12b0-l1e5r7_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-wisemen1-12b0-l1e5r7-v3-profiler
Waiting for inference service chaiml-wisemen1-12b0-l1e5r7-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 2333.68s
Shutdown handler de-registered
chaiml-wisemen1-12b0-l1e5r7_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-wisemen1-12b0-l1e5r7_v3 status is now torndown due to DeploymentManager action
chaiml-wisemen1-12b0-l1e5r7_v3 status is now torndown due to DeploymentManager action
chaiml-wisemen1-12b0-l1e5r7_v3 status is now torndown due to DeploymentManager action