submission_id: sicarius-prototyping-com_3807_v1
developer_uid: SicariusSicariiStuff
alignment_samples: 12909
alignment_score: 1.5789905271269096
best_of: 1
celo_rating: 1127.03
display_name: sicarius-prototyping-com_3807_v1
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': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Sicarius-Prototyping/Compliance_PreAlpha_Roleplay
latencies: [{'batch_size': 1, 'throughput': 1.0600557960643642, 'latency_mean': 0.9432490825653076, 'latency_p50': 0.9543071985244751, 'latency_p90': 1.0451612710952758}, {'batch_size': 5, 'throughput': 3.4647000491846014, 'latency_mean': 1.4328999626636505, 'latency_p50': 1.4293837547302246, 'latency_p90': 1.5909615516662596}, {'batch_size': 10, 'throughput': 5.164517580457035, 'latency_mean': 1.909692384004593, 'latency_p50': 1.8923085927963257, 'latency_p90': 2.146044921875}, {'batch_size': 15, 'throughput': 6.035818359441584, 'latency_mean': 2.4339771389961244, 'latency_p50': 2.4228581190109253, 'latency_p90': 2.7583127498626707}, {'batch_size': 20, 'throughput': 6.514230434092756, 'latency_mean': 3.0150824892520904, 'latency_p50': 2.996903657913208, 'latency_p90': 3.479066252708435}, {'batch_size': 25, 'throughput': 6.848745175160536, 'latency_mean': 3.568587814569473, 'latency_p50': 3.6046082973480225, 'latency_p90': 4.166011786460876}, {'batch_size': 30, 'throughput': 7.113041732535403, 'latency_mean': 4.113607475757599, 'latency_p50': 4.094318270683289, 'latency_p90': 4.882534527778625}, {'batch_size': 35, 'throughput': 7.2430210136429265, 'latency_mean': 4.687251479625702, 'latency_p50': 4.584257006645203, 'latency_p90': 5.571896362304686}, {'batch_size': 40, 'throughput': 7.194059893583142, 'latency_mean': 5.377878868579865, 'latency_p50': 5.327866435050964, 'latency_p90': 6.408310818672179}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sicarius-Prototyping/Com
model_name: sicarius-prototyping-com_3807_v1
model_num_parameters: 8030277632.0
model_repo: Sicarius-Prototyping/Compliance_PreAlpha_Roleplay
model_size: 8B
num_battles: 12909
num_wins: 4544
propriety_score: 0.7781851512373968
propriety_total_count: 1091.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 7.08
timestamp: 2024-09-05T22:12:14+00:00
us_pacific_date: 2024-09-05
win_ratio: 0.3520024788906964
Download Preference Data
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 sicarius-prototyping-com-3807-v1-mkmlizer
Waiting for job on sicarius-prototyping-com-3807-v1-mkmlizer to finish
sicarius-prototyping-com-3807-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sicarius-prototyping-com-3807-v1-mkmlizer: ║     _____            __           __                                ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║       /___/                                                         ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  belonging to:                                                      ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sicarius-prototyping-com-3807-v1-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sicarius-prototyping-com-3807-v1-mkmlizer: Downloaded to shared memory in 36.433s
sicarius-prototyping-com-3807-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq_ismaet, device:0
sicarius-prototyping-com-3807-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
sicarius-prototyping-com-3807-v1-mkmlizer: quantized model in 26.289s
sicarius-prototyping-com-3807-v1-mkmlizer: Processed model Sicarius-Prototyping/Compliance_PreAlpha_Roleplay in 62.722s
sicarius-prototyping-com-3807-v1-mkmlizer: creating bucket guanaco-mkml-models
sicarius-prototyping-com-3807-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sicarius-prototyping-com-3807-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v1
sicarius-prototyping-com-3807-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v1/config.json
sicarius-prototyping-com-3807-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v1/special_tokens_map.json
sicarius-prototyping-com-3807-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v1/tokenizer_config.json
sicarius-prototyping-com-3807-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v1/tokenizer.json
sicarius-prototyping-com-3807-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v1/flywheel_model.0.safetensors
sicarius-prototyping-com-3807-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 30.96it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:06, 42.99it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:05, 52.61it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:05, 46.49it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:05, 45.55it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 50.42it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:05, 47.69it/s]
Loading 0:  18%|█▊        | 51/291 [00:01<00:05, 47.11it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 46.66it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 54.41it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 50.00it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 51.05it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 36.94it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:05, 37.37it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:05, 38.05it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:04, 42.17it/s]
Loading 0:  37%|███▋      | 107/291 [00:02<00:04, 43.26it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:04, 39.39it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.72it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 44.98it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 44.64it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 50.42it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 46.53it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 44.21it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 49.40it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 43.06it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 41.63it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 42.61it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 46.84it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 46.92it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 29.64it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:02, 32.53it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 39.78it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 41.63it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:02, 38.63it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 47.67it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 45.27it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 44.06it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 47.32it/s]
Loading 0:  83%|████████▎ | 242/291 [00:05<00:01, 46.08it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 45.33it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 43.34it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 42.44it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 48.02it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 46.95it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 46.73it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 42.91it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.23it/s]
                                                            

Job sicarius-prototyping-com-3807-v1-mkmlizer completed after 84.75s with status: succeeded
Stopping job with name sicarius-prototyping-com-3807-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sicarius-prototyping-com-3807-v1
Waiting for inference service sicarius-prototyping-com-3807-v1 to be ready
Failed to get response for submission chaiml-horror-sft-v1-1e5_v3: ('http://chaiml-horror-sft-v1-1e5-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54850->127.0.0.1:8080: read: connection reset by peer\n')
Inference service sicarius-prototyping-com-3807-v1 ready after 140.84854555130005s
Pipeline stage MKMLDeployer completed in 141.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3818824291229248s
Received healthy response to inference request in 1.0966579914093018s
Received healthy response to inference request in 1.0265276432037354s
Received healthy response to inference request in 1.5040903091430664s
Received healthy response to inference request in 0.8175840377807617s
5 requests
0 failed requests
5th percentile: 0.8593727588653565
10th percentile: 0.9011614799499512
20th percentile: 0.9847389221191406
30th percentile: 1.0405537128448485
40th percentile: 1.0686058521270752
50th percentile: 1.0966579914093018
60th percentile: 1.210747766494751
70th percentile: 1.3248375415802
80th percentile: 1.4063240051269532
90th percentile: 1.4552071571350098
95th percentile: 1.479648733139038
99th percentile: 1.4992019939422607
mean time: 1.165348482131958
Pipeline stage StressChecker completed in 6.66s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.58s
Shutdown handler de-registered
sicarius-prototyping-com_3807_v1 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sicarius-prototyping-com-3807-v1-profiler
Waiting for inference service sicarius-prototyping-com-3807-v1-profiler to be ready
Inference service sicarius-prototyping-com-3807-v1-profiler ready after 150.35572028160095s
Pipeline stage MKMLProfilerDeployer completed in 150.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sicarius--deploklkwv:/code/chaiverse_profiler_1725574764 --namespace tenant-chaiml-guanaco
kubectl exec -it sicarius--deploklkwv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725574764 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725574764/summary.json'
kubectl exec -it sicarius--deploklkwv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725574764/summary.json'
Pipeline stage MKMLProfilerRunner completed in 467.26s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sicarius-prototyping-com-3807-v1-profiler is running
Tearing down inference service sicarius-prototyping-com-3807-v1-profiler
Service sicarius-prototyping-com-3807-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
sicarius-prototyping-com_3807_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics