chaiml-test-feed-convo-v1-1e5

submission_id: chaiml-test-feed-convo-v1-1e5_v2

developer_uid: zonemercy

alignment_samples: 12630

alignment_score: -0.3818136695946898

best_of: 8

celo_rating: 1248.9

display_name: chaiml-test-feed-convo-v1-1e5_v2

formatter: {'memory_template': "Bot's name: {bot_name}\nBot never initiated sex act unless User started first in the conversation\n####\n", 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}

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:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: True

language_model: ChaiML/Test-Feed-Convo-v1-1e5

latencies: [{'batch_size': 1, 'throughput': 0.6126822955237272, 'latency_mean': 1.6321062934398651, 'latency_p50': 1.6353261470794678, 'latency_p90': 1.786242699623108}, {'batch_size': 3, 'throughput': 1.088418600967662, 'latency_mean': 2.749775720834732, 'latency_p50': 2.7101876735687256, 'latency_p90': 3.0505573749542236}, {'batch_size': 5, 'throughput': 1.233575735454605, 'latency_mean': 4.037824395895004, 'latency_p50': 4.077077150344849, 'latency_p90': 4.52425479888916}, {'batch_size': 6, 'throughput': 1.259402653697253, 'latency_mean': 4.742764600515366, 'latency_p50': 4.7685956954956055, 'latency_p90': 5.395270538330078}, {'batch_size': 8, 'throughput': 1.2355878708968009, 'latency_mean': 6.4416616344451905, 'latency_p50': 6.4716269969940186, 'latency_p90': 7.259097146987915}, {'batch_size': 10, 'throughput': 1.1973201048204893, 'latency_mean': 8.2932173371315, 'latency_p50': 8.285890340805054, 'latency_p90': 9.374710083007812}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/Test-Feed-Convo-v

model_name: chaiml-test-feed-convo-v1-1e5_v2

model_num_parameters: 12772070400.0

model_repo: ChaiML/Test-Feed-Convo-v1-1e5

model_size: 13B

num_battles: 12628

num_wins: 6405

propriety_score: 0.7429906542056075

propriety_total_count: 1070.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.21

timestamp: 2024-09-11T12:56:20+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.5072062084257206

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 chaiml-test-feed-convo-v1-1e5-v2-mkmlizer
Waiting for job on chaiml-test-feed-convo-v1-1e5-v2-mkmlizer to finish
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
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║       /___/                                                         ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: Downloaded to shared memory in 36.758s
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp381_7qqe, device:0
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: quantized model in 35.914s
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: Processed model ChaiML/Test-Feed-Convo-v1-1e5 in 72.673s
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v2
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v2/config.json
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v2/special_tokens_map.json
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v2/tokenizer_config.json
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v2/tokenizer.json
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v2/flywheel_model.0.safetensors
chaiml-test-feed-convo-v1-1e5-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.62it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.30it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 41.68it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.19it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.77it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.45it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.59it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.12it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.77it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 47.23it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 27.14it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.07it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 35.99it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.85it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:06, 39.93it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 39.89it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 43.03it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 43.06it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 43.00it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.73it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 39.83it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 39.92it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.87it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.70it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 41.46it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 28.98it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 28.95it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.52it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.45it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.61it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.53it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 41.69it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 43.62it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:05, 35.35it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:04, 42.07it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 42.10it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 41.31it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 42.65it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 36.51it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 46.49it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 30.39it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.24it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 37.41it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.32it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.16it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.60it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.58it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.36it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 44.44it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.61it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 42.67it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 44.10it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 43.27it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 44.43it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 44.43it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.42it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.34it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.42it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  7.08it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.93it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.49it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.62it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.21it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 27.70it/s]
                                                            
Job chaiml-test-feed-convo-v1-1e5-v2-mkmlizer completed after 94.67s with status: succeeded
Stopping job with name chaiml-test-feed-convo-v1-1e5-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.85s
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-test-feed-convo-v1-1e5-v2
Waiting for inference service chaiml-test-feed-convo-v1-1e5-v2 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
Inference service chaiml-test-feed-convo-v1-1e5-v2 ready after 161.12966227531433s
Pipeline stage MKMLDeployer completed in 161.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.834547758102417s
Received healthy response to inference request in 2.022918939590454s
Received healthy response to inference request in 2.2017054557800293s
Received healthy response to inference request in 3.1460909843444824s
Received healthy response to inference request in 2.1089189052581787s
5 requests
0 failed requests
5th percentile: 2.040118932723999
10th percentile: 2.057318925857544
20th percentile: 2.091718912124634
30th percentile: 2.127476215362549
40th percentile: 2.164590835571289
50th percentile: 2.2017054557800293
60th percentile: 2.454842376708984
70th percentile: 2.7079792976379395
80th percentile: 2.89685640335083
90th percentile: 3.021473693847656
95th percentile: 3.0837823390960692
99th percentile: 3.1336292552948
mean time: 2.462836408615112
Pipeline stage StressChecker completed in 15.84s
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 6.73s
Shutdown handler de-registered
chaiml-test-feed-convo-v1-1e5_v2 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-test-feed-convo-v1-1e5-v2-profiler
Waiting for inference service chaiml-test-feed-convo-v1-1e5-v2-profiler to be ready
Inference service chaiml-test-feed-convo-v1-1e5-v2-profiler ready after 160.37605905532837s
Pipeline stage MKMLProfilerDeployer completed in 160.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-test-feed-con96dded52023d5cc70f75d4f8f28b5327-deplo6k4zz:/code/chaiverse_profiler_1726059864 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-test-feed-con96dded52023d5cc70f75d4f8f28b5327-deplo6k4zz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726059864 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726059864/summary.json'
kubectl exec -it chaiml-test-feed-con96dded52023d5cc70f75d4f8f28b5327-deplo6k4zz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726059864/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1167.51s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-test-feed-convo-v1-1e5-v2-profiler is running
Tearing down inference service chaiml-test-feed-convo-v1-1e5-v2-profiler
Service chaiml-test-feed-convo-v1-1e5-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.80s
Shutdown handler de-registered
chaiml-test-feed-convo-v1-1e5_v2 status is now inactive due to auto deactivation removed underperforming models