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

submission_id: chaiml-test-feed-convo-v1-1e5_v1

developer_uid: zonemercy

alignment_samples: 12565

alignment_score: -0.3350433681070158

best_of: 8

celo_rating: 1245.95

display_name: chaiml-test-feed-convo-v1-1e5_v1

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}

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': 0.6121079849630124, 'latency_mean': 1.6335967075824738, 'latency_p50': 1.6337180137634277, 'latency_p90': 1.8001588582992554}, {'batch_size': 3, 'throughput': 1.081423702912331, 'latency_mean': 2.7648790287971496, 'latency_p50': 2.740444540977478, 'latency_p90': 3.0575873613357545}, {'batch_size': 5, 'throughput': 1.2153453642596412, 'latency_mean': 4.0974514245986935, 'latency_p50': 4.098013520240784, 'latency_p90': 4.6379735469818115}, {'batch_size': 6, 'throughput': 1.2445543990839734, 'latency_mean': 4.794592007398605, 'latency_p50': 4.820624947547913, 'latency_p90': 5.372899222373962}, {'batch_size': 8, 'throughput': 1.2270608796651012, 'latency_mean': 6.483716238737106, 'latency_p50': 6.475721120834351, 'latency_p90': 7.227730727195739}, {'batch_size': 10, 'throughput': 1.1925649081009315, 'latency_mean': 8.337520914077759, 'latency_p50': 8.382830500602722, 'latency_p90': 9.43380048274994}]

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_v1

model_num_parameters: 12772070400.0

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

model_size: 13B

num_battles: 12565

num_wins: 6311

propriety_score: 0.7673545966228893

propriety_total_count: 1066.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.19

timestamp: 2024-09-11T12:51:53+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.5022682053322722

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-v1-mkmlizer
Waiting for job on chaiml-test-feed-convo-v1-1e5-v1-mkmlizer to finish
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║       /___/                                                         ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ║                                                                     ║
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_sanen_2024-09-09: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51170->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: Downloaded to shared memory in 47.169s
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1izkk1by, device:0
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: quantized model in 35.386s
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: Processed model ChaiML/Test-Feed-Convo-v1-1e5 in 82.555s
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v1
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v1/config.json
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v1/special_tokens_map.json
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v1/tokenizer_config.json
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v1/tokenizer.json
Retrying (%r) after connection broken by '%r': %s
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-test-feed-convo-v1-1e5-v1/flywheel_model.0.safetensors
chaiml-test-feed-convo-v1-1e5-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.77it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.83it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.12it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 48.62it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.56it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.71it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.54it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.00it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.75it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.39it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.82it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.36it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.44it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.37it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.23it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 44.64it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.49it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 50.00it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 45.63it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.93it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.77it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 44.88it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 45.00it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 44.74it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.92it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.89it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.86it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 39.83it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:05, 38.16it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 44.44it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 44.34it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 45.18it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 46.00it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 37.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 44.16it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 43.64it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:03, 38.98it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 42.76it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.64it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 36.13it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 34.48it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 39.90it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.94it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 42.69it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 42.88it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.88it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 45.18it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 45.28it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 46.25it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 46.98it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 39.43it/s]
Loading 0:  80%|████████  | 291/363 [00:06<00:01, 46.53it/s]
Loading 0:  82%|████████▏ | 296/363 [00:06<00:01, 44.29it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 47.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:21,  2.56it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.48it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.54it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.47it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.52it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.46it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.43it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.35it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 24.41it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 27.53it/s]
                                                            
Job chaiml-test-feed-convo-v1-1e5-v1-mkmlizer completed after 124.95s with status: succeeded
Stopping job with name chaiml-test-feed-convo-v1-1e5-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-test-feed-convo-v1-1e5-v1
Waiting for inference service chaiml-test-feed-convo-v1-1e5-v1 to be ready
Inference service chaiml-test-feed-convo-v1-1e5-v1 ready after 160.8984067440033s
Pipeline stage MKMLDeployer completed in 161.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4895358085632324s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.6803200244903564s
Received healthy response to inference request in 1.6865167617797852s
Received healthy response to inference request in 2.14538311958313s
Received healthy response to inference request in 1.7241003513336182s
5 requests
0 failed requests
5th percentile: 1.6815593719482422
10th percentile: 1.682798719406128
20th percentile: 1.6852774143218994
30th percentile: 1.6940334796905518
40th percentile: 1.709066915512085
50th percentile: 1.7241003513336182
60th percentile: 1.892613458633423
70th percentile: 2.0611265659332276
80th percentile: 2.2142136573791507
90th percentile: 2.3518747329711913
95th percentile: 2.4207052707672116
99th percentile: 2.4757697010040283
mean time: 1.9451712131500245
Pipeline stage StressChecker completed in 10.76s
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 5.82s
Shutdown handler de-registered
chaiml-test-feed-convo-v1-1e5_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-test-feed-convo-v1-1e5-v1-profiler
Waiting for inference service chaiml-test-feed-convo-v1-1e5-v1-profiler to be ready
Inference service chaiml-test-feed-convo-v1-1e5-v1-profiler ready after 160.37293791770935s
Pipeline stage MKMLProfilerDeployer completed in 160.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-test-feed-con381a88078c0b82fffd111871d7ead076-deplozz46j:/code/chaiverse_profiler_1726059618 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-test-feed-con381a88078c0b82fffd111871d7ead076-deplozz46j --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726059618 && 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_1726059618/summary.json'
kubectl exec -it chaiml-test-feed-con381a88078c0b82fffd111871d7ead076-deplozz46j --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726059618/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1175.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-test-feed-convo-v1-1e5-v1-profiler is running
Tearing down inference service chaiml-test-feed-convo-v1-1e5-v1-profiler
Service chaiml-test-feed-convo-v1-1e5-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.75s
Shutdown handler de-registered
chaiml-test-feed-convo-v1-1e5_v1 status is now inactive due to auto deactivation removed underperforming models