developer_uid: azuruce
submission_id: chaiml-0917-bot-supporti_5666_v1
model_name: supportive
model_group: ChaiML/0917-bot-supporti
status: torndown
timestamp: 2024-09-17T17:56:06+00:00
num_battles: 10563
num_wins: 5216
celo_rating: 1244.79
family_friendly_score: 0.0
submission_type: basic
model_repo: ChaiML/0917-bot-supportive-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6350328658680539, 'latency_mean': 1.5746339249610901, 'latency_p50': 1.5589017868041992, 'latency_p90': 1.7569761753082276}, {'batch_size': 3, 'throughput': 1.2389912297993582, 'latency_mean': 2.413640903234482, 'latency_p50': 2.4191678762435913, 'latency_p90': 2.654163861274719}, {'batch_size': 5, 'throughput': 1.5444182151514507, 'latency_mean': 3.2248764312267304, 'latency_p50': 3.225928783416748, 'latency_p90': 3.671866512298584}, {'batch_size': 6, 'throughput': 1.6234280772417464, 'latency_mean': 3.683324865102768, 'latency_p50': 3.7000633478164673, 'latency_p90': 4.091306376457214}, {'batch_size': 8, 'throughput': 1.7308560347391715, 'latency_mean': 4.573988338708878, 'latency_p50': 4.577356815338135, 'latency_p90': 5.157825016975403}, {'batch_size': 10, 'throughput': 1.768500372355347, 'latency_mean': 5.598606843948364, 'latency_p50': 5.609427809715271, 'latency_p90': 6.359077620506286}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: supportive
is_internal_developer: True
language_model: ChaiML/0917-bot-supportive-albert
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2024-09-17
win_ratio: 0.49379911010129696
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', '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 chaiml-0917-bot-supporti-5666-v1-mkmlizer
Waiting for job on chaiml-0917-bot-supporti-5666-v1-mkmlizer to finish
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ _____ __ __ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ /___/ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ Version: 0.10.1 ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ belonging to: ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ║ ║
chaiml-0917-bot-supporti-5666-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-0917-bot-supporti-5666-v1-mkmlizer: Downloaded to shared memory in 58.120s
chaiml-0917-bot-supporti-5666-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8r_hlbnk, device:0
chaiml-0917-bot-supporti-5666-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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
chaiml-0917-bot-supporti-5666-v1-mkmlizer: quantized model in 42.370s
chaiml-0917-bot-supporti-5666-v1-mkmlizer: Processed model ChaiML/0917-bot-supportive-albert in 100.490s
chaiml-0917-bot-supporti-5666-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0917-bot-supporti-5666-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0917-bot-supporti-5666-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0917-bot-supporti-5666-v1
chaiml-0917-bot-supporti-5666-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0917-bot-supporti-5666-v1/config.json
chaiml-0917-bot-supporti-5666-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0917-bot-supporti-5666-v1/special_tokens_map.json
chaiml-0917-bot-supporti-5666-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0917-bot-supporti-5666-v1/tokenizer_config.json
chaiml-0917-bot-supporti-5666-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0917-bot-supporti-5666-v1/tokenizer.json
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_sinam_2024-09-09: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42064->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-0917-bot-supporti-5666-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0917-bot-supporti-5666-v1/flywheel_model.0.safetensors
chaiml-0917-bot-supporti-5666-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:15, 22.86it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:11, 29.73it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.74it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:10, 31.89it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:14, 23.66it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:16, 20.71it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 26.40it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 28.02it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 29.64it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 28.16it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 31.60it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.92it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:11, 27.83it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 24.40it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 21.73it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 29.11it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 28.99it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:10, 27.45it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 29.82it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 28.08it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:09, 29.95it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:09, 28.35it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:11, 22.66it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 19.97it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 26.78it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:09, 25.12it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 30.25it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 28.49it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.05it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 29.07it/s] Loading 0: 38%|███▊ | 137/363 [00:05<00:07, 29.72it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 31.59it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 21.36it/s] Loading 0: 41%|████ | 149/363 [00:05<00:10, 20.96it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 27.18it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 26.64it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 29.20it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:07, 27.54it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 30.13it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 27.93it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:08, 22.36it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:08, 20.42it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:06, 26.93it/s] Loading 0: 54%|█████▎ | 195/363 [00:07<00:06, 24.58it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 29.12it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 27.89it/s] Loading 0: 57%|█████▋ | 208/363 [00:07<00:05, 28.32it/s] Loading 0: 58%|█████▊ | 212/363 [00:07<00:05, 25.37it/s] Loading 0: 60%|██████ | 218/363 [00:08<00:04, 30.25it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 26.36it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 24.79it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 23.02it/s] Loading 0: 65%|██████▍ | 235/363 [00:08<00:04, 27.77it/s] Loading 0: 66%|██████▌ | 239/363 [00:09<00:05, 24.78it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 29.61it/s] Loading 0: 68%|██████▊ | 248/363 [00:09<00:04, 26.74it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 32.83it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 30.05it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 24.26it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.95it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 25.96it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 23.58it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 30.14it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 28.79it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 30.64it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 28.64it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 27.73it/s] Loading 0: 83%|████████▎ | 303/363 [00:11<00:01, 30.27it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 20.06it/s] Loading 0: 85%|████████▌ | 310/363 [00:11<00:02, 21.74it/s] Loading 0: 86%|████████▌ | 313/363 [00:11<00:02, 22.35it/s] Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 23.79it/s] Loading 0: 88%|████████▊ | 320/363 [00:12<00:01, 22.23it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 29.01it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 27.08it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 28.94it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 27.63it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 1.90it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.56it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.73it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.83it/s]
Job chaiml-0917-bot-supporti-5666-v1-mkmlizer completed after 124.89s with status: succeeded
Stopping job with name chaiml-0917-bot-supporti-5666-v1-mkmlizer
Pipeline stage MKMLizer completed in 126.43s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-0917-bot-supporti-5666-v1
Waiting for inference service chaiml-0917-bot-supporti-5666-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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-0917-bot-supporti-5666-v1 ready after 180.9640908241272s
Pipeline stage MKMLDeployer completed in 181.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4212183952331543s
Received healthy response to inference request in 3.2490170001983643s
Received healthy response to inference request in 2.6206579208374023s
Received healthy response to inference request in 2.234635353088379s
Received healthy response to inference request in 1.8928136825561523s
5 requests
0 failed requests
5th percentile: 1.9611780166625976
10th percentile: 2.029542350769043
20th percentile: 2.1662710189819334
30th percentile: 2.271951961517334
40th percentile: 2.346585178375244
50th percentile: 2.4212183952331543
60th percentile: 2.5009942054748535
70th percentile: 2.5807700157165527
80th percentile: 2.746329736709595
90th percentile: 2.9976733684539796
95th percentile: 3.1233451843261717
99th percentile: 3.2238826370239257
mean time: 2.4836684703826903
Pipeline stage StressChecker completed in 13.29s
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 7.07s
Shutdown handler de-registered
chaiml-0917-bot-supporti_5666_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 0.14s
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-0917-bot-supporti-5666-v1-profiler
Waiting for inference service chaiml-0917-bot-supporti-5666-v1-profiler to be ready
Inference service chaiml-0917-bot-supporti-5666-v1-profiler ready after 180.4122714996338s
Pipeline stage MKMLProfilerDeployer completed in 180.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-0917-bot-supp8309e9fe424cbebef81f1bddbd4fbfda-deplo5w82d:/code/chaiverse_profiler_1726596327 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-0917-bot-supp8309e9fe424cbebef81f1bddbd4fbfda-deplo5w82d --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726596327 && python profiles.py profile --best_of_n 4 --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_1726596327/summary.json'
kubectl exec -it chaiml-0917-bot-supp8309e9fe424cbebef81f1bddbd4fbfda-deplo5w82d --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726596327/summary.json'
Pipeline stage MKMLProfilerRunner completed in 964.33s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-0917-bot-supporti-5666-v1-profiler is running
Tearing down inference service chaiml-0917-bot-supporti-5666-v1-profiler
Service chaiml-0917-bot-supporti-5666-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler de-registered
chaiml-0917-bot-supporti_5666_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-0917-bot-supporti_5666_v1 status is now torndown due to DeploymentManager action
chaiml-0917-bot-playful-_6039_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 3.57s
Pipeline stage MKMLModelDeleter completed in 3.57s
Pipeline stage %s skipped, reason=%s
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
admin requested tearing down of chaiml-0919-quad-dataset_3078_v2
chaiml-0917-bot-supporti_5666_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.57s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLModelDeleter completed in 4.40s
admin requested tearing down of chaiml-0919-quad-dataset_3078_v2
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 4.49s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
chaiml-0917-bot-supporti_5666_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 4.02s
run pipeline %s
chaiml-0917-bot-supporti_5666_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0919-virgo-top-bo_5943_v1
chaiml-0917-bot-supporti_5666_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0919-quad-dataset_3078_v2
Running pipeline stage MKMLModelDeleter
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLDeleter completed in 7.06s
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Waiting for job on nousresearch-meta-llama-4939-v63-mkmlizer to finish
chaiml-0917-bot-supporti_5666_v1 status is now torndown due to DeploymentManager action
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 6.58s
Connection pool is full, discarding connection: %s. Connection pool size: %s