submission_id: rica40325-feedback-11_v2
developer_uid: rica40325
best_of: 16
celo_rating: 1237.23
display_name: rica40325-feedback-11_v1
family_friendly_score: 0.0
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': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/feedback-11
latencies: [{'batch_size': 1, 'throughput': 0.9139963348439801, 'latency_mean': 1.093993045091629, 'latency_p50': 1.0931570529937744, 'latency_p90': 1.2357593297958374}, {'batch_size': 4, 'throughput': 1.8130630351700998, 'latency_mean': 2.195454521179199, 'latency_p50': 2.2030128240585327, 'latency_p90': 2.4517377376556397}, {'batch_size': 5, 'throughput': 1.9163506234692294, 'latency_mean': 2.5990102887153625, 'latency_p50': 2.600239634513855, 'latency_p90': 2.8778088092803955}, {'batch_size': 8, 'throughput': 2.0202436427500845, 'latency_mean': 3.934739543199539, 'latency_p50': 3.9537317752838135, 'latency_p90': 4.3830886602401735}, {'batch_size': 10, 'throughput': 2.042800514113316, 'latency_mean': 4.8493876242637635, 'latency_p50': 4.790267825126648, 'latency_p90': 5.746371579170226}, {'batch_size': 12, 'throughput': 2.0567502370031794, 'latency_mean': 5.752704870700836, 'latency_p50': 5.716389298439026, 'latency_p90': 6.531153917312622}, {'batch_size': 15, 'throughput': 2.0455833550158884, 'latency_mean': 7.193324397802353, 'latency_p50': 7.33178174495697, 'latency_p90': 7.980621719360352}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/feedback-11
model_name: rica40325-feedback-11_v1
model_num_parameters: 8030261248.0
model_repo: rica40325/feedback-11
model_size: 8B
num_battles: 11946
num_wins: 5868
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.02
timestamp: 2024-09-12T10:15:19+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.491210447011552
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 rica40325-feedback-11-v2-mkmlizer
Waiting for job on rica40325-feedback-11-v2-mkmlizer to finish
rica40325-feedback-11-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-11-v2-mkmlizer: ║ _____ __ __ ║
rica40325-feedback-11-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-feedback-11-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-feedback-11-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-feedback-11-v2-mkmlizer: ║ /___/ ║
rica40325-feedback-11-v2-mkmlizer: ║ ║
rica40325-feedback-11-v2-mkmlizer: ║ Version: 0.10.1 ║
rica40325-feedback-11-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-feedback-11-v2-mkmlizer: ║ https://mk1.ai ║
rica40325-feedback-11-v2-mkmlizer: ║ ║
rica40325-feedback-11-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-feedback-11-v2-mkmlizer: ║ belonging to: ║
rica40325-feedback-11-v2-mkmlizer: ║ ║
rica40325-feedback-11-v2-mkmlizer: ║ Chai Research Corp. ║
rica40325-feedback-11-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-feedback-11-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-feedback-11-v2-mkmlizer: ║ ║
rica40325-feedback-11-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedback-11-v2-mkmlizer: Downloaded to shared memory in 38.144s
rica40325-feedback-11-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnuqvaop8, device:0
rica40325-feedback-11-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedback-11-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-11-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-11-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-11-v2
rica40325-feedback-11-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-11-v2/config.json
rica40325-feedback-11-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-11-v2/special_tokens_map.json
rica40325-feedback-11-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-11-v2/tokenizer_config.json
rica40325-feedback-11-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-11-v2/tokenizer.json
rica40325-feedback-11-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedback-11-v2/flywheel_model.0.safetensors
rica40325-feedback-11-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.01it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 42.32it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:07, 38.09it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:07, 36.64it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:07, 35.53it/s] Loading 0: 11%|█ | 32/291 [00:00<00:07, 36.81it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.19it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.27it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 33.06it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 32.44it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.94it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.60it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 36.34it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.79it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.79it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.71it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 23.68it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 26.43it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:06, 29.59it/s] Loading 0: 33%|███▎ | 95/291 [00:03<00:06, 30.55it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.71it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.57it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.40it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.02it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.87it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.63it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 35.03it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.62it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.39it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.97it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.54it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.52it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.46it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:04, 32.72it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.83it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.10it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.02it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.96it/s] Loading 0: 64%|██████▎ | 185/291 [00:05<00:02, 38.12it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.66it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 26.11it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.33it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 32.02it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 35.06it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.22it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.32it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.92it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 34.54it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.08it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 23.37it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 22.99it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 29.83it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 29.08it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 31.64it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:01, 30.93it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 34.20it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 32.91it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.79it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.13it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 33.71it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.59it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.20it/s]
Job rica40325-feedback-11-v2-mkmlizer completed after 95.14s with status: succeeded
Stopping job with name rica40325-feedback-11-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-11-v2
Waiting for inference service rica40325-feedback-11-v2 to be ready
Inference service rica40325-feedback-11-v2 ready after 170.54490280151367s
Pipeline stage MKMLDeployer completed in 170.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.123968601226807s
Received healthy response to inference request in 1.8308725357055664s
Received healthy response to inference request in 1.4422693252563477s
Received healthy response to inference request in 5.6555256843566895s
Received healthy response to inference request in 8.516009092330933s
5 requests
0 failed requests
5th percentile: 1.5199899673461914
10th percentile: 1.5977106094360352
20th percentile: 1.7531518936157227
30th percentile: 2.4894917488098143
40th percentile: 3.806730175018311
50th percentile: 5.123968601226807
60th percentile: 5.33659143447876
70th percentile: 5.549214267730713
80th percentile: 6.227622365951539
90th percentile: 7.371815729141236
95th percentile: 7.9439124107360835
99th percentile: 8.401589756011962
mean time: 4.513729047775269
%s, retrying in %s seconds...
Received healthy response to inference request in 6.790812730789185s
Received healthy response to inference request in 1.845367431640625s
Received healthy response to inference request in 1.5691912174224854s
Received healthy response to inference request in 4.854174852371216s
Received healthy response to inference request in 1.4099223613739014s
5 requests
0 failed requests
5th percentile: 1.4417761325836183
10th percentile: 1.473629903793335
20th percentile: 1.5373374462127685
30th percentile: 1.6244264602661134
40th percentile: 1.7348969459533692
50th percentile: 1.845367431640625
60th percentile: 3.048890399932861
70th percentile: 4.252413368225097
80th percentile: 5.24150242805481
90th percentile: 6.016157579421997
95th percentile: 6.4034851551055905
99th percentile: 6.713347215652465
mean time: 3.2938937187194823
Pipeline stage StressChecker completed in 40.41s
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 6.14s
Shutdown handler de-registered
rica40325-feedback-11_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 0.10s
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 rica40325-feedback-11-v2-profiler
Waiting for inference service rica40325-feedback-11-v2-profiler to be ready
Inference service rica40325-feedback-11-v2-profiler ready after 170.39822936058044s
Pipeline stage MKMLProfilerDeployer completed in 170.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-11-v2-profiler-predictor-00001-deploymegtzct:/code/chaiverse_profiler_1726136640 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-11-v2-profiler-predictor-00001-deploymegtzct --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726136640 && python profiles.py profile --best_of_n 16 --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_1726136640/summary.json'
kubectl exec -it rica40325-feedback-11-v2-profiler-predictor-00001-deploymegtzct --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726136640/summary.json'
Pipeline stage MKMLProfilerRunner completed in 831.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-11-v2-profiler is running
Tearing down inference service rica40325-feedback-11-v2-profiler
Service rica40325-feedback-11-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.99s
Shutdown handler de-registered
rica40325-feedback-11_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-feedback-11_v2 status is now torndown due to DeploymentManager action