submission_id: rica40325-spin-first_v3
developer_uid: rica40325
best_of: 8
celo_rating: 1252.01
display_name: rica40325-spin-first_v2
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/spin_first
latencies: [{'batch_size': 1, 'throughput': 0.8670298883747266, 'latency_mean': 1.1533045303821563, 'latency_p50': 1.1582485437393188, 'latency_p90': 1.2621580600738525}, {'batch_size': 4, 'throughput': 1.842866085802872, 'latency_mean': 2.1582586097717287, 'latency_p50': 2.1456797122955322, 'latency_p90': 2.3798476457595825}, {'batch_size': 5, 'throughput': 1.9864487365135075, 'latency_mean': 2.507127116918564, 'latency_p50': 2.5197441577911377, 'latency_p90': 2.786963129043579}, {'batch_size': 8, 'throughput': 2.209352922137993, 'latency_mean': 3.5985847449302675, 'latency_p50': 3.61666202545166, 'latency_p90': 4.020754885673523}, {'batch_size': 10, 'throughput': 2.2599382262049343, 'latency_mean': 4.388161350488662, 'latency_p50': 4.388139963150024, 'latency_p90': 4.92284209728241}, {'batch_size': 12, 'throughput': 2.2795590125201954, 'latency_mean': 5.224575052261352, 'latency_p50': 5.286789655685425, 'latency_p90': 5.860528039932251}, {'batch_size': 15, 'throughput': 2.301900243099324, 'latency_mean': 6.430151287317276, 'latency_p50': 6.522559285163879, 'latency_p90': 7.075661945343017}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/spin_first
model_name: rica40325-spin-first_v2
model_num_parameters: 8030261248.0
model_repo: rica40325/spin_first
model_size: 8B
num_battles: 10277
num_wins: 5275
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 2.23
timestamp: 2024-09-19T04:50:07+00:00
us_pacific_date: 2024-09-18
win_ratio: 0.5132820862119295
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-spin-first-v3-mkmlizer
Waiting for job on rica40325-spin-first-v3-mkmlizer to finish
rica40325-spin-first-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-spin-first-v3-mkmlizer: ║ _____ __ __ ║
rica40325-spin-first-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-spin-first-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-spin-first-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-spin-first-v3-mkmlizer: ║ /___/ ║
rica40325-spin-first-v3-mkmlizer: ║ ║
rica40325-spin-first-v3-mkmlizer: ║ Version: 0.10.1 ║
rica40325-spin-first-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-spin-first-v3-mkmlizer: ║ https://mk1.ai ║
rica40325-spin-first-v3-mkmlizer: ║ ║
rica40325-spin-first-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-spin-first-v3-mkmlizer: ║ belonging to: ║
rica40325-spin-first-v3-mkmlizer: ║ ║
rica40325-spin-first-v3-mkmlizer: ║ Chai Research Corp. ║
rica40325-spin-first-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-spin-first-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
rica40325-spin-first-v3-mkmlizer: ║ ║
rica40325-spin-first-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-spin-first-v3-mkmlizer: Downloaded to shared memory in 43.797s
rica40325-spin-first-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0dno1i3d, device:0
rica40325-spin-first-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-spin-first-v3-mkmlizer: quantized model in 28.087s
rica40325-spin-first-v3-mkmlizer: Processed model rica40325/spin_first in 71.884s
rica40325-spin-first-v3-mkmlizer: creating bucket guanaco-mkml-models
rica40325-spin-first-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-spin-first-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-spin-first-v3
rica40325-spin-first-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-spin-first-v3/config.json
rica40325-spin-first-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-spin-first-v3/special_tokens_map.json
rica40325-spin-first-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-spin-first-v3/tokenizer_config.json
rica40325-spin-first-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-spin-first-v3/tokenizer.json
rica40325-spin-first-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-spin-first-v3/flywheel_model.0.safetensors
rica40325-spin-first-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.01it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 42.64it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 39.63it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 40.07it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 42.37it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 42.76it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:09, 28.07it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:08, 28.01it/s] Loading 0: 17%|█▋ | 49/291 [00:01<00:06, 36.84it/s] Loading 0: 19%|█▊ | 54/291 [00:01<00:05, 39.68it/s] Loading 0: 20%|██ | 59/291 [00:01<00:06, 33.54it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:05, 40.84it/s] Loading 0: 24%|██▍ | 71/291 [00:01<00:05, 40.18it/s] Loading 0: 26%|██▌ | 76/291 [00:02<00:05, 36.85it/s] Loading 0: 27%|██▋ | 80/291 [00:02<00:06, 30.19it/s] Loading 0: 29%|██▉ | 84/291 [00:02<00:07, 28.77it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:05, 35.01it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:05, 37.07it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:05, 33.90it/s] Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 41.39it/s] Loading 0: 39%|███▉ | 113/291 [00:03<00:04, 40.82it/s] Loading 0: 41%|████ | 118/291 [00:03<00:04, 42.78it/s] Loading 0: 43%|████▎ | 125/291 [00:03<00:03, 46.42it/s] Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 43.06it/s] Loading 0: 46%|████▋ | 135/291 [00:03<00:05, 26.81it/s] Loading 0: 48%|████▊ | 140/291 [00:03<00:05, 28.37it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 35.21it/s] Loading 0: 52%|█████▏ | 152/291 [00:04<00:03, 34.97it/s] Loading 0: 54%|█████▍ | 157/291 [00:04<00:03, 35.53it/s] Loading 0: 56%|█████▌ | 162/291 [00:04<00:03, 38.09it/s] Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 31.59it/s] Loading 0: 60%|█████▉ | 174/291 [00:04<00:03, 37.73it/s] Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 38.05it/s] Loading 0: 64%|██████▎ | 185/291 [00:05<00:02, 39.74it/s] Loading 0: 65%|██████▌ | 190/291 [00:05<00:03, 27.71it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.61it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 34.05it/s] Loading 0: 71%|███████ | 206/291 [00:05<00:02, 35.43it/s] Loading 0: 73%|███████▎ | 211/291 [00:05<00:02, 36.00it/s] Loading 0: 74%|███████▍ | 216/291 [00:06<00:01, 38.76it/s] Loading 0: 76%|███████▌ | 221/291 [00:06<00:02, 32.76it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 36.99it/s] Loading 0: 80%|███████▉ | 232/291 [00:06<00:01, 34.78it/s] Loading 0: 81%|████████ | 236/291 [00:06<00:01, 30.91it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:01, 28.73it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 34.27it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.47it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 34.47it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 33.10it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 36.08it/s] Loading 0: 92%|█████████▏| 268/291 [00:07<00:00, 33.97it/s] Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 36.95it/s] Loading 0: 95%|█████████▌| 277/291 [00:07<00:00, 34.66it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.78it/s] Loading 0: 98%|█████████▊| 286/291 [00:13<00:01, 2.61it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 3.24it/s]
Job rica40325-spin-first-v3-mkmlizer completed after 93.37s with status: succeeded
Stopping job with name rica40325-spin-first-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.33s
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 rica40325-spin-first-v3
Waiting for inference service rica40325-spin-first-v3 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
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 rica40325-spin-first-v3 ready after 191.14014434814453s
Pipeline stage MKMLDeployer completed in 191.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8434779644012451s
Received healthy response to inference request in 2.1474621295928955s
Received healthy response to inference request in 2.0366921424865723s
Received healthy response to inference request in 1.5518155097961426s
Received healthy response to inference request in 1.5627365112304688s
5 requests
0 failed requests
5th percentile: 1.5539997100830079
10th percentile: 1.5561839103698731
20th percentile: 1.5605523109436035
30th percentile: 1.618884801864624
40th percentile: 1.7311813831329346
50th percentile: 1.8434779644012451
60th percentile: 1.9207636356353759
70th percentile: 1.9980493068695069
80th percentile: 2.058846139907837
90th percentile: 2.1031541347503664
95th percentile: 2.125308132171631
99th percentile: 2.1430313301086428
mean time: 1.8284368515014648
Pipeline stage StressChecker completed in 11.14s
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
rica40325-spin-first_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-spin-first-v3-profiler
Waiting for inference service rica40325-spin-first-v3-profiler to be ready
Inference service rica40325-spin-first-v3-profiler ready after 190.63164401054382s
Pipeline stage MKMLProfilerDeployer completed in 191.00s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-spin-first-v3-profiler-predictor-00001-deploymen6qksk:/code/chaiverse_profiler_1726721954 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-spin-first-v3-profiler-predictor-00001-deploymen6qksk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726721954 && 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_1726721954/summary.json'
kubectl exec -it rica40325-spin-first-v3-profiler-predictor-00001-deploymen6qksk --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726721954/summary.json'
Pipeline stage MKMLProfilerRunner completed in 799.52s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-spin-first-v3-profiler is running
Tearing down inference service rica40325-spin-first-v3-profiler
Service rica40325-spin-first-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.17s
Shutdown handler de-registered
rica40325-spin-first_v3 status is now inactive due to auto deactivation removed underperforming models
rica40325-spin-first_v3 status is now torndown due to DeploymentManager action