developer_uid: valentin87
submission_id: valentin87-0920-curated-_9451_v1
model_name: valentin87-0920-curated-_9451_v1
model_group: valentin87/0920_curated_
status: torndown
timestamp: 2024-09-20T11:38:36+00:00
num_battles: 11731
num_wins: 5831
celo_rating: 1250.51
family_friendly_score: 0.0
submission_type: basic
model_repo: valentin87/0920_curated_convos
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6229968737923998, 'latency_mean': 1.605050424337387, 'latency_p50': 1.5996694564819336, 'latency_p90': 1.7897748947143555}, {'batch_size': 3, 'throughput': 1.08550878648686, 'latency_mean': 2.7527481269836427, 'latency_p50': 2.7703486680984497, 'latency_p90': 3.034984755516052}, {'batch_size': 5, 'throughput': 1.2407833088945974, 'latency_mean': 4.008973816633224, 'latency_p50': 4.038384675979614, 'latency_p90': 4.49950680732727}, {'batch_size': 6, 'throughput': 1.2854815403572588, 'latency_mean': 4.641377589702606, 'latency_p50': 4.62030827999115, 'latency_p90': 5.221617889404296}, {'batch_size': 8, 'throughput': 1.257376113099289, 'latency_mean': 6.326552252769471, 'latency_p50': 6.311727046966553, 'latency_p90': 7.185581016540527}, {'batch_size': 10, 'throughput': 1.2227770474614745, 'latency_mean': 8.125717794895172, 'latency_p50': 8.156328201293945, 'latency_p90': 9.156215071678162}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: valentin87-0920-curated-_9451_v1
is_internal_developer: True
language_model: valentin87/0920_curated_convos
model_size: 13B
ranking_group: single
throughput_3p7s: 1.22
us_pacific_date: 2024-09-20
win_ratio: 0.4970590742477197
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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}
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 valentin87-0920-curated-9451-v1-mkmlizer
Waiting for job on valentin87-0920-curated-9451-v1-mkmlizer to finish
valentin87-0920-curated-9451-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-0920-curated-9451-v1-mkmlizer: ║ _____ __ __ ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ /___/ ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ Version: 0.10.1 ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ https://mk1.ai ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ The license key for the current software has been verified as ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ belonging to: ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ Chai Research Corp. ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
valentin87-0920-curated-9451-v1-mkmlizer: ║ ║
valentin87-0920-curated-9451-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
valentin87-0920-curated-9451-v1-mkmlizer: Downloaded to shared memory in 45.570s
valentin87-0920-curated-9451-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmrxqi033, device:0
valentin87-0920-curated-9451-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
valentin87-0920-curated-9451-v1-mkmlizer: quantized model in 35.444s
valentin87-0920-curated-9451-v1-mkmlizer: Processed model valentin87/0920_curated_convos in 81.014s
valentin87-0920-curated-9451-v1-mkmlizer: creating bucket guanaco-mkml-models
valentin87-0920-curated-9451-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
valentin87-0920-curated-9451-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/valentin87-0920-curated-9451-v1
valentin87-0920-curated-9451-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-0920-curated-9451-v1/config.json
valentin87-0920-curated-9451-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-0920-curated-9451-v1/special_tokens_map.json
valentin87-0920-curated-9451-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/valentin87-0920-curated-9451-v1/tokenizer_config.json
valentin87-0920-curated-9451-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/valentin87-0920-curated-9451-v1/tokenizer.json
valentin87-0920-curated-9451-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/valentin87-0920-curated-9451-v1/flywheel_model.0.safetensors
valentin87-0920-curated-9451-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.80it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.98it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.96it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.70it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.51it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.07it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.61it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.61it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.85it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 33.47it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.21it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.75it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 40.74it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.19it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 45.64it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:05, 45.60it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.69it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 46.03it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 44.36it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 45.80it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 43.09it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.38it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 44.38it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 44.21it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 33.33it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.72it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.49it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 40.45it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 41.54it/s] Loading 0: 46%|████▌ | 167/363 [00:03<00:05, 39.12it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 47.51it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 45.49it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 43.10it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.09it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.01it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.57it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 48.52it/s] Loading 0: 60%|█████▉ | 216/363 [00:04<00:03, 48.33it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 44.77it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.59it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.59it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.91it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 38.61it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 39.57it/s] Loading 0: 69%|██████▉ | 252/363 [00:05<00:02, 41.67it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:02, 36.30it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.93it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 43.82it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 42.61it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 47.39it/s] Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 47.81it/s] Loading 0: 81%|████████ | 293/363 [00:06<00:01, 40.32it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 49.33it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:19, 2.89it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:13, 3.80it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.86it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.73it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.76it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.67it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.01it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 20.10it/s] Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 25.14it/s] Loading 0: 99%|█████████▉| 361/363 [00:14<00:00, 29.96it/s]
Job valentin87-0920-curated-9451-v1-mkmlizer completed after 103.08s with status: succeeded
Stopping job with name valentin87-0920-curated-9451-v1-mkmlizer
Pipeline stage MKMLizer completed in 103.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-0920-curated-9451-v1
Waiting for inference service valentin87-0920-curated-9451-v1 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
Inference service valentin87-0920-curated-9451-v1 ready after 201.22133016586304s
Pipeline stage MKMLDeployer completed in 201.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.944471836090088s
Received healthy response to inference request in 2.4814486503601074s
Received healthy response to inference request in 2.0010921955108643s
Received healthy response to inference request in 1.642843246459961s
Received healthy response to inference request in 1.775987148284912s
5 requests
0 failed requests
5th percentile: 1.6694720268249512
10th percentile: 1.6961008071899415
20th percentile: 1.7493583679199218
30th percentile: 1.8210081577301025
40th percentile: 1.9110501766204835
50th percentile: 2.0010921955108643
60th percentile: 2.1932347774505616
70th percentile: 2.3853773593902585
80th percentile: 2.5740532875061035
90th percentile: 2.7592625617980957
95th percentile: 2.851867198944092
99th percentile: 2.9259509086608886
mean time: 2.1691686153411864
Pipeline stage StressChecker completed in 11.53s
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 6.04s
Shutdown handler de-registered
valentin87-0920-curated-_9451_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service valentin87-0920-curated-9451-v1-profiler
Waiting for inference service valentin87-0920-curated-9451-v1-profiler to be ready
Inference service valentin87-0920-curated-9451-v1-profiler ready after 400.84769201278687s
Pipeline stage MKMLProfilerDeployer completed in 401.21s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-0920-cura1f6fbf15f98ec6cb2b7b097b25d01e3e-deplobwmw9:/code/chaiverse_profiler_1726833088 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-0920-cura1f6fbf15f98ec6cb2b7b097b25d01e3e-deplobwmw9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726833088 && 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_1726833088/summary.json'
kubectl exec -it valentin87-0920-cura1f6fbf15f98ec6cb2b7b097b25d01e3e-deplobwmw9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726833088/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1150.28s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-0920-curated-9451-v1-profiler is running
Tearing down inference service valentin87-0920-curated-9451-v1-profiler
Service valentin87-0920-curated-9451-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
Shutdown handler de-registered
valentin87-0920-curated-_9451_v1 status is now inactive due to auto deactivation removed underperforming models
valentin87-0920-curated-_9451_v1 status is now torndown due to DeploymentManager action