submission_id: cycy233-nemo-p-e-v2-c4_v1
developer_uid: shiroe40
best_of: 8
celo_rating: 1285.75
display_name: auto
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': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/nemo-p-e-v2-c4
latencies: [{'batch_size': 1, 'throughput': 0.6104464967671768, 'latency_mean': 1.638082319498062, 'latency_p50': 1.637527346611023, 'latency_p90': 1.8091560840606689}, {'batch_size': 3, 'throughput': 1.0687445264415816, 'latency_mean': 2.7963528168201446, 'latency_p50': 2.8021819591522217, 'latency_p90': 3.1798061609268187}, {'batch_size': 5, 'throughput': 1.210979443515792, 'latency_mean': 4.103957163095474, 'latency_p50': 4.109650135040283, 'latency_p90': 4.654695987701416}, {'batch_size': 6, 'throughput': 1.2259153266589196, 'latency_mean': 4.860736483335495, 'latency_p50': 4.8893715143203735, 'latency_p90': 5.442263984680176}, {'batch_size': 8, 'throughput': 1.2158465195989574, 'latency_mean': 6.5525545048713685, 'latency_p50': 6.543642282485962, 'latency_p90': 7.403339076042175}, {'batch_size': 10, 'throughput': 1.1753351248384938, 'latency_mean': 8.458709326982499, 'latency_p50': 8.450892329216003, 'latency_p90': 9.591595792770386}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cycy233/nemo-p-e-v2-c4
model_name: auto
model_num_parameters: 12772070400.0
model_repo: cycy233/nemo-p-e-v2-c4
model_size: 13B
num_battles: 64494
num_wins: 35973
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.18
timestamp: 2024-09-23T06:38:54+00:00
us_pacific_date: 2024-09-22
win_ratio: 0.557772816075914
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 cycy233-nemo-p-e-v2-c4-v1-mkmlizer
Waiting for job on cycy233-nemo-p-e-v2-c4-v1-mkmlizer to finish
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
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: Downloaded to shared memory in 47.545s
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5tbv515i, device:0
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
admin requested tearing down of nousresearch-meta-llama_4939_v19
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
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: quantized model in 36.179s
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: Processed model cycy233/nemo-p-e-v2-c4 in 83.725s
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c4-v1
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c4-v1/config.json
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c4-v1/special_tokens_map.json
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c4-v1/tokenizer_config.json
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c4-v1/tokenizer.json
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-e-v2-c4-v1/flywheel_model.0.safetensors
cycy233-nemo-p-e-v2-c4-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.58it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:07, 45.24it/s] Loading 0: 5%|▍ | 18/363 [00:00<00:07, 46.41it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 38.82it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 44.75it/s] Loading 0: 10%|▉ | 36/363 [00:00<00:07, 45.90it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:08, 37.85it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 46.09it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:06, 46.15it/s] Loading 0: 16%|█▋ | 59/363 [00:01<00:06, 46.69it/s] Loading 0: 18%|█▊ | 64/363 [00:01<00:11, 26.90it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:08, 34.16it/s] Loading 0: 21%|██ | 76/363 [00:01<00:08, 35.79it/s] Loading 0: 22%|██▏ | 81/363 [00:02<00:07, 38.59it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:06, 39.53it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 39.00it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 44.63it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 43.87it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 43.76it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 42.28it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 40.61it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:05, 43.57it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:05, 44.79it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:06, 35.34it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 31.61it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.94it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.81it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 39.46it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:04, 41.01it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 41.08it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 45.54it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 44.76it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 45.29it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:03, 44.10it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:03, 42.50it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 47.67it/s] Loading 0: 57%|█████▋ | 208/363 [00:05<00:03, 46.80it/s] Loading 0: 59%|█████▊ | 213/363 [00:05<00:03, 45.14it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 46.20it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.42it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 35.68it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.98it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 36.67it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 37.42it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 41.52it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 41.17it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 38.79it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 43.51it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.40it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 44.74it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 43.83it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 41.59it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 46.36it/s] Loading 0: 82%|████████▏ | 297/363 [00:07<00:01, 46.51it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 43.76it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:22, 2.44it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:15, 3.35it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.40it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:05, 7.31it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.34it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.28it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:01, 16.78it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 19.89it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 26.18it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.56it/s]
Job cycy233-nemo-p-e-v2-c4-v1-mkmlizer completed after 106.91s with status: succeeded
Stopping job with name cycy233-nemo-p-e-v2-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-e-v2-c4-v1
Waiting for inference service cycy233-nemo-p-e-v2-c4-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
Failed to get response for submission mistralai-mixtral-8x7b_3473_v136: ('http://mistralai-mixtral-8x7b-3473-v136-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60910->127.0.0.1:8080: read: connection reset by peer\n')
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 cycy233-nemo-p-e-v2-c4-v1 ready after 191.01308345794678s
Pipeline stage MKMLDeployer completed in 193.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.728339672088623s
Received healthy response to inference request in 1.9132890701293945s
Received healthy response to inference request in 2.2136011123657227s
Received healthy response to inference request in 2.642559051513672s
Received healthy response to inference request in 2.3885722160339355s
5 requests
0 failed requests
5th percentile: 1.9733514785766602
10th percentile: 2.033413887023926
20th percentile: 2.153538703918457
30th percentile: 2.2485953330993653
40th percentile: 2.31858377456665
50th percentile: 2.3885722160339355
60th percentile: 2.49016695022583
70th percentile: 2.5917616844177247
80th percentile: 2.659715175628662
90th percentile: 2.6940274238586426
95th percentile: 2.711183547973633
99th percentile: 2.724908447265625
mean time: 2.3772722244262696
Pipeline stage StressChecker completed in 13.10s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.50s
Shutdown handler de-registered
cycy233-nemo-p-e-v2-c4_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-nemo-p-e-v2-c4-v1-profiler
Waiting for inference service cycy233-nemo-p-e-v2-c4-v1-profiler to be ready
Inference service cycy233-nemo-p-e-v2-c4-v1-profiler ready after 200.48057532310486s
Pipeline stage MKMLProfilerDeployer completed in 200.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-e-v2-c4-v1-profiler-predictor-00001-deploym8mnf4:/code/chaiverse_profiler_1727074095 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-e-v2-c4-v1-profiler-predictor-00001-deploym8mnf4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727074095 && 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_1727074095/summary.json'
kubectl exec -it cycy233-nemo-p-e-v2-c4-v1-profiler-predictor-00001-deploym8mnf4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727074095/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1182.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-e-v2-c4-v1-profiler is running
Tearing down inference service cycy233-nemo-p-e-v2-c4-v1-profiler
Service cycy233-nemo-p-e-v2-c4-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
Shutdown handler de-registered
cycy233-nemo-p-e-v2-c4_v1 status is now inactive due to auto deactivation removed underperforming models
run pipeline stage %s
Job rica40325-mistral-test1-v6-mkmlizer completed after 134.97s with status: succeeded
Pipeline stage MKMLModelDeleter completed in 19.15s
Pipeline stage MKMLModelDeleter completed in 16.64s
Shutdown handler de-registered
Shutdown handler de-registered
Shutdown handler de-registered
Stopping job with name rica40325-mistral-test1-v6-mkmlizer
Shutdown handler de-registered
cycy233-nemo-p-e-v1-c2_v1 status is now torndown due to DeploymentManager action