developer_uid: shiroe40
submission_id: cycy233-nemo-p-v2-c4_v1
model_name: auto
model_group: cycy233/nemo-p-v2-c4
status: torndown
timestamp: 2024-09-18T02:37:59+00:00
num_battles: 10930
num_wins: 5327
celo_rating: 1242.61
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/nemo-p-v2-c4
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6963484401215456, 'latency_mean': 1.4360005056858063, 'latency_p50': 1.438572883605957, 'latency_p90': 1.5981045961380005}, {'batch_size': 3, 'throughput': 1.3387734047067654, 'latency_mean': 2.2328175950050353, 'latency_p50': 2.2119230031967163, 'latency_p90': 2.5063180208206175}, {'batch_size': 5, 'throughput': 1.5808286176872057, 'latency_mean': 3.1405912268161775, 'latency_p50': 3.136347770690918, 'latency_p90': 3.598155069351196}, {'batch_size': 6, 'throughput': 1.6208971536423114, 'latency_mean': 3.6818117117881775, 'latency_p50': 3.7038419246673584, 'latency_p90': 4.118337225914001}, {'batch_size': 8, 'throughput': 1.632216148283133, 'latency_mean': 4.878930468559265, 'latency_p50': 4.921693801879883, 'latency_p90': 5.611328291893005}, {'batch_size': 10, 'throughput': 1.5577498387247826, 'latency_mean': 6.3678972780704495, 'latency_p50': 6.404324173927307, 'latency_p90': 7.2225262165069575}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: auto
is_internal_developer: False
language_model: cycy233/nemo-p-v2-c4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2024-09-17
win_ratio: 0.48737419945105215
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': 512, 'best_of': 8, 'max_output_tokens': 64}
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}
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-v2-c4-v1-mkmlizer
Waiting for job on cycy233-nemo-p-v2-c4-v1-mkmlizer to finish
cycy233-nemo-p-v2-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ║ ║
cycy233-nemo-p-v2-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-nemo-p-v2-c4-v1-mkmlizer: Downloaded to shared memory in 45.471s
cycy233-nemo-p-v2-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptmds2mzy, device:0
cycy233-nemo-p-v2-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-v2-c4-v1-mkmlizer: quantized model in 35.034s
cycy233-nemo-p-v2-c4-v1-mkmlizer: Processed model cycy233/nemo-p-v2-c4 in 80.506s
cycy233-nemo-p-v2-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v2-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v2-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v2-c4-v1
cycy233-nemo-p-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v2-c4-v1/config.json
cycy233-nemo-p-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v2-c4-v1/special_tokens_map.json
cycy233-nemo-p-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v2-c4-v1/tokenizer_config.json
cycy233-nemo-p-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v2-c4-v1/tokenizer.json
cycy233-nemo-p-v2-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v2-c4-v1/flywheel_model.0.safetensors
cycy233-nemo-p-v2-c4-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 38.03it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:04, 69.60it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:03, 93.84it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:03, 93.60it/s] Loading 0: 15%|█▍ | 53/363 [00:00<00:03, 89.76it/s] Loading 0: 17%|█▋ | 62/363 [00:01<00:14, 21.31it/s] Loading 0: 19%|█▉ | 70/363 [00:01<00:11, 26.60it/s] Loading 0: 23%|██▎ | 85/363 [00:02<00:07, 39.40it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 48.78it/s] Loading 0: 31%|███ | 112/363 [00:02<00:04, 61.42it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:03, 67.86it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 73.04it/s] Loading 0: 39%|███▉ | 143/363 [00:03<00:09, 23.91it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:06, 32.86it/s] Loading 0: 47%|████▋ | 169/363 [00:03<00:04, 40.86it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 53.44it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 61.46it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 72.81it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:05, 27.57it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 36.99it/s] Loading 0: 69%|██████▉ | 250/363 [00:05<00:02, 44.67it/s] Loading 0: 73%|███████▎ | 265/363 [00:05<00:01, 55.77it/s] Loading 0: 76%|███████▋ | 277/363 [00:05<00:01, 62.00it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:00, 73.33it/s] Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 28.57it/s] Loading 0: 86%|████████▌ | 313/363 [00:07<00:01, 33.49it/s] Loading 0: 90%|█████████ | 328/363 [00:07<00:00, 44.67it/s] Loading 0: 93%|█████████▎| 337/363 [00:07<00:00, 50.32it/s] Loading 0: 96%|█████████▌| 349/363 [00:07<00:00, 58.92it/s] Loading 0: 100%|██████████| 363/363 [00:14<00:00, 6.03it/s]
Job cycy233-nemo-p-v2-c4-v1-mkmlizer completed after 117.15s with status: succeeded
Stopping job with name cycy233-nemo-p-v2-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-nemo-p-v2-c4-v1
Waiting for inference service cycy233-nemo-p-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
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', '')
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', '')
Inference service cycy233-nemo-p-v2-c4-v1 ready after 190.87677192687988s
Pipeline stage MKMLDeployer completed in 191.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2723281383514404s
Received healthy response to inference request in 2.138577938079834s
Received healthy response to inference request in 1.7740201950073242s
Received healthy response to inference request in 1.7054202556610107s
Received healthy response to inference request in 1.8484582901000977s
5 requests
0 failed requests
5th percentile: 1.7191402435302734
10th percentile: 1.732860231399536
20th percentile: 1.7603002071380616
30th percentile: 1.788907814025879
40th percentile: 1.8186830520629882
50th percentile: 1.8484582901000977
60th percentile: 1.9645061492919922
70th percentile: 2.0805540084838867
80th percentile: 2.1653279781341555
90th percentile: 2.218828058242798
95th percentile: 2.245578098297119
99th percentile: 2.266978130340576
mean time: 1.9477609634399413
Pipeline stage StressChecker completed in 10.52s
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 4.63s
Shutdown handler de-registered
cycy233-nemo-p-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 0.12s
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 cycy233-nemo-p-v2-c4-v1-profiler
Waiting for inference service cycy233-nemo-p-v2-c4-v1-profiler to be ready
Inference service cycy233-nemo-p-v2-c4-v1-profiler ready after 190.4480175971985s
Pipeline stage MKMLProfilerDeployer completed in 190.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-v2-c4-v1-profiler-predictor-00001-deploymenmmddq:/code/chaiverse_profiler_1726627638 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v2-c4-v1-profiler-predictor-00001-deploymenmmddq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726627638 && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726627638/summary.json'
kubectl exec -it cycy233-nemo-p-v2-c4-v1-profiler-predictor-00001-deploymenmmddq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726627638/summary.json'
Pipeline stage MKMLProfilerRunner completed in 942.32s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v2-c4-v1-profiler is running
Tearing down inference service cycy233-nemo-p-v2-c4-v1-profiler
Service cycy233-nemo-p-v2-c4-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
Shutdown handler de-registered
cycy233-nemo-p-v2-c4_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v2-c4_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.83s
cycy233-nemo-p-v0-c2_v1 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Running pipeline stage MKMLModelDeleter
run pipeline %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v2-c4_v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.82s
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 3.82s
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
cycy233-nemo-p-v0-c2_v2 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline %s
admin requested tearing down of cycy233-nemo-p-v3-c1_v1
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 4.32s
Pipeline stage MKMLModelDeleter completed in 4.10s
cycy233-nemo-p-v0-c3_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
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-0916-intent-suppo_6584_v1
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-nemo-p-v3-c2_v1
run pipeline stage %s
Shutdown handler de-registered
Pipeline stage MKMLDeleter completed in 4.97s
Pipeline stage %s skipped, reason=%s
cycy233-nemo-p-v0-c3_v2 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLModelDeleter completed in 5.00s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v2
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
admin requested tearing down of cycy233-nemo-p-v3-c4_v1
cycy233-nemo-p-v1-c1_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 6.15s
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
run pipeline %s
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 5.85s
run pipeline %s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0916-intent-suppo_6584_v4
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 6.11s
admin requested tearing down of deverdever-heavenly-mouse-v20_v1
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
cycy233-nemo-p-v1-c2_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 6.48s
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of chaiml-0917-bot-dominant_6324_v2
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of epiculous-azure-dusk-bas_2210_v1
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 8.17s
Running pipeline stage MKMLDeleter
cycy233-nemo-p-v1-c2_v2 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Connection pool is full, discarding connection: %s. Connection pool size: %s
admin requested tearing down of chaiml-0917-bot-dominant_6324_v3
Running pipeline stage MKMLModelDeleter
Connection pool is full, discarding connection: %s. Connection pool size: %s