developer_uid: shiroe40
submission_id: cycy233-nemo-p-v0-c3_v1
model_name: auto
model_group: cycy233/nemo-p-v0-c3
status: torndown
timestamp: 2024-09-15T07:57:26+00:00
num_battles: 11143
num_wins: 5584
celo_rating: 1252.07
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/nemo-p-v0-c3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6913431406689075, 'latency_mean': 1.446397076845169, 'latency_p50': 1.4453126192092896, 'latency_p90': 1.615378189086914}, {'batch_size': 3, 'throughput': 1.3171187005330536, 'latency_mean': 2.268307292461395, 'latency_p50': 2.2548402547836304, 'latency_p90': 2.5269261598587036}, {'batch_size': 5, 'throughput': 1.5548590365263242, 'latency_mean': 3.1931720423698424, 'latency_p50': 3.1589908599853516, 'latency_p90': 3.6651414394378663}, {'batch_size': 6, 'throughput': 1.6037056573304218, 'latency_mean': 3.7180467104911803, 'latency_p50': 3.7195159196853638, 'latency_p90': 4.171194720268249}, {'batch_size': 8, 'throughput': 1.6097521434446491, 'latency_mean': 4.94724126458168, 'latency_p50': 4.939053177833557, 'latency_p90': 5.613978600502014}, {'batch_size': 10, 'throughput': 1.5348768971113693, 'latency_mean': 6.47322505235672, 'latency_p50': 6.4783841371536255, 'latency_p90': 7.241090536117554}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: auto
is_internal_developer: False
language_model: cycy233/nemo-p-v0-c3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.61
us_pacific_date: 2024-09-15
win_ratio: 0.5011217804899937
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': ['<s>', '\n'], '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-v0-c3-v1-mkmlizer
Waiting for job on cycy233-nemo-p-v0-c3-v1-mkmlizer to finish
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', '')
cycy233-nemo-p-v0-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ /___/ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ║ ║
cycy233-nemo-p-v0-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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', '')
cycy233-nemo-p-v0-c3-v1-mkmlizer: Downloaded to shared memory in 57.249s
cycy233-nemo-p-v0-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb1qczo84, device:0
cycy233-nemo-p-v0-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-nemo-p-v0-c3-v1-mkmlizer: quantized model in 36.184s
cycy233-nemo-p-v0-c3-v1-mkmlizer: Processed model cycy233/nemo-p-v0-c3 in 93.433s
cycy233-nemo-p-v0-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-nemo-p-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-nemo-p-v0-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-nemo-p-v0-c3-v1
cycy233-nemo-p-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c3-v1/special_tokens_map.json
cycy233-nemo-p-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c3-v1/config.json
cycy233-nemo-p-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c3-v1/tokenizer_config.json
cycy233-nemo-p-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-nemo-p-v0-c3-v1/tokenizer.json
cycy233-nemo-p-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-nemo-p-v0-c3-v1/flywheel_model.0.safetensors
cycy233-nemo-p-v0-c3-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 36.70it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:05, 64.90it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:04, 73.62it/s] Loading 0: 11%|█ | 40/363 [00:00<00:03, 85.14it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:04, 77.54it/s] Loading 0: 16%|█▌ | 58/363 [00:00<00:03, 79.37it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:14, 20.92it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:12, 23.94it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 29.30it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:07, 37.01it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:06, 42.85it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 48.06it/s] Loading 0: 32%|███▏ | 116/363 [00:02<00:04, 58.10it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 60.74it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 66.83it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.24it/s] Loading 0: 42%|████▏ | 152/363 [00:04<00:07, 27.37it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.73it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 40.32it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 53.83it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 55.97it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:02, 62.24it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 65.90it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:01, 75.70it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:05, 22.30it/s] Loading 0: 66%|██████▌ | 238/363 [00:06<00:04, 25.38it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:03, 34.24it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 40.11it/s] Loading 0: 74%|███████▍ | 268/363 [00:06<00:02, 47.17it/s] Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 52.81it/s] Loading 0: 79%|███████▉ | 286/363 [00:06<00:01, 57.39it/s] Loading 0: 81%|████████▏ | 295/363 [00:06<00:01, 61.07it/s] Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 20.97it/s] Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 26.09it/s] Loading 0: 90%|█████████ | 328/363 [00:08<00:00, 38.13it/s] Loading 0: 93%|█████████▎| 337/363 [00:08<00:00, 44.82it/s] Loading 0: 95%|█████████▌| 346/363 [00:08<00:00, 48.07it/s] Loading 0: 98%|█████████▊| 355/363 [00:08<00:00, 53.36it/s] Loading 0: 100%|██████████| 363/363 [00:15<00:00, 4.45it/s]
Job cycy233-nemo-p-v0-c3-v1-mkmlizer completed after 115.08s with status: succeeded
Stopping job with name cycy233-nemo-p-v0-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.84s
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-v0-c3-v1
Waiting for inference service cycy233-nemo-p-v0-c3-v1 to be ready
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', '')
Inference service cycy233-nemo-p-v0-c3-v1 ready after 171.9603419303894s
Pipeline stage MKMLDeployer completed in 172.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0874640941619873s
Failed to get response for submission blend_hokok_2024-09-09: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Received healthy response to inference request in 1.9097020626068115s
Received healthy response to inference request in 1.7109966278076172s
Received healthy response to inference request in 3.6309385299682617s
Received healthy response to inference request in 3.233093023300171s
5 requests
0 failed requests
5th percentile: 1.750737714767456
10th percentile: 1.790478801727295
20th percentile: 1.8699609756469726
30th percentile: 1.9452544689178466
40th percentile: 2.016359281539917
50th percentile: 2.0874640941619873
60th percentile: 2.545715665817261
70th percentile: 3.003967237472534
80th percentile: 3.312662124633789
90th percentile: 3.4718003273010254
95th percentile: 3.5513694286346436
99th percentile: 3.615024709701538
mean time: 2.5144388675689697
Pipeline stage StressChecker completed in 22.60s
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 6.13s
Shutdown handler de-registered
cycy233-nemo-p-v0-c3_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-v0-c3-v1-profiler
Waiting for inference service cycy233-nemo-p-v0-c3-v1-profiler to be ready
Inference service cycy233-nemo-p-v0-c3-v1-profiler ready after 170.40050387382507s
Pipeline stage MKMLProfilerDeployer completed in 170.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-nemo-p-v0-c3-v1-profiler-predictor-00001-deploymenkdjqd:/code/chaiverse_profiler_1726387572 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-nemo-p-v0-c3-v1-profiler-predictor-00001-deploymenkdjqd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726387572 && 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_1726387572/summary.json'
kubectl exec -it cycy233-nemo-p-v0-c3-v1-profiler-predictor-00001-deploymenkdjqd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726387572/summary.json'
Pipeline stage MKMLProfilerRunner completed in 960.93s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-nemo-p-v0-c3-v1-profiler is running
Tearing down inference service cycy233-nemo-p-v0-c3-v1-profiler
Service cycy233-nemo-p-v0-c3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 8.43s
Shutdown handler de-registered
cycy233-nemo-p-v0-c3_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-nemo-p-v0-c3_v1 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
admin requested tearing down of chaiml-0916-intent-roman_3299_v3
Running pipeline stage MKMLModelDeleter
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