zonemercy-base-story-v1

developer_uid: zonemercy

submission_id: zonemercy-base-story-v1_v5

model_name: 0906stv1-0

model_group: zonemercy/Base-Story-v1

status: torndown

timestamp: 2024-09-06T12:40:54+00:00

num_battles: 9131

num_wins: 4282

celo_rating: 1199.45

family_friendly_score: 0.0

submission_type: basic

model_repo: zonemercy/Base-Story-v1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 2

max_input_tokens: 1024

max_output_tokens: 128

latencies: [{'batch_size': 1, 'throughput': 0.3623854881946469, 'latency_mean': 2.759429579973221, 'latency_p50': 2.751216769218445, 'latency_p90': 2.9170730352401733}, {'batch_size': 3, 'throughput': 0.8469283959847729, 'latency_mean': 3.520107548236847, 'latency_p50': 3.5166234970092773, 'latency_p90': 3.7131749391555786}, {'batch_size': 5, 'throughput': 1.184902240516834, 'latency_mean': 4.189788210391998, 'latency_p50': 4.173055529594421, 'latency_p90': 4.516862559318542}, {'batch_size': 6, 'throughput': 1.3095472615500976, 'latency_mean': 4.546606720685959, 'latency_p50': 4.551595568656921, 'latency_p90': 4.937437844276428}, {'batch_size': 8, 'throughput': 1.495052548330821, 'latency_mean': 5.2813620078563694, 'latency_p50': 5.30181097984314, 'latency_p90': 5.69717698097229}, {'batch_size': 10, 'throughput': 1.6037403580522533, 'latency_mean': 6.18205144405365, 'latency_p50': 6.1881173849105835, 'latency_p90': 6.726597642898559}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 0906stv1-0

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: zonemercy/Base-Story-v1

model_size: 13B

ranking_group: single

throughput_3p7s: 0.96

us_pacific_date: 2024-09-06

win_ratio: 0.4689519220238747

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', 'User:', 'You:'], 'max_input_tokens': 1024, 'best_of': 2, 'max_output_tokens': 128}

formatter: {'memory_template': "Write a slice of story that takes place over the course of a single day in Bot's life. Use stream-of-consciousness narration to explore the character's thoughts and perceptions. Include poetic, impressionistic descriptions of the character's surroundings and sensations. Weave in memories and reflections that provide insight into the Bot's past and inner life. The scene should feel like part of a lived-in world, with the scene naturally existing in a wider story.\nBot's Name: {bot_name}\nBot's Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', '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 zonemercy-base-story-v1-v5-mkmlizer
Waiting for job on zonemercy-base-story-v1-v5-mkmlizer to finish
zonemercy-base-story-v1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-base-story-v1-v5-mkmlizer: ║     _____            __           __                                ║
zonemercy-base-story-v1-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-base-story-v1-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-base-story-v1-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-base-story-v1-v5-mkmlizer: ║       /___/                                                         ║
zonemercy-base-story-v1-v5-mkmlizer: ║                                                                     ║
zonemercy-base-story-v1-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-base-story-v1-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-base-story-v1-v5-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-base-story-v1-v5-mkmlizer: ║                                                                     ║
zonemercy-base-story-v1-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-base-story-v1-v5-mkmlizer: ║  belonging to:                                                      ║
zonemercy-base-story-v1-v5-mkmlizer: ║                                                                     ║
zonemercy-base-story-v1-v5-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-base-story-v1-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-base-story-v1-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-base-story-v1-v5-mkmlizer: ║                                                                     ║
zonemercy-base-story-v1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-lexical-nemo-_1518_v23: ('http://zonemercy-lexical-nemo-1518-v23-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\')]"}')
Failed to get response for submission zonemercy-base-story-v1_v3: ('http://zonemercy-base-story-v1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
Failed to get response for submission zonemercy-base-story-v1_v3: ('http://zonemercy-base-story-v1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
zonemercy-base-story-v1-v5-mkmlizer: Downloaded to shared memory in 56.529s
zonemercy-base-story-v1-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6s216419, device:0
zonemercy-base-story-v1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission zonemercy-lexical-nemo-_1518_v23: ('http://zonemercy-lexical-nemo-1518-v23-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\')]"}')
zonemercy-base-story-v1-v5-mkmlizer: quantized model in 40.467s
zonemercy-base-story-v1-v5-mkmlizer: Processed model zonemercy/Base-Story-v1 in 96.997s
zonemercy-base-story-v1-v5-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-base-story-v1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-base-story-v1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-base-story-v1-v5
zonemercy-base-story-v1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-base-story-v1-v5/config.json
zonemercy-base-story-v1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-base-story-v1-v5/special_tokens_map.json
zonemercy-base-story-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-base-story-v1-v5/tokenizer_config.json
zonemercy-base-story-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-base-story-v1-v5/tokenizer.json
zonemercy-base-story-v1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-base-story-v1-v5/flywheel_model.0.safetensors
Failed to get response for submission zonemercy-base-story-v1_v3: ('http://zonemercy-base-story-v1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
Job zonemercy-base-story-v1-v5-mkmlizer completed after 126.87s with status: succeeded
Stopping job with name zonemercy-base-story-v1-v5-mkmlizer
Pipeline stage MKMLizer completed in 128.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-base-story-v1-v5
Waiting for inference service zonemercy-base-story-v1-v5 to be ready
Failed to get response for submission zonemercy-lexical-nemo-_1518_v23: ('http://zonemercy-lexical-nemo-1518-v23-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\')]"}')
Failed to get response for submission zonemercy-lexical-nemo-_1518_v23: ('http://zonemercy-lexical-nemo-1518-v23-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\')]"}')
Failed to get response for submission zonemercy-base-story-v1_v3: ('http://zonemercy-base-story-v1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
Inference service zonemercy-base-story-v1-v5 ready after 151.02170825004578s
Pipeline stage MKMLDeployer completed in 151.34s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission zonemercy-base-story-v1_v4: ('http://zonemercy-base-story-v1-v4-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 3.457693099975586s
Received healthy response to inference request in 2.6705269813537598s
Received healthy response to inference request in 2.9269299507141113s
Received healthy response to inference request in 1.474039077758789s
Received healthy response to inference request in 2.8003058433532715s
5 requests
0 failed requests
5th percentile: 1.7133366584777832
10th percentile: 1.9526342391967773
20th percentile: 2.4312294006347654
30th percentile: 2.696482753753662
40th percentile: 2.7483942985534666
50th percentile: 2.8003058433532715
60th percentile: 2.8509554862976074
70th percentile: 2.9016051292419434
80th percentile: 3.0330825805664063
90th percentile: 3.245387840270996
95th percentile: 3.351540470123291
99th percentile: 3.436462574005127
mean time: 2.6658989906311037
Pipeline stage StressChecker completed in 14.09s
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 9.70s
Shutdown handler de-registered
zonemercy-base-story-v1_v5 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 zonemercy-base-story-v1-v5-profiler
Waiting for inference service zonemercy-base-story-v1-v5-profiler to be ready
Inference service zonemercy-base-story-v1-v5-profiler ready after 150.34540224075317s
Pipeline stage MKMLProfilerDeployer completed in 150.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-base-story-v1-v5-profiler-predictor-00001-deploysdt8r:/code/chaiverse_profiler_1725626947 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-base-story-v1-v5-profiler-predictor-00001-deploysdt8r --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725626947 && python profiles.py profile --best_of_n 2 --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 128 --summary /code/chaiverse_profiler_1725626947/summary.json'
kubectl exec -it zonemercy-base-story-v1-v5-profiler-predictor-00001-deploysdt8r --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725626947/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1376.56s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-base-story-v1-v5-profiler is running
Tearing down inference service zonemercy-base-story-v1-v5-profiler
Service zonemercy-base-story-v1-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.64s
Shutdown handler de-registered
zonemercy-base-story-v1_v5 status is now inactive due to auto deactivation removed underperforming models
run pipeline stage %s
Cleaning model data from model cache
Running pipeline stage MKMLModelDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Cleaning model data from S3
Checking if service zonemercy-base-story-v1-v1 is running
admin requested tearing down of zonemercy-base-story-v1_v5
Running pipeline stage MKMLDeleter
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Tearing down inference service trace2333-mistral-trial6-v2
Tearing down inference service trace2333-mistral-trial6-v3
Cleaning model data from S3
run pipeline stage %s
run pipeline %s
Tearing down inference service trace2333-mistral-trial6-v4
Cleaning model data from model cache
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-base-story-v1_v6
Checking if service zonemercy-base-story-v1-v2 is running
Tearing down inference service trace2333-mistral-trial6-v5
Tearing down inference service trace2333-mistral-trial6-v6
Tearing down inference service zonemercy-base-story-v1-v1
Service trace2333-mistral-trial6-v2 has been torndown
Service trace2333-mistral-trial6-v3 has been torndown
Cleaning model data from model cache
Running pipeline stage MKMLDeleter
run pipeline stage %s
Service trace2333-mistral-trial6-v4 has been torndown
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-base-story-v1_v7
Service trace2333-mistral-trial6-v5 has been torndown
Service trace2333-mistral-trial6-v6 has been torndown
Service zonemercy-base-story-v1-v1 has been torndown
Pipeline stage MKMLDeleter completed in 34.06s
Pipeline stage MKMLDeleter completed in 30.97s
Checking if service zonemercy-base-story-v1-v3 is running
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 28.44s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage MKMLDeleter completed in 27.06s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLDeleter completed in 24.18s
Pipeline stage MKMLDeleter completed in 20.96s
run pipeline stage %s
admin requested tearing down of zonemercy-base-story-v1_v8
run pipeline stage %s
Checking if service zonemercy-base-story-v1-v4 is running
Running pipeline stage MKMLDeleter
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
run pipeline %s
run pipeline stage %s
Tearing down inference service zonemercy-base-story-v1-v2
Tearing down inference service zonemercy-base-story-v1-v3
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
Checking if service zonemercy-base-story-v1-v5 is running
Running pipeline stage MKMLModelDeleter
admin requested tearing down of zonemercy-lexical-nemo-_1518_v23
Deleting key sao10k-hanami-1-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd5w-dl1w-ultr-6985-v2/config.json from bucket guanaco-mkml-models
Deleting key jic062-instruct-v19-con-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-hina-1-v1/config.json from bucket guanaco-mkml-models
Deleting key riverise-feedback-dpo-merged-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-mistral-align-8132-v3/config.json from bucket guanaco-mkml-models
Deleting key trace2333-mistral-align-8132-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-mistral-align-8132-v1/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLDeleter
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Service zonemercy-base-story-v1-v2 has been torndown
Service zonemercy-base-story-v1-v3 has been torndown
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Cleaning model data from model cache
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
admin requested tearing down of zonemercy-base-story-v1_v5
Cleaning model data from S3
Cleaning model data from model cache
run pipeline stage %s
%s, retrying in %s seconds...
Shutdown handler not registered because Python interpreter is not running in the main thread
Cleaning model data from model cache
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
run pipeline %s
admin requested tearing down of zonemercy-base-story-v1_v6
%s, retrying in %s seconds...
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
run pipeline stage %s
Deleting key trace2333-mistral-align-8132-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-mistral-align-8132-v3/config.json from bucket guanaco-mkml-models
Deleting key trace2333-mistral-align-8132-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-mistral-trial6-v2/config.json from bucket guanaco-mkml-models
Checking if service zonemercy-base-story-v1-v2 is running
Shutdown handler not registered because Python interpreter is not running in the main thread
Checking if service zonemercy-base-story-v1-v4 is running
Deleting key trace2333-mistral-trial5-v2/config.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Running pipeline stage MKMLDeleter
Deleting key trace2333-mistral-align-8132-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-mistral-trial6-v4/config.json from bucket guanaco-mkml-models
zonemercy-base-story-v1_v5 status is now torndown due to DeploymentManager action