developer_uid: Riverise
submission_id: riverise-mistral-0920_v1
model_name: riverise-mistral-0920_v1
model_group: Riverise/mistral_0920
status: torndown
timestamp: 2024-09-21T09:37:37+00:00
num_battles: 369175
num_wins: 186910
celo_rating: 1252.5
family_friendly_score: 0.0
submission_type: basic
model_repo: Riverise/mistral_0920
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6177076668110909, 'latency_mean': 1.6188281464576721, 'latency_p50': 1.6115690469741821, 'latency_p90': 1.7930610179901123}, {'batch_size': 3, 'throughput': 1.094128885426839, 'latency_mean': 2.732712619304657, 'latency_p50': 2.7297329902648926, 'latency_p90': 2.9984692573547362}, {'batch_size': 5, 'throughput': 1.2487816199445123, 'latency_mean': 3.9953776848316194, 'latency_p50': 4.033215880393982, 'latency_p90': 4.414471745491028}, {'batch_size': 6, 'throughput': 1.264901662735218, 'latency_mean': 4.713031898736954, 'latency_p50': 4.715177416801453, 'latency_p90': 5.342811131477356}, {'batch_size': 8, 'throughput': 1.2461788216325778, 'latency_mean': 6.382394552230835, 'latency_p50': 6.344717621803284, 'latency_p90': 7.213940453529358}, {'batch_size': 10, 'throughput': 1.2048170189021443, 'latency_mean': 8.251523329019546, 'latency_p50': 8.244447112083435, 'latency_p90': 9.231536245346069}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: riverise-mistral-0920_v1
is_internal_developer: False
language_model: Riverise/mistral_0920
model_size: 13B
ranking_group: single
throughput_3p7s: 1.22
us_pacific_date: 2024-09-21
win_ratio: 0.506291054378005
generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 30, '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': "{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
Failed to get response for submission mistralai-mistral-small-_5341_v6: ('http://mistralai-mistral-small-5341-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Starting job with name riverise-mistral-0920-v1-mkmlizer
Waiting for job on riverise-mistral-0920-v1-mkmlizer to finish
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 riverise-mistral-0920-v1-mkmlizer
Stopping job with name riverise-mistral-0920-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-mistral-0920-v1-mkmlizer
Waiting for job on riverise-mistral-0920-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
riverise-mistral-0920-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-mistral-0920-v1-mkmlizer: ║     _____            __           __                                ║
riverise-mistral-0920-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-mistral-0920-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-mistral-0920-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-mistral-0920-v1-mkmlizer: ║       /___/                                                         ║
riverise-mistral-0920-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-mistral-0920-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-mistral-0920-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-mistral-0920-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-mistral-0920-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-mistral-0920-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-mistral-0920-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-mistral-0920-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-mistral-0920-v1-mkmlizer: ║                                                                     ║
riverise-mistral-0920-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission mistralai-mistral-small_5341_v11: ('http://mistralai-mistral-small-5341-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
riverise-mistral-0920-v1-mkmlizer: Downloaded to shared memory in 44.298s
riverise-mistral-0920-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsx37qbma, device:0
riverise-mistral-0920-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-small-_5341_v6: ('http://mistralai-mistral-small-5341-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
riverise-mistral-0920-v1-mkmlizer: quantized model in 37.760s
riverise-mistral-0920-v1-mkmlizer: Processed model Riverise/mistral_0920 in 82.059s
riverise-mistral-0920-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-mistral-0920-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-mistral-0920-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-mistral-0920-v1
riverise-mistral-0920-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-mistral-0920-v1/config.json
riverise-mistral-0920-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-mistral-0920-v1/special_tokens_map.json
riverise-mistral-0920-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-mistral-0920-v1/tokenizer_config.json
riverise-mistral-0920-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-mistral-0920-v1/tokenizer.json
riverise-mistral-0920-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-mistral-0920-v1/flywheel_model.0.safetensors
Job riverise-mistral-0920-v1-mkmlizer completed after 118.27s with status: succeeded
Stopping job with name riverise-mistral-0920-v1-mkmlizer
Pipeline stage MKMLizer completed in 120.35s
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 riverise-mistral-0920-v1
Waiting for inference service riverise-mistral-0920-v1 to be ready
Failed to get response for submission mistralai-mistral-small-_5341_v6: ('http://mistralai-mistral-small-5341-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission mistralai-mistral-small_5341_v11: ('http://mistralai-mistral-small-5341-v11-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
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
Failed to get response for submission mistralai-mistral-small_5341_v19: ('http://mistralai-mistral-small-5341-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:47388->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 riverise-mistral-0920-v1 ready after 200.5111541748047s
Failed to get response for submission mistralai-mistral-small_5341_v19: ('http://mistralai-mistral-small-5341-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38032->127.0.0.1:8080: read: connection reset by peer\n')
Pipeline stage MKMLDeployer completed in 207.00s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 3.0352590084075928s
Received healthy response to inference request in 3.186897039413452s
Received healthy response to inference request in 1.869006872177124s
Received healthy response to inference request in 3.347688674926758s
Received healthy response to inference request in 2.0792665481567383s
5 requests
0 failed requests
5th percentile: 1.9110588073730468
10th percentile: 1.9531107425689698
20th percentile: 2.0372146129608155
30th percentile: 2.270465040206909
40th percentile: 2.652862024307251
50th percentile: 3.0352590084075928
60th percentile: 3.0959142208099366
70th percentile: 3.1565694332122805
80th percentile: 3.2190553665161135
90th percentile: 3.2833720207214356
95th percentile: 3.3155303478240965
99th percentile: 3.3412570095062257
mean time: 2.703623628616333
Pipeline stage StressChecker completed in 22.92s
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 4.52s
Shutdown handler de-registered
riverise-mistral-0920_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-mistral-0920-v1-profiler
Waiting for inference service riverise-mistral-0920-v1-profiler to be ready
Inference service riverise-mistral-0920-v1-profiler ready after 190.41895580291748s
Pipeline stage MKMLProfilerDeployer completed in 193.44s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/riverise-mistral-0920-v1-profiler-predictor-00001-deployme85ccr:/code/chaiverse_profiler_1726912057 --namespace tenant-chaiml-guanaco
kubectl exec -it riverise-mistral-0920-v1-profiler-predictor-00001-deployme85ccr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726912057 && 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_1726912057/summary.json'
kubectl exec -it riverise-mistral-0920-v1-profiler-predictor-00001-deployme85ccr --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726912057/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1167.57s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-mistral-0920-v1-profiler is running
Tearing down inference service riverise-mistral-0920-v1-profiler
Service riverise-mistral-0920-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 5.31s
Shutdown handler de-registered
riverise-mistral-0920_v1 status is now inactive due to auto deactivation removed underperforming models
riverise-mistral-0920_v1 status is now torndown due to DeploymentManager action