submission_id: rinen0721-mistral12b-exp5_v1
developer_uid: rinen0721
best_of: 8
celo_rating: 1248.19
display_name: rinen0721-mistral12b-exp5_v1
family_friendly_score: 0.5674
family_friendly_standard_error: 0.007006528955196004
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': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rinen0721/Mistral12b-exp5
latencies: [{'batch_size': 1, 'throughput': 0.605320167924484, 'latency_mean': 1.6519217705726623, 'latency_p50': 1.6542634963989258, 'latency_p90': 1.811401653289795}, {'batch_size': 3, 'throughput': 1.106213308569736, 'latency_mean': 2.7037637388706206, 'latency_p50': 2.700139045715332, 'latency_p90': 3.01259503364563}, {'batch_size': 5, 'throughput': 1.344500611475846, 'latency_mean': 3.7055870127677917, 'latency_p50': 3.7019556760787964, 'latency_p90': 4.0958603620529175}, {'batch_size': 6, 'throughput': 1.392717611637045, 'latency_mean': 4.2881111395359035, 'latency_p50': 4.319886922836304, 'latency_p90': 4.820456719398498}, {'batch_size': 8, 'throughput': 1.4583134096664738, 'latency_mean': 5.447754828929901, 'latency_p50': 5.48000693321228, 'latency_p90': 6.168739891052246}, {'batch_size': 10, 'throughput': 1.506694284854632, 'latency_mean': 6.576491302251815, 'latency_p50': 6.593212008476257, 'latency_p90': 7.453585743904114}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: rinen0721/Mistral12b-exp
model_name: rinen0721-mistral12b-exp5_v1
model_num_parameters: 12772070400.0
model_repo: rinen0721/Mistral12b-exp5
model_size: 13B
num_battles: 21752
num_wins: 11012
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.35
timestamp: 2024-11-11T15:30:44+00:00
us_pacific_date: 2024-11-11
win_ratio: 0.5062522986392056
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 rinen0721-mistral12b-exp5-v1-mkmlizer
Waiting for job on rinen0721-mistral12b-exp5-v1-mkmlizer to finish
rinen0721-mistral12b-exp5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ /___/ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ Version: 0.11.33 ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ belonging to: ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ║ ║
rinen0721-mistral12b-exp5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-nemo-20241010-tie_5991_v2: ('http://chaiml-nemo-20241010-tie-5991-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:34548->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
Failed to get response for submission zonemercy-lexical-viral-_1979_v5: ('http://zonemercy-lexical-viral-1979-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:55320->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
rinen0721-mistral12b-exp5-v1-mkmlizer: Downloaded to shared memory in 130.479s
rinen0721-mistral12b-exp5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa5bvcasd, device:0
rinen0721-mistral12b-exp5-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
rinen0721-mistral12b-exp5-v1-mkmlizer: quantized model in 36.885s
rinen0721-mistral12b-exp5-v1-mkmlizer: Processed model rinen0721/Mistral12b-exp5 in 167.365s
rinen0721-mistral12b-exp5-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral12b-exp5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral12b-exp5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v1
rinen0721-mistral12b-exp5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v1/config.json
rinen0721-mistral12b-exp5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v1/special_tokens_map.json
rinen0721-mistral12b-exp5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v1/tokenizer_config.json
rinen0721-mistral12b-exp5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v1/tokenizer.json
rinen0721-mistral12b-exp5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral12b-exp5-v1/flywheel_model.0.safetensors
Job rinen0721-mistral12b-exp5-v1-mkmlizer completed after 197.72s with status: succeeded
Stopping job with name rinen0721-mistral12b-exp5-v1-mkmlizer
Pipeline stage MKMLizer completed in 198.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-mistral12b-exp5-v1
Waiting for inference service rinen0721-mistral12b-exp5-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
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 rinen0721-mistral12b-exp5-v1 ready after 180.75384616851807s
Pipeline stage MKMLDeployer completed in 181.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1579184532165527s
Received healthy response to inference request in 1.6962461471557617s
Received healthy response to inference request in 1.7512519359588623s
Received healthy response to inference request in 1.6004219055175781s
Received healthy response to inference request in 0.9591310024261475s
5 requests
0 failed requests
5th percentile: 1.0873891830444335
10th percentile: 1.2156473636627196
20th percentile: 1.472163724899292
30th percentile: 1.6195867538452149
40th percentile: 1.6579164505004882
50th percentile: 1.6962461471557617
60th percentile: 1.718248462677002
70th percentile: 1.7402507781982421
80th percentile: 1.8325852394104005
90th percentile: 1.9952518463134765
95th percentile: 2.0765851497650147
99th percentile: 2.141651792526245
mean time: 1.6329938888549804
Pipeline stage StressChecker completed in 9.70s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.12s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.15s
Shutdown handler de-registered
rinen0721-mistral12b-exp5_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rinen0721-mistral12b-exp5-v1-profiler
Waiting for inference service rinen0721-mistral12b-exp5-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2936.91s
Shutdown handler de-registered
rinen0721-mistral12b-exp5_v1 status is now inactive due to auto deactivation removed underperforming models
Deleting key rinen0721-mistral12b-exp6-v2/special_tokens_map.json from bucket guanaco-mkml-models
rinen0721-mistral12b-exp5_v1 status is now torndown due to DeploymentManager action