chaiml-snugstable1-5-12_59274

developer_uid: zonemercy

submission_id: chaiml-snugstable1-5-12_59274_v5

model_name: tempv1-5

model_group: ChaiML/SnugStable1.5-12b

status: torndown

timestamp: 2024-12-28T11:54:35+00:00

num_battles: 10772

num_wins: 5843

celo_rating: 1299.65

family_friendly_score: 0.5920000000000001

family_friendly_standard_error: 0.006950338121271511

submission_type: basic

model_repo: ChaiML/SnugStable1.5-12b0-l1e5r7

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6401820073120993, 'latency_mean': 1.5619990980625154, 'latency_p50': 1.574065923690796, 'latency_p90': 1.7225128173828126}, {'batch_size': 3, 'throughput': 1.2685936673708293, 'latency_mean': 2.3591006529331207, 'latency_p50': 2.3492389917373657, 'latency_p90': 2.5613005638122557}, {'batch_size': 5, 'throughput': 1.6115941375230873, 'latency_mean': 3.091689361333847, 'latency_p50': 3.102053165435791, 'latency_p90': 3.430113053321838}, {'batch_size': 6, 'throughput': 1.7136862640740864, 'latency_mean': 3.4813160562515257, 'latency_p50': 3.48268985748291, 'latency_p90': 3.9719266414642336}, {'batch_size': 8, 'throughput': 1.857247673203717, 'latency_mean': 4.276531111001969, 'latency_p50': 4.287944436073303, 'latency_p90': 4.843975019454956}, {'batch_size': 10, 'throughput': 1.9538476634694653, 'latency_mean': 5.081910462379455, 'latency_p50': 5.080609321594238, 'latency_p90': 5.748681545257568}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-5

is_internal_developer: True

language_model: ChaiML/SnugStable1.5-12b0-l1e5r7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2024-12-28

win_ratio: 0.54242480505013

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': 4, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}

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 chaiml-snugstable1-5-12-59274-v5-mkmlizer
Waiting for job on chaiml-snugstable1-5-12-59274-v5-mkmlizer to finish
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-59274-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-5-12-59274-v5-mkmlizer: Downloaded to shared memory in 34.669s
chaiml-snugstable1-5-12-59274-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzfj217ot, device:0
chaiml-snugstable1-5-12-59274-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-12-59274-v5-mkmlizer: quantized model in 37.659s
chaiml-snugstable1-5-12-59274-v5-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7 in 72.329s
chaiml-snugstable1-5-12-59274-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-12-59274-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-12-59274-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-12-59274-v5
chaiml-snugstable1-5-12-59274-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-59274-v5/config.json
chaiml-snugstable1-5-12-59274-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-59274-v5/special_tokens_map.json
chaiml-snugstable1-5-12-59274-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-59274-v5/tokenizer_config.json
chaiml-snugstable1-5-12-59274-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-59274-v5/tokenizer.json
chaiml-snugstable1-5-12-59274-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-5-12-59274-v5/flywheel_model.0.safetensors
Job chaiml-snugstable1-5-12-59274-v5-mkmlizer completed after 103.91s with status: succeeded
Stopping job with name chaiml-snugstable1-5-12-59274-v5-mkmlizer
Pipeline stage MKMLizer completed in 104.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-5-12-59274-v5
Waiting for inference service chaiml-snugstable1-5-12-59274-v5 to be ready
Failed to get response for submission function_lijit_2024-11-26: ('http://chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43284->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-snugstable1-5-12-59274-v5 ready after 301.13892674446106s
Pipeline stage MKMLDeployer completed in 301.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8420734405517578s
Received healthy response to inference request in 1.4888567924499512s
Received healthy response to inference request in 1.6988904476165771s
Received healthy response to inference request in 2.0213539600372314s
Received healthy response to inference request in 1.4911348819732666s
5 requests
0 failed requests
5th percentile: 1.4893124103546143
10th percentile: 1.4897680282592773
20th percentile: 1.4906792640686035
30th percentile: 1.5326859951019287
40th percentile: 1.615788221359253
50th percentile: 1.6988904476165771
60th percentile: 1.7561636447906495
70th percentile: 1.8134368419647215
80th percentile: 1.8779295444488526
90th percentile: 1.949641752243042
95th percentile: 1.9854978561401366
99th percentile: 2.0141827392578127
mean time: 1.7084619045257567
Pipeline stage StressChecker completed in 9.76s
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 0.62s
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 0.67s
Shutdown handler de-registered
chaiml-snugstable1-5-12_59274_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 0.09s
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 chaiml-snugstable1-5-12-59274-v5-profiler
Waiting for inference service chaiml-snugstable1-5-12-59274-v5-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 2515.84s
Shutdown handler de-registered
chaiml-snugstable1-5-12_59274_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-12_59274_v5 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12_59274_v5 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12_59274_v5 status is now torndown due to DeploymentManager action