chaiml-snugstable1-2-12b_8172

developer_uid: zonemercy

submission_id: chaiml-snugstable1-2-12b_8172_v1

model_name: tempv1-1

model_group: ChaiML/SnugStable1.2-12b

status: torndown

timestamp: 2024-12-26T21:44:16+00:00

num_battles: 11016

num_wins: 6128

celo_rating: 1303.79

family_friendly_score: 0.5918

family_friendly_standard_error: 0.0069508669962818305

submission_type: basic

model_repo: ChaiML/SnugStable1.2-12b0-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': 0.638271449284062, 'latency_mean': 1.5666325283050537, 'latency_p50': 1.562401533126831, 'latency_p90': 1.729912233352661}, {'batch_size': 3, 'throughput': 1.2780757370023275, 'latency_mean': 2.341119955778122, 'latency_p50': 2.3382190465927124, 'latency_p90': 2.5665902614593503}, {'batch_size': 5, 'throughput': 1.6292220195902818, 'latency_mean': 3.0509419059753418, 'latency_p50': 3.026288866996765, 'latency_p90': 3.481124234199524}, {'batch_size': 6, 'throughput': 1.7322723316186994, 'latency_mean': 3.432472401857376, 'latency_p50': 3.4444442987442017, 'latency_p90': 3.8298011541366574}, {'batch_size': 8, 'throughput': 1.912558307881941, 'latency_mean': 4.160744122266769, 'latency_p50': 4.127679705619812, 'latency_p90': 4.78083906173706}, {'batch_size': 10, 'throughput': 1.9823736556437381, 'latency_mean': 5.006535036563873, 'latency_p50': 5.037771105766296, 'latency_p90': 5.620377135276794}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-1

is_internal_developer: True

language_model: ChaiML/SnugStable1.2-12b0-l1e5r7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.82

us_pacific_date: 2024-12-26

win_ratio: 0.5562817719680465

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####', 'Bot:', '\n', 'You:', 'User:', '<|im_end|>', '</s>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-snugstable1-2-12b-8172-v1-mkmlizer
Waiting for job on chaiml-snugstable1-2-12b-8172-v1-mkmlizer to finish
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: Downloaded to shared memory in 54.264s
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaza15gv3, device:0
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-2-12b-8172-v1
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-2-12b-8172-v1/config.json
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-2-12b-8172-v1/special_tokens_map.json
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-2-12b-8172-v1/tokenizer_config.json
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-2-12b-8172-v1/tokenizer.json
chaiml-snugstable1-2-12b-8172-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-2-12b-8172-v1/flywheel_model.0.safetensors
Job chaiml-snugstable1-2-12b-8172-v1-mkmlizer completed after 125.44s with status: succeeded
Stopping job with name chaiml-snugstable1-2-12b-8172-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.88s
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-snugstable1-2-12b-8172-v1
Waiting for inference service chaiml-snugstable1-2-12b-8172-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
Inference service chaiml-snugstable1-2-12b-8172-v1 ready after 271.1750087738037s
Pipeline stage MKMLDeployer completed in 271.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.340946912765503s
Received healthy response to inference request in 1.782519817352295s
Received healthy response to inference request in 1.3628449440002441s
Received healthy response to inference request in 1.5736992359161377s
Received healthy response to inference request in 1.482666015625s
5 requests
0 failed requests
5th percentile: 1.3868091583251954
10th percentile: 1.4107733726501466
20th percentile: 1.4587018013000488
30th percentile: 1.5008726596832276
40th percentile: 1.5372859477996825
50th percentile: 1.5736992359161377
60th percentile: 1.6572274684906005
70th percentile: 1.7407557010650634
80th percentile: 1.8942052364349367
90th percentile: 2.11757607460022
95th percentile: 2.2292614936828614
99th percentile: 2.3186098289489747
mean time: 1.708535385131836
Pipeline stage StressChecker completed in 9.92s
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 0.67s
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 0.65s
Shutdown handler de-registered
chaiml-snugstable1-2-12b_8172_v1 status is now deployed due to DeploymentManager action
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 2408.81s
Shutdown handler de-registered
chaiml-snugstable1-2-12b_8172_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-2-12b_8172_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.84s
chaiml-snugstable1-2-12b_8172_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s
chaiml-snugstable1-2-12b_8172_v1 status is now torndown due to DeploymentManager action