developer_uid: zonemercy
submission_id: chaiml-snugstable2-12b0_49557_v1
model_name: tempv1-3
model_group: ChaiML/SnugStable2-12b0-
status: torndown
timestamp: 2025-01-06T08:17:31+00:00
num_battles: 12586
num_wins: 6799
celo_rating: 1291.05
family_friendly_score: 0.5926
family_friendly_standard_error: 0.0069487443470025575
submission_type: basic
model_repo: ChaiML/SnugStable2-12b0-l1e5r7b25
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6418789656084806, 'latency_mean': 1.5578282213211059, 'latency_p50': 1.5582425594329834, 'latency_p90': 1.7201692819595338}, {'batch_size': 3, 'throughput': 1.2475348268505746, 'latency_mean': 2.4003222966194153, 'latency_p50': 2.398552656173706, 'latency_p90': 2.6392826557159426}, {'batch_size': 5, 'throughput': 1.518372263334624, 'latency_mean': 3.2682735192775727, 'latency_p50': 3.25935435295105, 'latency_p90': 3.7163048505783083}, {'batch_size': 6, 'throughput': 1.6187652719978767, 'latency_mean': 3.6810211420059202, 'latency_p50': 3.6623995304107666, 'latency_p90': 4.068422508239746}, {'batch_size': 8, 'throughput': 1.698495954980242, 'latency_mean': 4.686333960294723, 'latency_p50': 4.714865565299988, 'latency_p90': 5.251374435424805}, {'batch_size': 10, 'throughput': 1.7473546508717144, 'latency_mean': 5.675852638483048, 'latency_p50': 5.726527452468872, 'latency_p90': 6.3694534540176395}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-3
is_internal_developer: True
language_model: ChaiML/SnugStable2-12b0-l1e5r7b25
model_size: 13B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2025-01-06
win_ratio: 0.5402034006038455
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': ['<|eot_id|>', 'You:', 'Bot:', '####', '\n', '</s>', '<|im_end|>', 'User:'], 'max_input_tokens': 768, 'best_of': 8, '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-snugstable2-12b0-49557-v1-mkmlizer
Waiting for job on chaiml-snugstable2-12b0-49557-v1-mkmlizer to finish
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ║                                                                     ║
chaiml-snugstable2-12b0-49557-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable2-12b0-49557-v1-mkmlizer: Downloaded to shared memory in 47.741s
chaiml-snugstable2-12b0-49557-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpra87upny, device:0
chaiml-snugstable2-12b0-49557-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission rirv938-viral-40k-1248-_40308_v2: HTTPConnectionPool(host='rirv938-viral-40k-1248-40308-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-snugstable2-12b0-49557-v1-mkmlizer: quantized model in 38.642s
chaiml-snugstable2-12b0-49557-v1-mkmlizer: Processed model ChaiML/SnugStable2-12b0-l1e5r7b25 in 86.383s
chaiml-snugstable2-12b0-49557-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable2-12b0-49557-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable2-12b0-49557-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable2-12b0-49557-v1
chaiml-snugstable2-12b0-49557-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-49557-v1/config.json
chaiml-snugstable2-12b0-49557-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-49557-v1/special_tokens_map.json
chaiml-snugstable2-12b0-49557-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-49557-v1/tokenizer_config.json
chaiml-snugstable2-12b0-49557-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable2-12b0-49557-v1/tokenizer.json
chaiml-snugstable2-12b0-49557-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable2-12b0-49557-v1/flywheel_model.0.safetensors
Job chaiml-snugstable2-12b0-49557-v1-mkmlizer completed after 124.74s with status: succeeded
Stopping job with name chaiml-snugstable2-12b0-49557-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.24s
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-snugstable2-12b0-49557-v1
Waiting for inference service chaiml-snugstable2-12b0-49557-v1 to be ready
Failed to get response for submission rirv938-viral-40k-1248-_40308_v2: HTTPConnectionPool(host='rirv938-viral-40k-1248-40308-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-viral-40k-1248-_40308_v2: HTTPConnectionPool(host='rirv938-viral-40k-1248-40308-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-viral-40k-1248-_40308_v2: HTTPConnectionPool(host='rirv938-viral-40k-1248-40308-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-viral-40k-1248-_40308_v2: HTTPConnectionPool(host='rirv938-viral-40k-1248-40308-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-snugstable2-12b0-49557-v1 ready after 351.23536491394043s
Pipeline stage MKMLDeployer completed in 351.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8694777488708496s
Received healthy response to inference request in 1.6597888469696045s
Received healthy response to inference request in 1.5727250576019287s
Received healthy response to inference request in 1.5457055568695068s
Received healthy response to inference request in 6.892883062362671s
5 requests
0 failed requests
5th percentile: 1.5511094570159911
10th percentile: 1.5565133571624756
20th percentile: 1.5673211574554444
30th percentile: 1.590137815475464
40th percentile: 1.6249633312225342
50th percentile: 1.6597888469696045
60th percentile: 1.7436644077301025
70th percentile: 1.8275399684906006
80th percentile: 2.874158811569215
90th percentile: 4.883520936965943
95th percentile: 5.888201999664306
99th percentile: 6.6919468498229975
mean time: 2.708116054534912
Pipeline stage StressChecker completed in 15.32s
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 0.73s
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 0.70s
Shutdown handler de-registered
chaiml-snugstable2-12b0_49557_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 2590.05s
Shutdown handler de-registered
chaiml-snugstable2-12b0_49557_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable2-12b0_49557_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable2-12b0_49557_v1 status is now torndown due to DeploymentManager action
chaiml-snugstable2-12b0_49557_v1 status is now torndown due to DeploymentManager action