developer_uid: chai_backend_admin
submission_id: chaiml-lexical-nemov8-1k1e5_v38
model_name: tempv1-3
model_group: ChaiML/Lexical-Nemov8-1k
status: torndown
timestamp: 2024-11-12T12:29:16+00:00
num_battles: 10889
num_wins: 5510
celo_rating: 1253.24
family_friendly_score: 0.5682
family_friendly_standard_error: 0.0070049805138915275
submission_type: basic
model_repo: ChaiML/Lexical-Nemov8-1k1e5
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6231362062205169, 'latency_mean': 1.6046959733963013, 'latency_p50': 1.6142354011535645, 'latency_p90': 1.7589295625686645}, {'batch_size': 3, 'throughput': 1.2354818192829036, 'latency_mean': 2.4138098204135896, 'latency_p50': 2.4111839532852173, 'latency_p90': 2.6699421882629393}, {'batch_size': 5, 'throughput': 1.5644630572960951, 'latency_mean': 3.182641426324844, 'latency_p50': 3.172813653945923, 'latency_p90': 3.5167927980422973}, {'batch_size': 6, 'throughput': 1.6524204681613601, 'latency_mean': 3.6096011281013487, 'latency_p50': 3.6156797409057617, 'latency_p90': 4.0586728096008295}, {'batch_size': 8, 'throughput': 1.8247728110963797, 'latency_mean': 4.354843657016755, 'latency_p50': 4.319145321846008, 'latency_p90': 4.964234471321106}, {'batch_size': 10, 'throughput': 1.8898819387017018, 'latency_mean': 5.255092095136643, 'latency_p50': 5.308000326156616, 'latency_p90': 5.9118043899536135}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-3
is_internal_developer: True
language_model: ChaiML/Lexical-Nemov8-1k1e5
model_size: 13B
ranking_group: single
throughput_3p7s: 1.69
us_pacific_date: 2024-11-12
win_ratio: 0.5060152447424006
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': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|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-lexical-nemov8-1k1e5-v38-mkmlizer
Waiting for job on chaiml-lexical-nemov8-1k1e5-v38-mkmlizer to finish
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║     _____            __           __                                ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║       /___/                                                         ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║                                                                     ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  Version: 0.11.33                                                   ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║                                                                     ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  belonging to:                                                      ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║                                                                     ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ║                                                                     ║
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: Downloaded to shared memory in 92.660s
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj9m8cewd, device:0
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: quantized model in 41.533s
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: Processed model ChaiML/Lexical-Nemov8-1k1e5 in 134.193s
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v38
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v38/config.json
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v38/special_tokens_map.json
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v38/tokenizer_config.json
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v38/tokenizer.json
chaiml-lexical-nemov8-1k1e5-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v38/flywheel_model.0.safetensors
Job chaiml-lexical-nemov8-1k1e5-v38-mkmlizer completed after 165.9s with status: succeeded
Stopping job with name chaiml-lexical-nemov8-1k1e5-v38-mkmlizer
Pipeline stage MKMLizer completed in 166.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-lexical-nemov8-1k1e5-v38
Waiting for inference service chaiml-lexical-nemov8-1k1e5-v38 to be ready
Inference service chaiml-lexical-nemov8-1k1e5-v38 ready after 190.69254064559937s
Pipeline stage MKMLDeployer completed in 191.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1413443088531494s
Received healthy response to inference request in 1.4643864631652832s
Received healthy response to inference request in 1.5661964416503906s
Received healthy response to inference request in 1.1996710300445557s
Received healthy response to inference request in 1.439732551574707s
5 requests
0 failed requests
5th percentile: 1.247683334350586
10th percentile: 1.2956956386566163
20th percentile: 1.3917202472686767
30th percentile: 1.4446633338928223
40th percentile: 1.4545248985290526
50th percentile: 1.4643864631652832
60th percentile: 1.5051104545593261
70th percentile: 1.545834445953369
80th percentile: 1.6812260150909424
90th percentile: 1.911285161972046
95th percentile: 2.0263147354125977
99th percentile: 2.118338394165039
mean time: 1.5622661590576172
Pipeline stage StressChecker completed in 9.18s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 5.26s
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 2.16s
Shutdown handler de-registered
chaiml-lexical-nemov8-1k1e5_v38 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 2425.00s
Shutdown handler de-registered
chaiml-lexical-nemov8-1k1e5_v38 status is now inactive due to auto deactivation removed underperforming models
chaiml-lexical-nemov8-1k1e5_v38 status is now torndown due to DeploymentManager action