developer_uid: chai_backend_admin
submission_id: chaiml-lexical-nemo-v4-1k1e5_v26
model_name: tempv1-2
model_group: ChaiML/Lexical-Nemo-v4-1
status: torndown
timestamp: 2024-11-13T14:09:48+00:00
num_battles: 16734
num_wins: 8273
celo_rating: 1245.91
family_friendly_score: 0.5676
family_friendly_standard_error: 0.007006143589736082
submission_type: basic
model_repo: ChaiML/Lexical-Nemo-v4-1k1e5
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6258150196622303, 'latency_mean': 1.5978560853004455, 'latency_p50': 1.5929818153381348, 'latency_p90': 1.7620410203933716}, {'batch_size': 3, 'throughput': 1.2260140709965208, 'latency_mean': 2.4385656762123107, 'latency_p50': 2.4406505823135376, 'latency_p90': 2.702165126800537}, {'batch_size': 5, 'throughput': 1.5267955262345587, 'latency_mean': 3.2495697581768037, 'latency_p50': 3.226367235183716, 'latency_p90': 3.7286179065704346}, {'batch_size': 6, 'throughput': 1.6368526467474824, 'latency_mean': 3.635789830684662, 'latency_p50': 3.646709442138672, 'latency_p90': 4.057483053207397}, {'batch_size': 8, 'throughput': 1.778194847442523, 'latency_mean': 4.475816115140915, 'latency_p50': 4.486960411071777, 'latency_p90': 5.148503518104553}, {'batch_size': 10, 'throughput': 1.851501007230287, 'latency_mean': 5.360119770765305, 'latency_p50': 5.381699323654175, 'latency_p90': 6.07929949760437}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-2
is_internal_developer: True
language_model: ChaiML/Lexical-Nemo-v4-1k1e5
model_size: 13B
ranking_group: single
throughput_3p7s: 1.66
us_pacific_date: 2024-11-13
win_ratio: 0.494382693916577
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': "{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}
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-nemo-v4-1k1e5-v26-mkmlizer
Waiting for job on chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer to finish
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-nemo-v4-1k1e5-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ _____ __ __ ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ /___/ ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ Version: 0.11.33 ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ https://mk1.ai ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ belonging to: ║
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-lexical-nemo-v4-1k1e5-v26-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
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
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ Chai Research Corp. ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ║ ║
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: Downloaded to shared memory in 66.585s
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxj1ot2gp, device:0
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: quantized model in 44.345s
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: Processed model ChaiML/Lexical-Nemo-v4-1k1e5 in 110.930s
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexical-nemo-v4-1k1e5-v26
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexical-nemo-v4-1k1e5-v26/special_tokens_map.json
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexical-nemo-v4-1k1e5-v26/config.json
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexical-nemo-v4-1k1e5-v26/tokenizer_config.json
chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexical-nemo-v4-1k1e5-v26/tokenizer.json
Job chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer completed after 166.67s with status: succeeded
Stopping job with name chaiml-lexical-nemo-v4-1k1e5-v26-mkmlizer
Pipeline stage MKMLizer completed in 167.23s
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 chaiml-lexical-nemo-v4-1k1e5-v26
Waiting for inference service chaiml-lexical-nemo-v4-1k1e5-v26 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
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-lexical-nemo-v4-1k1e5-v26 ready after 200.7442569732666s
Pipeline stage MKMLDeployer completed in 201.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.10823655128479s
Received healthy response to inference request in 1.5247766971588135s
Received healthy response to inference request in 1.4049162864685059s
Received healthy response to inference request in 1.4204492568969727s
Received healthy response to inference request in 1.4000492095947266s
5 requests
0 failed requests
5th percentile: 1.4010226249694824
10th percentile: 1.4019960403442382
20th percentile: 1.40394287109375
30th percentile: 1.4080228805541992
40th percentile: 1.414236068725586
50th percentile: 1.4204492568969727
60th percentile: 1.462180233001709
70th percentile: 1.5039112091064453
80th percentile: 1.641468667984009
90th percentile: 1.8748526096343994
95th percentile: 1.9915445804595946
99th percentile: 2.084898157119751
mean time: 1.5716856002807618
Pipeline stage StressChecker completed in 9.30s
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 2.57s
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 2.44s
Shutdown handler de-registered
chaiml-lexical-nemo-v4-1k1e5_v26 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 2477.43s
Shutdown handler de-registered
chaiml-lexical-nemo-v4-1k1e5_v26 status is now inactive due to auto deactivation removed underperforming models
chaiml-lexical-nemo-v4-1k1e5_v26 status is now torndown due to DeploymentManager action