developer_uid: chace9580
submission_id: jic062-instruct-v18-4-5w_v2
model_name: jic062-instruct-v18-4-5w_v2
model_group: jic062/instruct_v18_4.5w
status: torndown
timestamp: 2024-08-30T03:30:29+00:00
num_battles: 10672
num_wins: 5590
celo_rating: 1249.55
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v18_4.5w
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-instruct-v18-4-5w_v2
is_internal_developer: False
language_model: jic062/instruct_v18_4.5w
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-29
win_ratio: 0.5238005997001499
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', '<|end_of_text|>', '|eot_id|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v18-4-5w-v2-mkmlizer
Waiting for job on jic062-instruct-v18-4-5w-v2-mkmlizer to finish
jic062-instruct-v18-4-5w-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v18-4-5w-v2-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v18-4-5w-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v18-4-5w-v2-mkmlizer: Downloaded to shared memory in 39.226s
jic062-instruct-v18-4-5w-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_pehmtrb, device:0
jic062-instruct-v18-4-5w-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v18-4-5w-v2-mkmlizer: quantized model in 26.050s
jic062-instruct-v18-4-5w-v2-mkmlizer: Processed model jic062/instruct_v18_4.5w in 65.276s
jic062-instruct-v18-4-5w-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v18-4-5w-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v18-4-5w-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v2
jic062-instruct-v18-4-5w-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v2/config.json
jic062-instruct-v18-4-5w-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v2/special_tokens_map.json
jic062-instruct-v18-4-5w-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v2/tokenizer_config.json
jic062-instruct-v18-4-5w-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v2/tokenizer.json
jic062-instruct-v18-4-5w-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v18-4-5w-v2/flywheel_model.0.safetensors
Job jic062-instruct-v18-4-5w-v2-mkmlizer completed after 95.26s with status: succeeded
Stopping job with name jic062-instruct-v18-4-5w-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v18-4-5w-v2
Waiting for inference service jic062-instruct-v18-4-5w-v2 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
Inference service jic062-instruct-v18-4-5w-v2 ready after 180.8932240009308s
Pipeline stage ISVCDeployer completed in 181.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1524555683135986s
Received healthy response to inference request in 1.883857011795044s
Failed to get response for submission blend_filor_2024-08-16: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45490->127.0.0.1:8080: read: connection reset by peer\n')
Received healthy response to inference request in 2.4521963596343994s
Received healthy response to inference request in 1.6923940181732178s
Received healthy response to inference request in 2.0905210971832275s
5 requests
0 failed requests
5th percentile: 1.730686616897583
10th percentile: 1.7689792156219482
20th percentile: 1.8455644130706788
30th percentile: 1.9251898288726808
40th percentile: 2.007855463027954
50th percentile: 2.0905210971832275
60th percentile: 2.2351912021636964
70th percentile: 2.3798613071441648
80th percentile: 2.5922482013702393
90th percentile: 2.872351884841919
95th percentile: 3.012403726577759
99th percentile: 3.1244451999664307
mean time: 2.2542848110198976
Pipeline stage StressChecker completed in 13.22s
jic062-instruct-v18-4-5w_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v18-4-5w_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v18-4-5w_v2 status is now torndown due to DeploymentManager action