submission_id: jic062-instruct-v14-v15_v4
developer_uid: chace9580
alignment_samples: 9748
alignment_score: 0.7869845591041597
best_of: 16
celo_rating: 1246.56
display_name: jic062-instruct-v14-v15_v4
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}
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', '|eot_id|', '<|end_of_text|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: jic062/instruct_v14_v15
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_v14_v15
model_name: jic062-instruct-v14-v15_v4
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_v14_v15
model_size: 8B
num_battles: 9748
num_wins: 4979
propriety_score: 0.7100115074798619
propriety_total_count: 869.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-08-27T02:30:41+00:00
us_pacific_date: 2024-08-26
win_ratio: 0.5107714402954452
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v14-v15-v4-mkmlizer
Waiting for job on jic062-instruct-v14-v15-v4-mkmlizer to finish
Stopping job with name jic062-instruct-v14-v15-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v14-v15-v4-mkmlizer
Waiting for job on jic062-instruct-v14-v15-v4-mkmlizer to finish
jic062-instruct-v14-v15-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v14-v15-v4-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ /___/ ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ Version: 0.10.1 ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ belonging to: ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v14-v15-v4-mkmlizer: ║ ║
jic062-instruct-v14-v15-v4-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
jic062-instruct-v14-v15-v4-mkmlizer: Downloaded to shared memory in 43.015s
jic062-instruct-v14-v15-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsas373lt, device:0
jic062-instruct-v14-v15-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v14-v15-v4-mkmlizer: quantized model in 25.787s
jic062-instruct-v14-v15-v4-mkmlizer: Processed model jic062/instruct_v14_v15 in 68.802s
jic062-instruct-v14-v15-v4-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v14-v15-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v14-v15-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v14-v15-v4
jic062-instruct-v14-v15-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v4/config.json
jic062-instruct-v14-v15-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v4/special_tokens_map.json
jic062-instruct-v14-v15-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v4/tokenizer_config.json
jic062-instruct-v14-v15-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v4/tokenizer.json
jic062-instruct-v14-v15-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v14-v15-v4/flywheel_model.0.safetensors
jic062-instruct-v14-v15-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 52.13it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 70.36it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 71.99it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 75.52it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 79.45it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 80.34it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 89.61it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 87.15it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.68it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 29.71it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 35.92it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.02it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 50.75it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 57.85it/s] Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 66.82it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 70.59it/s] Loading 0: 55%|█████▍ | 159/291 [00:02<00:01, 77.56it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 74.06it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 77.61it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 22.30it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 28.57it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 35.51it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 41.40it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 48.38it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 55.64it/s] Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 62.36it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 66.43it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 69.16it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 72.71it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 76.66it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 77.62it/s]
Job jic062-instruct-v14-v15-v4-mkmlizer completed after 95.88s with status: succeeded
Stopping job with name jic062-instruct-v14-v15-v4-mkmlizer
Pipeline stage MKMLizer completed in 97.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.70s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v14-v15-v4
Waiting for inference service jic062-instruct-v14-v15-v4 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
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
Failed to get response for submission zonemercy-lexical-nemo-_1518_v18: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:35572->127.0.0.1:8080: read: connection reset by peer\n')
Inference service jic062-instruct-v14-v15-v4 ready after 171.5607476234436s
Pipeline stage ISVCDeployer completed in 172.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.124502658843994s
Received healthy response to inference request in 1.8888261318206787s
Received healthy response to inference request in 1.5311081409454346s
Received healthy response to inference request in 1.7494635581970215s
Received healthy response to inference request in 1.5800812244415283s
5 requests
0 failed requests
5th percentile: 1.5409027576446532
10th percentile: 1.5506973743438721
20th percentile: 1.5702866077423097
30th percentile: 1.613957691192627
40th percentile: 1.6817106246948241
50th percentile: 1.7494635581970215
60th percentile: 1.8052085876464843
70th percentile: 1.8609536170959473
80th percentile: 1.9359614372253418
90th percentile: 2.030232048034668
95th percentile: 2.077367353439331
99th percentile: 2.1150755977630613
mean time: 1.7747963428497315
Pipeline stage StressChecker completed in 11.02s
jic062-instruct-v14-v15_v4 status is now deployed due to DeploymentManager action
Connection pool is full, discarding connection: %s. Connection pool size: %s
jic062-instruct-v14-v15_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics