submission_id: jic062-instruct-g32-lr25_4505_v2
developer_uid: chace9580
alignment_samples: 9803
alignment_score: 0.8777195668093213
best_of: 16
celo_rating: 1243.76
display_name: jic062-instruct-g32-lr25_4505_v2
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', '<|end_of_text|>', '|eot_id|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: jic062/instruct_g32_lr25_dp7_c3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct_g32_lr25
model_name: jic062-instruct-g32-lr25_4505_v2
model_num_parameters: 8030261248.0
model_repo: jic062/instruct_g32_lr25_dp7_c3
model_size: 8B
num_battles: 9803
num_wins: 4966
propriety_score: 0.7192575406032483
propriety_total_count: 862.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-08-27T02:29:48+00:00
us_pacific_date: 2024-08-26
win_ratio: 0.5065796184841375
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-g32-lr25-4505-v2-mkmlizer
Waiting for job on jic062-instruct-g32-lr25-4505-v2-mkmlizer to finish
Stopping job with name jic062-instruct-g32-lr25-4505-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-g32-lr25-4505-v2-mkmlizer
Waiting for job on jic062-instruct-g32-lr25-4505-v2-mkmlizer to finish
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ _____ __ __ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ /___/ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ Version: 0.10.1 ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ belonging to: ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ║ ║
jic062-instruct-g32-lr25-4505-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-g32-lr25-4505-v2-mkmlizer: Downloaded to shared memory in 34.517s
jic062-instruct-g32-lr25-4505-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6tyksvme, device:0
jic062-instruct-g32-lr25-4505-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
jic062-instruct-g32-lr25-4505-v2-mkmlizer: quantized model in 25.589s
jic062-instruct-g32-lr25-4505-v2-mkmlizer: Processed model jic062/instruct_g32_lr25_dp7_c3 in 60.106s
jic062-instruct-g32-lr25-4505-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-g32-lr25-4505-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-g32-lr25-4505-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-g32-lr25-4505-v2
jic062-instruct-g32-lr25-4505-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-g32-lr25-4505-v2/config.json
jic062-instruct-g32-lr25-4505-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-g32-lr25-4505-v2/special_tokens_map.json
jic062-instruct-g32-lr25-4505-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-g32-lr25-4505-v2/tokenizer_config.json
jic062-instruct-g32-lr25-4505-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-g32-lr25-4505-v2/tokenizer.json
jic062-instruct-g32-lr25-4505-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-g32-lr25-4505-v2/flywheel_model.0.safetensors
jic062-instruct-g32-lr25-4505-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:05, 53.57it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 71.52it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:03, 77.64it/s] Loading 0: 12%|█▏ | 34/291 [00:00<00:03, 79.10it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 80.66it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 82.13it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 83.47it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 91.50it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:07, 25.75it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.21it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 37.13it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 44.28it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 50.24it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 56.40it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 62.83it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 68.54it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 71.46it/s] Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 73.13it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 77.32it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 83.29it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:04, 22.81it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 27.84it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 34.61it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 41.62it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 48.05it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 55.16it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 61.42it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 66.41it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 69.67it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 72.20it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 69.52it/s] Loading 0: 100%|██████████| 291/291 [00:10<00:00, 5.09it/s]
Job jic062-instruct-g32-lr25-4505-v2-mkmlizer completed after 84.51s with status: succeeded
Stopping job with name jic062-instruct-g32-lr25-4505-v2-mkmlizer
Pipeline stage MKMLizer completed in 87.05s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-g32-lr25-4505-v2
Waiting for inference service jic062-instruct-g32-lr25-4505-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
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
Inference service jic062-instruct-g32-lr25-4505-v2 ready after 170.9312903881073s
Pipeline stage ISVCDeployer completed in 172.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.184185266494751s
Received healthy response to inference request in 1.877511978149414s
Received healthy response to inference request in 1.3388707637786865s
Received healthy response to inference request in 1.5022201538085938s
Received healthy response to inference request in 1.891000747680664s
5 requests
0 failed requests
5th percentile: 1.371540641784668
10th percentile: 1.4042105197906494
20th percentile: 1.4695502758026122
30th percentile: 1.5772785186767577
40th percentile: 1.727395248413086
50th percentile: 1.877511978149414
60th percentile: 1.8829074859619142
70th percentile: 1.888302993774414
80th percentile: 1.9496376514434814
90th percentile: 2.066911458969116
95th percentile: 2.1255483627319336
99th percentile: 2.1724578857421877
mean time: 1.7587577819824218
Pipeline stage StressChecker completed in 9.76s
jic062-instruct-g32-lr25_4505_v2 status is now deployed due to DeploymentManager action
jic062-instruct-g32-lr25_4505_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics