developer_uid: chace9580
submission_id: jic062-instruct-v18-aggr_2098_v1
model_name: jic062-instruct-v18-aggr_2098_v1
model_group: jic062/instruct_v18_aggr
status: torndown
timestamp: 2024-08-16T23:53:00+00:00
num_battles: 11232
num_wins: 6103
celo_rating: 1252.05
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v18_aggresive_lr5_dp10_c3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-instruct-v18-aggr_2098_v1
is_internal_developer: False
language_model: jic062/instruct_v18_aggresive_lr5_dp10_c3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-16
win_ratio: 0.5433582621082621
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-aggr-2098-v1-mkmlizer
Waiting for job on jic062-instruct-v18-aggr-2098-v1-mkmlizer to finish
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  Version: 0.9.11                                                    ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v18-aggr-2098-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v18-aggr-2098-v1-mkmlizer: Downloaded to shared memory in 42.546s
jic062-instruct-v18-aggr-2098-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxsi0hvu8, device:0
jic062-instruct-v18-aggr-2098-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v18-aggr-2098-v1-mkmlizer: quantized model in 27.308s
jic062-instruct-v18-aggr-2098-v1-mkmlizer: Processed model jic062/instruct_v18_aggresive_lr5_dp10_c3 in 69.854s
jic062-instruct-v18-aggr-2098-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v18-aggr-2098-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v1
jic062-instruct-v18-aggr-2098-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v1/config.json
jic062-instruct-v18-aggr-2098-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v1/special_tokens_map.json
jic062-instruct-v18-aggr-2098-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v1/tokenizer_config.json
jic062-instruct-v18-aggr-2098-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v1/tokenizer.json
jic062-instruct-v18-aggr-2098-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v1/flywheel_model.0.safetensors
jic062-instruct-v18-aggr-2098-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 49.33it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:04, 63.63it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 69.48it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 71.76it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 73.44it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 71.76it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 74.34it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:02, 76.58it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:02, 73.03it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:10, 18.91it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:08, 23.31it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:06, 30.28it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 36.06it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 43.51it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 50.34it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:02, 55.52it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 61.31it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 67.03it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:01, 71.65it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 73.55it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 74.26it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:04, 20.32it/s]
Loading 0:  68%|██████▊   | 198/291 [00:04<00:03, 23.77it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 28.74it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 37.06it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 45.58it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 53.90it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:00, 60.14it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 64.94it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 70.14it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 74.32it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 75.38it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 79.12it/s]
                                                            

Job jic062-instruct-v18-aggr-2098-v1-mkmlizer completed after 98.04s with status: succeeded
Stopping job with name jic062-instruct-v18-aggr-2098-v1-mkmlizer
Pipeline stage MKMLizer completed in 99.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v18-aggr-2098-v1
Waiting for inference service jic062-instruct-v18-aggr-2098-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Tearing down inference service jic062-instruct-v18-aggr-2098-v1
%s, retrying in %s seconds...
Creating inference service jic062-instruct-v18-aggr-2098-v1
Ignoring service jic062-instruct-v18-aggr-2098-v1 already deployed
Waiting for inference service jic062-instruct-v18-aggr-2098-v1 to be ready
Tearing down inference service jic062-instruct-v18-aggr-2098-v1
%s, retrying in %s seconds...
Creating inference service jic062-instruct-v18-aggr-2098-v1
Waiting for inference service jic062-instruct-v18-aggr-2098-v1 to be ready
Inference service jic062-instruct-v18-aggr-2098-v1 ready after 100.80131793022156s
Pipeline stage ISVCDeployer completed in 717.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0226082801818848s
Received healthy response to inference request in 2.3665266036987305s
Received healthy response to inference request in 1.7803401947021484s
Received healthy response to inference request in 1.4680566787719727s
Received healthy response to inference request in 1.6998729705810547s
5 requests
0 failed requests
5th percentile: 1.514419937133789
10th percentile: 1.5607831954956055
20th percentile: 1.6535097122192384
30th percentile: 1.7159664154052734
40th percentile: 1.748153305053711
50th percentile: 1.7803401947021484
60th percentile: 1.877247428894043
70th percentile: 1.9741546630859375
80th percentile: 2.091391944885254
90th percentile: 2.2289592742919924
95th percentile: 2.2977429389953614
99th percentile: 2.3527698707580567
mean time: 1.8674809455871582
Pipeline stage StressChecker completed in 10.02s
jic062-instruct-v18-aggr_2098_v1 status is now deployed due to DeploymentManager action
jic062-instruct-v18-aggr_2098_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v18-aggr_2098_v1 status is now torndown due to DeploymentManager action