developer_uid: chace9580
submission_id: jic062-instruct-v18-aggr_2098_v2
model_name: jic062-instruct-v18-aggr_2098_v2
model_group: jic062/instruct_v18_aggr
status: torndown
timestamp: 2024-08-30T03:30:07+00:00
num_battles: 10670
num_wins: 5593
celo_rating: 1249.1
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_v2
is_internal_developer: False
language_model: jic062/instruct_v18_aggresive_lr5_dp10_c3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-29
win_ratio: 0.5241799437675726
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-v2-mkmlizer
Waiting for job on jic062-instruct-v18-aggr-2098-v2-mkmlizer to finish
Stopping job with name jic062-instruct-v18-aggr-2098-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name jic062-instruct-v18-aggr-2098-v2-mkmlizer
Waiting for job on jic062-instruct-v18-aggr-2098-v2-mkmlizer to finish
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ /___/ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ Version: 0.10.1 ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ belonging to: ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ║ ║
jic062-instruct-v18-aggr-2098-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v18-aggr-2098-v2-mkmlizer: Downloaded to shared memory in 39.003s
jic062-instruct-v18-aggr-2098-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmkmex36o, device:0
jic062-instruct-v18-aggr-2098-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v18-aggr-2098-v2-mkmlizer: quantized model in 26.620s
jic062-instruct-v18-aggr-2098-v2-mkmlizer: Processed model jic062/instruct_v18_aggresive_lr5_dp10_c3 in 65.624s
jic062-instruct-v18-aggr-2098-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v18-aggr-2098-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v18-aggr-2098-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v2
jic062-instruct-v18-aggr-2098-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v2/config.json
jic062-instruct-v18-aggr-2098-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v2/special_tokens_map.json
jic062-instruct-v18-aggr-2098-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v2/tokenizer_config.json
jic062-instruct-v18-aggr-2098-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v2/tokenizer.json
jic062-instruct-v18-aggr-2098-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v18-aggr-2098-v2/flywheel_model.0.safetensors
jic062-instruct-v18-aggr-2098-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:06, 44.09it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 55.97it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:04, 62.11it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:03, 73.88it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:03, 78.74it/s] Loading 0: 18%|█▊ | 53/291 [00:00<00:03, 78.76it/s] Loading 0: 21%|██▏ | 62/291 [00:00<00:03, 75.92it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 76.37it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 79.59it/s] Loading 0: 30%|███ | 88/291 [00:02<00:10, 19.13it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 24.56it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:06, 30.50it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:04, 37.17it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 43.25it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 47.70it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:02, 52.41it/s] Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 55.58it/s] Loading 0: 55%|█████▍ | 160/291 [00:03<00:02, 56.41it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:02, 60.40it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 65.48it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:05, 19.95it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 25.69it/s] Loading 0: 70%|███████ | 205/291 [00:05<00:02, 32.04it/s] Loading 0: 74%|███████▎ | 214/291 [00:05<00:02, 38.34it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:01, 45.20it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:00, 59.68it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 69.25it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 69.60it/s] Loading 0: 92%|█████████▏| 269/291 [00:05<00:00, 75.92it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 79.44it/s]
Job jic062-instruct-v18-aggr-2098-v2-mkmlizer completed after 95.88s with status: succeeded
Stopping job with name jic062-instruct-v18-aggr-2098-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v18-aggr-2098-v2
Waiting for inference service jic062-instruct-v18-aggr-2098-v2 to be ready
Inference service jic062-instruct-v18-aggr-2098-v2 ready after 180.9982888698578s
Pipeline stage ISVCDeployer completed in 181.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6231300830841064s
Received healthy response to inference request in 1.8652231693267822s
Received healthy response to inference request in 1.6688084602355957s
Received healthy response to inference request in 2.042071580886841s
Received healthy response to inference request in 1.7900919914245605s
5 requests
0 failed requests
5th percentile: 1.6930651664733887
10th percentile: 1.7173218727111816
20th percentile: 1.7658352851867676
30th percentile: 1.8051182270050048
40th percentile: 1.8351706981658935
50th percentile: 1.8652231693267822
60th percentile: 1.9359625339508058
70th percentile: 2.0067018985748293
80th percentile: 2.158283281326294
90th percentile: 2.3907066822052
95th percentile: 2.506918382644653
99th percentile: 2.599887742996216
mean time: 1.9978650569915772
Pipeline stage StressChecker completed in 11.05s
jic062-instruct-v18-aggr_2098_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v18-aggr_2098_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v18-aggr_2098_v2 status is now torndown due to DeploymentManager action