developer_uid: chace9580
submission_id: jic062-instruct-v14-v15_v2
model_name: jic062-instruct_resubmit
model_group: jic062/instruct_v14_v15
status: torndown
timestamp: 2024-08-12T07:30:21+00:00
num_battles: 12010
num_wins: 6189
celo_rating: 1234.36
family_friendly_score: 0.0
submission_type: basic
model_repo: jic062/instruct_v14_v15
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jic062-instruct_resubmit
is_internal_developer: False
language_model: jic062/instruct_v14_v15
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-12
win_ratio: 0.5153205661948377
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, 'reward_max_token_input': 256}
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}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jic062-instruct-v14-v15-v2-mkmlizer
Waiting for job on jic062-instruct-v14-v15-v2-mkmlizer to finish
jic062-instruct-v14-v15-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v14-v15-v2-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v14-v15-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v14-v15-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v14-v15-v2-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v14-v15-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  Version: 0.9.9                                                     ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v14-v15-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v14-v15-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v14-v15-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v14-v15-v2-mkmlizer: ║                                                                     ║
jic062-instruct-v14-v15-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v14-v15-v2-mkmlizer: Downloaded to shared memory in 26.629s
jic062-instruct-v14-v15-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphzoyjvtx, device:0
jic062-instruct-v14-v15-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v14-v15-v2-mkmlizer: quantized model in 25.678s
jic062-instruct-v14-v15-v2-mkmlizer: Processed model jic062/instruct_v14_v15 in 52.307s
jic062-instruct-v14-v15-v2-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v14-v15-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v14-v15-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v14-v15-v2
jic062-instruct-v14-v15-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v2/config.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v2/special_tokens_map.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v14-v15-v2/tokenizer_config.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v14-v15-v2/flywheel_model.0.safetensors
jic062-instruct-v14-v15-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jic062-instruct-v14-v15-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 53.89it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 85.53it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 79.18it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 81.79it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:02, 86.87it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 91.73it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 89.02it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:08, 24.51it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 34.74it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 42.32it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 48.54it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 60.73it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 63.95it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 68.61it/s]
Loading 0:  58%|█████▊    | 168/291 [00:02<00:01, 77.48it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:01, 76.63it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 23.56it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 33.97it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 41.60it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 53.07it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 58.30it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 65.66it/s]
Loading 0:  89%|████████▊ | 258/291 [00:04<00:00, 71.49it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 65.17it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 76.04it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jic062-instruct-v14-v15-v2-mkmlizer:   warnings.warn(
jic062-instruct-v14-v15-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jic062-instruct-v14-v15-v2-mkmlizer:   warnings.warn(
jic062-instruct-v14-v15-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jic062-instruct-v14-v15-v2-mkmlizer: Saving duration: 1.490s
jic062-instruct-v14-v15-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 13.513s
jic062-instruct-v14-v15-v2-mkmlizer: creating bucket guanaco-reward-models
jic062-instruct-v14-v15-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jic062-instruct-v14-v15-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/config.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/special_tokens_map.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/tokenizer_config.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/merges.txt
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/vocab.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/tokenizer.json
jic062-instruct-v14-v15-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jic062-instruct-v14-v15-v2_reward/reward.tensors
Job jic062-instruct-v14-v15-v2-mkmlizer completed after 105.5s with status: succeeded
Stopping job with name jic062-instruct-v14-v15-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jic062-instruct-v14-v15-v2
Waiting for inference service jic062-instruct-v14-v15-v2 to be ready
Inference service jic062-instruct-v14-v15-v2 ready after 211.24863862991333s
Pipeline stage ISVCDeployer completed in 213.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2930121421813965s
Received healthy response to inference request in 1.4762382507324219s
Received healthy response to inference request in 1.4394111633300781s
Received healthy response to inference request in 1.4107322692871094s
Received healthy response to inference request in 1.487257480621338s
5 requests
0 failed requests
5th percentile: 1.416468048095703
10th percentile: 1.422203826904297
20th percentile: 1.4336753845214845
30th percentile: 1.4467765808105468
40th percentile: 1.4615074157714845
50th percentile: 1.4762382507324219
60th percentile: 1.4806459426879883
70th percentile: 1.4850536346435548
80th percentile: 1.6484084129333498
90th percentile: 1.970710277557373
95th percentile: 2.1318612098693848
99th percentile: 2.2607819557189943
mean time: 1.6213302612304688
Pipeline stage StressChecker completed in 8.85s
jic062-instruct-v14-v15_v2 status is now deployed due to DeploymentManager action
jic062-instruct-v14-v15_v2 status is now inactive due to auto deactivation removed underperforming models
jic062-instruct-v14-v15_v2 status is now torndown due to DeploymentManager action