submission_id: wespro-psaiki-l3rp-8b_v2
developer_uid: WesPro
best_of: 4
display_name: wespro-psaiki-l3rp-8b_v2
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: WesPro/PsAiKi_L3RP_8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: error
model_group: WesPro/PsAiKi_L3RP_8B
model_name: wespro-psaiki-l3rp-8b_v2
model_num_parameters: 8030261248.0
model_repo: WesPro/PsAiKi_L3RP_8B
model_size: 8B
num_battles: 583
num_wins: 294
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: rejected
submission_type: basic
timestamp: 2024-06-03T18:06:55+00:00
us_pacific_date: 2024-06-03
win_ratio: 0.5042881646655232
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-psaiki-l3rp-8b-v2-mkmlizer
Waiting for job on wespro-psaiki-l3rp-8b-v2-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
wespro-psaiki-l3rp-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║     _____            __           __                                ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║       /___/                                                         ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  belonging to:                                                      ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-psaiki-l3rp-8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
wespro-psaiki-l3rp-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-psaiki-l3rp-8b-v2-mkmlizer: Downloaded to shared memory in 45.182s
wespro-psaiki-l3rp-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-psaiki-l3rp-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-psaiki-l3rp-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:33,  2.40s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:17,  3.57it/s]
Loading 0:   8%|▊         | 23/291 [00:05<00:36,  7.35it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:21, 12.26it/s]
Loading 0:  16%|█▌        | 46/291 [00:05<00:11, 20.55it/s]
Loading 0:  20%|█▉        | 58/291 [00:05<00:07, 29.31it/s]
Loading 0:  24%|██▎       | 69/291 [00:05<00:07, 28.83it/s]
Loading 0:  28%|██▊       | 82/291 [00:05<00:05, 39.76it/s]
Loading 0:  33%|███▎      | 95/291 [00:05<00:03, 50.62it/s]
Loading 0:  36%|███▌      | 105/291 [00:06<00:03, 57.74it/s]
Loading 0:  42%|████▏     | 121/291 [00:06<00:02, 74.08it/s]
Loading 0:  45%|████▌     | 132/291 [00:06<00:02, 77.32it/s]
Loading 0:  51%|█████     | 148/291 [00:06<00:01, 92.61it/s]
Loading 0:  55%|█████▍    | 160/291 [00:06<00:01, 94.77it/s]
Loading 0:  59%|█████▉    | 172/291 [00:06<00:01, 62.62it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 70.92it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 75.96it/s]
Loading 0:  71%|███████▏  | 208/291 [00:07<00:00, 87.05it/s]
Loading 0:  76%|███████▌  | 220/291 [00:07<00:00, 91.88it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:00, 88.25it/s]
Loading 0:  84%|████████▍ | 244/291 [00:07<00:00, 97.22it/s]
Loading 0:  88%|████████▊ | 257/291 [00:07<00:00, 101.12it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 62.79it/s] 
Loading 0:  96%|█████████▌| 280/291 [00:08<00:00, 72.99it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-psaiki-l3rp-8b-v2-mkmlizer: quantized model in 24.908s
wespro-psaiki-l3rp-8b-v2-mkmlizer: Processed model WesPro/PsAiKi_L3RP_8B in 72.850s
wespro-psaiki-l3rp-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
wespro-psaiki-l3rp-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-psaiki-l3rp-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v2
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v2/config.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v2/tokenizer_config.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v2/tokenizer.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v2/special_tokens_map.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v2/flywheel_model.0.safetensors
wespro-psaiki-l3rp-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-psaiki-l3rp-8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
wespro-psaiki-l3rp-8b-v2-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
wespro-psaiki-l3rp-8b-v2-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
wespro-psaiki-l3rp-8b-v2-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-8b-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
wespro-psaiki-l3rp-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-psaiki-l3rp-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-psaiki-l3rp-8b-v2-mkmlizer: Saving duration: 0.420s
wespro-psaiki-l3rp-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.410s
wespro-psaiki-l3rp-8b-v2-mkmlizer: creating bucket guanaco-reward-models
wespro-psaiki-l3rp-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-psaiki-l3rp-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/tokenizer_config.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/special_tokens_map.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/merges.txt
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/vocab.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/config.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/tokenizer.json
wespro-psaiki-l3rp-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v2_reward/reward.tensors
Job wespro-psaiki-l3rp-8b-v2-mkmlizer completed after 257.04s with status: succeeded
Stopping job with name wespro-psaiki-l3rp-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 258.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service wespro-psaiki-l3rp-8b-v2
Waiting for inference service wespro-psaiki-l3rp-8b-v2 to be ready
Inference service wespro-psaiki-l3rp-8b-v2 ready after 40.37695527076721s
Pipeline stage ISVCDeployer completed in 46.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0029678344726562s
Received healthy response to inference request in 1.1108479499816895s
Received healthy response to inference request in 1.152261734008789s
Received healthy response to inference request in 1.1071405410766602s
Received healthy response to inference request in 1.1717743873596191s
5 requests
0 failed requests
5th percentile: 1.107882022857666
10th percentile: 1.1086235046386719
20th percentile: 1.1101064682006836
30th percentile: 1.1191307067871095
40th percentile: 1.1356962203979493
50th percentile: 1.152261734008789
60th percentile: 1.160066795349121
70th percentile: 1.167871856689453
80th percentile: 1.3380130767822267
90th percentile: 1.6704904556274416
95th percentile: 1.8367291450500487
99th percentile: 1.9697200965881347
mean time: 1.3089984893798827
Pipeline stage StressChecker completed in 7.16s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
wespro-psaiki-l3rp-8b_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
wespro-psaiki-l3rp-8b_v2 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.