submission_id: wespro-l3-limarp-oas-8b_v3
developer_uid: WesPro
best_of: 4
celo_rating: 1152.07
display_name: wespro-l3-limarp-oas-8b_v1
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}
is_internal_developer: False
language_model: WesPro/L3-LimaRP-OAS-8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: WesPro/L3-LimaRP-OAS-8B
model_name: wespro-l3-limarp-oas-8b_v1
model_num_parameters: 8030261248.0
model_repo: WesPro/L3-LimaRP-OAS-8B
model_size: 8B
num_battles: 81157
num_wins: 38699
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: torndown
submission_type: basic
timestamp: 2024-06-02T16:36:29+00:00
us_pacific_date: 2024-06-02
win_ratio: 0.4768411843710339
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-l3-limarp-oas-8b-v3-mkmlizer
Waiting for job on wespro-l3-limarp-oas-8b-v3-mkmlizer to finish
wespro-l3-limarp-oas-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║     _____            __           __                                ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║       /___/                                                         ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  belonging to:                                                      ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-l3-limarp-oas-8b-v3-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-l3-limarp-oas-8b-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-l3-limarp-oas-8b-v3-mkmlizer: Downloaded to shared memory in 54.016s
wespro-l3-limarp-oas-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-l3-limarp-oas-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-l3-limarp-oas-8b-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:16,  2.34s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:15,  3.66it/s]
Loading 0:   8%|▊         | 24/291 [00:04<00:33,  7.94it/s]
Loading 0:  14%|█▎        | 40/291 [00:04<00:15, 16.22it/s]
Loading 0:  18%|█▊        | 52/291 [00:05<00:10, 23.51it/s]
Loading 0:  22%|██▏       | 63/291 [00:05<00:08, 25.80it/s]
Loading 0:  26%|██▋       | 77/291 [00:05<00:05, 36.30it/s]
Loading 0:  31%|███▏      | 91/291 [00:05<00:04, 48.48it/s]
Loading 0:  36%|███▌      | 104/291 [00:05<00:03, 59.11it/s]
Loading 0:  40%|████      | 117/291 [00:05<00:02, 70.68it/s]
Loading 0:  45%|████▍     | 130/291 [00:05<00:01, 82.00it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 87.47it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 100.10it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:01, 66.53it/s] 
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 79.33it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 84.22it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:00, 99.78it/s]
Loading 0:  77%|███████▋  | 224/291 [00:06<00:00, 103.65it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 111.39it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 113.02it/s]
Loading 0:  91%|█████████▏| 266/291 [00:07<00:00, 69.98it/s] 
Loading 0:  95%|█████████▍| 276/291 [00:07<00:00, 73.19it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-l3-limarp-oas-8b-v3-mkmlizer: quantized model in 23.718s
wespro-l3-limarp-oas-8b-v3-mkmlizer: Processed model WesPro/L3-LimaRP-OAS-8B in 80.369s
wespro-l3-limarp-oas-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
wespro-l3-limarp-oas-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-l3-limarp-oas-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v3
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v3/config.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v3/special_tokens_map.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v3/tokenizer_config.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v3/tokenizer.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v3/flywheel_model.0.safetensors
wespro-l3-limarp-oas-8b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-l3-limarp-oas-8b-v3-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-l3-limarp-oas-8b-v3-mkmlizer:   warnings.warn(
wespro-l3-limarp-oas-8b-v3-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-l3-limarp-oas-8b-v3-mkmlizer:   warnings.warn(
wespro-l3-limarp-oas-8b-v3-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-l3-limarp-oas-8b-v3-mkmlizer:   warnings.warn(
wespro-l3-limarp-oas-8b-v3-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-l3-limarp-oas-8b-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-l3-limarp-oas-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-l3-limarp-oas-8b-v3-mkmlizer: Saving duration: 0.515s
wespro-l3-limarp-oas-8b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 27.271s
wespro-l3-limarp-oas-8b-v3-mkmlizer: creating bucket guanaco-reward-models
wespro-l3-limarp-oas-8b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-l3-limarp-oas-8b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/special_tokens_map.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/tokenizer_config.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/vocab.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/merges.txt
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/config.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/tokenizer.json
wespro-l3-limarp-oas-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v3_reward/reward.tensors
Job wespro-l3-limarp-oas-8b-v3-mkmlizer completed after 163.49s with status: succeeded
Stopping job with name wespro-l3-limarp-oas-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 166.36s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service wespro-l3-limarp-oas-8b-v3
Waiting for inference service wespro-l3-limarp-oas-8b-v3 to be ready
Inference service wespro-l3-limarp-oas-8b-v3 ready after 30.179603099822998s
Pipeline stage ISVCDeployer completed in 37.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9238083362579346s
Received healthy response to inference request in 1.0960509777069092s
Received healthy response to inference request in 1.090914011001587s
Received healthy response to inference request in 1.112959623336792s
Received healthy response to inference request in 1.00132417678833s
5 requests
0 failed requests
5th percentile: 1.0192421436309815
10th percentile: 1.0371601104736328
20th percentile: 1.0729960441589355
30th percentile: 1.0919414043426514
40th percentile: 1.0939961910247802
50th percentile: 1.0960509777069092
60th percentile: 1.1028144359588623
70th percentile: 1.1095778942108154
80th percentile: 1.2751293659210208
90th percentile: 1.5994688510894777
95th percentile: 1.7616385936737058
99th percentile: 1.891374387741089
mean time: 1.2450114250183106
Pipeline stage StressChecker completed in 6.84s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
wespro-l3-limarp-oas-8b_v3 status is now deployed due to DeploymentManager action
wespro-l3-limarp-oas-8b_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-l3-limarp-oas-8b_v3
Running pipeline stage ISVCDeleter
Checking if service wespro-l3-limarp-oas-8b-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.31s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-l3-limarp-oas-8b-v3/config.json from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-l3-limarp-oas-8b-v3_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.90s
wespro-l3-limarp-oas-8b_v3 status is now torndown due to DeploymentManager action