submission_id: wespro-l3-limarp-oas-8b_v2
developer_uid: WesPro
best_of: 4
celo_rating: 1151.08
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: 81018
num_wins: 38495
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: 2024-06-02T16:36:26+00:00
us_pacific_date: 2024-06-02
win_ratio: 0.47514132661877606
Resubmit model
Running pipeline stage MKMLizer
Starting job with name wespro-l3-limarp-oas-8b-v2-mkmlizer
Waiting for job on wespro-l3-limarp-oas-8b-v2-mkmlizer to finish
wespro-l3-limarp-oas-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║     _____            __           __                                ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║       /___/                                                         ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  belonging to:                                                      ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ║                                                                     ║
wespro-l3-limarp-oas-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-l3-limarp-oas-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-l3-limarp-oas-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-l3-limarp-oas-8b-v2-mkmlizer: Downloaded to shared memory in 51.304s
wespro-l3-limarp-oas-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-l3-limarp-oas-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-l3-limarp-oas-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:31,  2.39s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:17,  3.59it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:34,  7.78it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:15, 15.86it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:10, 22.35it/s]
Loading 0:  21%|██▏       | 62/291 [00:05<00:09, 24.47it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 35.18it/s]
Loading 0:  30%|██▉       | 87/291 [00:05<00:04, 43.26it/s]
Loading 0:  35%|███▌      | 103/291 [00:05<00:03, 58.98it/s]
Loading 0:  40%|███▉      | 115/291 [00:06<00:02, 67.21it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:01, 81.48it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 86.78it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 99.00it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:01, 64.87it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 77.25it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 81.57it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 98.03it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 101.07it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 112.18it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 113.48it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 115.94it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 68.58it/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-v2-mkmlizer: quantized model in 24.195s
wespro-l3-limarp-oas-8b-v2-mkmlizer: Processed model WesPro/L3-LimaRP-OAS-8B in 78.231s
wespro-l3-limarp-oas-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
wespro-l3-limarp-oas-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-l3-limarp-oas-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v2
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v2/config.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v2/tokenizer_config.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v2/special_tokens_map.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v2/tokenizer.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-l3-limarp-oas-8b-v2/flywheel_model.0.safetensors
wespro-l3-limarp-oas-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-l3-limarp-oas-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-l3-limarp-oas-8b-v2-mkmlizer:   warnings.warn(
wespro-l3-limarp-oas-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-l3-limarp-oas-8b-v2-mkmlizer:   warnings.warn(
wespro-l3-limarp-oas-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-l3-limarp-oas-8b-v2-mkmlizer:   warnings.warn(
wespro-l3-limarp-oas-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-l3-limarp-oas-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-l3-limarp-oas-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-l3-limarp-oas-8b-v2-mkmlizer: Saving duration: 0.514s
wespro-l3-limarp-oas-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.233s
wespro-l3-limarp-oas-8b-v2-mkmlizer: creating bucket guanaco-reward-models
wespro-l3-limarp-oas-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-l3-limarp-oas-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward/tokenizer_config.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward/config.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward/special_tokens_map.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward/merges.txt
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward/vocab.json
wespro-l3-limarp-oas-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-l3-limarp-oas-8b-v2_reward/tokenizer.json
Job wespro-l3-limarp-oas-8b-v2-mkmlizer completed after 164.65s with status: succeeded
Stopping job with name wespro-l3-limarp-oas-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 169.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service wespro-l3-limarp-oas-8b-v2
Waiting for inference service wespro-l3-limarp-oas-8b-v2 to be ready
Inference service wespro-l3-limarp-oas-8b-v2 ready after 40.2156286239624s
Pipeline stage ISVCDeployer completed in 47.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9558947086334229s
Received healthy response to inference request in 1.088923692703247s
Received healthy response to inference request in 1.1391520500183105s
Received healthy response to inference request in 13.634419918060303s
Received healthy response to inference request in 0.8332138061523438s
5 requests
0 failed requests
5th percentile: 0.8843557834625244
10th percentile: 0.9354977607727051
20th percentile: 1.0377817153930664
30th percentile: 1.0989693641662597
40th percentile: 1.1190607070922851
50th percentile: 1.1391520500183105
60th percentile: 1.4658491134643554
70th percentile: 1.7925461769104003
80th percentile: 4.291599750518801
90th percentile: 8.96300983428955
95th percentile: 11.298714876174925
99th percentile: 13.167278909683228
mean time: 3.7303208351135253
Pipeline stage StressChecker completed in 19.35s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
wespro-l3-limarp-oas-8b_v2 status is now deployed due to DeploymentManager action
wespro-l3-limarp-oas-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-l3-limarp-oas-8b_v2
Running pipeline stage ISVCDeleter
Checking if service wespro-l3-limarp-oas-8b-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-l3-limarp-oas-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-l3-limarp-oas-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-l3-limarp-oas-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-l3-limarp-oas-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.31s
wespro-l3-limarp-oas-8b_v2 status is now torndown due to DeploymentManager action