wespro-psaiki-l3rp-8b

submission_id: wespro-psaiki-l3rp-8b_v1

developer_uid: WesPro

best_of: 4

celo_rating: 1185.09

display_name: wespro-psaiki-l3rp-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/PsAiKi_L3RP_8B

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: WesPro/PsAiKi_L3RP_8B

model_name: wespro-psaiki-l3rp-8b_v1

model_num_parameters: 8030261248.0

model_repo: WesPro/PsAiKi_L3RP_8B

model_size: 8B

num_battles: 22596

num_wins: 11138

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: 2024-06-03T15:23:44+00:00

us_pacific_date: 2024-06-03

win_ratio: 0.4929191007257922

Resubmit model

Running pipeline stage MKMLizer
Starting job with name wespro-psaiki-l3rp-8b-v1-mkmlizer
Waiting for job on wespro-psaiki-l3rp-8b-v1-mkmlizer to finish
wespro-psaiki-l3rp-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║     _____            __           __                                ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║       /___/                                                         ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  belonging to:                                                      ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-psaiki-l3rp-8b-v1-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-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-psaiki-l3rp-8b-v1-mkmlizer: Downloaded to shared memory in 42.656s
wespro-psaiki-l3rp-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-psaiki-l3rp-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-psaiki-l3rp-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:50,  2.46s/it]
Loading 0:   4%|▍         | 13/291 [00:05<01:19,  3.50it/s]
Loading 0:   8%|▊         | 23/291 [00:05<00:37,  7.23it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:21, 12.06it/s]
Loading 0:  17%|█▋        | 49/291 [00:05<00:10, 22.05it/s]
Loading 0:  21%|██        | 60/291 [00:05<00:09, 23.76it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 35.71it/s]
Loading 0:  30%|██▉       | 86/291 [00:05<00:04, 43.04it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:03, 50.94it/s]
Loading 0:  38%|███▊      | 112/291 [00:06<00:02, 66.98it/s]
Loading 0:  42%|████▏     | 123/291 [00:06<00:02, 72.15it/s]
Loading 0:  48%|████▊     | 139/291 [00:06<00:01, 86.61it/s]
Loading 0:  52%|█████▏    | 151/291 [00:06<00:01, 89.33it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 64.19it/s]
Loading 0:  60%|██████    | 176/291 [00:07<00:01, 69.56it/s]
Loading 0:  64%|██████▍   | 186/291 [00:07<00:01, 75.10it/s]
Loading 0:  69%|██████▊   | 200/291 [00:07<00:01, 89.09it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 93.31it/s]
Loading 0:  76%|███████▋  | 222/291 [00:07<00:00, 91.01it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 103.39it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:00, 102.89it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 110.76it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 66.20it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-psaiki-l3rp-8b-v1-mkmlizer: quantized model in 25.510s
wespro-psaiki-l3rp-8b-v1-mkmlizer: Processed model WesPro/PsAiKi_L3RP_8B in 70.764s
wespro-psaiki-l3rp-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
wespro-psaiki-l3rp-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-psaiki-l3rp-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v1
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v1/tokenizer_config.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v1/config.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v1/special_tokens_map.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v1/tokenizer.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v1/flywheel_model.0.safetensors
wespro-psaiki-l3rp-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-psaiki-l3rp-8b-v1-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-v1-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-8b-v1-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-v1-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-8b-v1-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-v1-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-8b-v1-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-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-psaiki-l3rp-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-psaiki-l3rp-8b-v1-mkmlizer: Saving duration: 0.396s
wespro-psaiki-l3rp-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.373s
wespro-psaiki-l3rp-8b-v1-mkmlizer: creating bucket guanaco-reward-models
wespro-psaiki-l3rp-8b-v1-mkmlizer: WARNING: Retrying failed request: / ([Errno 110] Connection timed out)
wespro-psaiki-l3rp-8b-v1-mkmlizer: WARNING: Waiting 3 sec...
wespro-psaiki-l3rp-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-psaiki-l3rp-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/config.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/special_tokens_map.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/tokenizer_config.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/merges.txt
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/vocab.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/tokenizer.json
wespro-psaiki-l3rp-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v1_reward/reward.tensors
Job wespro-psaiki-l3rp-8b-v1-mkmlizer completed after 373.3s with status: succeeded
Stopping job with name wespro-psaiki-l3rp-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 376.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service wespro-psaiki-l3rp-8b-v1
Waiting for inference service wespro-psaiki-l3rp-8b-v1 to be ready
Inference service wespro-psaiki-l3rp-8b-v1 ready after 40.23810434341431s
Pipeline stage ISVCDeployer completed in 47.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.03529691696167s
Received healthy response to inference request in 1.1279563903808594s
Received healthy response to inference request in 1.123565912246704s
Received healthy response to inference request in 1.1104083061218262s
Received healthy response to inference request in 1.131986379623413s
5 requests
0 failed requests
5th percentile: 1.1130398273468018
10th percentile: 1.1156713485717773
20th percentile: 1.1209343910217284
30th percentile: 1.1244440078735352
40th percentile: 1.1262001991271973
50th percentile: 1.1279563903808594
60th percentile: 1.129568386077881
70th percentile: 1.1311803817749024
80th percentile: 1.3126484870910646
90th percentile: 1.6739727020263673
95th percentile: 1.8546348094940184
99th percentile: 1.9991644954681396
mean time: 1.3058427810668944
Pipeline stage StressChecker completed in 7.21s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
wespro-psaiki-l3rp-8b_v1 status is now deployed due to DeploymentManager action
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
wespro-psaiki-l3rp-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-psaiki-l3rp-8b_v1
Running pipeline stage ISVCDeleter
Checking if service wespro-psaiki-l3rp-8b-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.61s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-psaiki-l3rp-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-psaiki-l3rp-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.34s
wespro-psaiki-l3rp-8b_v1 status is now torndown due to DeploymentManager action