wespro-psaiki-l3rp-8b

submission_id: wespro-psaiki-l3rp-8b_v3

developer_uid: WesPro

best_of: 4

celo_rating: 1176.83

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: 21252

num_wins: 10599

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: 2024-06-05T16:55:06+00:00

us_pacific_date: 2024-06-05

win_ratio: 0.498729531338227

Resubmit model

Running pipeline stage MKMLizer
Starting job with name wespro-psaiki-l3rp-8b-v3-mkmlizer
Waiting for job on wespro-psaiki-l3rp-8b-v3-mkmlizer to finish
wespro-psaiki-l3rp-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║     _____            __           __                                ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║       /___/                                                         ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  https://mk1.ai                                                     ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  belonging to:                                                      ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  Chai Research Corp.                                                ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ║                                                                     ║
wespro-psaiki-l3rp-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
wespro-psaiki-l3rp-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-psaiki-l3rp-8b-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
wespro-psaiki-l3rp-8b-v3-mkmlizer: Downloaded to shared memory in 53.655s
wespro-psaiki-l3rp-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
wespro-psaiki-l3rp-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
wespro-psaiki-l3rp-8b-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:49,  2.46s/it]
Loading 0:   4%|▍         | 11/291 [00:05<01:35,  2.94it/s]
Loading 0:   8%|▊         | 22/291 [00:05<00:38,  7.06it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:21, 11.88it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:13, 17.80it/s]
Loading 0:  19%|█▊        | 54/291 [00:05<00:08, 26.77it/s]
Loading 0:  22%|██▏       | 64/291 [00:05<00:08, 26.29it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 35.78it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 43.42it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:03, 50.50it/s]
Loading 0:  37%|███▋      | 107/291 [00:06<00:03, 60.91it/s]
Loading 0:  40%|████      | 117/291 [00:06<00:02, 64.98it/s]
Loading 0:  44%|████▎     | 127/291 [00:06<00:02, 72.22it/s]
Loading 0:  48%|████▊     | 139/291 [00:06<00:01, 79.76it/s]
Loading 0:  51%|█████     | 149/291 [00:06<00:01, 80.00it/s]
Loading 0:  55%|█████▍    | 159/291 [00:06<00:01, 84.48it/s]
Loading 0:  58%|█████▊    | 169/291 [00:07<00:02, 52.99it/s]
Loading 0:  62%|██████▏   | 181/291 [00:07<00:01, 64.61it/s]
Loading 0:  66%|██████▋   | 193/291 [00:07<00:01, 73.62it/s]
Loading 0:  70%|██████▉   | 203/291 [00:07<00:01, 78.51it/s]
Loading 0:  73%|███████▎  | 213/291 [00:07<00:00, 81.52it/s]
Loading 0:  77%|███████▋  | 225/291 [00:07<00:00, 90.21it/s]
Loading 0:  81%|████████▏ | 237/291 [00:07<00:00, 97.96it/s]
Loading 0:  85%|████████▌ | 248/291 [00:08<00:00, 91.31it/s]
Loading 0:  89%|████████▊ | 258/291 [00:08<00:00, 89.40it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 56.65it/s]
Loading 0:  96%|█████████▌| 280/291 [00:08<00:00, 67.63it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
wespro-psaiki-l3rp-8b-v3-mkmlizer: quantized model in 25.516s
wespro-psaiki-l3rp-8b-v3-mkmlizer: Processed model WesPro/PsAiKi_L3RP_8B in 81.886s
wespro-psaiki-l3rp-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
wespro-psaiki-l3rp-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
wespro-psaiki-l3rp-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v3
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v3/special_tokens_map.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v3/config.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v3/tokenizer_config.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v3/tokenizer.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/wespro-psaiki-l3rp-8b-v3/flywheel_model.0.safetensors
wespro-psaiki-l3rp-8b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
wespro-psaiki-l3rp-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-psaiki-l3rp-8b-v3-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-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-psaiki-l3rp-8b-v3-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-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-psaiki-l3rp-8b-v3-mkmlizer:   warnings.warn(
wespro-psaiki-l3rp-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-psaiki-l3rp-8b-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
wespro-psaiki-l3rp-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
wespro-psaiki-l3rp-8b-v3-mkmlizer: Saving duration: 0.454s
wespro-psaiki-l3rp-8b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.353s
wespro-psaiki-l3rp-8b-v3-mkmlizer: creating bucket guanaco-reward-models
wespro-psaiki-l3rp-8b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
wespro-psaiki-l3rp-8b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/tokenizer_config.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/config.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/special_tokens_map.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/merges.txt
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/vocab.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/tokenizer.json
wespro-psaiki-l3rp-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/wespro-psaiki-l3rp-8b-v3_reward/reward.tensors
Job wespro-psaiki-l3rp-8b-v3-mkmlizer completed after 128.12s with status: succeeded
Stopping job with name wespro-psaiki-l3rp-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 132.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service wespro-psaiki-l3rp-8b-v3
Waiting for inference service wespro-psaiki-l3rp-8b-v3 to be ready
Inference service wespro-psaiki-l3rp-8b-v3 ready after 181.09531998634338s
Pipeline stage ISVCDeployer completed in 189.04s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.054022789001465s
Received healthy response to inference request in 1.1230123043060303s
Received healthy response to inference request in 1.1187705993652344s
Received healthy response to inference request in 1.123823881149292s
Received healthy response to inference request in 1.114126443862915s
5 requests
0 failed requests
5th percentile: 1.1150552749633789
10th percentile: 1.1159841060638427
20th percentile: 1.1178417682647706
30th percentile: 1.1196189403533936
40th percentile: 1.1213156223297118
50th percentile: 1.1230123043060303
60th percentile: 1.1233369350433349
70th percentile: 1.1236615657806397
80th percentile: 1.3098636627197267
90th percentile: 1.6819432258605957
95th percentile: 1.8679830074310302
99th percentile: 2.016814832687378
mean time: 1.3067512035369873
Pipeline stage StressChecker completed in 7.16s
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_v3 status is now deployed due to DeploymentManager action
wespro-psaiki-l3rp-8b_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of wespro-psaiki-l3rp-8b_v3
Running pipeline stage ISVCDeleter
Checking if service wespro-psaiki-l3rp-8b-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.29s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key wespro-psaiki-l3rp-8b-v3/config.json from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key wespro-psaiki-l3rp-8b-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key wespro-psaiki-l3rp-8b-v3_reward/config.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key wespro-psaiki-l3rp-8b-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.99s
wespro-psaiki-l3rp-8b_v3 status is now torndown due to DeploymentManager action