grimjim-llama-3-luminurs_4053

submission_id: grimjim-llama-3-luminurs_4053_v1

developer_uid: grimjim.

best_of: 16

celo_rating: 1185.09

display_name: grimjim-llama-3-luminurs_4053_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': 0.02, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: grimjim/Llama-3-Luminurse-v0.1-OAS-8B

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: grimjim/Llama-3-Luminurs

model_name: grimjim-llama-3-luminurs_4053_v1

model_num_parameters: 8030261248.0

model_repo: grimjim/Llama-3-Luminurse-v0.1-OAS-8B

model_size: 8B

num_battles: 13578

num_wins: 7007

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: 2024-06-01T21:15:45+00:00

us_pacific_date: 2024-06-01

win_ratio: 0.5160553837089409

Resubmit model

Running pipeline stage MKMLizer
Starting job with name grimjim-llama-3-luminurs-4053-v1-mkmlizer
Waiting for job on grimjim-llama-3-luminurs-4053-v1-mkmlizer to finish
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║     _____            __           __                                ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║       /___/                                                         ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  https://mk1.ai                                                     ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  belonging to:                                                      ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  Chai Research Corp.                                                ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-4053-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
grimjim-llama-3-luminurs-4053-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.
grimjim-llama-3-luminurs-4053-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Downloaded to shared memory in 31.495s
grimjim-llama-3-luminurs-4053-v1-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
grimjim-llama-3-luminurs-4053-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:45,  2.23s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:01,  4.46it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:21, 11.84it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.26it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.21it/s]
Loading 0:  27%|██▋       | 79/291 [00:05<00:06, 34.60it/s]
Loading 0:  33%|███▎      | 95/291 [00:05<00:04, 47.65it/s]
Loading 0:  39%|███▉      | 113/291 [00:05<00:02, 63.98it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:01, 80.65it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:01, 96.60it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 73.77it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 88.84it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 104.00it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 117.74it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 129.87it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 138.29it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 90.97it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 98.09it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
grimjim-llama-3-luminurs-4053-v1-mkmlizer: quantized model in 22.849s
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Processed model grimjim/Llama-3-Luminurse-v0.1-OAS-8B in 56.936s
grimjim-llama-3-luminurs-4053-v1-mkmlizer: creating bucket guanaco-mkml-models
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
grimjim-llama-3-luminurs-4053-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/grimjim-llama-3-luminurs-4053-v1
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-4053-v1/config.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-4053-v1/tokenizer_config.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-4053-v1/special_tokens_map.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-4053-v1/tokenizer.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/grimjim-llama-3-luminurs-4053-v1/flywheel_model.0.safetensors
grimjim-llama-3-luminurs-4053-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.
grimjim-llama-3-luminurs-4053-v1-mkmlizer:   warnings.warn(
grimjim-llama-3-luminurs-4053-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.
grimjim-llama-3-luminurs-4053-v1-mkmlizer:   warnings.warn(
grimjim-llama-3-luminurs-4053-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()
grimjim-llama-3-luminurs-4053-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Saving duration: 0.424s
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.108s
grimjim-llama-3-luminurs-4053-v1-mkmlizer: creating bucket guanaco-reward-models
grimjim-llama-3-luminurs-4053-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
grimjim-llama-3-luminurs-4053-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/config.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/special_tokens_map.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/tokenizer_config.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/merges.txt
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/vocab.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/tokenizer.json
grimjim-llama-3-luminurs-4053-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-llama-3-luminurs-4053-v1_reward/reward.tensors
Job grimjim-llama-3-luminurs-4053-v1-mkmlizer completed after 83.32s with status: succeeded
Stopping job with name grimjim-llama-3-luminurs-4053-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-llama-3-luminurs-4053-v1
Waiting for inference service grimjim-llama-3-luminurs-4053-v1 to be ready
Inference service grimjim-llama-3-luminurs-4053-v1 ready after 60.35935163497925s
Pipeline stage ISVCDeployer completed in 65.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.171736717224121s
Received healthy response to inference request in 1.258920669555664s
Received healthy response to inference request in 1.2291812896728516s
Received healthy response to inference request in 1.232429027557373s
Received healthy response to inference request in 1.227752923965454s
5 requests
0 failed requests
5th percentile: 1.2280385971069336
10th percentile: 1.2283242702484132
20th percentile: 1.228895616531372
30th percentile: 1.229830837249756
40th percentile: 1.2311299324035645
50th percentile: 1.232429027557373
60th percentile: 1.2430256843566894
70th percentile: 1.253622341156006
80th percentile: 1.4414838790893556
90th percentile: 1.8066102981567385
95th percentile: 1.9891735076904296
99th percentile: 2.1352240753173826
mean time: 1.4240041255950928
Pipeline stage StressChecker completed in 7.71s
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
grimjim-llama-3-luminurs_4053_v1 status is now deployed due to DeploymentManager action
grimjim-llama-3-luminurs_4053_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of grimjim-llama-3-luminurs_4053_v1
Running pipeline stage ISVCDeleter
Checking if service grimjim-llama-3-luminurs-4053-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key grimjim-llama-3-luminurs-4053-v1/config.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-4053-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-4053-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-4053-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-4053-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/config.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-4053-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.57s
grimjim-llama-3-luminurs_4053_v1 status is now torndown due to DeploymentManager action