grimjim-llama-3-luminurs_1981

submission_id: grimjim-llama-3-luminurs_1981_v1

developer_uid: grimjim.

best_of: 16

celo_rating: 1185.03

display_name: grimjim-llama-3-luminurs_1981_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': 1.41, '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-v0.2-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_1981_v1

model_num_parameters: 8030261248.0

model_repo: grimjim/Llama-3-Luminurse-v0.2-OAS-8B

model_size: 8B

num_battles: 18188

num_wins: 9116

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: 2024-06-09T02:03:37+00:00

us_pacific_date: 2024-06-08

win_ratio: 0.5012095887398285

Resubmit model

Running pipeline stage MKMLizer
Starting job with name grimjim-llama-3-luminurs-1981-v1-mkmlizer
Waiting for job on grimjim-llama-3-luminurs-1981-v1-mkmlizer to finish
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║     _____            __           __                                ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║       /___/                                                         ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  https://mk1.ai                                                     ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  belonging to:                                                      ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  Chai Research Corp.                                                ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ║                                                                     ║
grimjim-llama-3-luminurs-1981-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
grimjim-llama-3-luminurs-1981-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-1981-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Downloaded to shared memory in 35.627s
grimjim-llama-3-luminurs-1981-v1-mkmlizer: quantizing model to /dev/shm/model_cache
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
grimjim-llama-3-luminurs-1981-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:46,  2.24s/it]
Loading 0:   6%|▌         | 18/291 [00:04<00:50,  5.38it/s]
Loading 0:  12%|█▏        | 34/291 [00:04<00:21, 11.92it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.82it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.23it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 33.95it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:03, 48.97it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 65.08it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 81.16it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.53it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.55it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 90.44it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 104.74it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 118.98it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 130.46it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 140.66it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 90.55it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:06<00:00, 102.54it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
grimjim-llama-3-luminurs-1981-v1-mkmlizer: quantized model in 22.704s
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Processed model grimjim/Llama-3-Luminurse-v0.2-OAS-8B in 60.866s
grimjim-llama-3-luminurs-1981-v1-mkmlizer: creating bucket guanaco-mkml-models
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
grimjim-llama-3-luminurs-1981-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/grimjim-llama-3-luminurs-1981-v1
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-1981-v1/tokenizer_config.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-1981-v1/config.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-1981-v1/special_tokens_map.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/grimjim-llama-3-luminurs-1981-v1/tokenizer.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/grimjim-llama-3-luminurs-1981-v1/flywheel_model.0.safetensors
grimjim-llama-3-luminurs-1981-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
grimjim-llama-3-luminurs-1981-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.
grimjim-llama-3-luminurs-1981-v1-mkmlizer:   warnings.warn(
grimjim-llama-3-luminurs-1981-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-1981-v1-mkmlizer:   warnings.warn(
grimjim-llama-3-luminurs-1981-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-1981-v1-mkmlizer:   warnings.warn(
grimjim-llama-3-luminurs-1981-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-1981-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Saving duration: 0.416s
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.269s
grimjim-llama-3-luminurs-1981-v1-mkmlizer: creating bucket guanaco-reward-models
grimjim-llama-3-luminurs-1981-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
grimjim-llama-3-luminurs-1981-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/config.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/special_tokens_map.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/tokenizer_config.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/merges.txt
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/vocab.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/tokenizer.json
grimjim-llama-3-luminurs-1981-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/grimjim-llama-3-luminurs-1981-v1_reward/reward.tensors
Job grimjim-llama-3-luminurs-1981-v1-mkmlizer completed after 83.23s with status: succeeded
Stopping job with name grimjim-llama-3-luminurs-1981-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service grimjim-llama-3-luminurs-1981-v1
Waiting for inference service grimjim-llama-3-luminurs-1981-v1 to be ready
Inference service grimjim-llama-3-luminurs-1981-v1 ready after 50.27407097816467s
Pipeline stage ISVCDeployer completed in 56.31s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 2.174722671508789s
Received healthy response to inference request in 1.3037030696868896s
Received healthy response to inference request in 1.2748987674713135s
Received healthy response to inference request in 1.4239275455474854s
Received healthy response to inference request in 1.7196121215820312s
5 requests
0 failed requests
5th percentile: 1.2806596279144287
10th percentile: 1.2864204883575439
20th percentile: 1.2979422092437745
30th percentile: 1.3277479648590087
40th percentile: 1.375837755203247
50th percentile: 1.4239275455474854
60th percentile: 1.5422013759613038
70th percentile: 1.660475206375122
80th percentile: 1.810634231567383
90th percentile: 1.992678451538086
95th percentile: 2.0837005615234374
99th percentile: 2.1565182495117186
mean time: 1.5793728351593017
Pipeline stage StressChecker completed in 28.62s
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_1981_v1 status is now deployed due to DeploymentManager action
grimjim-llama-3-luminurs_1981_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of grimjim-llama-3-luminurs_1981_v1
Running pipeline stage ISVCDeleter
Checking if service grimjim-llama-3-luminurs-1981-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key grimjim-llama-3-luminurs-1981-v1/config.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-1981-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-1981-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-1981-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key grimjim-llama-3-luminurs-1981-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/config.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key grimjim-llama-3-luminurs-1981-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.73s
grimjim-llama-3-luminurs_1981_v1 status is now torndown due to DeploymentManager action