hastagaras-halu-8b-llama_4027

submission_id: hastagaras-halu-8b-llama_4027_v1

developer_uid: Hastagaras

best_of: 16

celo_rating: 1210.91

display_name: weird-and-strange

family_friendly_score: 0.0

formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, '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: Hastagaras/HALU-8B-LLAMA3-EXP-6

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/HALU-8B-LLAMA

model_name: weird-and-strange

model_num_parameters: 8030261248.0

model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-6

model_size: 8B

num_battles: 10285

num_wins: 5612

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: 2024-06-01T06:12:30+00:00

us_pacific_date: 2024-05-31

win_ratio: 0.5456490034030141

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-4027-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-4027-v1-mkmlizer to finish
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4027-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Downloaded to shared memory in 30.950s
hastagaras-halu-8b-llama-4027-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-4027-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:53,  2.26s/it]
Loading 0:   5%|▌         | 16/291 [00:04<00:58,  4.72it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.62it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.02it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.54it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 36.62it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.53it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.78it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 81.73it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 98.03it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 73.99it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 89.83it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 103.78it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 117.27it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 128.38it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 137.52it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 90.09it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 95.90it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-4027-v1-mkmlizer: quantized model in 23.766s
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-EXP-6 in 57.286s
hastagaras-halu-8b-llama-4027-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-4027-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v1
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v1/config.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v1/special_tokens_map.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v1/tokenizer_config.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v1/tokenizer.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4027-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-4027-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4027-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.
hastagaras-halu-8b-llama-4027-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4027-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()
hastagaras-halu-8b-llama-4027-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Saving duration: 0.458s
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.293s
hastagaras-halu-8b-llama-4027-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-4027-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-4027-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/config.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/vocab.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/merges.txt
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-4027-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-4027-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-4027-v1-mkmlizer completed after 83.21s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-4027-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-4027-v1
Waiting for inference service hastagaras-halu-8b-llama-4027-v1 to be ready
Inference service hastagaras-halu-8b-llama-4027-v1 ready after 50.24022126197815s
Pipeline stage ISVCDeployer completed in 57.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.159491539001465s
Received healthy response to inference request in 1.3455297946929932s
Received healthy response to inference request in 1.2975199222564697s
Received healthy response to inference request in 1.2823941707611084s
Received healthy response to inference request in 1.2469258308410645s
5 requests
0 failed requests
5th percentile: 1.2540194988250732
10th percentile: 1.261113166809082
20th percentile: 1.2753005027770996
30th percentile: 1.2854193210601808
40th percentile: 1.2914696216583252
50th percentile: 1.2975199222564697
60th percentile: 1.3167238712310791
70th percentile: 1.3359278202056886
80th percentile: 1.5083221435546876
90th percentile: 1.8339068412780763
95th percentile: 1.9966991901397704
99th percentile: 2.1269330692291257
mean time: 1.4663722515106201
Pipeline stage StressChecker completed in 7.96s
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
hastagaras-halu-8b-llama_4027_v1 status is now deployed due to DeploymentManager action
Scoring model output for bot %s
hastagaras-halu-8b-llama_4027_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_4027_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-4027-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-4027-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4027-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4027-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4027-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4027-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4027-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.65s
hastagaras-halu-8b-llama_4027_v1 status is now torndown due to DeploymentManager action