hastagaras-halu-8b-llama-3

developer_uid: Hastagaras

submission_id: hastagaras-halu-8b-llama-3_v3

model_name: menghalu3

model_group: Hastagaras/Halu-8B-Llama

status: torndown

timestamp: 2024-05-24T00:56:37+00:00

num_battles: 14612

num_wins: 7485

celo_rating: 1187.27

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Halu-8B-Llama-3

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: menghalu3

is_internal_developer: False

language_model: Hastagaras/Halu-8B-Llama-3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-23

win_ratio: 0.5122502053107035

generation_params: {'temperature': 0.85, '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': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': 'Example: {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}

model_eval_status: success

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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3-v3-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3-v3-mkmlizer to finish
hastagaras-halu-8b-llama-3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3-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.
hastagaras-halu-8b-llama-3-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3-v3-mkmlizer: Downloaded to shared memory in 33.513s
hastagaras-halu-8b-llama-3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 115.79it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 144.57it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 154.34it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 157.63it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 84.58it/s] 
Loading 0:  34%|███▎      | 98/291 [00:00<00:01, 97.32it/s]
Loading 0:  38%|███▊      | 111/291 [00:01<00:01, 103.46it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 118.19it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 130.37it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:00, 137.88it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 141.04it/s]
Loading 0:  67%|██████▋   | 196/291 [00:01<00:01, 81.64it/s] 
Loading 0:  73%|███████▎  | 212/291 [00:01<00:00, 94.79it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 110.51it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 123.48it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 134.13it/s]
Loading 0:  98%|█████████▊| 285/291 [00:02<00:00, 147.18it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3-v3-mkmlizer: quantized model in 22.652s
hastagaras-halu-8b-llama-3-v3-mkmlizer: Processed model Hastagaras/Halu-8B-Llama-3 in 58.680s
hastagaras-halu-8b-llama-3-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v3
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v3/tokenizer_config.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v3/special_tokens_map.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v3/config.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v3/tokenizer.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v3/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3-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.
hastagaras-halu-8b-llama-3-v3-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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.
hastagaras-halu-8b-llama-3-v3-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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.
hastagaras-halu-8b-llama-3-v3-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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()
hastagaras-halu-8b-llama-3-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3-v3-mkmlizer: Saving duration: 0.409s
hastagaras-halu-8b-llama-3-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.310s
hastagaras-halu-8b-llama-3-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/config.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/merges.txt
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/vocab.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/tokenizer.json
hastagaras-halu-8b-llama-3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v3_reward/reward.tensors
Job hastagaras-halu-8b-llama-3-v3-mkmlizer completed after 83.33s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.17s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3-v3
Waiting for inference service hastagaras-halu-8b-llama-3-v3 to be ready
Inference service hastagaras-halu-8b-llama-3-v3 ready after 71.11898732185364s
Pipeline stage ISVCDeployer completed in 79.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1795687675476074s
Received healthy response to inference request in 1.3628180027008057s
Received healthy response to inference request in 1.3434112071990967s
Received healthy response to inference request in 1.3163378238677979s
Received healthy response to inference request in 1.3641679286956787s
5 requests
0 failed requests
5th percentile: 1.3217525005340576
10th percentile: 1.3271671772003173
20th percentile: 1.337996530532837
30th percentile: 1.3472925662994384
40th percentile: 1.355055284500122
50th percentile: 1.3628180027008057
60th percentile: 1.3633579730987548
70th percentile: 1.363897943496704
80th percentile: 1.5272480964660646
90th percentile: 1.853408432006836
95th percentile: 2.0164885997772215
99th percentile: 2.14695273399353
mean time: 1.5132607460021972
Pipeline stage StressChecker completed in 8.16s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama-3_v3 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama-3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama-3_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-3-v3 is running
Tearing down inference service hastagaras-halu-8b-llama-3-v3
Toredown service hastagaras-halu-8b-llama-3-v3
Pipeline stage ISVCDeleter completed in 5.24s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.91s
hastagaras-halu-8b-llama-3_v3 status is now torndown due to DeploymentManager action