hastagaras-halu-8b-llama_2564

developer_uid: Hastagaras

submission_id: hastagaras-halu-8b-llama_2564_v2

model_name: hashslingingslasherrr

model_group: Hastagaras/Halu-8B-Llama

status: torndown

timestamp: 2024-05-24T07:35:25+00:00

num_battles: 12573

num_wins: 7020

celo_rating: 1208.8

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Halu-8B-Llama3-v0.3

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: hashslingingslasherrr

is_internal_developer: False

language_model: Hastagaras/Halu-8B-Llama3-v0.3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-24

win_ratio: 0.5583392984967788

generation_params: {'temperature': 1.1, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 80, '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': '{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-2564-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-2564-v2-mkmlizer to finish
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-2564-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-2564-v2-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-2564-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-2564-v2-mkmlizer: Downloaded to shared memory in 18.245s
hastagaras-halu-8b-llama-2564-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-2564-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 121.10it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 146.23it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 155.19it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 159.17it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 86.06it/s] 
Loading 0:  34%|███▎      | 98/291 [00:00<00:01, 98.77it/s]
Loading 0:  39%|███▉      | 113/291 [00:00<00:01, 109.30it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 124.32it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 136.06it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 145.25it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 98.28it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 105.97it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 120.07it/s]
Loading 0:  82%|████████▏ | 238/291 [00:01<00:00, 132.23it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 142.15it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 149.24it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.37it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-2564-v2-mkmlizer: quantized model in 22.778s
hastagaras-halu-8b-llama-2564-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.3 in 43.559s
hastagaras-halu-8b-llama-2564-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-2564-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v2
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v2/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v2/config.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v2/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v2/tokenizer.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-2564-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-2564-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-2564-v2-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-2564-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2564-v2-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-2564-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2564-v2-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-2564-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-2564-v2-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-2564-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-2564-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-2564-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-2564-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/config.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/merges.txt
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/vocab.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-2564-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-2564-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-2564-v2-mkmlizer completed after 72.62s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-2564-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-2564-v2
Waiting for inference service hastagaras-halu-8b-llama-2564-v2 to be ready
Inference service hastagaras-halu-8b-llama-2564-v2 ready after 152.29599976539612s
Pipeline stage ISVCDeployer completed in 160.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1914360523223877s
Received healthy response to inference request in 1.3624279499053955s
Received healthy response to inference request in 1.3457491397857666s
Received healthy response to inference request in 1.3045220375061035s
Received healthy response to inference request in 1.2639164924621582s
5 requests
0 failed requests
5th percentile: 1.2720376014709474
10th percentile: 1.2801587104797363
20th percentile: 1.2964009284973144
30th percentile: 1.312767457962036
40th percentile: 1.3292582988739015
50th percentile: 1.3457491397857666
60th percentile: 1.3524206638336183
70th percentile: 1.3590921878814697
80th percentile: 1.528229570388794
90th percentile: 1.8598328113555909
95th percentile: 2.025634431838989
99th percentile: 2.158275728225708
mean time: 1.4936103343963623
Pipeline stage StressChecker completed in 8.08s
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_2564_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_2564_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_2564_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-2564-v2 is running
Tearing down inference service hastagaras-halu-8b-llama-2564-v2
Toredown service hastagaras-halu-8b-llama-2564-v2
Pipeline stage ISVCDeleter completed in 3.84s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-2564-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2564-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2564-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2564-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-2564-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-2564-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.89s
hastagaras-halu-8b-llama_2564_v2 status is now torndown due to DeploymentManager action