hastagaras-halu-8b-llama-3

developer_uid: Hastagaras

submission_id: hastagaras-halu-8b-llama-3_v1

model_name: menghalu

model_group: Hastagaras/Halu-8B-Llama

status: torndown

timestamp: 2024-05-23T22:59:10+00:00

num_battles: 13973

num_wins: 7086

celo_rating: 1193.18

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: menghalu

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: 0.5071208759750948

generation_params: {'temperature': 1.0, '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': '{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-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3-v1-mkmlizer to finish
hastagaras-halu-8b-llama-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3-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-3-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3-v1-mkmlizer: Downloaded to shared memory in 31.507s
hastagaras-halu-8b-llama-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 128.65it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 153.09it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 160.45it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 165.26it/s]
Loading 0:  29%|██▉       | 84/291 [00:00<00:02, 88.02it/s] 
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 105.62it/s]
Loading 0:  41%|████      | 120/291 [00:00<00:01, 121.06it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 133.86it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 142.39it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 148.45it/s]
Loading 0:  65%|██████▌   | 190/291 [00:01<00:01, 94.99it/s] 
Loading 0:  71%|███████   | 206/291 [00:01<00:00, 107.47it/s]
Loading 0:  77%|███████▋  | 224/291 [00:01<00:00, 122.49it/s]
Loading 0:  83%|████████▎ | 242/291 [00:01<00:00, 135.48it/s]
Loading 0:  89%|████████▊ | 258/291 [00:02<00:00, 131.29it/s]
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 140.67it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00,  9.88it/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-v1-mkmlizer: quantized model in 22.686s
hastagaras-halu-8b-llama-3-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama-3 in 56.682s
hastagaras-halu-8b-llama-3-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v1
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v1/config.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v1/special_tokens_map.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v1/tokenizer_config.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v1/tokenizer.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3-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-3-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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-3-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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-3-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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-3-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3-v1-mkmlizer: Saving duration: 0.398s
hastagaras-halu-8b-llama-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.558s
hastagaras-halu-8b-llama-3-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/config.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/merges.txt
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/vocab.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-3-v1-mkmlizer completed after 83.13s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3-v1
Waiting for inference service hastagaras-halu-8b-llama-3-v1 to be ready
Inference service hastagaras-halu-8b-llama-3-v1 ready after 30.169256448745728s
Pipeline stage ISVCDeployer completed in 38.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2499585151672363s
Received healthy response to inference request in 1.3418912887573242s
Received healthy response to inference request in 1.3211913108825684s
Received healthy response to inference request in 1.3019018173217773s
Received healthy response to inference request in 1.3729348182678223s
5 requests
0 failed requests
5th percentile: 1.3057597160339356
10th percentile: 1.3096176147460938
20th percentile: 1.3173334121704101
30th percentile: 1.3253313064575196
40th percentile: 1.333611297607422
50th percentile: 1.3418912887573242
60th percentile: 1.3543087005615235
70th percentile: 1.3667261123657226
80th percentile: 1.5483395576477053
90th percentile: 1.8991490364074708
95th percentile: 2.0745537757873533
99th percentile: 2.2148775672912597
mean time: 1.5175755500793457
Pipeline stage StressChecker completed in 8.26s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
hastagaras-halu-8b-llama-3_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama-3_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-3-v1 is running
Tearing down inference service hastagaras-halu-8b-llama-3-v1
Toredown service hastagaras-halu-8b-llama-3-v1
Pipeline stage ISVCDeleter completed in 3.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.17s
hastagaras-halu-8b-llama-3_v1 status is now torndown due to DeploymentManager action