submission_id: hastagaras-halu-8b-llama-3_v2
developer_uid: Hastagaras
best_of: 16
celo_rating: 1191.9
display_name: menghalu2
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': 1.15, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 200, 'presence_penalty': 0.25, '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-Llama-3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/Halu-8B-Llama
model_name: menghalu2
model_num_parameters: 8030261248.0
model_repo: Hastagaras/Halu-8B-Llama-3
model_size: 8B
num_battles: 8763
num_wins: 4417
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: 2024-05-23T23:29:12+00:00
us_pacific_date: 2024-05-23
win_ratio: 0.5040511240442771
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3-v2-mkmlizer to finish
hastagaras-halu-8b-llama-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3-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-3-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3-v2-mkmlizer: Downloaded to shared memory in 16.321s
hastagaras-halu-8b-llama-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 120.37it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 146.65it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 157.25it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 160.63it/s]
Loading 0:  29%|██▉       | 84/291 [00:00<00:02, 86.22it/s] 
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 103.43it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:01, 117.99it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 130.46it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 140.38it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 145.88it/s]
Loading 0:  65%|██████▍   | 189/291 [00:01<00:01, 91.49it/s] 
Loading 0:  71%|███████   | 206/291 [00:01<00:00, 105.61it/s]
Loading 0:  76%|███████▌  | 221/291 [00:01<00:00, 114.74it/s]
Loading 0:  82%|████████▏ | 239/291 [00:01<00:00, 128.04it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 138.64it/s]
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 146.51it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.06it/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-v2-mkmlizer: quantized model in 22.841s
hastagaras-halu-8b-llama-3-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama-3 in 41.674s
hastagaras-halu-8b-llama-3-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v2
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v2/tokenizer_config.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v2/tokenizer.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v2/special_tokens_map.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v2/config.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3-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-3-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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-3-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3-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-3-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3-v2-mkmlizer: Saving duration: 0.401s
hastagaras-halu-8b-llama-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.476s
hastagaras-halu-8b-llama-3-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/config.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/vocab.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/merges.txt
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-3-v2-mkmlizer completed after 65.28s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 70.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3-v2
Waiting for inference service hastagaras-halu-8b-llama-3-v2 to be ready
Inference service hastagaras-halu-8b-llama-3-v2 ready after 40.212087869644165s
Pipeline stage ISVCDeployer completed in 48.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.27577543258667s
Received healthy response to inference request in 1.3910963535308838s
Received healthy response to inference request in 1.3323204517364502s
Received healthy response to inference request in 1.3391532897949219s
Received healthy response to inference request in 1.3711872100830078s
5 requests
0 failed requests
5th percentile: 1.3336870193481445
10th percentile: 1.3350535869598388
20th percentile: 1.3377867221832276
30th percentile: 1.345560073852539
40th percentile: 1.3583736419677734
50th percentile: 1.3711872100830078
60th percentile: 1.3791508674621582
70th percentile: 1.3871145248413086
80th percentile: 1.5680321693420411
90th percentile: 1.9219038009643556
95th percentile: 2.0988396167755123
99th percentile: 2.2403882694244386
mean time: 1.5419065475463867
Pipeline stage StressChecker completed in 8.28s
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_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama-3_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-3-v2 is running
Tearing down inference service hastagaras-halu-8b-llama-3-v2
Toredown service hastagaras-halu-8b-llama-3-v2
Pipeline stage ISVCDeleter completed in 4.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.73s
hastagaras-halu-8b-llama-3_v2 status is now torndown due to DeploymentManager action