submission_id: hastagaras-llama-3-8b-no_7499_v5
developer_uid: Hastagaras
best_of: 16
celo_rating: 1186.56
display_name: copyyyyhehe
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nText transcript of a never-ending conversation between {bot_name} and {user_name}. In the transcript, gestures and other non-verbal actions are written between asterisks (for example, *waves hello* or *moves closer*).\n\n{bot_name}'s Persona: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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': True}
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-not-okay
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-no
model_name: copyyyyhehe
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-not-okay
model_size: 8B
num_battles: 6489
num_wins: 3344
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': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-16T06:12:52+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5153336415472338
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-no-7499-v5-mkmlizer
Waiting for job on hastagaras-llama-3-8b-no-7499-v5-mkmlizer to finish
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-no-7499-v5-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-llama-3-8b-no-7499-v5-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: Downloaded to shared memory in 13.345s
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 202.10it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 192.76it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 204.25it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:02, 89.96it/s] 
Loading 0:  37%|███▋      | 107/291 [00:00<00:01, 110.40it/s]
Loading 0:  44%|████▍     | 129/291 [00:00<00:01, 128.76it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 139.33it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 149.00it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 95.17it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 106.14it/s]
Loading 0:  78%|███████▊  | 228/291 [00:01<00:00, 132.16it/s]
Loading 0:  85%|████████▍ | 247/291 [00:01<00:00, 143.97it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 151.39it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 12.96it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: quantized model in 17.878s
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: Processed model Hastagaras/llama-3-8b-not-okay in 32.272s
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v5
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v5/config.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v5/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v5/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v5/tokenizer.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v5/flywheel_model.0.safetensors
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-no-7499-v5-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-llama-3-8b-no-7499-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v5-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-llama-3-8b-no-7499-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v5-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-llama-3-8b-no-7499-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v5-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-llama-3-8b-no-7499-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/config.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/merges.txt
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/vocab.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/tokenizer.json
hastagaras-llama-3-8b-no-7499-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v5_reward/reward.tensors
Job hastagaras-llama-3-8b-no-7499-v5-mkmlizer completed after 62.91s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-no-7499-v5-mkmlizer
Pipeline stage MKMLizer completed in 67.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-no-7499-v5
Waiting for inference service hastagaras-llama-3-8b-no-7499-v5 to be ready
Inference service hastagaras-llama-3-8b-no-7499-v5 ready after 30.171449422836304s
Pipeline stage ISVCDeployer completed in 37.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9698996543884277s
Received healthy response to inference request in 1.3512353897094727s
Received healthy response to inference request in 1.2366700172424316s
Received healthy response to inference request in 1.2299020290374756s
Received healthy response to inference request in 1.317295789718628s
5 requests
0 failed requests
5th percentile: 1.2312556266784669
10th percentile: 1.232609224319458
20th percentile: 1.2353164196014403
30th percentile: 1.2527951717376709
40th percentile: 1.2850454807281495
50th percentile: 1.317295789718628
60th percentile: 1.3308716297149659
70th percentile: 1.3444474697113038
80th percentile: 1.4749682426452637
90th percentile: 1.7224339485168458
95th percentile: 1.8461668014526367
99th percentile: 1.9451530838012696
mean time: 1.4210005760192872
Pipeline stage StressChecker completed in 7.72s
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-llama-3-8b-no_7499_v5 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-no_7499_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-no_7499_v5
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-no-7499-v5 is running
Tearing down inference service hastagaras-llama-3-8b-no-7499-v5
Toredown service hastagaras-llama-3-8b-no-7499-v5
Pipeline stage ISVCDeleter completed in 3.67s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v5/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.04s
hastagaras-llama-3-8b-no_7499_v5 status is now torndown due to DeploymentManager action