submission_id: hastagaras-llama-3-8b-no_7499_v6
developer_uid: Hastagaras
best_of: 16
celo_rating: 1192.95
display_name: one-more
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nText transcript of a never-ending roleplay 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': False}
generation_params: {'temperature': 0.75, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, '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: one-more
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-not-okay
model_size: 8B
num_battles: 9278
num_wins: 4948
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: 2024-05-16T06:59:34+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5333045915067902
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-no-7499-v6-mkmlizer
Waiting for job on hastagaras-llama-3-8b-no-7499-v6-mkmlizer to finish
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-no-7499-v6-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-v6-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Downloaded to shared memory in 14.183s
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 176.30it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 184.23it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 141.47it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 150.98it/s]
Loading 0:  32%|███▏      | 92/291 [00:00<00:02, 75.91it/s] 
Loading 0:  38%|███▊      | 111/291 [00:01<00:01, 95.46it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 112.51it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 128.97it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 142.48it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 87.10it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 98.06it/s]
Loading 0:  78%|███████▊  | 226/291 [00:01<00:00, 123.29it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 137.97it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 148.60it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 12.37it/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-v6-mkmlizer: quantized model in 18.550s
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Processed model Hastagaras/llama-3-8b-not-okay in 33.849s
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v6
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v6/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v6/config.json
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v6/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v6/tokenizer.json
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v6/flywheel_model.0.safetensors
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-no-7499-v6-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-v6-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v6-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-v6-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v6-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-v6-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v6-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-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Saving duration: 0.268s
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.444s
hastagaras-llama-3-8b-no-7499-v6-mkmlizer: creating bucket guanaco-reward-models
Job hastagaras-llama-3-8b-no-7499-v6-mkmlizer completed after 62.64s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-no-7499-v6-mkmlizer
Pipeline stage MKMLizer completed in 68.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-no-7499-v6
Waiting for inference service hastagaras-llama-3-8b-no-7499-v6 to be ready
Inference service hastagaras-llama-3-8b-no-7499-v6 ready after 30.285972356796265s
Pipeline stage ISVCDeployer completed in 38.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3590247631073s
Received healthy response to inference request in 1.308581829071045s
Received healthy response to inference request in 1.361156702041626s
Received healthy response to inference request in 1.2993793487548828s
Received healthy response to inference request in 1.2872464656829834s
5 requests
0 failed requests
5th percentile: 1.2896730422973632
10th percentile: 1.292099618911743
20th percentile: 1.296952772140503
30th percentile: 1.3012198448181151
40th percentile: 1.30490083694458
50th percentile: 1.308581829071045
60th percentile: 1.3296117782592773
70th percentile: 1.3506417274475098
80th percentile: 1.5607303142547608
90th percentile: 1.9598775386810303
95th percentile: 2.159451150894165
99th percentile: 2.3191100406646727
mean time: 1.5230778217315675
Pipeline stage StressChecker completed in 8.27s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama-3-8b-no_7499_v6 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-no_7499_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-no_7499_v6
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-no-7499-v6 is running
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-no-7499-v6
Toredown service hastagaras-llama-3-8b-no-7499-v6
Pipeline stage ISVCDeleter completed in 9.73s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v6/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.80s
hastagaras-llama-3-8b-no_7499_v6 status is now torndown due to DeploymentManager action