submission_id: hastagaras-llama-3-8b-ehehe_v2
developer_uid: Hastagaras
best_of: 16
celo_rating: 1182.12
display_name: hehe_test
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s persona: {memory}\n\nPlay the role of {bot_name} and write a short response based on the above persona. Actions are wrapped inside asterisks *like this*<|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': 0.85, 'top_p': 1.0, 'min_p': 0.1, '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-ehehe
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-eh
model_name: hehe_test
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-ehehe
model_size: 8B
num_battles: 10584
num_wins: 5406
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: 2024-05-16T01:48:01+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5107709750566893
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-ehehe-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ehehe-v2-mkmlizer to finish
Stopping job with name hastagaras-llama-3-8b-ehehe-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama-3-8b-ehehe-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ehehe-v2-mkmlizer to finish
Stopping job with name hastagaras-llama-3-8b-ehehe-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama-3-8b-ehehe-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ehehe-v2-mkmlizer to finish
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Downloaded to shared memory in 14.631s
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 178.16it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 189.75it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 183.80it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:01, 178.70it/s]
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 81.92it/s] 
Loading 0:  40%|███▉      | 116/291 [00:00<00:01, 105.36it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 126.60it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:00, 139.17it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 157.09it/s]
Loading 0:  68%|██████▊   | 198/291 [00:01<00:01, 89.46it/s] 
Loading 0:  75%|███████▌  | 219/291 [00:01<00:00, 107.96it/s]
Loading 0:  82%|████████▏ | 238/291 [00:01<00:00, 122.91it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 136.85it/s]
Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 156.83it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: quantized model in 17.939s
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-ehehe in 33.723s
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v2
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Saving duration: 0.264s
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.823s
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-ehehe-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v2_reward
Job hastagaras-llama-3-8b-ehehe-v2-mkmlizer completed after 62.62s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ehehe-v2-mkmlizer
Pipeline stage MKMLizer completed in 68.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ehehe-v2
Waiting for inference service hastagaras-llama-3-8b-ehehe-v2 to be ready
Inference service hastagaras-llama-3-8b-ehehe-v2 ready after 40.4933762550354s
Pipeline stage ISVCDeployer completed in 48.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.086178779602051s
Received healthy response to inference request in 1.2824201583862305s
Received healthy response to inference request in 1.2583999633789062s
Received healthy response to inference request in 1.2358100414276123s
Received healthy response to inference request in 1.1995034217834473s
5 requests
0 failed requests
5th percentile: 1.2067647457122803
10th percentile: 1.2140260696411134
20th percentile: 1.2285487174987793
30th percentile: 1.240328025817871
40th percentile: 1.2493639945983888
50th percentile: 1.2583999633789062
60th percentile: 1.268008041381836
70th percentile: 1.2776161193847657
80th percentile: 1.4431718826293947
90th percentile: 1.7646753311157228
95th percentile: 1.9254270553588866
99th percentile: 2.054028434753418
mean time: 1.4124624729156494
Pipeline stage StressChecker completed in 7.70s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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 0.06s
hastagaras-llama-3-8b-ehehe_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-ehehe_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-ehehe_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-ehehe-v2 is running
Tearing down inference service hastagaras-llama-3-8b-ehehe-v2
Toredown service hastagaras-llama-3-8b-ehehe-v2
Pipeline stage ISVCDeleter completed in 4.16s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ehehe-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.95s
hastagaras-llama-3-8b-ehehe_v2 status is now torndown due to DeploymentManager action