submission_id: hastagaras-llama-3-8b-ehehe_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1177.26
display_name: hehe
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': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 30, 'presence_penalty': 0.0, 'frequency_penalty': 1.0, '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-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
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-ehehe
model_size: 8B
num_battles: 21364
num_wins: 10747
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: 2024-05-16T01:01:36+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5030425014042315
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-ehehe-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ehehe-v1-mkmlizer to finish
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Downloaded to shared memory in 34.453s
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 124.63it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 138.67it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:01, 133.67it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 132.33it/s]
Loading 0:  25%|██▌       | 74/291 [00:00<00:01, 141.72it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:03, 65.59it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 77.41it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:01, 93.04it/s]
Loading 0:  46%|████▌     | 133/291 [00:01<00:01, 100.02it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 108.96it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:01, 119.91it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 122.82it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 68.22it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 83.10it/s]
Loading 0:  76%|███████▋  | 222/291 [00:02<00:00, 89.74it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 101.81it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 113.89it/s]
Loading 0:  92%|█████████▏| 269/291 [00:02<00:00, 117.78it/s]
Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 120.20it/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-v1-mkmlizer: quantized model in 19.414s
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-ehehe in 55.008s
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v1
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v1/config.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v1/tokenizer_config.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v1/special_tokens_map.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v1/tokenizer.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ehehe-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ehehe-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-llama-3-8b-ehehe-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Saving duration: 0.242s
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.136s
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/config.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/merges.txt
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/vocab.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/tokenizer.json
hastagaras-llama-3-8b-ehehe-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-ehehe-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-ehehe-v1-mkmlizer completed after 83.58s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ehehe-v1-mkmlizer
Pipeline stage MKMLizer completed in 88.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ehehe-v1
Waiting for inference service hastagaras-llama-3-8b-ehehe-v1 to be ready
Inference service hastagaras-llama-3-8b-ehehe-v1 ready after 40.231459856033325s
Pipeline stage ISVCDeployer completed in 48.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.328433036804199s
Received healthy response to inference request in 1.2794911861419678s
Received healthy response to inference request in 1.279329776763916s
Received healthy response to inference request in 1.2675678730010986s
Received healthy response to inference request in 1.155937671661377s
5 requests
0 failed requests
5th percentile: 1.1782637119293213
10th percentile: 1.2005897521972657
20th percentile: 1.2452418327331543
30th percentile: 1.269920253753662
40th percentile: 1.274625015258789
50th percentile: 1.279329776763916
60th percentile: 1.2793943405151367
70th percentile: 1.2794589042663573
80th percentile: 1.4892795562744143
90th percentile: 1.9088562965393068
95th percentile: 2.1186446666717527
99th percentile: 2.28647536277771
mean time: 1.4621519088745116
Pipeline stage StressChecker completed in 7.94s
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-llama-3-8b-ehehe_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-ehehe_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-ehehe_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-ehehe-v1 is running
Tearing down inference service hastagaras-llama-3-8b-ehehe-v1
Toredown service hastagaras-llama-3-8b-ehehe-v1
Pipeline stage ISVCDeleter completed in 4.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ehehe-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ehehe-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ehehe-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.90s
hastagaras-llama-3-8b-ehehe_v1 status is now torndown due to DeploymentManager action