submission_id: hastagaras-llama-3-8b-o128_v1
developer_uid: Hastagaras
best_of: 16
celo_rating: 1202.45
display_name: strongerrr
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this roleplay chat between {user_name} and {bot_name}. Always write your response as {bot_name} based on the following description.\n\nDescription: {memory}\n", 'prompt_template': 'Previously: {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': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, '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-o128
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-o1
model_name: strongerrr
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-o128
model_size: 8B
num_battles: 11902
num_wins: 6344
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-14T23:34:31+00:00
us_pacific_date: 2024-05-14
win_ratio: 0.5330196605612502
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-o128-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-o128-v1-mkmlizer to finish
hastagaras-llama-3-8b-o128-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-o128-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-o128-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-o128-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-o128-v1-mkmlizer: Downloaded to shared memory in 26.955s
hastagaras-llama-3-8b-o128-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-o128-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-o128-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 200.96it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 201.38it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 212.45it/s]
Loading 0:  30%|███       | 88/291 [00:00<00:02, 100.85it/s]
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 125.94it/s]
Loading 0:  45%|████▍     | 130/291 [00:00<00:01, 140.00it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:00, 151.34it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:00, 150.60it/s]
Loading 0:  64%|██████▍   | 186/291 [00:01<00:00, 142.22it/s]
Loading 0:  69%|██████▉   | 202/291 [00:01<00:01, 86.03it/s] 
Loading 0:  76%|███████▌  | 221/291 [00:01<00:00, 103.31it/s]
Loading 0:  85%|████████▍ | 246/291 [00:01<00:00, 129.80it/s]
Loading 0:  91%|█████████ | 265/291 [00:01<00:00, 140.23it/s]
Loading 0:  98%|█████████▊| 285/291 [00:02<00:00, 153.05it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-o128-v1-mkmlizer: quantized model in 17.744s
hastagaras-llama-3-8b-o128-v1-mkmlizer: Processed model Hastagaras/llama-3-8b-o128 in 45.760s
hastagaras-llama-3-8b-o128-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-o128-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-o128-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v1
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v1/tokenizer.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v1/config.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v1/tokenizer_config.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v1/special_tokens_map.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-o128-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-o128-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-o128-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-o128-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-o128-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-o128-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-o128-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-o128-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-o128-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-o128-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-o128-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-o128-v1-mkmlizer: Saving duration: 0.240s
hastagaras-llama-3-8b-o128-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.712s
hastagaras-llama-3-8b-o128-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-o128-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-o128-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/config.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/vocab.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/tokenizer.json
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/merges.txt
hastagaras-llama-3-8b-o128-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-o128-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-o128-v1-mkmlizer completed after 62.74s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-o128-v1-mkmlizer
Pipeline stage MKMLizer completed in 65.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-o128-v1
Waiting for inference service hastagaras-llama-3-8b-o128-v1 to be ready
Inference service hastagaras-llama-3-8b-o128-v1 ready after 40.2295286655426s
Pipeline stage ISVCDeployer completed in 47.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.194761037826538s
Received healthy response to inference request in 1.2779033184051514s
Received healthy response to inference request in 1.3494062423706055s
Received healthy response to inference request in 1.307920217514038s
Received healthy response to inference request in 1.2837848663330078s
5 requests
0 failed requests
5th percentile: 1.2790796279907226
10th percentile: 1.2802559375762939
20th percentile: 1.2826085567474366
30th percentile: 1.288611936569214
40th percentile: 1.2982660770416259
50th percentile: 1.307920217514038
60th percentile: 1.324514627456665
70th percentile: 1.341109037399292
80th percentile: 1.5184772014617922
90th percentile: 1.856619119644165
95th percentile: 2.0256900787353516
99th percentile: 2.160946846008301
mean time: 1.4827551364898681
Pipeline stage StressChecker completed in 8.06s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-o128_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-o128_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-o128_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-o128-v1 is running
Tearing down inference service hastagaras-llama-3-8b-o128-v1
Toredown service hastagaras-llama-3-8b-o128-v1
Pipeline stage ISVCDeleter completed in 4.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-o128-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-o128-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-o128-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-o128-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.51s
hastagaras-llama-3-8b-o128_v1 status is now torndown due to DeploymentManager action