developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-ouch_v2
model_name: ouch-wrong-format
model_group: Hastagaras/llama-3-8b-ou
status: torndown
timestamp: 2024-05-14T10:49:33+00:00
num_battles: 12220
num_wins: 6286
celo_rating: 1181.73
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-ouch
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: ouch-wrong-format
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-ouch
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-14
win_ratio: 0.5144026186579378
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nDescription:\n{memory}\n", 'prompt_template': 'Example conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>{user_name}<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-ouch-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ouch-v2-mkmlizer to finish
Stopping job with name hastagaras-llama-3-8b-ouch-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-llama-3-8b-ouch-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ouch-v2-mkmlizer to finish
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ouch-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ouch-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-ouch-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Downloaded to shared memory in 11.024s
hastagaras-llama-3-8b-ouch-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ouch-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  45%|████▌     | 131/291 [00:00<00:01, 131.12it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 137.42it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-ouch-v2-mkmlizer: quantized model in 17.065s
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-ouch in 29.123s
hastagaras-llama-3-8b-ouch-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ouch-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v2
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v2/tokenizer_config.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v2/config.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v2/special_tokens_map.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v2/tokenizer.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ouch-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ouch-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-ouch-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-ouch-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ouch-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-ouch-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ouch-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-ouch-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ouch-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-ouch-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Saving duration: 0.240s
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.361s
hastagaras-llama-3-8b-ouch-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-ouch-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-ouch-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/config.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/merges.txt
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/vocab.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/tokenizer.json
hastagaras-llama-3-8b-ouch-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-ouch-v2_reward/reward.tensors
Job hastagaras-llama-3-8b-ouch-v2-mkmlizer completed after 53.32s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ouch-v2-mkmlizer
Pipeline stage MKMLizer completed in 58.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ouch-v2
Waiting for inference service hastagaras-llama-3-8b-ouch-v2 to be ready
Inference service hastagaras-llama-3-8b-ouch-v2 ready after 40.21695613861084s
Pipeline stage ISVCDeployer completed in 47.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0844833850860596s
Received healthy response to inference request in 1.3551185131072998s
Received healthy response to inference request in 1.3336923122406006s
Received healthy response to inference request in 1.3115324974060059s
Received healthy response to inference request in 1.2633435726165771s
5 requests
0 failed requests
5th percentile: 1.2729813575744628
10th percentile: 1.2826191425323485
20th percentile: 1.3018947124481202
30th percentile: 1.3159644603729248
40th percentile: 1.3248283863067627
50th percentile: 1.3336923122406006
60th percentile: 1.3422627925872803
70th percentile: 1.35083327293396
80th percentile: 1.500991487503052
90th percentile: 1.7927374362945558
95th percentile: 1.9386104106903075
99th percentile: 2.055308790206909
mean time: 1.4696340560913086
Pipeline stage StressChecker completed in 8.02s
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 0.07s
hastagaras-llama-3-8b-ouch_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-ouch_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-ouch_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-ouch-v2 is running
Tearing down inference service hastagaras-llama-3-8b-ouch-v2
Toredown service hastagaras-llama-3-8b-ouch-v2
Pipeline stage ISVCDeleter completed in 8.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ouch-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ouch-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ouch-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.35s
hastagaras-llama-3-8b-ouch_v2 status is now torndown due to DeploymentManager action