developer_uid: sao10k
submission_id: sao10k-stheno-3-2-beta_v1
model_name: L3-Itr-1
model_group: Sao10K/Stheno-3.2-Beta
status: torndown
timestamp: 2024-06-02T06:08:22+00:00
num_battles: 7999
num_wins: 3915
celo_rating: 1189.26
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/Stheno-3.2-Beta
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: L3-Itr-1
is_internal_developer: False
language_model: Sao10K/Stheno-3.2-Beta
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-01
win_ratio: 0.4894361795224403
generation_params: {'temperature': 1.12, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n,', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.', 'prompt_template': 'Example Conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>[{user_name}]<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>[{bot_name}]<|end_header_id|>\n\n', 'truncate_by_message': True}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-stheno-3-2-beta-v1-mkmlizer
Waiting for job on sao10k-stheno-3-2-beta-v1-mkmlizer to finish
sao10k-stheno-3-2-beta-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-stheno-3-2-beta-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║       /___/                                                         ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║                                                                     ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║                                                                     ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║                                                                     ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ║                                                                     ║
sao10k-stheno-3-2-beta-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-stheno-3-2-beta-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.
sao10k-stheno-3-2-beta-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
sao10k-stheno-3-2-beta-v1-mkmlizer: Downloaded to shared memory in 31.701s
sao10k-stheno-3-2-beta-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-stheno-3-2-beta-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-stheno-3-2-beta-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 78.00it/s]
Loading 0:  64%|██████▍   | 187/291 [00:02<00:01, 92.39it/s]
Loading 0:  99%|█████████▊| 287/291 [00:02<00:00, 135.39it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-stheno-3-2-beta-v1-mkmlizer: quantized model in 23.562s
sao10k-stheno-3-2-beta-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-stheno-3-2-beta-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-stheno-3-2-beta-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-stheno-3-2-beta-v1
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-stheno-3-2-beta-v1/special_tokens_map.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-stheno-3-2-beta-v1/tokenizer_config.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-stheno-3-2-beta-v1/config.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-stheno-3-2-beta-v1/tokenizer.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-stheno-3-2-beta-v1/flywheel_model.0.safetensors
sao10k-stheno-3-2-beta-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.
sao10k-stheno-3-2-beta-v1-mkmlizer:   warnings.warn(
sao10k-stheno-3-2-beta-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-stheno-3-2-beta-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.
sao10k-stheno-3-2-beta-v1-mkmlizer:   warnings.warn(
sao10k-stheno-3-2-beta-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.
sao10k-stheno-3-2-beta-v1-mkmlizer:   warnings.warn(
sao10k-stheno-3-2-beta-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()
sao10k-stheno-3-2-beta-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-stheno-3-2-beta-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-stheno-3-2-beta-v1-mkmlizer: Saving duration: 0.441s
sao10k-stheno-3-2-beta-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.341s
sao10k-stheno-3-2-beta-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-stheno-3-2-beta-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-stheno-3-2-beta-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/special_tokens_map.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/merges.txt
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/tokenizer_config.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/config.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/vocab.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/tokenizer.json
sao10k-stheno-3-2-beta-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-stheno-3-2-beta-v1_reward/reward.tensors
Job sao10k-stheno-3-2-beta-v1-mkmlizer completed after 82.89s with status: succeeded
Stopping job with name sao10k-stheno-3-2-beta-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-stheno-3-2-beta-v1
Waiting for inference service sao10k-stheno-3-2-beta-v1 to be ready
Inference service sao10k-stheno-3-2-beta-v1 ready after 40.21829414367676s
Pipeline stage ISVCDeployer completed in 47.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2277777194976807s
Received healthy response to inference request in 1.256937026977539s
Received healthy response to inference request in 1.3404674530029297s
Received healthy response to inference request in 1.318760871887207s
Received healthy response to inference request in 1.2914929389953613s
5 requests
0 failed requests
5th percentile: 1.2638482093811034
10th percentile: 1.270759391784668
20th percentile: 1.284581756591797
30th percentile: 1.2969465255737305
40th percentile: 1.3078536987304688
50th percentile: 1.318760871887207
60th percentile: 1.327443504333496
70th percentile: 1.3361261367797852
80th percentile: 1.51792950630188
90th percentile: 1.8728536128997804
95th percentile: 2.0503156661987303
99th percentile: 2.1922853088378904
mean time: 1.4870872020721435
Pipeline stage StressChecker completed in 8.05s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
sao10k-stheno-3-2-beta_v1 status is now deployed due to DeploymentManager action
sao10k-stheno-3-2-beta_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-stheno-3-2-beta_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-stheno-3-2-beta-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-stheno-3-2-beta-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-stheno-3-2-beta-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-stheno-3-2-beta-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-stheno-3-2-beta-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-stheno-3-2-beta-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-stheno-3-2-beta-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-stheno-3-2-beta-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-stheno-3-2-beta-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-stheno-3-2-beta-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-stheno-3-2-beta-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-stheno-3-2-beta-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-stheno-3-2-beta-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.38s
sao10k-stheno-3-2-beta_v1 status is now torndown due to DeploymentManager action