submission_id: hastagaras-l3-uneimo-8b-_2833_v3
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/L3-Uneimo-8B-ChatML
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n{user_name}:', '\n{bot_name}:', '<|eot_id|>', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\nYou\'re {bot_name} in this uncensored fictional roleplay with {user_name}. \n\n*Gesture and narrations written inside asterisk (*).*\n`Inner thoughts written inside backticks (\').`\n"Dialogues written inside quotes (")."\n\nRemember to stay in character and respond accordingly to {user_name}\'s actions and dialogues. Feel free to add your own gestures, thoughts, and emotions to make the roleplay more engaging and immersive.\n\n{memory}\n\n', 'prompt_template': '{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}: ', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-23T07:21:17+00:00
model_name: hastagaras-l3-uneimo-8b-_2833_v3
model_eval_status: pending
model_group: Hastagaras/L3-Uneimo-8B-
num_battles: 8069
num_wins: 4439
celo_rating: 1186.97
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-l3-uneimo-8b-_2833_v3
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/L3-Uneimo-8B-ChatML
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-23
win_ratio: 0.5501301276490271
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-uneimo-8b-2833-v3-mkmlizer
Waiting for job on hastagaras-l3-uneimo-8b-2833-v3-mkmlizer to finish
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ /___/ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ belonging to: ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ║ ║
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-uneimo-8b-2833-v3-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-l3-uneimo-8b-2833-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Downloaded to shared memory in 15.511s
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 55%|█████▌ | 161/291 [00:01<00:00, 160.96it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 38.67it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: quantized model in 16.704s
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Processed model Hastagaras/L3-Uneimo-8B-ChatML in 33.115s
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v3
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v3/special_tokens_map.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v3/tokenizer_config.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v3/config.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v3/tokenizer.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-uneimo-8b-2833-v3/flywheel_model.0.safetensors
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-uneimo-8b-2833-v3-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-l3-uneimo-8b-2833-v3-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v3-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-l3-uneimo-8b-2833-v3-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v3-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-l3-uneimo-8b-2833-v3-mkmlizer: warnings.warn(
hastagaras-l3-uneimo-8b-2833-v3-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-l3-uneimo-8b-2833-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Saving duration: 0.218s
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.760s
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/special_tokens_map.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/vocab.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/config.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/merges.txt
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/tokenizer_config.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/tokenizer.json
hastagaras-l3-uneimo-8b-2833-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-uneimo-8b-2833-v3_reward/reward.tensors
Job hastagaras-l3-uneimo-8b-2833-v3-mkmlizer completed after 69.98s with status: succeeded
Stopping job with name hastagaras-l3-uneimo-8b-2833-v3-mkmlizer
Pipeline stage MKMLizer completed in 73.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-uneimo-8b-2833-v3
Waiting for inference service hastagaras-l3-uneimo-8b-2833-v3 to be ready
Inference service hastagaras-l3-uneimo-8b-2833-v3 ready after 40.28243112564087s
Pipeline stage ISVCDeployer completed in 47.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1819608211517334s
Received healthy response to inference request in 1.2609412670135498s
Received healthy response to inference request in 1.2749156951904297s
Received healthy response to inference request in 1.520392656326294s
Received healthy response to inference request in 1.2765796184539795s
5 requests
0 failed requests
5th percentile: 1.2637361526489257
10th percentile: 1.2665310382843018
20th percentile: 1.2721208095550538
30th percentile: 1.2752484798431396
40th percentile: 1.2759140491485597
50th percentile: 1.2765796184539795
60th percentile: 1.3741048336029054
70th percentile: 1.471630048751831
80th percentile: 1.652706289291382
90th percentile: 1.9173335552215578
95th percentile: 2.0496471881866456
99th percentile: 2.1554980945587157
mean time: 1.5029580116271972
Pipeline stage StressChecker completed in 8.22s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-uneimo-8b-_2833_v3 status is now deployed due to DeploymentManager action
hastagaras-l3-uneimo-8b-_2833_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-uneimo-8b-_2833_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-uneimo-8b-2833-v3 is running
Tearing down inference service hastagaras-l3-uneimo-8b-2833-v3
Toredown service hastagaras-l3-uneimo-8b-2833-v3
Pipeline stage ISVCDeleter completed in 6.91s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-uneimo-8b-2833-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-uneimo-8b-2833-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.65s
hastagaras-l3-uneimo-8b-_2833_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics