developer_uid: Hastagaras
submission_id: hastagaras-l3-djarcok-8b_v1
model_name: hastagaras-l3-djarcok-8b_v1
model_group: Hastagaras/L3-Djarcok-8B
status: torndown
timestamp: 2024-04-24T14:08:06+00:00
num_battles: 8801
num_wins: 4607
celo_rating: 1170.43
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Djarcok-8B
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: hastagaras-l3-djarcok-8b_v1
is_internal_developer: False
language_model: Hastagaras/L3-Djarcok-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-24
win_ratio: 0.5234632428133167
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n{user_name}:', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay between {bot_name} and {user_name}.\n\n{memory}\n\n", 'prompt_template': "{prompt}<|eot_id|><|start_header_id|>user({user_name})<|end_header_id|>\n\n{user_name}: Let's begin.<|eot_id|>", 'bot_template': '<|start_header_id|>assistant({bot_name})<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user({user_name})<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant({bot_name})<|end_header_id|>\n\n{bot_name}: ', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-l3-djarcok-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-djarcok-8b-v1-mkmlizer to finish
hastagaras-l3-djarcok-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-djarcok-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-djarcok-8b-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-l3-djarcok-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-djarcok-8b-v1-mkmlizer: Downloaded to shared memory in 31.775s
hastagaras-l3-djarcok-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-djarcok-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-djarcok-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 139.98it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 37.09it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-djarcok-8b-v1-mkmlizer: quantized model in 17.449s
hastagaras-l3-djarcok-8b-v1-mkmlizer: Processed model Hastagaras/L3-Djarcok-8B in 50.221s
hastagaras-l3-djarcok-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-djarcok-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-djarcok-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-djarcok-8b-v1
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-djarcok-8b-v1/special_tokens_map.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-djarcok-8b-v1/config.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-djarcok-8b-v1/tokenizer_config.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-djarcok-8b-v1/tokenizer.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-djarcok-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-djarcok-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-djarcok-8b-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-l3-djarcok-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-djarcok-8b-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-l3-djarcok-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-djarcok-8b-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-l3-djarcok-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-djarcok-8b-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-l3-djarcok-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-djarcok-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-djarcok-8b-v1-mkmlizer: Saving duration: 0.243s
hastagaras-l3-djarcok-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.425s
hastagaras-l3-djarcok-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-djarcok-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-djarcok-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/special_tokens_map.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/config.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/tokenizer_config.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/merges.txt
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/vocab.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/tokenizer.json
hastagaras-l3-djarcok-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-djarcok-8b-v1_reward/reward.tensors
Job hastagaras-l3-djarcok-8b-v1-mkmlizer completed after 73.88s with status: succeeded
Stopping job with name hastagaras-l3-djarcok-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-djarcok-8b-v1
Waiting for inference service hastagaras-l3-djarcok-8b-v1 to be ready
Inference service hastagaras-l3-djarcok-8b-v1 ready after 40.28497815132141s
Pipeline stage ISVCDeployer completed in 48.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2165298461914062s
Received healthy response to inference request in 1.3182427883148193s
Received healthy response to inference request in 1.290602684020996s
Received healthy response to inference request in 1.2451884746551514s
Received healthy response to inference request in 1.2825064659118652s
5 requests
0 failed requests
5th percentile: 1.252652072906494
10th percentile: 1.260115671157837
20th percentile: 1.2750428676605225
30th percentile: 1.2841257095336913
40th percentile: 1.2873641967773437
50th percentile: 1.290602684020996
60th percentile: 1.3016587257385255
70th percentile: 1.3127147674560546
80th percentile: 1.697900199890137
90th percentile: 2.4572150230407717
95th percentile: 2.8368724346160885
99th percentile: 3.1405983638763426
mean time: 1.6706140518188477
Pipeline stage StressChecker completed in 9.02s
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 0.08s
hastagaras-l3-djarcok-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-djarcok-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-djarcok-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-djarcok-8b-v1 is running
Tearing down inference service hastagaras-l3-djarcok-8b-v1
Toredown service hastagaras-l3-djarcok-8b-v1
Pipeline stage ISVCDeleter completed in 4.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-djarcok-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-djarcok-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-djarcok-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-djarcok-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-djarcok-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-djarcok-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-djarcok-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-djarcok-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-djarcok-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-djarcok-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-djarcok-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-djarcok-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.60s
hastagaras-l3-djarcok-8b_v1 status is now torndown due to DeploymentManager action