developer_uid: Hastagaras
submission_id: hastagaras-lm3-8b-overtune_v1
model_name: hastagaras-lm3-8b-overtune_v1
model_group: Hastagaras/lm3-8b-overtu
status: torndown
timestamp: 2024-05-12T00:51:16+00:00
num_battles: 7802
num_wins: 4352
celo_rating: 1201.15
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/lm3-8b-overtune
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-lm3-8b-overtune_v1
is_internal_developer: False
language_model: Hastagaras/lm3-8b-overtune
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-11
win_ratio: 0.5578056908485004
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', '<|eot_id|>'], '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're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", 'prompt_template': 'Notes: {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}
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-lm3-8b-overtune-v1-mkmlizer
Waiting for job on hastagaras-lm3-8b-overtune-v1-mkmlizer to finish
hastagaras-lm3-8b-overtune-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-8b-overtune-v1-mkmlizer: Downloaded to shared memory in 29.112s
hastagaras-lm3-8b-overtune-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-8b-overtune-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-8b-overtune-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  39%|███▉      | 113/291 [00:00<00:01, 113.03it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 123.61it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 30.41it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-8b-overtune-v1-mkmlizer: quantized model in 17.565s
hastagaras-lm3-8b-overtune-v1-mkmlizer: Processed model Hastagaras/lm3-8b-overtune in 47.766s
hastagaras-lm3-8b-overtune-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-8b-overtune-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-8b-overtune-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v1
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v1/config.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v1/tokenizer_config.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v1/special_tokens_map.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v1/tokenizer.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v1/flywheel_model.0.safetensors
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-8b-overtune-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-8b-overtune-v1-mkmlizer: Saving duration: 0.236s
hastagaras-lm3-8b-overtune-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.663s
hastagaras-lm3-8b-overtune-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-8b-overtune-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-8b-overtune-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/config.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/special_tokens_map.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/tokenizer_config.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/merges.txt
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/vocab.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/tokenizer.json
hastagaras-lm3-8b-overtune-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v1_reward/reward.tensors
Job hastagaras-lm3-8b-overtune-v1-mkmlizer completed after 83.31s with status: succeeded
Stopping job with name hastagaras-lm3-8b-overtune-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-8b-overtune-v1
Waiting for inference service hastagaras-lm3-8b-overtune-v1 to be ready
Inference service hastagaras-lm3-8b-overtune-v1 ready after 30.171313285827637s
Pipeline stage ISVCDeployer completed in 37.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1873257160186768s
Received healthy response to inference request in 1.3237676620483398s
Received healthy response to inference request in 1.3015251159667969s
Received healthy response to inference request in 1.3522918224334717s
Received healthy response to inference request in 1.3268132209777832s
5 requests
0 failed requests
5th percentile: 1.3059736251831056
10th percentile: 1.310422134399414
20th percentile: 1.3193191528320312
30th percentile: 1.3243767738342285
40th percentile: 1.325594997406006
50th percentile: 1.3268132209777832
60th percentile: 1.3370046615600586
70th percentile: 1.347196102142334
80th percentile: 1.519298601150513
90th percentile: 1.8533121585845949
95th percentile: 2.0203189373016355
99th percentile: 2.1539243602752687
mean time: 1.4983447074890137
Pipeline stage StressChecker completed in 8.12s
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-lm3-8b-overtune_v1 status is now deployed due to DeploymentManager action
hastagaras-lm3-8b-overtune_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-8b-overtune_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-overtune-v1 is running
admin requested tearing down of hastagaras-lp-8b-dpotest_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lp-8b-dpotest-v3 is running
Tearing down inference service hastagaras-lm3-8b-overtune-v1
Toredown service hastagaras-lm3-8b-overtune-v1
Pipeline stage ISVCDeleter completed in 8.31s
Running pipeline stage MKMLModelDeleter
Tearing down inference service hastagaras-lp-8b-dpotest-v3
Cleaning model data from S3
Toredown service hastagaras-lp-8b-dpotest-v3
Cleaning model data from model cache
Pipeline stage ISVCDeleter completed in 5.45s
Deleting key hastagaras-lm3-8b-overtune-v1/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Deleting key hastagaras-lm3-8b-overtune-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lp-8b-dpotest-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lp-8b-dpotest-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lp-8b-dpotest-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v1_reward/reward.tensors from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-overtune-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v1_reward/vocab.json from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lp-8b-dpotest-v3_reward/tokenizer.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.07s
Deleting key hastagaras-lp-8b-dpotest-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
hastagaras-lm3-8b-overtune_v1 status is now torndown due to DeploymentManager action
Deleting key hastagaras-lp-8b-dpotest-v3_reward/vocab.json from bucket guanaco-reward-models