developer_uid: Hastagaras
submission_id: hastagaras-lm3-8b-overtune_v2
model_name: hastagaras-lm3-8b-overtune_v1
model_group: Hastagaras/lm3-8b-overtu
status: torndown
timestamp: 2024-05-12T01:16:28+00:00
num_battles: 9721
num_wins: 5304
celo_rating: 1198.37
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: 0.5456228783047011
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, '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-v2-mkmlizer
Waiting for job on hastagaras-lm3-8b-overtune-v2-mkmlizer to finish
Stopping job with name hastagaras-lm3-8b-overtune-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-lm3-8b-overtune-v2-mkmlizer
Waiting for job on hastagaras-lm3-8b-overtune-v2-mkmlizer to finish
hastagaras-lm3-8b-overtune-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-overtune-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-8b-overtune-v2-mkmlizer: Downloaded to shared memory in 16.240s
hastagaras-lm3-8b-overtune-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-8b-overtune-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-8b-overtune-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 120.29it/s]
Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 108.25it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 30.72it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-8b-overtune-v2-mkmlizer: quantized model in 17.901s
hastagaras-lm3-8b-overtune-v2-mkmlizer: Processed model Hastagaras/lm3-8b-overtune in 35.250s
hastagaras-lm3-8b-overtune-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-8b-overtune-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-8b-overtune-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v2
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v2/config.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v2/tokenizer_config.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v2/special_tokens_map.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v2/tokenizer.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-8b-overtune-v2/flywheel_model.0.safetensors
hastagaras-lm3-8b-overtune-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-overtune-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-lm3-8b-overtune-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-8b-overtune-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-8b-overtune-v2-mkmlizer: Saving duration: 0.234s
hastagaras-lm3-8b-overtune-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.137s
hastagaras-lm3-8b-overtune-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-8b-overtune-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-8b-overtune-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/config.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/special_tokens_map.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/tokenizer_config.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/vocab.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/merges.txt
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/tokenizer.json
hastagaras-lm3-8b-overtune-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-8b-overtune-v2_reward/reward.tensors
Job hastagaras-lm3-8b-overtune-v2-mkmlizer completed after 99.49s with status: succeeded
Stopping job with name hastagaras-lm3-8b-overtune-v2-mkmlizer
Pipeline stage MKMLizer completed in 103.23s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-8b-overtune-v2
Waiting for inference service hastagaras-lm3-8b-overtune-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service hastagaras-lm3-8b-overtune-v2 ready after 70.4301826953888s
Pipeline stage ISVCDeployer completed in 77.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2774713039398193s
Received healthy response to inference request in 1.3156683444976807s
Received healthy response to inference request in 1.2782025337219238s
Received healthy response to inference request in 1.3345973491668701s
Received healthy response to inference request in 1.300018310546875s
5 requests
0 failed requests
5th percentile: 1.2825656890869142
10th percentile: 1.2869288444519043
20th percentile: 1.2956551551818847
30th percentile: 1.3031483173370362
40th percentile: 1.3094083309173583
50th percentile: 1.3156683444976807
60th percentile: 1.3232399463653564
70th percentile: 1.3308115482330323
80th percentile: 1.5231721401214602
90th percentile: 1.9003217220306396
95th percentile: 2.0888965129852295
99th percentile: 2.2397563457489014
mean time: 1.5011915683746337
Pipeline stage StressChecker completed in 8.11s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
hastagaras-lm3-8b-overtune_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-lm3-8b-overtune_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-8b-overtune_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-overtune-v2 is running
Tearing down inference service hastagaras-lm3-8b-overtune-v2
Toredown service hastagaras-lm3-8b-overtune-v2
Pipeline stage ISVCDeleter completed in 5.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-overtune-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-overtune-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-overtune-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-overtune-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.97s
hastagaras-lm3-8b-overtune_v2 status is now torndown due to DeploymentManager action