developer_uid: Hastagaras
submission_id: hastagaras-lm3-8b-lightune_v2
model_name: hastagaras-lm3-8b-lightune_v1
model_group: Hastagaras/lm3-8b-lightu
status: torndown
timestamp: 2024-05-09T04:06:47+00:00
num_battles: 22640
num_wins: 12277
celo_rating: 1187.1
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/lm3-8b-lightune
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-lightune_v1
is_internal_developer: False
language_model: Hastagaras/lm3-8b-lightune
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-08
win_ratio: 0.5422703180212014
generation_params: {'temperature': 0.83, 'top_p': 0.9, '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': "<|start_header_id|>system<|end_header_id|>\n\nYou're `{bot_name}` in this uncensored fictional roleplay chat with `{user_name}`.\n\nYour persona as {bot_name}: {memory}\n\n", 'prompt_template': 'Your message example: {bot_name}: {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}
model_eval_status: success
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{bot_name}: {prompt}\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 hastagaras-lm3-8b-lightune-v2-mkmlizer
Waiting for job on hastagaras-lm3-8b-lightune-v2-mkmlizer to finish
hastagaras-lm3-8b-lightune-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-8b-lightune-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-lightune-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-8b-lightune-v2-mkmlizer: Downloaded to shared memory in 20.640s
hastagaras-lm3-8b-lightune-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-8b-lightune-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-8b-lightune-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 92.61it/s]
Loading 0:  65%|██████▍   | 189/291 [00:02<00:01, 93.06it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 27.98it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-8b-lightune-v2-mkmlizer: quantized model in 19.594s
hastagaras-lm3-8b-lightune-v2-mkmlizer: Processed model Hastagaras/lm3-8b-lightune in 41.228s
hastagaras-lm3-8b-lightune-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-8b-lightune-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-8b-lightune-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v2
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v2/special_tokens_map.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v2/config.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v2/tokenizer_config.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v2/tokenizer.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v2/flywheel_model.0.safetensors
hastagaras-lm3-8b-lightune-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-8b-lightune-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-lightune-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-lightune-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-lightune-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-lightune-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-lightune-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-lightune-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-lightune-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-8b-lightune-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-8b-lightune-v2-mkmlizer: Saving duration: 0.240s
hastagaras-lm3-8b-lightune-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.686s
hastagaras-lm3-8b-lightune-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-8b-lightune-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-8b-lightune-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/special_tokens_map.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/tokenizer_config.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/vocab.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/merges.txt
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/config.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/tokenizer.json
hastagaras-lm3-8b-lightune-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v2_reward/reward.tensors
Job hastagaras-lm3-8b-lightune-v2-mkmlizer completed after 72.84s with status: succeeded
Stopping job with name hastagaras-lm3-8b-lightune-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-8b-lightune-v2
Waiting for inference service hastagaras-lm3-8b-lightune-v2 to be ready
Inference service hastagaras-lm3-8b-lightune-v2 ready after 30.299800157546997s
Pipeline stage ISVCDeployer completed in 36.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2916316986083984s
Received healthy response to inference request in 1.2620134353637695s
Received healthy response to inference request in 1.2962150573730469s
Received healthy response to inference request in 1.2573332786560059s
Received healthy response to inference request in 1.3242278099060059s
5 requests
0 failed requests
5th percentile: 1.2582693099975586
10th percentile: 1.2592053413391113
20th percentile: 1.2610774040222168
30th percentile: 1.268853759765625
40th percentile: 1.282534408569336
50th percentile: 1.2962150573730469
60th percentile: 1.3074201583862304
70th percentile: 1.318625259399414
80th percentile: 1.5177085876464846
90th percentile: 1.9046701431274415
95th percentile: 2.0981509208679197
99th percentile: 2.252935543060303
mean time: 1.4862842559814453
Pipeline stage StressChecker completed in 8.10s
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-lm3-8b-lightune_v2 status is now deployed due to DeploymentManager action
hastagaras-lm3-8b-lightune_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-8b-lightune_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-lightune-v2 is running
Tearing down inference service hastagaras-lm3-8b-lightune-v2
Toredown service hastagaras-lm3-8b-lightune-v2
Pipeline stage ISVCDeleter completed in 8.68s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-lightune-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-lightune-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.11s
hastagaras-lm3-8b-lightune_v2 status is now torndown due to DeploymentManager action