jellywibble-chateaulafit_7738

submission_id: jellywibble-chateaulafit_7738_v2

developer_uid: Jellywibble

best_of: 4

celo_rating: 1190.61

display_name: jellywibble-chateaulafit_v2

family_friendly_score: 0.0

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

is_internal_developer: True

language_model: Jellywibble/ChateauLafite8BRawQLORA

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Jellywibble/ChateauLafit

model_name: jellywibble-chateaulafit_v2

model_num_parameters: 8030261248.0

model_repo: Jellywibble/ChateauLafite8BRawQLORA

model_size: 8B

num_battles: 5842

num_wins: 3059

ranking_group: single

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-05-22T07:40:50+00:00

us_pacific_date: 2024-05-22

win_ratio: 0.5236220472440944

Resubmit model

Running pipeline stage MKMLizer
Starting job with name jellywibble-chateaulafit-7738-v2-mkmlizer
Waiting for job on jellywibble-chateaulafit-7738-v2-mkmlizer to finish
jellywibble-chateaulafit-7738-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-chateaulafit-7738-v2-mkmlizer: ║     _____            __           __                                ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║       /___/                                                         ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║                                                                     ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║                                                                     ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  belonging to:                                                      ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║                                                                     ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ║                                                                     ║
jellywibble-chateaulafit-7738-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
jellywibble-chateaulafit-7738-v2-mkmlizer: Downloaded to shared memory in 44.127s
jellywibble-chateaulafit-7738-v2-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-chateaulafit-7738-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-chateaulafit-7738-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 114.99it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 103.20it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:05, 50.13it/s] 
Loading 0:  15%|█▌        | 45/291 [00:00<00:04, 61.07it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:03, 75.10it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 81.34it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:03, 55.33it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:03, 63.01it/s]
Loading 0:  35%|███▍      | 101/291 [00:01<00:02, 70.05it/s]
Loading 0:  40%|███▉      | 116/291 [00:01<00:02, 85.02it/s]
Loading 0:  44%|████▍     | 128/291 [00:01<00:01, 93.19it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 57.98it/s]
Loading 0:  52%|█████▏    | 152/291 [00:02<00:01, 69.95it/s]
Loading 0:  57%|█████▋    | 165/291 [00:02<00:01, 81.40it/s]
Loading 0:  60%|██████    | 176/291 [00:02<00:01, 83.18it/s]
Loading 0:  64%|██████▍   | 186/291 [00:02<00:01, 59.76it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 60.27it/s]
Loading 0:  72%|███████▏  | 210/291 [00:02<00:01, 78.09it/s]
Loading 0:  76%|███████▌  | 221/291 [00:03<00:00, 81.43it/s]
Loading 0:  80%|████████  | 233/291 [00:03<00:00, 58.73it/s]
Loading 0:  84%|████████▍ | 244/291 [00:03<00:00, 67.54it/s]
Loading 0:  88%|████████▊ | 256/291 [00:03<00:00, 75.52it/s]
Loading 0:  92%|█████████▏| 269/291 [00:03<00:00, 86.60it/s]
Loading 0:  97%|█████████▋| 281/291 [00:03<00:00, 92.44it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-chateaulafit-7738-v2-mkmlizer: quantized model in 19.510s
jellywibble-chateaulafit-7738-v2-mkmlizer: Processed model Jellywibble/ChateauLafite8BRawQLORA in 65.642s
jellywibble-chateaulafit-7738-v2-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-chateaulafit-7738-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-chateaulafit-7738-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v2
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v2/tokenizer_config.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v2/special_tokens_map.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v2/config.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v2/tokenizer.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-chateaulafit-7738-v2/flywheel_model.0.safetensors
jellywibble-chateaulafit-7738-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v2-mkmlizer:   warnings.warn(
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v2-mkmlizer:   warnings.warn(
jellywibble-chateaulafit-7738-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.
jellywibble-chateaulafit-7738-v2-mkmlizer:   warnings.warn(
jellywibble-chateaulafit-7738-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()
jellywibble-chateaulafit-7738-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
jellywibble-chateaulafit-7738-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-chateaulafit-7738-v2-mkmlizer: Saving duration: 0.219s
jellywibble-chateaulafit-7738-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.323s
jellywibble-chateaulafit-7738-v2-mkmlizer: creating bucket guanaco-reward-models
jellywibble-chateaulafit-7738-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-chateaulafit-7738-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/special_tokens_map.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/tokenizer_config.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/config.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/merges.txt
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/vocab.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/tokenizer.json
jellywibble-chateaulafit-7738-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-chateaulafit-7738-v2_reward/reward.tensors
Job jellywibble-chateaulafit-7738-v2-mkmlizer completed after 93.5s with status: succeeded
Stopping job with name jellywibble-chateaulafit-7738-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-chateaulafit-7738-v2
Waiting for inference service jellywibble-chateaulafit-7738-v2 to be ready
Inference service jellywibble-chateaulafit-7738-v2 ready after 40.209277629852295s
Pipeline stage ISVCDeployer completed in 46.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0600268840789795s
Received healthy response to inference request in 1.1322855949401855s
Received healthy response to inference request in 1.1248626708984375s
Received healthy response to inference request in 1.1193232536315918s
Received healthy response to inference request in 1.1077892780303955s
5 requests
0 failed requests
5th percentile: 1.1100960731506349
10th percentile: 1.112402868270874
20th percentile: 1.1170164585113525
30th percentile: 1.120431137084961
40th percentile: 1.1226469039916993
50th percentile: 1.1248626708984375
60th percentile: 1.1278318405151366
70th percentile: 1.130801010131836
80th percentile: 1.3178338527679445
90th percentile: 1.688930368423462
95th percentile: 1.8744786262512205
99th percentile: 2.0229172325134277
mean time: 1.308857536315918
Pipeline stage StressChecker completed in 7.14s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
jellywibble-chateaulafit_7738_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
jellywibble-chateaulafit_7738_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-chateaulafit_7738_v2
Running pipeline stage ISVCDeleter
Checking if service jellywibble-chateaulafit-7738-v2 is running
Tearing down inference service jellywibble-chateaulafit-7738-v2
Toredown service jellywibble-chateaulafit-7738-v2
Pipeline stage ISVCDeleter completed in 5.12s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-chateaulafit-7738-v2/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-7738-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-7738-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-7738-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-7738-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-chateaulafit-7738-v2_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-7738-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-7738-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-7738-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-7738-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-7738-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-7738-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.43s
jellywibble-chateaulafit_7738_v2 status is now torndown due to DeploymentManager action