submission_id: jellywibble-chateaulafit_1556_v2
developer_uid: Jellywibble
status: torndown
model_repo: Jellywibble/ChateauLafite8BLORA
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
reward_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}
timestamp: 2024-05-24T04:55:53+00:00
model_name: jellywibble-chateaulafit_v2
model_eval_status: success
model_group: Jellywibble/ChateauLafit
num_battles: 15485
num_wins: 8286
celo_rating: 1201.41
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: jellywibble-chateaulafit_v2
ineligible_reason: propriety_total_count < 800
language_model: Jellywibble/ChateauLafite8BLORA
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-23
win_ratio: 0.5350984824023248
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-chateaulafit-1556-v2-mkmlizer
Waiting for job on jellywibble-chateaulafit-1556-v2-mkmlizer to finish
jellywibble-chateaulafit-1556-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ _____ __ __ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ /___/ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ https://mk1.ai ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ belonging to: ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ Chai Research Corp. ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ║ ║
jellywibble-chateaulafit-1556-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-chateaulafit-1556-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-1556-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
jellywibble-chateaulafit-1556-v2-mkmlizer: Downloaded to shared memory in 39.082s
jellywibble-chateaulafit-1556-v2-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-chateaulafit-1556-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-chateaulafit-1556-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:05, 48.90it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:04, 63.00it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:04, 66.97it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:06, 38.62it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:06, 40.73it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:04, 49.69it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:04, 57.28it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:03, 63.18it/s] Loading 0: 25%|██▌ | 74/291 [00:01<00:03, 65.41it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:05, 36.62it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:04, 43.94it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:03, 50.69it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:03, 56.62it/s] Loading 0: 41%|████ | 119/291 [00:02<00:02, 65.21it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:02, 64.60it/s] Loading 0: 46%|████▋ | 135/291 [00:02<00:03, 39.76it/s] Loading 0: 49%|████▉ | 143/291 [00:02<00:03, 46.41it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 52.72it/s] Loading 0: 54%|█████▍ | 158/291 [00:03<00:02, 55.58it/s] Loading 0: 57%|█████▋ | 167/291 [00:03<00:01, 62.30it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:01, 67.62it/s] Loading 0: 64%|██████▍ | 186/291 [00:03<00:02, 45.10it/s] Loading 0: 66%|██████▋ | 193/291 [00:03<00:02, 45.74it/s] Loading 0: 69%|██████▉ | 202/291 [00:03<00:01, 53.13it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 59.83it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 65.84it/s] Loading 0: 78%|███████▊ | 228/291 [00:04<00:00, 68.31it/s] Loading 0: 81%|████████ | 236/291 [00:04<00:01, 43.55it/s] Loading 0: 84%|████████▎ | 243/291 [00:04<00:00, 48.36it/s] Loading 0: 87%|████████▋ | 252/291 [00:04<00:00, 56.89it/s] Loading 0: 90%|█████████ | 262/291 [00:04<00:00, 66.40it/s] Loading 0: 94%|█████████▍| 273/291 [00:05<00:00, 72.42it/s] Loading 0: 97%|█████████▋| 282/291 [00:05<00:00, 76.34it/s] Loading 0: 100%|██████████| 291/291 [00:10<00:00, 5.59it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-chateaulafit-1556-v2-mkmlizer: quantized model in 21.593s
jellywibble-chateaulafit-1556-v2-mkmlizer: Processed model Jellywibble/ChateauLafite8BLORA in 62.800s
jellywibble-chateaulafit-1556-v2-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-chateaulafit-1556-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-chateaulafit-1556-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-chateaulafit-1556-v2
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-chateaulafit-1556-v2/special_tokens_map.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-1556-v2/config.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-chateaulafit-1556-v2/tokenizer_config.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-chateaulafit-1556-v2/tokenizer.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-chateaulafit-1556-v2/flywheel_model.0.safetensors
jellywibble-chateaulafit-1556-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jellywibble-chateaulafit-1556-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-1556-v2-mkmlizer: warnings.warn(
jellywibble-chateaulafit-1556-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-1556-v2-mkmlizer: warnings.warn(
jellywibble-chateaulafit-1556-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-1556-v2-mkmlizer: warnings.warn(
jellywibble-chateaulafit-1556-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-1556-v2-mkmlizer: return self.fget.__get__(instance, owner)()
jellywibble-chateaulafit-1556-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-chateaulafit-1556-v2-mkmlizer: Saving duration: 0.308s
jellywibble-chateaulafit-1556-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.695s
jellywibble-chateaulafit-1556-v2-mkmlizer: creating bucket guanaco-reward-models
jellywibble-chateaulafit-1556-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-chateaulafit-1556-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/config.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/special_tokens_map.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/tokenizer_config.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/merges.txt
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/vocab.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/tokenizer.json
jellywibble-chateaulafit-1556-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-chateaulafit-1556-v2_reward/reward.tensors
Job jellywibble-chateaulafit-1556-v2-mkmlizer completed after 93.95s with status: succeeded
Stopping job with name jellywibble-chateaulafit-1556-v2-mkmlizer
Pipeline stage MKMLizer completed in 97.81s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-chateaulafit-1556-v2
Waiting for inference service jellywibble-chateaulafit-1556-v2 to be ready
Inference service jellywibble-chateaulafit-1556-v2 ready after 90.42621731758118s
Pipeline stage ISVCDeployer completed in 97.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.188730239868164s
Received healthy response to inference request in 1.244755506515503s
Received healthy response to inference request in 1.2685234546661377s
Received healthy response to inference request in 1.2486696243286133s
Received healthy response to inference request in 1.241391897201538s
5 requests
0 failed requests
5th percentile: 1.242064619064331
10th percentile: 1.242737340927124
20th percentile: 1.24408278465271
30th percentile: 1.245538330078125
40th percentile: 1.2471039772033692
50th percentile: 1.2486696243286133
60th percentile: 1.256611156463623
70th percentile: 1.264552688598633
80th percentile: 1.452564811706543
90th percentile: 1.8206475257873536
95th percentile: 2.0046888828277587
99th percentile: 2.151921968460083
mean time: 1.4384141445159913
Pipeline stage StressChecker completed in 7.79s
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 0.06s
jellywibble-chateaulafit_1556_v2 status is now deployed due to DeploymentManager action
jellywibble-chateaulafit_1556_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-chateaulafit_1556_v2
Running pipeline stage ISVCDeleter
Checking if service jellywibble-chateaulafit-1556-v2 is running
Tearing down inference service jellywibble-chateaulafit-1556-v2
Toredown service jellywibble-chateaulafit-1556-v2
Pipeline stage ISVCDeleter completed in 3.22s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-chateaulafit-1556-v2/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-1556-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-1556-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-1556-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-chateaulafit-1556-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-chateaulafit-1556-v2_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-1556-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-1556-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-1556-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-1556-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-1556-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-chateaulafit-1556-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.74s
jellywibble-chateaulafit_1556_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics