developer_uid: Hastagaras
submission_id: hastagaras-bu8bl3-rp_v1
model_name: bubble
model_group: Hastagaras/Bu8bl3-RP
status: torndown
timestamp: 2024-06-15T08:41:27+00:00
num_battles: 21953
num_wins: 11714
celo_rating: 1197.68
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Bu8bl3-RP
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: bubble
is_internal_developer: False
language_model: Hastagaras/Bu8bl3-RP
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-15
win_ratio: 0.5335944973352161
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, '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\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{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': '{prompt}\n<START>\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-bu8bl3-rp-v1-mkmlizer
Waiting for job on hastagaras-bu8bl3-rp-v1-mkmlizer to finish
hastagaras-bu8bl3-rp-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ /___/ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ belonging to: ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ║ ║
hastagaras-bu8bl3-rp-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bu8bl3-rp-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-bu8bl3-rp-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-bu8bl3-rp-v1-mkmlizer: Downloaded to shared memory in 29.497s
hastagaras-bu8bl3-rp-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bu8bl3-rp-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bu8bl3-rp-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 120.54it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 147.06it/s] Loading 0: 15%|█▌ | 45/291 [00:00<00:01, 145.48it/s] Loading 0: 21%|██ | 60/291 [00:00<00:01, 144.94it/s] Loading 0: 26%|██▋ | 77/291 [00:00<00:01, 147.12it/s] Loading 0: 32%|███▏ | 92/291 [00:00<00:02, 77.05it/s] Loading 0: 36%|███▌ | 105/291 [00:01<00:02, 87.24it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 102.58it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 117.05it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 128.69it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 146.13it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 84.25it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 97.19it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 111.07it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 122.20it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 132.97it/s] Loading 0: 98%|█████████▊| 285/291 [00:02<00:00, 145.38it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bu8bl3-rp-v1-mkmlizer: quantized model in 23.252s
hastagaras-bu8bl3-rp-v1-mkmlizer: Processed model Hastagaras/Bu8bl3-RP in 55.456s
hastagaras-bu8bl3-rp-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bu8bl3-rp-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bu8bl3-rp-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v1
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v1/tokenizer_config.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v1/special_tokens_map.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v1/config.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v1/tokenizer.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bu8bl3-rp-v1/flywheel_model.0.safetensors
hastagaras-bu8bl3-rp-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bu8bl3-rp-v1-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-bu8bl3-rp-v1-mkmlizer: warnings.warn(
hastagaras-bu8bl3-rp-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-bu8bl3-rp-v1-mkmlizer: warnings.warn(
hastagaras-bu8bl3-rp-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-bu8bl3-rp-v1-mkmlizer: warnings.warn(
hastagaras-bu8bl3-rp-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-bu8bl3-rp-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-bu8bl3-rp-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bu8bl3-rp-v1-mkmlizer: Saving duration: 0.432s
hastagaras-bu8bl3-rp-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.887s
hastagaras-bu8bl3-rp-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bu8bl3-rp-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bu8bl3-rp-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/special_tokens_map.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/config.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/tokenizer_config.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/vocab.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/merges.txt
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/tokenizer.json
hastagaras-bu8bl3-rp-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bu8bl3-rp-v1_reward/reward.tensors
Job hastagaras-bu8bl3-rp-v1-mkmlizer completed after 82.85s with status: succeeded
Stopping job with name hastagaras-bu8bl3-rp-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bu8bl3-rp-v1
Waiting for inference service hastagaras-bu8bl3-rp-v1 to be ready
Inference service hastagaras-bu8bl3-rp-v1 ready after 40.235822439193726s
Pipeline stage ISVCDeployer completed in 47.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0776281356811523s
Received healthy response to inference request in 1.3512427806854248s
Received healthy response to inference request in 1.3147013187408447s
Received healthy response to inference request in 1.2855360507965088s
Received healthy response to inference request in 1.2996914386749268s
5 requests
0 failed requests
5th percentile: 1.2883671283721925
10th percentile: 1.291198205947876
20th percentile: 1.296860361099243
30th percentile: 1.3026934146881104
40th percentile: 1.3086973667144775
50th percentile: 1.3147013187408447
60th percentile: 1.3293179035186768
70th percentile: 1.3439344882965087
80th percentile: 1.4965198516845704
90th percentile: 1.7870739936828615
95th percentile: 1.9323510646820068
99th percentile: 2.048572721481323
mean time: 1.4657599449157714
Pipeline stage StressChecker completed in 7.89s
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-bu8bl3-rp_v1 status is now deployed due to DeploymentManager action
hastagaras-bu8bl3-rp_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-bu8bl3-rp_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-bu8bl3-rp-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.25s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-bu8bl3-rp-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-rp-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-rp-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-rp-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-rp-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-bu8bl3-rp-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-rp-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-rp-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-rp-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-rp-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-rp-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-rp-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.16s
hastagaras-bu8bl3-rp_v1 status is now torndown due to DeploymentManager action