developer_uid: Hastagaras
submission_id: hastagaras-bu8bl3-x-x_v6
model_name: x__X
model_group: Hastagaras/bu8bl3-x_x
status: torndown
timestamp: 2024-06-14T14:56:06+00:00
num_battles: 42935
num_wins: 23326
celo_rating: 1213.04
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/bu8bl3-x_x
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: x__X
is_internal_developer: False
language_model: Hastagaras/bu8bl3-x_x
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-14
win_ratio: 0.5432863631070223
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.1, '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-x-x-v6-mkmlizer
Waiting for job on hastagaras-bu8bl3-x-x-v6-mkmlizer to finish
hastagaras-bu8bl3-x-x-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║     _____            __           __                                ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║       /___/                                                         ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║                                                                     ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║                                                                     ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  belonging to:                                                      ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║                                                                     ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ║                                                                     ║
hastagaras-bu8bl3-x-x-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bu8bl3-x-x-v6-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-x-x-v6-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
hastagaras-bu8bl3-x-x-v6-mkmlizer: Downloaded to shared memory in 33.654s
hastagaras-bu8bl3-x-x-v6-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bu8bl3-x-x-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:00,  2.29s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:03,  4.36it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.59it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.86it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.20it/s]
Loading 0:  27%|██▋       | 79/291 [00:05<00:06, 34.59it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.26it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.27it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 80.85it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.95it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 75.74it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 91.46it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 106.62it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 119.25it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 129.34it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 138.21it/s]
Loading 0:  93%|█████████▎| 272/291 [00:07<00:00, 87.88it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00, 100.16it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bu8bl3-x-x-v6-mkmlizer: quantized model in 23.574s
hastagaras-bu8bl3-x-x-v6-mkmlizer: Processed model Hastagaras/bu8bl3-x_x in 59.793s
hastagaras-bu8bl3-x-x-v6-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bu8bl3-x-x-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bu8bl3-x-x-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v6
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v6/tokenizer_config.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v6/special_tokens_map.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v6/config.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v6/tokenizer.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bu8bl3-x-x-v6/flywheel_model.0.safetensors
hastagaras-bu8bl3-x-x-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bu8bl3-x-x-v6-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-x-x-v6-mkmlizer:   warnings.warn(
hastagaras-bu8bl3-x-x-v6-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-x-x-v6-mkmlizer:   warnings.warn(
hastagaras-bu8bl3-x-x-v6-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-x-x-v6-mkmlizer:   warnings.warn(
hastagaras-bu8bl3-x-x-v6-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-x-x-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-bu8bl3-x-x-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bu8bl3-x-x-v6-mkmlizer: Saving duration: 0.402s
hastagaras-bu8bl3-x-x-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.333s
hastagaras-bu8bl3-x-x-v6-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bu8bl3-x-x-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bu8bl3-x-x-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/special_tokens_map.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/vocab.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/merges.txt
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/config.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/tokenizer_config.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/tokenizer.json
hastagaras-bu8bl3-x-x-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bu8bl3-x-x-v6_reward/reward.tensors
Job hastagaras-bu8bl3-x-x-v6-mkmlizer completed after 83.59s with status: succeeded
Stopping job with name hastagaras-bu8bl3-x-x-v6-mkmlizer
Pipeline stage MKMLizer completed in 87.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bu8bl3-x-x-v6
Waiting for inference service hastagaras-bu8bl3-x-x-v6 to be ready
Inference service hastagaras-bu8bl3-x-x-v6 ready after 40.26020884513855s
Pipeline stage ISVCDeployer completed in 47.36s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.183410406112671s
Received healthy response to inference request in 1.3563568592071533s
Received healthy response to inference request in 1.3347089290618896s
Received healthy response to inference request in 1.2806909084320068s
Received healthy response to inference request in 1.3732328414916992s
5 requests
0 failed requests
5th percentile: 1.2914945125579833
10th percentile: 1.30229811668396
20th percentile: 1.3239053249359132
30th percentile: 1.3390385150909423
40th percentile: 1.3476976871490478
50th percentile: 1.3563568592071533
60th percentile: 1.3631072521209717
70th percentile: 1.3698576450347901
80th percentile: 1.5352683544158938
90th percentile: 1.8593393802642824
95th percentile: 2.0213748931884763
99th percentile: 2.151003303527832
mean time: 1.505679988861084
Pipeline stage StressChecker completed in 8.13s
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-x-x_v6 status is now deployed due to DeploymentManager action
hastagaras-bu8bl3-x-x_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-bu8bl3-x-x_v6
Running pipeline stage ISVCDeleter
Checking if service hastagaras-bu8bl3-x-x-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.92s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-bu8bl3-x-x-v6/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-x-x-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-x-x-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-x-x-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-bu8bl3-x-x-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-bu8bl3-x-x-v6_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-x-x-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-x-x-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-x-x-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-x-x-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-x-x-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-bu8bl3-x-x-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.15s
hastagaras-bu8bl3-x-x_v6 status is now torndown due to DeploymentManager action