hastagaras-my-models-col_6015

developer_uid: Hastagaras

submission_id: hastagaras-my-models-col_6015_v1

model_name: 1

model_group: Hastagaras/My-Models-Col

status: torndown

timestamp: 2024-06-16T22:55:31+00:00

num_battles: 23409

num_wins: 12473

celo_rating: 1217.37

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/My-Models-Collection

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: 1

is_internal_developer: False

language_model: Hastagaras/My-Models-Collection

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-16

win_ratio: 0.5328292537058397

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 50, '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': "<|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-my-models-col-6015-v1-mkmlizer
Waiting for job on hastagaras-my-models-col-6015-v1-mkmlizer to finish
hastagaras-my-models-col-6015-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-my-models-col-6015-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║                                                                     ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║                                                                     ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║                                                                     ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-my-models-col-6015-v1-mkmlizer: ║                                                                     ║
hastagaras-my-models-col-6015-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-my-models-col-6015-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-my-models-col-6015-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-my-models-col-6015-v1-mkmlizer: Downloaded to shared memory in 35.165s
hastagaras-my-models-col-6015-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-my-models-col-6015-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-my-models-col-6015-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 115.46it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 145.75it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:01, 154.00it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 159.11it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 85.84it/s] 
Loading 0:  34%|███▎      | 98/291 [00:00<00:01, 98.86it/s]
Loading 0:  39%|███▉      | 114/291 [00:00<00:01, 112.69it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 125.43it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 136.89it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 143.50it/s]
Loading 0:  63%|██████▎   | 183/291 [00:01<00:00, 141.33it/s]
Loading 0:  68%|██████▊   | 198/291 [00:01<00:01, 82.13it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:01<00:00, 89.12it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 102.30it/s]
Loading 0:  84%|████████▎ | 243/291 [00:02<00:00, 111.93it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 118.51it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 126.06it/s]
Loading 0:  99%|█████████▉| 288/291 [00:08<00:00,  8.37it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-my-models-col-6015-v1-mkmlizer: quantized model in 34.752s
hastagaras-my-models-col-6015-v1-mkmlizer: Processed model Hastagaras/My-Models-Collection in 72.507s
hastagaras-my-models-col-6015-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-my-models-col-6015-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-my-models-col-6015-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-my-models-col-6015-v1
hastagaras-my-models-col-6015-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-my-models-col-6015-v1/config.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-my-models-col-6015-v1/special_tokens_map.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-my-models-col-6015-v1/tokenizer_config.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-my-models-col-6015-v1/tokenizer.json
hastagaras-my-models-col-6015-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-my-models-col-6015-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-my-models-col-6015-v1-mkmlizer:   warnings.warn(
hastagaras-my-models-col-6015-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-my-models-col-6015-v1-mkmlizer:   warnings.warn(
hastagaras-my-models-col-6015-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-my-models-col-6015-v1-mkmlizer:   warnings.warn(
hastagaras-my-models-col-6015-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-my-models-col-6015-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-my-models-col-6015-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-my-models-col-6015-v1-mkmlizer: Saving duration: 0.453s
hastagaras-my-models-col-6015-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.155s
hastagaras-my-models-col-6015-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-my-models-col-6015-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-my-models-col-6015-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/config.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/merges.txt
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/special_tokens_map.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/tokenizer_config.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/vocab.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/tokenizer.json
hastagaras-my-models-col-6015-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-my-models-col-6015-v1_reward/reward.tensors
Job hastagaras-my-models-col-6015-v1-mkmlizer completed after 93.24s with status: succeeded
Stopping job with name hastagaras-my-models-col-6015-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-my-models-col-6015-v1
Waiting for inference service hastagaras-my-models-col-6015-v1 to be ready
Inference service hastagaras-my-models-col-6015-v1 ready after 30.1706485748291s
Pipeline stage ISVCDeployer completed in 36.83s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 4.063803195953369s
Received healthy response to inference request in 1.3332161903381348s
Received healthy response to inference request in 1.296877384185791s
Received healthy response to inference request in 1.2872436046600342s
Received healthy response to inference request in 1.3526177406311035s
5 requests
0 failed requests
5th percentile: 1.2891703605651856
10th percentile: 1.2910971164703369
20th percentile: 1.2949506282806396
30th percentile: 1.3041451454162598
40th percentile: 1.3186806678771972
50th percentile: 1.3332161903381348
60th percentile: 1.3409768104553224
70th percentile: 1.3487374305725097
80th percentile: 1.8948548316955571
90th percentile: 2.9793290138244632
95th percentile: 3.5215661048889153
99th percentile: 3.955355777740478
mean time: 1.8667516231536865
Pipeline stage StressChecker completed in 29.99s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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 0.07s
hastagaras-my-models-col_6015_v1 status is now deployed due to DeploymentManager action
hastagaras-my-models-col_6015_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-my-models-col_6015_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-my-models-col-6015-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.80s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-my-models-col-6015-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-my-models-col-6015-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-my-models-col-6015-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-my-models-col-6015-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-my-models-col-6015-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-my-models-col-6015-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-my-models-col-6015-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-my-models-col-6015-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-my-models-col-6015-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-my-models-col-6015-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-my-models-col-6015-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-my-models-col-6015-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.37s
hastagaras-my-models-col_6015_v1 status is now torndown due to DeploymentManager action