hastagaras-notmpltsft

submission_id: hastagaras-notmpltsft_v1

developer_uid: Hastagaras

best_of: 4

celo_rating: 1184.6

display_name: hastagaras-notmpltsft_v1

family_friendly_score: 0.0

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

generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

is_internal_developer: False

language_model: Hastagaras/notmpltsft

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/notmpltsft

model_name: hastagaras-notmpltsft_v1

model_num_parameters: 8030261248.0

model_repo: Hastagaras/notmpltsft

model_size: 8B

num_battles: 22062

num_wins: 11106

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: 2024-06-13T09:53:40+00:00

us_pacific_date: 2024-06-13

win_ratio: 0.5033995104704923

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-notmpltsft-v1-mkmlizer
Waiting for job on hastagaras-notmpltsft-v1-mkmlizer to finish
hastagaras-notmpltsft-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-notmpltsft-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-notmpltsft-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-notmpltsft-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-notmpltsft-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-notmpltsft-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-notmpltsft-v1-mkmlizer: ║                                                                     ║
hastagaras-notmpltsft-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-notmpltsft-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-notmpltsft-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-notmpltsft-v1-mkmlizer: ║                                                                     ║
hastagaras-notmpltsft-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-notmpltsft-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-notmpltsft-v1-mkmlizer: ║                                                                     ║
hastagaras-notmpltsft-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-notmpltsft-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-notmpltsft-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-notmpltsft-v1-mkmlizer: ║                                                                     ║
hastagaras-notmpltsft-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-notmpltsft-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-notmpltsft-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-notmpltsft-v1-mkmlizer: Downloaded to shared memory in 32.455s
hastagaras-notmpltsft-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-notmpltsft-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-notmpltsft-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 113.34it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 108.10it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 124.30it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:01, 120.74it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 126.06it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 122.28it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:03, 60.71it/s] 
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 68.25it/s]
Loading 0:  40%|████      | 117/291 [00:01<00:02, 82.20it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 90.65it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 101.89it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 106.51it/s]
Loading 0:  59%|█████▉    | 171/291 [00:01<00:01, 113.64it/s]
Loading 0:  63%|██████▎   | 184/291 [00:01<00:00, 117.69it/s]
Loading 0:  68%|██████▊   | 197/291 [00:02<00:01, 63.66it/s] 
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 74.77it/s]
Loading 0:  77%|███████▋  | 225/291 [00:02<00:00, 86.67it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 92.96it/s]
Loading 0:  87%|████████▋ | 252/291 [00:02<00:00, 103.18it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 107.61it/s]
Loading 0:  96%|█████████▌| 279/291 [00:02<00:00, 115.15it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-notmpltsft-v1-mkmlizer: quantized model in 19.878s
hastagaras-notmpltsft-v1-mkmlizer: Processed model Hastagaras/notmpltsft in 53.436s
hastagaras-notmpltsft-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-notmpltsft-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-notmpltsft-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-notmpltsft-v1
hastagaras-notmpltsft-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-notmpltsft-v1/config.json
hastagaras-notmpltsft-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-notmpltsft-v1/special_tokens_map.json
hastagaras-notmpltsft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-notmpltsft-v1/tokenizer_config.json
hastagaras-notmpltsft-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-notmpltsft-v1/tokenizer.json
hastagaras-notmpltsft-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-notmpltsft-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-notmpltsft-v1-mkmlizer:   warnings.warn(
hastagaras-notmpltsft-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-notmpltsft-v1-mkmlizer:   warnings.warn(
hastagaras-notmpltsft-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-notmpltsft-v1-mkmlizer:   warnings.warn(
hastagaras-notmpltsft-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-notmpltsft-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-notmpltsft-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-notmpltsft-v1-mkmlizer: Saving duration: 0.260s
hastagaras-notmpltsft-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.390s
hastagaras-notmpltsft-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-notmpltsft-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-notmpltsft-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/config.json
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/tokenizer_config.json
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/special_tokens_map.json
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/vocab.json
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/merges.txt
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/tokenizer.json
hastagaras-notmpltsft-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-notmpltsft-v1_reward/reward.tensors
Job hastagaras-notmpltsft-v1-mkmlizer completed after 83.86s with status: succeeded
Stopping job with name hastagaras-notmpltsft-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-notmpltsft-v1
Waiting for inference service hastagaras-notmpltsft-v1 to be ready
Inference service hastagaras-notmpltsft-v1 ready after 40.22543478012085s
Pipeline stage ISVCDeployer completed in 47.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8101387023925781s
Received healthy response to inference request in 1.1219546794891357s
Received healthy response to inference request in 0.953838586807251s
Received healthy response to inference request in 1.1168816089630127s
Received healthy response to inference request in 1.1373419761657715s
5 requests
0 failed requests
5th percentile: 0.9864471912384033
10th percentile: 1.0190557956695556
20th percentile: 1.0842730045318603
30th percentile: 1.1178962230682372
40th percentile: 1.1199254512786865
50th percentile: 1.1219546794891357
60th percentile: 1.12810959815979
70th percentile: 1.1342645168304444
80th percentile: 1.271901321411133
90th percentile: 1.5410200119018556
95th percentile: 1.6755793571472166
99th percentile: 1.7832268333435057
mean time: 1.2280311107635498
Pipeline stage StressChecker completed in 6.94s
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-notmpltsft_v1 status is now deployed due to DeploymentManager action
hastagaras-notmpltsft_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-notmpltsft_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-notmpltsft-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-notmpltsft-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-notmpltsft-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-notmpltsft-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-notmpltsft-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-notmpltsft-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-notmpltsft-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-notmpltsft-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-notmpltsft-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-notmpltsft-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-notmpltsft-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-notmpltsft-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-notmpltsft-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.35s
hastagaras-notmpltsft_v1 status is now torndown due to DeploymentManager action