developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-ok_5775_v4
model_name: new-okay-two-repetition-fixed
model_group: Hastagaras/llama-3-8b-ok
status: torndown
timestamp: 2024-05-20T12:22:35+00:00
num_battles: 20405
num_wins: 10822
celo_rating: 1193.26
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-okay-two
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: new-okay-two-repetition-fixed
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay-two
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-20
win_ratio: 0.5303602058319039
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.15, 'top_k': 82, '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': "<|start_header_id|>system<|end_header_id|>\n\nAct as{bot_name}, short reply.\n\n{bot_name}'s personality: {memory}\n\n", 'prompt_template': 'Scenario: {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-llama-3-8b-ok-5775-v4-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ok-5775-v4-mkmlizer to finish
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ok-5775-v4-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-llama-3-8b-ok-5775-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Retrying (%r) after connection broken by '%r': %s
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Downloaded to shared memory in 28.415s
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:01, 189.26it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 193.62it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:01, 183.97it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 94.08it/s] 
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 112.87it/s]
Loading 0:  42%|████▏     | 122/291 [00:00<00:01, 129.33it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:00, 155.94it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 163.15it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 103.64it/s]
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 112.34it/s]
Loading 0:  79%|███████▊  | 229/291 [00:01<00:00, 139.58it/s]
Loading 0:  88%|████████▊ | 255/291 [00:01<00:00, 163.10it/s]
Loading 0:  95%|█████████▍| 275/291 [00:01<00:00, 171.82it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: quantized model in 17.150s
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Processed model Hastagaras/llama-3-8b-okay-two in 46.564s
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v4
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v4/special_tokens_map.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v4/config.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v4/tokenizer_config.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v4/tokenizer.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v4/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-ok-5775-v4-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-llama-3-8b-ok-5775-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ok-5775-v4-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-llama-3-8b-ok-5775-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ok-5775-v4-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-llama-3-8b-ok-5775-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ok-5775-v4-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-llama-3-8b-ok-5775-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Saving duration: 0.232s
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.507s
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/config.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/special_tokens_map.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/tokenizer_config.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/merges.txt
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/vocab.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/tokenizer.json
hastagaras-llama-3-8b-ok-5775-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v4_reward/reward.tensors
Job hastagaras-llama-3-8b-ok-5775-v4-mkmlizer completed after 73.57s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ok-5775-v4-mkmlizer
Pipeline stage MKMLizer completed in 76.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ok-5775-v4
Waiting for inference service hastagaras-llama-3-8b-ok-5775-v4 to be ready
Inference service hastagaras-llama-3-8b-ok-5775-v4 ready after 30.192827701568604s
Pipeline stage ISVCDeployer completed in 37.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2991325855255127s
Received healthy response to inference request in 1.3468286991119385s
Received healthy response to inference request in 1.3044259548187256s
Received healthy response to inference request in 1.2915170192718506s
Received healthy response to inference request in 1.400505542755127s
5 requests
0 failed requests
5th percentile: 1.2940988063812255
10th percentile: 1.2966805934906005
20th percentile: 1.3018441677093506
30th percentile: 1.3129065036773682
40th percentile: 1.3298676013946533
50th percentile: 1.3468286991119385
60th percentile: 1.3682994365692138
70th percentile: 1.3897701740264892
80th percentile: 1.5802309513092043
90th percentile: 1.9396817684173584
95th percentile: 2.1194071769714355
99th percentile: 2.2631875038146974
mean time: 1.5284819602966309
Pipeline stage StressChecker completed in 8.28s
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-llama-3-8b-ok_5775_v4 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-ok_5775_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-ok_5775_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-ok-5775-v4 is running
Tearing down inference service hastagaras-llama-3-8b-ok-5775-v4
Toredown service hastagaras-llama-3-8b-ok-5775-v4
Pipeline stage ISVCDeleter completed in 3.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ok-5775-v4/config.json from bucket guanaco-mkml-models
admin requested tearing down of hastagaras-waduh-1-sft-l_7494_v3
Deleting key hastagaras-llama-3-8b-ok-5775-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage ISVCDeleter
Checking if service hastagaras-waduh-1-sft-l-7494-v3 is running
Deleting key hastagaras-llama-3-8b-ok-5775-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.95s
hastagaras-llama-3-8b-ok_5775_v4 status is now torndown due to DeploymentManager action