developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-ok_5775_v5
model_name: new-okay-two-repetition-fixed
model_group: Hastagaras/llama-3-8b-ok
status: torndown
timestamp: 2024-05-20T12:37:51+00:00
num_battles: 12876
num_wins: 6771
celo_rating: 1192.53
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: 0.5258620689655172
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, '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': True}
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': True, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-ok-5775-v5-mkmlizer
Waiting for job on hastagaras-llama-3-8b-ok-5775-v5-mkmlizer to finish
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-ok-5775-v5-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-v5-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Downloaded to shared memory in 125.699s
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:01, 169.03it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:01, 186.83it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:01, 190.77it/s]
Loading 0:  26%|██▋       | 77/291 [00:00<00:01, 183.71it/s]
Loading 0:  33%|███▎      | 96/291 [00:00<00:02, 85.20it/s] 
Loading 0:  41%|████      | 120/291 [00:00<00:01, 111.95it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 126.34it/s]
Loading 0:  54%|█████▍    | 158/291 [00:01<00:00, 140.58it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 158.37it/s]
Loading 0:  69%|██████▊   | 200/291 [00:01<00:00, 101.65it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 118.47it/s]
Loading 0:  84%|████████▎ | 243/291 [00:01<00:00, 140.80it/s]
Loading 0:  91%|█████████ | 265/291 [00:01<00:00, 156.16it/s]
Loading 0:  98%|█████████▊| 284/291 [00:02<00:00, 157.11it/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-v5-mkmlizer: quantized model in 17.856s
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Processed model Hastagaras/llama-3-8b-okay-two in 144.527s
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v5
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v5/tokenizer_config.json
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v5/config.json
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v5/special_tokens_map.json
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v5/tokenizer.json
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-ok-5775-v5/flywheel_model.0.safetensors
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-ok-5775-v5-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-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ok-5775-v5-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-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ok-5775-v5-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-v5-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-ok-5775-v5-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-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Saving duration: 0.236s
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.204s
hastagaras-llama-3-8b-ok-5775-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-ok-5775-v5_reward/reward.tensors
Job hastagaras-llama-3-8b-ok-5775-v5-mkmlizer completed after 175.03s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-ok-5775-v5-mkmlizer
Pipeline stage MKMLizer completed in 178.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-ok-5775-v5
Waiting for inference service hastagaras-llama-3-8b-ok-5775-v5 to be ready
Inference service hastagaras-llama-3-8b-ok-5775-v5 ready after 40.267561197280884s
Pipeline stage ISVCDeployer completed in 47.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.314000129699707s
Received healthy response to inference request in 1.3120207786560059s
Received healthy response to inference request in 1.3297066688537598s
Received healthy response to inference request in 1.3566420078277588s
Received healthy response to inference request in 1.3064799308776855s
5 requests
0 failed requests
5th percentile: 1.3075881004333496
10th percentile: 1.3086962699890137
20th percentile: 1.3109126091003418
30th percentile: 1.3155579566955566
40th percentile: 1.3226323127746582
50th percentile: 1.3297066688537598
60th percentile: 1.3404808044433594
70th percentile: 1.351254940032959
80th percentile: 1.5481136322021487
90th percentile: 1.9310568809509279
95th percentile: 2.122528505325317
99th percentile: 2.275705804824829
mean time: 1.5237699031829834
Pipeline stage StressChecker completed in 8.80s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-ok_5775_v5 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-ok_5775_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-ok_5775_v5
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-ok-5775-v5 is running
Tearing down inference service hastagaras-llama-3-8b-ok-5775-v5
Toredown service hastagaras-llama-3-8b-ok-5775-v5
Pipeline stage ISVCDeleter completed in 3.49s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ok-5775-v5/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-ok-5775-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.94s
hastagaras-llama-3-8b-ok_5775_v5 status is now torndown due to DeploymentManager action