developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-no_7499_v3
model_name: fix-healed
model_group: Hastagaras/llama-3-8b-no
status: torndown
timestamp: 2024-05-16T05:44:11+00:00
num_battles: 10509
num_wins: 5165
celo_rating: 1171.15
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-not-okay
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: fix-healed
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-not-okay
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-15
win_ratio: 0.49148349034161193
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-no-7499-v3-mkmlizer
Waiting for job on hastagaras-llama-3-8b-no-7499-v3-mkmlizer to finish
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-no-7499-v3-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-no-7499-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Downloaded to shared memory in 27.701s
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 176.52it/s]
Loading 0:  12%|█▏        | 36/291 [00:00<00:01, 177.58it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 167.39it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:01, 156.86it/s]
Loading 0:  30%|██▉       | 87/291 [00:00<00:02, 74.15it/s] 
Loading 0:  37%|███▋      | 108/291 [00:00<00:01, 98.55it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 119.91it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 132.99it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 144.67it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 90.50it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 100.97it/s]
Loading 0:  78%|███████▊  | 228/291 [00:01<00:00, 127.32it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 140.66it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 150.76it/s]
Loading 0:  98%|█████████▊| 284/291 [00:02<00:00, 149.57it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: quantized model in 18.046s
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Processed model Hastagaras/llama-3-8b-not-okay in 46.880s
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v3
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v3/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v3/config.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v3/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v3/tokenizer.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v3/flywheel_model.0.safetensors
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-no-7499-v3-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-no-7499-v3-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v3-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-no-7499-v3-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-v3-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-no-7499-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Saving duration: 0.275s
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.903s
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/config.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/merges.txt
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/vocab.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/tokenizer.json
hastagaras-llama-3-8b-no-7499-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v3_reward/reward.tensors
Job hastagaras-llama-3-8b-no-7499-v3-mkmlizer completed after 72.81s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-no-7499-v3-mkmlizer
Pipeline stage MKMLizer completed in 77.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-no-7499-v3
Waiting for inference service hastagaras-llama-3-8b-no-7499-v3 to be ready
Inference service hastagaras-llama-3-8b-no-7499-v3 ready after 30.168245553970337s
Pipeline stage ISVCDeployer completed in 37.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.095451593399048s
Received healthy response to inference request in 1.1353812217712402s
Received healthy response to inference request in 1.127242088317871s
Received healthy response to inference request in 1.111475944519043s
Received healthy response to inference request in 0.9476444721221924s
5 requests
0 failed requests
5th percentile: 0.9804107666015625
10th percentile: 1.0131770610809325
20th percentile: 1.078709650039673
30th percentile: 1.1146291732788085
40th percentile: 1.1209356307983398
50th percentile: 1.127242088317871
60th percentile: 1.1304977416992188
70th percentile: 1.1337533950805665
80th percentile: 1.3273952960968018
90th percentile: 1.7114234447479248
95th percentile: 1.9034375190734862
99th percentile: 2.0570487785339355
mean time: 1.2834390640258788
Pipeline stage StressChecker completed in 7.05s
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-no_7499_v3 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-no_7499_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-no_7499_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-no-7499-v3 is running
Tearing down inference service hastagaras-llama-3-8b-no-7499-v3
Toredown service hastagaras-llama-3-8b-no-7499-v3
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-llama-3-8b-no-7499-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.95s
hastagaras-llama-3-8b-no_7499_v3 status is now torndown due to DeploymentManager action