submission_id: hastagaras-llama-3-8b-no_7499_v4
developer_uid: Hastagaras
best_of: 16
celo_rating: 1184.2
display_name: retry-wrong-format
family_friendly_score: 0.0
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nText transcript of a never-ending conversation between {bot_name} and {user_name}. In the transcript, gestures and other non-verbal actions are written between asterisks (for example, *waves hello* or *moves closer*).\n\n{bot_name}'s Persona: {memory}<|eot_id|>", 'prompt_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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}
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', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-not-okay
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-no
model_name: retry-wrong-format
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-not-okay
model_size: 8B
num_battles: 9415
num_wins: 4794
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': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-16T05:47:31+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5091874668082846
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-no-7499-v4-mkmlizer
Waiting for job on hastagaras-llama-3-8b-no-7499-v4-mkmlizer to finish
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-no-7499-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-no-7499-v4-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Downloaded to shared memory in 16.607s
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:01, 178.70it/s]
Loading 0:  12%|█▏        | 36/291 [00:00<00:01, 179.41it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 177.81it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:01, 183.19it/s]
Loading 0:  32%|███▏      | 94/291 [00:00<00:02, 82.02it/s] 
Loading 0:  39%|███▉      | 113/291 [00:00<00:01, 100.83it/s]
Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 126.83it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 140.78it/s]
Loading 0:  60%|██████    | 175/291 [00:01<00:00, 151.59it/s]
Loading 0:  67%|██████▋   | 194/291 [00:01<00:01, 86.54it/s] 
Loading 0:  74%|███████▍  | 216/291 [00:01<00:00, 108.24it/s]
Loading 0:  81%|████████▏ | 237/291 [00:01<00:00, 127.43it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 139.75it/s]
Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 158.71it/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-v4-mkmlizer: quantized model in 17.797s
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Processed model Hastagaras/llama-3-8b-not-okay in 35.516s
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v4
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v4/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v4/tokenizer.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v4/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v4/config.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-no-7499-v4/flywheel_model.0.safetensors
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-no-7499-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-no-7499-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-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-no-7499-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-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-no-7499-v4-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-no-7499-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-no-7499-v4-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Saving duration: 0.264s
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.474s
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/config.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/special_tokens_map.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/merges.txt
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/vocab.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/tokenizer_config.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/tokenizer.json
hastagaras-llama-3-8b-no-7499-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-no-7499-v4_reward/reward.tensors
Job hastagaras-llama-3-8b-no-7499-v4-mkmlizer completed after 62.55s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-no-7499-v4-mkmlizer
Pipeline stage MKMLizer completed in 66.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-no-7499-v4
Waiting for inference service hastagaras-llama-3-8b-no-7499-v4 to be ready
Inference service hastagaras-llama-3-8b-no-7499-v4 ready after 40.27093553543091s
Pipeline stage ISVCDeployer completed in 47.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.181074619293213s
Received healthy response to inference request in 1.1023080348968506s
Received healthy response to inference request in 1.1606838703155518s
Received healthy response to inference request in 1.1008265018463135s
Received healthy response to inference request in 1.1487524509429932s
5 requests
0 failed requests
5th percentile: 1.1011228084564209
10th percentile: 1.1014191150665282
20th percentile: 1.1020117282867432
30th percentile: 1.1115969181060792
40th percentile: 1.1301746845245362
50th percentile: 1.1487524509429932
60th percentile: 1.1535250186920165
70th percentile: 1.15829758644104
80th percentile: 1.3647620201110842
90th percentile: 1.7729183197021485
95th percentile: 1.9769964694976805
99th percentile: 2.1402589893341064
mean time: 1.3387290954589843
Pipeline stage StressChecker completed in 7.34s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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 0.06s
hastagaras-llama-3-8b-no_7499_v4 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-no_7499_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-no_7499_v4
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-no-7499-v4 is running
Tearing down inference service hastagaras-llama-3-8b-no-7499-v4
Toredown service hastagaras-llama-3-8b-no-7499-v4
Pipeline stage ISVCDeleter completed in 3.56s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v4/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-no-7499-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-no-7499-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.28s
hastagaras-llama-3-8b-no_7499_v4 status is now torndown due to DeploymentManager action