submission_id: hastagaras-llama-3-8b-okay_v8
developer_uid: Hastagaras
best_of: 16
celo_rating: 1185.72
display_name: test-l3-short-fix
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a roleplay storywriter, below is the task for you.\n\n{bot_name}'s Persona:\n{memory}\n\n", 'prompt_template': "Previously:\n{prompt}\n\nYour task:\nWrite the next concise response in short but contain both dialogue and action in one line. *A description of {bot_name}'s physical actions, gestures or movements goes here, enclosed in asterisks*<|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}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama-3-8b-ok
model_name: test-l3-short-fix
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama-3-8b-okay
model_size: 8B
num_battles: 29895
num_wins: 15728
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-14T00:12:46+00:00
us_pacific_date: 2024-05-13
win_ratio: 0.5261080448235491
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v8-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v8-mkmlizer to finish
hastagaras-llama-3-8b-okay-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v8-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-okay-v8-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v8-mkmlizer: Downloaded to shared memory in 16.020s
hastagaras-llama-3-8b-okay-v8-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v8-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 93.79it/s]
Loading 0:  66%|██████▌   | 192/291 [00:02<00:01, 96.04it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 26.82it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-okay-v8-mkmlizer: quantized model in 19.968s
hastagaras-llama-3-8b-okay-v8-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 37.046s
hastagaras-llama-3-8b-okay-v8-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v8
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v8/special_tokens_map.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v8/config.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v8/tokenizer_config.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v8/tokenizer.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v8-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-okay-v8-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v8-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-okay-v8-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v8-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-okay-v8-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v8-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-okay-v8-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v8-mkmlizer: Saving duration: 0.255s
hastagaras-llama-3-8b-okay-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.565s
hastagaras-llama-3-8b-okay-v8-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/config.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/merges.txt
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/vocab.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v8_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v8-mkmlizer completed after 310.43s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v8-mkmlizer
Pipeline stage MKMLizer completed in 315.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v8
Waiting for inference service hastagaras-llama-3-8b-okay-v8 to be ready
Inference service hastagaras-llama-3-8b-okay-v8 ready after 30.17466974258423s
Pipeline stage ISVCDeployer completed in 38.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.214388370513916s
Received healthy response to inference request in 1.2852139472961426s
Received healthy response to inference request in 1.374345302581787s
Received healthy response to inference request in 1.3471124172210693s
Received healthy response to inference request in 1.2852158546447754s
5 requests
0 failed requests
5th percentile: 1.285214328765869
10th percentile: 1.2852147102355957
20th percentile: 1.285215473175049
30th percentile: 1.297595167160034
40th percentile: 1.3223537921905517
50th percentile: 1.3471124172210693
60th percentile: 1.3580055713653565
70th percentile: 1.3688987255096436
80th percentile: 1.5423539161682132
90th percentile: 1.8783711433410646
95th percentile: 2.04637975692749
99th percentile: 2.180786647796631
mean time: 1.501255178451538
Pipeline stage StressChecker completed in 8.41s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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-okay_v8 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v8
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v8 is running
Tearing down inference service hastagaras-llama-3-8b-okay-v8
Toredown service hastagaras-llama-3-8b-okay-v8
Pipeline stage ISVCDeleter completed in 7.15s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v8/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v8_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.81s
hastagaras-llama-3-8b-okay_v8 status is now torndown due to DeploymentManager action