developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-okay_v2
model_name: hastagaras-llama-3-8b-okay_v1
model_group: Hastagaras/llama-3-8b-ok
status: torndown
timestamp: 2024-05-12T05:38:58+00:00
num_battles: 8516
num_wins: 4546
celo_rating: 1194.22
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-okay
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: hastagaras-llama-3-8b-okay_v1
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-okay
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-11
win_ratio: 0.5338186942226397
generation_params: {'temperature': 0.88, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're `{bot_name}` in this vulgar roleplay. Write `{bot_name}`'s next response based on the below information.\n\n{memory}\n\n", 'prompt_template': 'Previous message: {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}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-okay-v2-mkmlizer
Waiting for job on hastagaras-llama-3-8b-okay-v2-mkmlizer to finish
hastagaras-llama-3-8b-okay-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-okay-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-okay-v2-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-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-okay-v2-mkmlizer: Downloaded to shared memory in 12.055s
hastagaras-llama-3-8b-okay-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-okay-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 137.00it/s]
Loading 0:  98%|█████████▊| 284/291 [00:02<00:00, 142.02it/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-v2-mkmlizer: quantized model in 17.252s
hastagaras-llama-3-8b-okay-v2-mkmlizer: Processed model Hastagaras/llama-3-8b-okay in 30.327s
hastagaras-llama-3-8b-okay-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-okay-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-okay-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v2
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v2/special_tokens_map.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v2/tokenizer_config.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v2/config.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v2/tokenizer.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-okay-v2/flywheel_model.0.safetensors
hastagaras-llama-3-8b-okay-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-okay-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v2-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-v2-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-okay-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-okay-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-okay-v2-mkmlizer: Saving duration: 0.232s
hastagaras-llama-3-8b-okay-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.241s
hastagaras-llama-3-8b-okay-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-okay-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-okay-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/config.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/tokenizer_config.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/special_tokens_map.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/merges.txt
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/vocab.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/tokenizer.json
hastagaras-llama-3-8b-okay-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-okay-v2_reward/reward.tensors
Job hastagaras-llama-3-8b-okay-v2-mkmlizer completed after 52.64s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-okay-v2-mkmlizer
Pipeline stage MKMLizer completed in 55.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-okay-v2
Waiting for inference service hastagaras-llama-3-8b-okay-v2 to be ready
Inference service hastagaras-llama-3-8b-okay-v2 ready after 40.19166302680969s
Pipeline stage ISVCDeployer completed in 47.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1743149757385254s
Received healthy response to inference request in 1.3985028266906738s
Received healthy response to inference request in 1.3373973369598389s
Received healthy response to inference request in 1.30061936378479s
Received healthy response to inference request in 1.385932207107544s
5 requests
0 failed requests
5th percentile: 1.3079749584197997
10th percentile: 1.3153305530548096
20th percentile: 1.3300417423248292
30th percentile: 1.3471043109893799
40th percentile: 1.366518259048462
50th percentile: 1.385932207107544
60th percentile: 1.390960454940796
70th percentile: 1.3959887027740479
80th percentile: 1.5536652565002442
90th percentile: 1.8639901161193848
95th percentile: 2.019152545928955
99th percentile: 2.1432824897766114
mean time: 1.5193533420562744
Pipeline stage StressChecker completed in 8.19s
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-okay_v2 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-okay_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-okay_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-okay-v2 is running
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Tearing down inference service hastagaras-llama-3-8b-okay-v2
Toredown service hastagaras-llama-3-8b-okay-v2
Pipeline stage ISVCDeleter completed in 4.73s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-okay-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-okay-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-okay-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.16s
hastagaras-llama-3-8b-okay_v2 status is now torndown due to DeploymentManager action