developer_uid: Hastagaras
submission_id: hastagaras-llama-3-8b-well_v1
model_name: another-test-manual
model_group: Hastagaras/llama-3-8b-we
status: torndown
timestamp: 2024-05-14T03:22:21+00:00
num_battles: 24643
num_wins: 13058
celo_rating: 1190.23
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/llama-3-8b-well
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: another-test-manual
is_internal_developer: False
language_model: Hastagaras/llama-3-8b-well
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-13
win_ratio: 0.5298867832650246
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}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nScenario of {bot_name} and {user_name}.\n\n{bot_name}'s Persona:\n{memory}\n\n", 'prompt_template': 'Previously:\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': False}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-well-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-well-v1-mkmlizer to finish
hastagaras-llama-3-8b-well-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama-3-8b-well-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ║                                                                     ║
hastagaras-llama-3-8b-well-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama-3-8b-well-v1-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-well-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama-3-8b-well-v1-mkmlizer: Downloaded to shared memory in 26.373s
hastagaras-llama-3-8b-well-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-well-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-well-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  51%|█████     | 147/291 [00:00<00:00, 147.06it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 38.41it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-well-v1-mkmlizer: quantized model in 16.908s
hastagaras-llama-3-8b-well-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-well-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-well-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-well-v1
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-well-v1/config.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-well-v1/special_tokens_map.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-well-v1/tokenizer_config.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-well-v1/tokenizer.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-well-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-well-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-well-v1-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-well-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-well-v1-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-well-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-well-v1-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-well-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-well-v1-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-well-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-well-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-well-v1-mkmlizer: Saving duration: 0.213s
hastagaras-llama-3-8b-well-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.085s
hastagaras-llama-3-8b-well-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-well-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-well-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/config.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/vocab.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/merges.txt
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/tokenizer.json
hastagaras-llama-3-8b-well-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-well-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-well-v1-mkmlizer completed after 73.43s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-well-v1-mkmlizer
Pipeline stage MKMLizer completed in 78.07s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-well-v1
Waiting for inference service hastagaras-llama-3-8b-well-v1 to be ready
Inference service hastagaras-llama-3-8b-well-v1 ready after 40.28967809677124s
Pipeline stage ISVCDeployer completed in 48.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1060678958892822s
Received healthy response to inference request in 1.3482446670532227s
Received healthy response to inference request in 1.3366260528564453s
Received healthy response to inference request in 1.26021146774292s
Received healthy response to inference request in 1.341040849685669s
5 requests
0 failed requests
5th percentile: 1.275494384765625
10th percentile: 1.2907773017883302
20th percentile: 1.3213431358337402
30th percentile: 1.3375090122222901
40th percentile: 1.3392749309539795
50th percentile: 1.341040849685669
60th percentile: 1.3439223766326904
70th percentile: 1.346803903579712
80th percentile: 1.4998093128204346
90th percentile: 1.8029386043548585
95th percentile: 1.9545032501220703
99th percentile: 2.0757549667358397
mean time: 1.4784381866455079
Pipeline stage StressChecker completed in 8.10s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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 0.07s
hastagaras-llama-3-8b-well_v1 status is now deployed due to DeploymentManager action
hastagaras-llama-3-8b-well_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama-3-8b-well_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama-3-8b-well-v1 is running
Tearing down inference service hastagaras-llama-3-8b-well-v1
Toredown service hastagaras-llama-3-8b-well-v1
Pipeline stage ISVCDeleter completed in 7.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-well-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-well-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-well-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-well-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama-3-8b-well-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama-3-8b-well-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-well-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-well-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-well-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-well-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-well-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama-3-8b-well-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.84s
hastagaras-llama-3-8b-well_v1 status is now torndown due to DeploymentManager action