hastagaras-llama3-8b-claoas

submission_id: hastagaras-llama3-8b-claoas_v1

developer_uid: Hastagaras

best_of: 16

celo_rating: 1168.3

display_name: hastagaras-llama3-8b-claoas_v1

family_friendly_score: 0.0

formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name} in this roleplay chat.\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': 'Message Example: {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}

generation_params: {'temperature': 0.9, '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}

is_internal_developer: False

language_model: Hastagaras/llama3-8b-CLaOaS

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/llama3-8b-CLa

model_name: hastagaras-llama3-8b-claoas_v1

model_num_parameters: 8030261248.0

model_repo: Hastagaras/llama3-8b-CLaOaS

model_size: 8B

num_battles: 27137

num_wins: 13565

ranking_group: single

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{bot_name}: {prompt}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-05-05T11:24:41+00:00

us_pacific_date: 2024-05-05

win_ratio: 0.49987102480008844

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-claoas-v1-mkmlizer
Waiting for job on hastagaras-llama3-8b-claoas-v1-mkmlizer to finish
hastagaras-llama3-8b-claoas-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-claoas-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-claoas-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-llama3-8b-claoas-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-claoas-v1-mkmlizer: Downloaded to shared memory in 24.531s
hastagaras-llama3-8b-claoas-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-claoas-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-claoas-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 125.87it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 133.41it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 29.23it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-claoas-v1-mkmlizer: quantized model in 17.592s
hastagaras-llama3-8b-claoas-v1-mkmlizer: Processed model Hastagaras/llama3-8b-CLaOaS in 43.239s
hastagaras-llama3-8b-claoas-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-claoas-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-claoas-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v1
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v1/special_tokens_map.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v1/tokenizer_config.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v1/config.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v1/tokenizer.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-claoas-v1/flywheel_model.0.safetensors
hastagaras-llama3-8b-claoas-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-claoas-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-llama3-8b-claoas-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-claoas-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-llama3-8b-claoas-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-claoas-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-llama3-8b-claoas-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-claoas-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-llama3-8b-claoas-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-claoas-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-claoas-v1-mkmlizer: Saving duration: 0.270s
hastagaras-llama3-8b-claoas-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.904s
hastagaras-llama3-8b-claoas-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-claoas-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-claoas-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/config.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/special_tokens_map.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/tokenizer_config.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/merges.txt
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/vocab.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/tokenizer.json
hastagaras-llama3-8b-claoas-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-claoas-v1_reward/reward.tensors
Job hastagaras-llama3-8b-claoas-v1-mkmlizer completed after 72.66s with status: succeeded
Stopping job with name hastagaras-llama3-8b-claoas-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.21s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-claoas-v1
Waiting for inference service hastagaras-llama3-8b-claoas-v1 to be ready
Inference service hastagaras-llama3-8b-claoas-v1 ready after 30.157665014266968s
Pipeline stage ISVCDeployer completed in 36.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5462493896484375s
Received healthy response to inference request in 1.302358865737915s
Received healthy response to inference request in 1.2607088088989258s
Received healthy response to inference request in 1.246899127960205s
Received healthy response to inference request in 1.3053126335144043s
5 requests
0 failed requests
5th percentile: 1.2496610641479493
10th percentile: 1.2524230003356933
20th percentile: 1.2579468727111816
30th percentile: 1.2690388202667235
40th percentile: 1.2856988430023193
50th percentile: 1.302358865737915
60th percentile: 1.3035403728485107
70th percentile: 1.3047218799591065
80th percentile: 1.7534999847412114
90th percentile: 2.649874687194824
95th percentile: 3.0980620384216304
99th percentile: 3.456611919403076
mean time: 1.7323057651519775
Pipeline stage StressChecker completed in 9.27s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama3-8b-claoas_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-8b-claoas_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-claoas_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-claoas-v1 is running
Tearing down inference service hastagaras-llama3-8b-claoas-v1
Toredown service hastagaras-llama3-8b-claoas-v1
Pipeline stage ISVCDeleter completed in 3.55s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-claoas-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-claoas-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-claoas-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-claoas-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-claoas-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-claoas-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-claoas-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-claoas-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-claoas-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-claoas-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-claoas-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-claoas-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.27s
hastagaras-llama3-8b-claoas_v1 status is now torndown due to DeploymentManager action