hastagaras-llama3-cukai-8b

developer_uid: Hastagaras

submission_id: hastagaras-llama3-cukai-8b_v1

model_name: hastagaras-llama3-cukai-8b_v1

model_group: Hastagaras/Llama3-Cukai-

status: torndown

timestamp: 2024-04-25T15:28:11+00:00

num_battles: 7325

num_wins: 4068

celo_rating: 1190.77

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Llama3-Cukai-8B

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-llama3-cukai-8b_v1

is_internal_developer: False

language_model: Hastagaras/Llama3-Cukai-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2024-04-25

win_ratio: 0.5553583617747441

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 35, 'presence_penalty': 0.0, 'frequency_penalty': 1.05, 'stopping_words': ['\n', '###', '</s>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\nWrite {bot_name}'s next reply in a fictional roleplay chat between {user_name} and {bot_name}.\n\n{memory}", 'prompt_template': '\n\n### Response:\n{bot_name}: {prompt}<|end_of_text|>', 'bot_template': '\n\n### Response:\n{bot_name}: {message}<|end_of_text|>', 'user_template': '\n\n### Instruction:\n{user_name}: {message}', 'response_template': '\n\n### Response:\n{bot_name}:', 'truncate_by_message': False}

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

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-cukai-8b-v1-mkmlizer
Waiting for job on hastagaras-llama3-cukai-8b-v1-mkmlizer to finish
hastagaras-llama3-cukai-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-llama3-cukai-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-cukai-8b-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-cukai-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-cukai-8b-v1-mkmlizer: Downloaded to shared memory in 41.298s
hastagaras-llama3-cukai-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-cukai-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-cukai-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  32%|███▏      | 93/291 [00:01<00:02, 91.67it/s]
Loading 0:  65%|██████▌   | 190/291 [00:02<00:01, 94.75it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 30.09it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-cukai-8b-v1-mkmlizer: quantized model in 19.262s
hastagaras-llama3-cukai-8b-v1-mkmlizer: Processed model Hastagaras/Llama3-Cukai-8B in 61.618s
hastagaras-llama3-cukai-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-cukai-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-cukai-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v1
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v1/config.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v1/tokenizer_config.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v1/tokenizer.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v1/special_tokens_map.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-cukai-8b-v1/flywheel_model.0.safetensors
hastagaras-llama3-cukai-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-cukai-8b-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-cukai-8b-v1-mkmlizer:   warnings.warn(
hastagaras-llama3-cukai-8b-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-cukai-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-cukai-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-cukai-8b-v1-mkmlizer: Saving duration: 0.270s
hastagaras-llama3-cukai-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.964s
hastagaras-llama3-cukai-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-cukai-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-cukai-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/config.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/special_tokens_map.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/tokenizer_config.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/merges.txt
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/vocab.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/tokenizer.json
hastagaras-llama3-cukai-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-cukai-8b-v1_reward/reward.tensors
Job hastagaras-llama3-cukai-8b-v1-mkmlizer completed after 98.51s with status: succeeded
Stopping job with name hastagaras-llama3-cukai-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 102.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-cukai-8b-v1
Waiting for inference service hastagaras-llama3-cukai-8b-v1 to be ready
Inference service hastagaras-llama3-cukai-8b-v1 ready after 40.81424880027771s
Pipeline stage ISVCDeployer completed in 48.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1265318393707275s
Received healthy response to inference request in 2.5644283294677734s
Received healthy response to inference request in 1.3388638496398926s
Received healthy response to inference request in 1.308680772781372s
Received healthy response to inference request in 1.3371007442474365s
5 requests
0 failed requests
5th percentile: 1.314364767074585
10th percentile: 1.3200487613677978
20th percentile: 1.3314167499542235
30th percentile: 1.3374533653259277
40th percentile: 1.3381586074829102
50th percentile: 1.3388638496398926
60th percentile: 1.6539310455322265
70th percentile: 1.9689982414245604
80th percentile: 2.214111137390137
90th percentile: 2.389269733428955
95th percentile: 2.476849031448364
99th percentile: 2.5469124698638916
mean time: 1.7351211071014405
Pipeline stage StressChecker completed in 9.31s
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 0.09s
hastagaras-llama3-cukai-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-llama3-cukai-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-cukai-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-cukai-8b-v1 is running
Tearing down inference service hastagaras-llama3-cukai-8b-v1
admin requested tearing down of hastagaras-lp-8b-dpotest_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lp-8b-dpotest-v1 is running
Toredown service hastagaras-llama3-cukai-8b-v1
Pipeline stage ISVCDeleter completed in 10.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-cukai-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-cukai-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-cukai-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-cukai-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.25s
hastagaras-llama3-cukai-8b_v1 status is now torndown due to DeploymentManager action