hastagaras-anjrit-8b-lla_8545

developer_uid: Hastagaras

submission_id: hastagaras-anjrit-8b-lla_8545_v1

model_name: test

model_group: Hastagaras/anjrit-8b-lla

status: torndown

timestamp: 2024-05-29T09:13:56+00:00

num_battles: 8956

num_wins: 4651

celo_rating: 1190.25

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/anjrit-8b-llama3-v0.2

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: test

is_internal_developer: False

language_model: Hastagaras/anjrit-8b-llama3-v0.2

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-29

win_ratio: 0.5193166592228674

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 200, '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': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{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_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-anjrit-8b-lla-8545-v1-mkmlizer
Waiting for job on hastagaras-anjrit-8b-lla-8545-v1-mkmlizer to finish
Failed to get response for submission blend_ripuf_2024-05-23: ('http://chaoticneutrals-poppy-po-3816-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║                                                                     ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║                                                                     ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║                                                                     ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ║                                                                     ║
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjrit-8b-lla-8545-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-anjrit-8b-lla-8545-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Downloaded to shared memory in 26.468s
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:01, 195.08it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:01, 193.13it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 213.41it/s]
Loading 0:  31%|███       | 89/291 [00:00<00:01, 109.73it/s]
Loading 0:  38%|███▊      | 112/291 [00:00<00:01, 133.99it/s]
Loading 0:  46%|████▋     | 135/291 [00:00<00:00, 156.33it/s]
Loading 0:  54%|█████▍    | 157/291 [00:00<00:00, 170.97it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 185.24it/s]
Loading 0:  69%|██████▉   | 201/291 [00:01<00:00, 114.17it/s]
Loading 0:  76%|███████▌  | 221/291 [00:01<00:00, 129.36it/s]
Loading 0:  85%|████████▍ | 247/291 [00:01<00:00, 153.30it/s]
Loading 0:  93%|█████████▎| 270/291 [00:01<00:00, 170.65it/s]
Loading 0: 100%|██████████| 291/291 [00:06<00:00, 14.53it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: quantized model in 16.528s
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Processed model Hastagaras/anjrit-8b-llama3-v0.2 in 43.874s
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjrit-8b-lla-8545-v1
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjrit-8b-lla-8545-v1/config.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjrit-8b-lla-8545-v1/special_tokens_map.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjrit-8b-lla-8545-v1/tokenizer_config.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjrit-8b-lla-8545-v1/tokenizer.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjrit-8b-lla-8545-v1/flywheel_model.0.safetensors
hastagaras-anjrit-8b-lla-8545-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-anjrit-8b-lla-8545-v1-mkmlizer:   warnings.warn(
hastagaras-anjrit-8b-lla-8545-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-anjrit-8b-lla-8545-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Saving duration: 0.210s
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.416s
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/config.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/special_tokens_map.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/tokenizer_config.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/merges.txt
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/vocab.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/tokenizer.json
hastagaras-anjrit-8b-lla-8545-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjrit-8b-lla-8545-v1_reward/reward.tensors
Job hastagaras-anjrit-8b-lla-8545-v1-mkmlizer completed after 65.14s with status: succeeded
Stopping job with name hastagaras-anjrit-8b-lla-8545-v1-mkmlizer
Pipeline stage MKMLizer completed in 68.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjrit-8b-lla-8545-v1
Waiting for inference service hastagaras-anjrit-8b-lla-8545-v1 to be ready
Inference service hastagaras-anjrit-8b-lla-8545-v1 ready after 40.245882987976074s
Pipeline stage ISVCDeployer completed in 52.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.250598669052124s
Received healthy response to inference request in 1.3827893733978271s
Received healthy response to inference request in 1.323049545288086s
Received healthy response to inference request in 1.2925820350646973s
Received healthy response to inference request in 1.2505347728729248s
5 requests
0 failed requests
5th percentile: 1.2589442253112793
10th percentile: 1.2673536777496337
20th percentile: 1.2841725826263428
30th percentile: 1.298675537109375
40th percentile: 1.3108625411987305
50th percentile: 1.323049545288086
60th percentile: 1.3469454765319824
70th percentile: 1.3708414077758788
80th percentile: 1.5563512325286868
90th percentile: 1.9034749507904054
95th percentile: 2.0770368099212644
99th percentile: 2.215886297225952
mean time: 1.4999108791351319
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjrit-8b-lla_8545_v1 status is now deployed due to DeploymentManager action
hastagaras-anjrit-8b-lla_8545_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjrit-8b-lla_8545_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjrit-8b-lla-8545-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.40s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjrit-8b-lla-8545-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjrit-8b-lla-8545-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.85s
hastagaras-anjrit-8b-lla_8545_v1 status is now torndown due to DeploymentManager action