hastagaras-halu-oas-8b-l_8790

developer_uid: Hastagaras

submission_id: hastagaras-halu-oas-8b-l_8790_v1

model_name: hastagaras-halu-oas-8b-l_8790_v1

model_group: Hastagaras/Halu-OAS-8B-L

status: torndown

timestamp: 2024-05-27T13:31:53+00:00

num_battles: 20309

num_wins: 10258

celo_rating: 1175.45

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Halu-OAS-8B-Llama3-ALT

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-halu-oas-8b-l_8790_v1

is_internal_developer: False

language_model: Hastagaras/Halu-OAS-8B-Llama3-ALT

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-27

win_ratio: 0.5050962627406569

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 100, '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-halu-oas-8b-l-8790-v1-mkmlizer
Waiting for job on hastagaras-halu-oas-8b-l-8790-v1-mkmlizer to finish
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-oas-8b-l-8790-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-halu-oas-8b-l-8790-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Downloaded to shared memory in 37.889s
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 113.65it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 99.63it/s] 
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 112.48it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:02, 105.62it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 114.54it/s]
Loading 0:  27%|██▋       | 78/291 [00:00<00:01, 107.97it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:03, 54.09it/s] 
Loading 0:  35%|███▌      | 102/291 [00:01<00:02, 66.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:02, 72.55it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:02, 78.30it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 93.92it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 92.70it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:01, 103.85it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:01, 109.60it/s]
Loading 0:  66%|██████▌   | 191/291 [00:02<00:01, 61.44it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 68.05it/s]
Loading 0:  74%|███████▎  | 214/291 [00:02<00:00, 77.73it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 89.28it/s]
Loading 0:  82%|████████▏ | 239/291 [00:02<00:00, 89.97it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 102.26it/s]
Loading 0:  92%|█████████▏| 267/291 [00:03<00:00, 102.70it/s]
Loading 0:  97%|█████████▋| 281/291 [00:03<00:00, 109.44it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: quantized model in 27.017s
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Processed model Hastagaras/Halu-OAS-8B-Llama3-ALT in 67.779s
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-8790-v1
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-8790-v1/config.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-8790-v1/special_tokens_map.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-8790-v1/tokenizer_config.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-8790-v1/tokenizer.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-oas-8b-l-8790-v1/flywheel_model.0.safetensors
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-oas-8b-l-8790-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-halu-oas-8b-l-8790-v1-mkmlizer:   warnings.warn(
hastagaras-halu-oas-8b-l-8790-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-halu-oas-8b-l-8790-v1-mkmlizer:   warnings.warn(
hastagaras-halu-oas-8b-l-8790-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-halu-oas-8b-l-8790-v1-mkmlizer:   warnings.warn(
hastagaras-halu-oas-8b-l-8790-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-halu-oas-8b-l-8790-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Saving duration: 0.517s
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.580s
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward/config.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward/special_tokens_map.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward/tokenizer_config.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward/merges.txt
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward/vocab.json
hastagaras-halu-oas-8b-l-8790-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-oas-8b-l-8790-v1_reward/tokenizer.json
Failed to get response for submission blend_larer_2024-05-23: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44694->127.0.0.1:8080: read: connection reset by peer\n')
Job hastagaras-halu-oas-8b-l-8790-v1-mkmlizer completed after 104.42s with status: succeeded
Stopping job with name hastagaras-halu-oas-8b-l-8790-v1-mkmlizer
Pipeline stage MKMLizer completed in 109.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-oas-8b-l-8790-v1
Waiting for inference service hastagaras-halu-oas-8b-l-8790-v1 to be ready
Inference service hastagaras-halu-oas-8b-l-8790-v1 ready after 40.232556104660034s
Pipeline stage ISVCDeployer completed in 48.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2390410900115967s
Received healthy response to inference request in 1.389441967010498s
Received healthy response to inference request in 1.3432502746582031s
Received healthy response to inference request in 1.3439433574676514s
Received healthy response to inference request in 1.2569901943206787s
5 requests
0 failed requests
5th percentile: 1.2742422103881836
10th percentile: 1.2914942264556886
20th percentile: 1.3259982585906982
30th percentile: 1.3433888912200929
40th percentile: 1.3436661243438721
50th percentile: 1.3439433574676514
60th percentile: 1.36214280128479
70th percentile: 1.3803422451019287
80th percentile: 1.5593617916107179
90th percentile: 1.8992014408111573
95th percentile: 2.069121265411377
99th percentile: 2.2050571250915527
mean time: 1.5145333766937257
Pipeline stage StressChecker completed in 8.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-oas-8b-l_8790_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-oas-8b-l_8790_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-oas-8b-l_8790_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-oas-8b-l-8790-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-oas-8b-l-8790-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-oas-8b-l-8790-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.57s
hastagaras-halu-oas-8b-l_8790_v1 status is now torndown due to DeploymentManager action