hastagaras-halu-8b-llama_3098

submission_id: hastagaras-halu-8b-llama_3098_v2

developer_uid: Hastagaras

best_of: 16

celo_rating: 1195.35

display_name: no-b

family_friendly_score: 0.0

formatter: {'memory_template': "<|begin_of_text|><|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}

generation_params: {'temperature': 1.1, 'top_p': 0.95, 'min_p': 0.01, 'top_k': 60, '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/Halu-8B-Llama3-v0.5

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/Halu-8B-Llama

model_name: no-b

model_num_parameters: 8030261248.0

model_repo: Hastagaras/Halu-8B-Llama3-v0.5

model_size: 8B

num_battles: 56124

num_wins: 29414

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-06-12T23:55:11+00:00

us_pacific_date: 2024-06-12

win_ratio: 0.5240895160715558

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3098-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3098-v2-mkmlizer to finish
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3098-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3098-v2-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-8b-llama-3098-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Downloaded to shared memory in 19.746s
hastagaras-halu-8b-llama-3098-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3098-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 107.99it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:02, 98.05it/s] 
Loading 0:  12%|█▏        | 36/291 [00:00<00:02, 111.21it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 109.10it/s]
Loading 0:  20%|██        | 59/291 [00:00<00:02, 98.94it/s] 
Loading 0:  25%|██▍       | 72/291 [00:00<00:02, 108.32it/s]
Loading 0:  29%|██▉       | 84/291 [00:01<00:05, 39.79it/s] 
Loading 0:  32%|███▏      | 94/291 [00:01<00:04, 47.34it/s]
Loading 0:  36%|███▌      | 104/291 [00:01<00:03, 54.88it/s]
Loading 0:  40%|████      | 117/291 [00:01<00:02, 68.46it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:02, 77.94it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 80.10it/s]
Loading 0:  54%|█████▎    | 156/291 [00:02<00:01, 95.54it/s]
Loading 0:  58%|█████▊    | 168/291 [00:02<00:01, 98.65it/s]
Loading 0:  62%|██████▏   | 181/291 [00:02<00:01, 105.03it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 52.97it/s] 
Loading 0:  71%|███████   | 206/291 [00:02<00:01, 64.55it/s]
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 76.30it/s]
Loading 0:  79%|███████▉  | 230/291 [00:03<00:00, 80.81it/s]
Loading 0:  85%|████████▍ | 246/291 [00:03<00:00, 95.93it/s]
Loading 0:  89%|████████▊ | 258/291 [00:03<00:00, 97.96it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 108.34it/s]
Loading 0:  98%|█████████▊| 286/291 [00:03<00:00, 111.13it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3098-v2-mkmlizer: quantized model in 22.868s
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.5 in 44.193s
hastagaras-halu-8b-llama-3098-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3098-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3098-v2
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3098-v2/config.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3098-v2/tokenizer_config.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3098-v2/special_tokens_map.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3098-v2/tokenizer.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3098-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3098-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3098-v2-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-8b-llama-3098-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3098-v2-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-8b-llama-3098-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3098-v2-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-8b-llama-3098-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3098-v2-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-8b-llama-3098-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Saving duration: 0.252s
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.462s
hastagaras-halu-8b-llama-3098-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3098-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3098-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/config.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/merges.txt
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/vocab.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-3098-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3098-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-3098-v2-mkmlizer completed after 72.89s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3098-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3098-v2
Waiting for inference service hastagaras-halu-8b-llama-3098-v2 to be ready
Inference service hastagaras-halu-8b-llama-3098-v2 ready after 30.170355796813965s
Pipeline stage ISVCDeployer completed in 37.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.054081916809082s
Received healthy response to inference request in 1.318608045578003s
Received healthy response to inference request in 1.3144567012786865s
Received healthy response to inference request in 1.2629368305206299s
Received healthy response to inference request in 1.3457729816436768s
5 requests
0 failed requests
5th percentile: 1.2732408046722412
10th percentile: 1.2835447788238525
20th percentile: 1.3041527271270752
30th percentile: 1.31528697013855
40th percentile: 1.3169475078582764
50th percentile: 1.318608045578003
60th percentile: 1.3294740200042725
70th percentile: 1.340339994430542
80th percentile: 1.487434768676758
90th percentile: 1.77075834274292
95th percentile: 1.9124201297760008
99th percentile: 2.025749559402466
mean time: 1.4591712951660156
Pipeline stage StressChecker completed in 7.94s
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-halu-8b-llama_3098_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_3098_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_3098_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-3098-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3098-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3098-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3098-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3098-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3098-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3098-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.95s
hastagaras-halu-8b-llama_3098_v2 status is now torndown due to DeploymentManager action