hastagaras-halu-8b-llama_3117

submission_id: hastagaras-halu-8b-llama_3117_v1

developer_uid: Hastagaras

best_of: 16

celo_rating: 1192.64

display_name: HALUUUU

family_friendly_score: 0.0

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}

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: Hastagaras/Halu-8B-Llama3-v0.2

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/Halu-8B-Llama

model_name: HALUUUU

model_num_parameters: 8030261248.0

model_repo: Hastagaras/Halu-8B-Llama3-v0.2

model_size: 8B

num_battles: 9124

num_wins: 4717

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: 2024-05-24T04:21:36+00:00

us_pacific_date: 2024-05-23

win_ratio: 0.5169881630863656

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3117-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3117-v1-mkmlizer to finish
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3117-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3117-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-8b-llama-3117-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Downloaded to shared memory in 35.933s
hastagaras-halu-8b-llama-3117-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3117-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 114.79it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:01, 133.40it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:01, 130.10it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 129.85it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:01, 138.44it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:03, 66.43it/s] 
Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 79.25it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 96.45it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 111.42it/s]
Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 119.49it/s]
Loading 0:  58%|█████▊    | 168/291 [00:01<00:00, 123.95it/s]
Loading 0:  64%|██████▍   | 186/291 [00:01<00:00, 138.43it/s]
Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 74.25it/s] 
Loading 0:  75%|███████▌  | 219/291 [00:02<00:00, 89.41it/s]
Loading 0:  80%|████████  | 234/291 [00:02<00:00, 100.24it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 106.35it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 119.82it/s]
Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 128.39it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3117-v1-mkmlizer: quantized model in 19.333s
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-v0.2 in 56.346s
hastagaras-halu-8b-llama-3117-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3117-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v1
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v1/config.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v1/special_tokens_map.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v1/tokenizer.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3117-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3117-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3117-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-8b-llama-3117-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3117-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-8b-llama-3117-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3117-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-8b-llama-3117-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3117-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-8b-llama-3117-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Saving duration: 0.308s
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.459s
hastagaras-halu-8b-llama-3117-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3117-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3117-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/config.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/merges.txt
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/vocab.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-3117-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3117-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-3117-v1-mkmlizer completed after 86.59s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3117-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3117-v1
Waiting for inference service hastagaras-halu-8b-llama-3117-v1 to be ready
Inference service hastagaras-halu-8b-llama-3117-v1 ready after 40.207024574279785s
Pipeline stage ISVCDeployer completed in 47.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.038571834564209s
Received healthy response to inference request in 1.3227298259735107s
Received healthy response to inference request in 1.3271677494049072s
Received healthy response to inference request in 1.2966363430023193s
Received healthy response to inference request in 1.3433294296264648s
5 requests
0 failed requests
5th percentile: 1.3018550395965576
10th percentile: 1.3070737361907958
20th percentile: 1.3175111293792725
30th percentile: 1.32361741065979
40th percentile: 1.3253925800323487
50th percentile: 1.3271677494049072
60th percentile: 1.3336324214935302
70th percentile: 1.3400970935821532
80th percentile: 1.4823779106140138
90th percentile: 1.7604748725891115
95th percentile: 1.89952335357666
99th percentile: 2.010762138366699
mean time: 1.4656870365142822
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_3117_v1 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_3117_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_3117_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-3117-v1 is running
Tearing down inference service hastagaras-halu-8b-llama-3117-v1
Toredown service hastagaras-halu-8b-llama-3117-v1
Pipeline stage ISVCDeleter completed in 4.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3117-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3117-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3117-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3117-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3117-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3117-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.80s
hastagaras-halu-8b-llama_3117_v1 status is now torndown due to DeploymentManager action