hastagaras-halu-8b-llama_3560

submission_id: hastagaras-halu-8b-llama_3560_v1

developer_uid: Hastagaras

best_of: 16

celo_rating: 1210.94

display_name: merge-test

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': 0.85, 'top_p': 0.95, 'min_p': 0.05, '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}

is_internal_developer: False

language_model: Hastagaras/Halu-8B-Llama3-Blackroot

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/Halu-8B-Llama

model_name: merge-test

model_num_parameters: 8030261248.0

model_repo: Hastagaras/Halu-8B-Llama3-Blackroot

model_size: 8B

num_battles: 11143

num_wins: 6250

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: 2024-05-28T10:24:40+00:00

us_pacific_date: 2024-05-28

win_ratio: 0.560890244996859

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-3560-v1-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-3560-v1-mkmlizer to finish
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-3560-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-3560-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-3560-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Downloaded to shared memory in 52.550s
hastagaras-halu-8b-llama-3560-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-3560-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:25,  2.37s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:16,  3.62it/s]
Loading 0:   8%|▊         | 24/291 [00:04<00:34,  7.82it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:15, 15.88it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:10, 22.29it/s]
Loading 0:  21%|██        | 61/291 [00:05<00:10, 22.30it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 33.18it/s]
Loading 0:  30%|██▉       | 87/291 [00:05<00:04, 41.23it/s]
Loading 0:  35%|███▌      | 103/291 [00:05<00:03, 56.63it/s]
Loading 0:  39%|███▉      | 114/291 [00:06<00:02, 63.77it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:02, 80.44it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 85.99it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 98.91it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:01, 60.64it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 72.48it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 76.40it/s]
Loading 0:  71%|███████   | 207/291 [00:07<00:00, 84.19it/s]
Loading 0:  76%|███████▌  | 220/291 [00:07<00:00, 89.88it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:00, 83.46it/s]
Loading 0:  83%|████████▎ | 241/291 [00:07<00:00, 87.20it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 88.57it/s]
Loading 0:  90%|████████▉ | 261/291 [00:07<00:00, 90.44it/s]
Loading 0:  93%|█████████▎| 271/291 [00:08<00:00, 54.71it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 62.75it/s]
Loading 0: 100%|█████████▉| 290/291 [00:08<00:00, 67.53it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-3560-v1-mkmlizer: quantized model in 24.546s
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Processed model Hastagaras/Halu-8B-Llama3-Blackroot in 79.871s
hastagaras-halu-8b-llama-3560-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-3560-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3560-v1
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3560-v1/special_tokens_map.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3560-v1/config.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3560-v1/tokenizer_config.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-3560-v1/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-3560-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-3560-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-3560-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3560-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-3560-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3560-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-3560-v1-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-3560-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-3560-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Saving duration: 0.429s
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 32.461s
hastagaras-halu-8b-llama-3560-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-3560-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-3560-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/config.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/tokenizer_config.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/merges.txt
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/special_tokens_map.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/vocab.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/tokenizer.json
hastagaras-halu-8b-llama-3560-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-3560-v1_reward/reward.tensors
Job hastagaras-halu-8b-llama-3560-v1-mkmlizer completed after 164.55s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-3560-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-3560-v1
Waiting for inference service hastagaras-halu-8b-llama-3560-v1 to be ready
Inference service hastagaras-halu-8b-llama-3560-v1 ready after 50.271907806396484s
Pipeline stage ISVCDeployer completed in 56.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.193560838699341s
Received healthy response to inference request in 1.3634347915649414s
Received healthy response to inference request in 1.3278791904449463s
Received healthy response to inference request in 1.294818639755249s
Received healthy response to inference request in 1.2447271347045898s
5 requests
0 failed requests
5th percentile: 1.2547454357147216
10th percentile: 1.2647637367248534
20th percentile: 1.2848003387451172
30th percentile: 1.3014307498931885
40th percentile: 1.3146549701690673
50th percentile: 1.3278791904449463
60th percentile: 1.3421014308929444
70th percentile: 1.3563236713409423
80th percentile: 1.5294600009918216
90th percentile: 1.8615104198455812
95th percentile: 2.0275356292724607
99th percentile: 2.1603557968139646
mean time: 1.4848841190338136
Pipeline stage StressChecker completed in 8.30s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-halu-8b-llama_3560_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-halu-8b-llama_3560_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_3560_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-3560-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.33s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3560-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3560-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3560-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3560-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-3560-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-3560-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.63s
hastagaras-halu-8b-llama_3560_v1 status is now torndown due to DeploymentManager action