hastagaras-halu-8b-llama_4766

submission_id: hastagaras-halu-8b-llama_4766_v2

developer_uid: Hastagaras

best_of: 16

celo_rating: 1210.31

display_name: renamed-from-exp2-2

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': 1.05, 'top_p': 1.0, 'min_p': 0.08, '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-BRSLURP

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Hastagaras/HALU-8B-LLAMA

model_name: renamed-from-exp2-2

model_num_parameters: 8030261248.0

model_repo: Hastagaras/HALU-8B-LLAMA3-BRSLURP

model_size: 8B

num_battles: 12195

num_wins: 6549

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: 2024-06-01T02:40:41+00:00

us_pacific_date: 2024-05-31

win_ratio: 0.5370233702337024

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-halu-8b-llama-4766-v2-mkmlizer
Waiting for job on hastagaras-halu-8b-llama-4766-v2-mkmlizer to finish
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ║                                                                     ║
hastagaras-halu-8b-llama-4766-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-halu-8b-llama-4766-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-4766-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Downloaded to shared memory in 18.028s
hastagaras-halu-8b-llama-4766-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-halu-8b-llama-4766-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:45,  2.23s/it]
Loading 0:   6%|▌         | 18/291 [00:04<00:50,  5.39it/s]
Loading 0:  12%|█▏        | 34/291 [00:04<00:21, 11.94it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.88it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.53it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 36.80it/s]
Loading 0:  33%|███▎      | 97/291 [00:05<00:03, 49.98it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 65.45it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 81.95it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 98.76it/s]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:01, 76.65it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 92.94it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 108.39it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 121.68it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 133.18it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 142.83it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 94.58it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:06<00:00, 104.43it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-halu-8b-llama-4766-v2-mkmlizer: quantized model in 22.941s
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Processed model Hastagaras/HALU-8B-LLAMA3-BRSLURP in 43.507s
hastagaras-halu-8b-llama-4766-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-halu-8b-llama-4766-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v2
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v2/special_tokens_map.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v2/config.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v2/tokenizer_config.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v2/tokenizer.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-halu-8b-llama-4766-v2/flywheel_model.0.safetensors
hastagaras-halu-8b-llama-4766-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-halu-8b-llama-4766-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-4766-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4766-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-4766-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4766-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-4766-v2-mkmlizer:   warnings.warn(
hastagaras-halu-8b-llama-4766-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-4766-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Saving duration: 0.400s
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.125s
hastagaras-halu-8b-llama-4766-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-halu-8b-llama-4766-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-halu-8b-llama-4766-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/tokenizer_config.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/special_tokens_map.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/merges.txt
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/vocab.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/config.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/tokenizer.json
hastagaras-halu-8b-llama-4766-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-halu-8b-llama-4766-v2_reward/reward.tensors
Job hastagaras-halu-8b-llama-4766-v2-mkmlizer completed after 62.64s with status: succeeded
Stopping job with name hastagaras-halu-8b-llama-4766-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-halu-8b-llama-4766-v2
Waiting for inference service hastagaras-halu-8b-llama-4766-v2 to be ready
Inference service hastagaras-halu-8b-llama-4766-v2 ready after 40.23104214668274s
Pipeline stage ISVCDeployer completed in 47.54s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.13116717338562s
Received healthy response to inference request in 1.3328406810760498s
Received healthy response to inference request in 1.314209222793579s
Received healthy response to inference request in 1.2813291549682617s
Received healthy response to inference request in 1.2459192276000977s
5 requests
0 failed requests
5th percentile: 1.2530012130737305
10th percentile: 1.2600831985473633
20th percentile: 1.274247169494629
30th percentile: 1.2879051685333252
40th percentile: 1.3010571956634522
50th percentile: 1.314209222793579
60th percentile: 1.3216618061065675
70th percentile: 1.3291143894195556
80th percentile: 1.492505979537964
90th percentile: 1.811836576461792
95th percentile: 1.9715018749237059
99th percentile: 2.099234113693237
mean time: 1.4610930919647216
Pipeline stage StressChecker completed in 7.89s
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_4766_v2 status is now deployed due to DeploymentManager action
hastagaras-halu-8b-llama_4766_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-halu-8b-llama_4766_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-halu-8b-llama-4766-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-4766-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4766-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4766-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4766-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-halu-8b-llama-4766-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-halu-8b-llama-4766-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.77s
hastagaras-halu-8b-llama_4766_v2 status is now torndown due to DeploymentManager action