invisietch-etherealrainb_9091

submission_id: invisietch-etherealrainb_9091_v1

developer_uid: invisietch

best_of: 4

celo_rating: 1183.77

display_name: invisietch-etherealrainbow-v0_3

family_friendly_score: 0.0

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

is_internal_developer: False

language_model: invisietch/EtherealRainbow-v0.3-8B

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: invisietch/EtherealRainb

model_name: invisietch-etherealrainbow-v0_3

model_num_parameters: 8030261248.0

model_repo: invisietch/EtherealRainbow-v0.3-8B

model_size: 8B

num_battles: 35872

num_wins: 17567

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: 2024-07-07T20:41:45+00:00

us_pacific_date: 2024-07-07

win_ratio: 0.4897134255129349

Resubmit model

Running pipeline stage MKMLizer
Starting job with name invisietch-etherealrainb-9091-v1-mkmlizer
Waiting for job on invisietch-etherealrainb-9091-v1-mkmlizer to finish
invisietch-etherealrainb-9091-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
invisietch-etherealrainb-9091-v1-mkmlizer: ║     _____            __           __                                ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║       /___/                                                         ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║                                                                     ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  https://mk1.ai                                                     ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║                                                                     ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  belonging to:                                                      ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║                                                                     ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  Chai Research Corp.                                                ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
invisietch-etherealrainb-9091-v1-mkmlizer: ║                                                                     ║
invisietch-etherealrainb-9091-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
invisietch-etherealrainb-9091-v1-mkmlizer: Downloaded to shared memory in 84.619s
invisietch-etherealrainb-9091-v1-mkmlizer: quantizing model to /dev/shm/model_cache
invisietch-etherealrainb-9091-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
invisietch-etherealrainb-9091-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:43,  2.85s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:24,  3.27it/s]
Loading 0:   8%|▊         | 22/291 [00:06<00:49,  5.42it/s]
Loading 0:  11%|█▏        | 33/291 [00:06<00:26,  9.86it/s]
Loading 0:  14%|█▍        | 42/291 [00:06<00:17, 14.31it/s]
Loading 0:  18%|█▊        | 51/291 [00:06<00:12, 19.97it/s]
Loading 0:  23%|██▎       | 67/291 [00:06<00:06, 33.35it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:05, 41.70it/s]
Loading 0:  30%|███       | 88/291 [00:07<00:05, 37.51it/s]
Loading 0:  35%|███▌      | 103/291 [00:07<00:03, 51.90it/s]
Loading 0:  39%|███▉      | 114/291 [00:07<00:02, 59.78it/s]
Loading 0:  45%|████▍     | 130/291 [00:07<00:02, 76.27it/s]
Loading 0:  49%|████▉     | 142/291 [00:07<00:02, 56.22it/s]
Loading 0:  54%|█████▍    | 157/291 [00:07<00:01, 70.42it/s]
Loading 0:  58%|█████▊    | 168/291 [00:07<00:01, 75.60it/s]
Loading 0:  63%|██████▎   | 184/291 [00:08<00:01, 90.02it/s]
Loading 0:  67%|██████▋   | 196/291 [00:08<00:01, 82.53it/s]
Loading 0:  71%|███████   | 206/291 [00:08<00:01, 58.51it/s]
Loading 0:  76%|███████▌  | 220/291 [00:08<00:00, 71.63it/s]
Loading 0:  79%|███████▉  | 231/291 [00:08<00:00, 76.79it/s]
Loading 0:  85%|████████▍ | 247/291 [00:08<00:00, 92.23it/s]
Loading 0:  89%|████████▊ | 258/291 [00:09<00:00, 93.18it/s]
Loading 0:  92%|█████████▏| 269/291 [00:09<00:00, 62.60it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 72.91it/s]
Loading 0: 100%|██████████| 291/291 [00:09<00:00, 76.68it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
invisietch-etherealrainb-9091-v1-mkmlizer: quantized model in 30.428s
invisietch-etherealrainb-9091-v1-mkmlizer: Processed model invisietch/EtherealRainbow-v0.3-8B in 115.047s
invisietch-etherealrainb-9091-v1-mkmlizer: creating bucket guanaco-mkml-models
invisietch-etherealrainb-9091-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
invisietch-etherealrainb-9091-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v1
invisietch-etherealrainb-9091-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v1/special_tokens_map.json
invisietch-etherealrainb-9091-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v1/config.json
invisietch-etherealrainb-9091-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v1/tokenizer_config.json
invisietch-etherealrainb-9091-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v1/tokenizer.json
invisietch-etherealrainb-9091-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/invisietch-etherealrainb-9091-v1/flywheel_model.0.safetensors
invisietch-etherealrainb-9091-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
invisietch-etherealrainb-9091-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
invisietch-etherealrainb-9091-v1-mkmlizer:   warnings.warn(
invisietch-etherealrainb-9091-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
invisietch-etherealrainb-9091-v1-mkmlizer:   warnings.warn(
invisietch-etherealrainb-9091-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
invisietch-etherealrainb-9091-v1-mkmlizer:   warnings.warn(
invisietch-etherealrainb-9091-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.
invisietch-etherealrainb-9091-v1-mkmlizer:   warnings.warn(
invisietch-etherealrainb-9091-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()
invisietch-etherealrainb-9091-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
invisietch-etherealrainb-9091-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
invisietch-etherealrainb-9091-v1-mkmlizer: Saving duration: 0.562s
invisietch-etherealrainb-9091-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.929s
invisietch-etherealrainb-9091-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/invisietch-etherealrainb-9091-v1_reward/reward.tensors
Job invisietch-etherealrainb-9091-v1-mkmlizer completed after 144.87s with status: succeeded
Stopping job with name invisietch-etherealrainb-9091-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service invisietch-etherealrainb-9091-v1
Waiting for inference service invisietch-etherealrainb-9091-v1 to be ready
Inference service invisietch-etherealrainb-9091-v1 ready after 30.228844165802002s
Pipeline stage ISVCDeployer completed in 36.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8123958110809326s
Received healthy response to inference request in 1.1199183464050293s
Received healthy response to inference request in 1.148606777191162s
Received healthy response to inference request in 1.1399002075195312s
Received healthy response to inference request in 1.1353943347930908s
5 requests
0 failed requests
5th percentile: 1.1230135440826416
10th percentile: 1.126108741760254
20th percentile: 1.1322991371154785
30th percentile: 1.1362955093383789
40th percentile: 1.1380978584289552
50th percentile: 1.1399002075195312
60th percentile: 1.1433828353881836
70th percentile: 1.146865463256836
80th percentile: 1.2813645839691163
90th percentile: 1.5468801975250246
95th percentile: 1.6796380043029784
99th percentile: 1.7858442497253417
mean time: 1.2712430953979492
Pipeline stage StressChecker completed in 7.04s
invisietch-etherealrainb_9091_v1 status is now deployed due to DeploymentManager action
invisietch-etherealrainb_9091_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of invisietch-etherealrainb_9091_v1
Running pipeline stage ISVCDeleter
Checking if service invisietch-etherealrainb-9091-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.65s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key invisietch-etherealrainb-9091-v1/config.json from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key invisietch-etherealrainb-9091-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key invisietch-etherealrainb-9091-v1_reward/config.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key invisietch-etherealrainb-9091-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.39s
invisietch-etherealrainb_9091_v1 status is now torndown due to DeploymentManager action