resplendentai-nymph-8b

submission_id: resplendentai-nymph-8b_v3

developer_uid: Azazelle

best_of: 16

celo_rating: 1168.31

display_name: resplendentai-nymph-8b

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': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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: ResplendentAI/Nymph_8B

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: ResplendentAI/Nymph_8B

model_name: resplendentai-nymph-8b

model_num_parameters: 8030261248.0

model_repo: ResplendentAI/Nymph_8B

model_size: 8B

num_battles: 30974

num_wins: 14805

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: 2024-07-06T01:03:48+00:00

us_pacific_date: 2024-07-05

win_ratio: 0.4779815328985601

Resubmit model

Running pipeline stage MKMLizer
Starting job with name resplendentai-nymph-8b-v3-mkmlizer
Waiting for job on resplendentai-nymph-8b-v3-mkmlizer to finish
resplendentai-nymph-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
resplendentai-nymph-8b-v3-mkmlizer: ║     _____            __           __                                ║
resplendentai-nymph-8b-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
resplendentai-nymph-8b-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
resplendentai-nymph-8b-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
resplendentai-nymph-8b-v3-mkmlizer: ║       /___/                                                         ║
resplendentai-nymph-8b-v3-mkmlizer: ║                                                                     ║
resplendentai-nymph-8b-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
resplendentai-nymph-8b-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
resplendentai-nymph-8b-v3-mkmlizer: ║  https://mk1.ai                                                     ║
resplendentai-nymph-8b-v3-mkmlizer: ║                                                                     ║
resplendentai-nymph-8b-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
resplendentai-nymph-8b-v3-mkmlizer: ║  belonging to:                                                      ║
resplendentai-nymph-8b-v3-mkmlizer: ║                                                                     ║
resplendentai-nymph-8b-v3-mkmlizer: ║  Chai Research Corp.                                                ║
resplendentai-nymph-8b-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
resplendentai-nymph-8b-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
resplendentai-nymph-8b-v3-mkmlizer: ║                                                                     ║
resplendentai-nymph-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
resplendentai-nymph-8b-v3-mkmlizer: Downloaded to shared memory in 22.018s
resplendentai-nymph-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
resplendentai-nymph-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
resplendentai-nymph-8b-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<12:02,  2.50s/it]
Loading 0:   4%|▍         | 13/291 [00:05<01:21,  3.43it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:35,  7.43it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:16, 15.18it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:11, 21.41it/s]
Loading 0:  21%|██▏       | 62/291 [00:05<00:09, 23.63it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 34.04it/s]
Loading 0:  30%|██▉       | 87/291 [00:06<00:04, 41.91it/s]
Loading 0:  35%|███▌      | 103/291 [00:06<00:03, 57.42it/s]
Loading 0:  39%|███▉      | 114/291 [00:06<00:02, 64.39it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:02, 80.49it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 85.51it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 97.60it/s]
Loading 0:  58%|█████▊    | 169/291 [00:06<00:01, 63.70it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 77.68it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 81.92it/s]
Loading 0:  73%|███████▎  | 211/291 [00:07<00:00, 97.11it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 99.14it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 109.57it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 109.82it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 115.88it/s]
Loading 0:  96%|█████████▌| 278/291 [00:08<00:00, 71.73it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
resplendentai-nymph-8b-v3-mkmlizer: quantized model in 25.288s
resplendentai-nymph-8b-v3-mkmlizer: Processed model ResplendentAI/Nymph_8B in 47.306s
resplendentai-nymph-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/resplendentai-nymph-8b-v3/tokenizer.json
resplendentai-nymph-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/resplendentai-nymph-8b-v3/flywheel_model.0.safetensors
resplendentai-nymph-8b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
resplendentai-nymph-8b-v3-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.
resplendentai-nymph-8b-v3-mkmlizer:   warnings.warn(
resplendentai-nymph-8b-v3-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`.
resplendentai-nymph-8b-v3-mkmlizer:   warnings.warn(
resplendentai-nymph-8b-v3-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.
resplendentai-nymph-8b-v3-mkmlizer:   warnings.warn(
resplendentai-nymph-8b-v3-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.
resplendentai-nymph-8b-v3-mkmlizer:   warnings.warn(
resplendentai-nymph-8b-v3-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()
resplendentai-nymph-8b-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
resplendentai-nymph-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
resplendentai-nymph-8b-v3-mkmlizer: Saving duration: 0.516s
resplendentai-nymph-8b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.650s
resplendentai-nymph-8b-v3-mkmlizer: creating bucket guanaco-reward-models
resplendentai-nymph-8b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
resplendentai-nymph-8b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/special_tokens_map.json
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/config.json
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/tokenizer_config.json
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/merges.txt
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/vocab.json
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/tokenizer.json
resplendentai-nymph-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/resplendentai-nymph-8b-v3_reward/reward.tensors
Job resplendentai-nymph-8b-v3-mkmlizer completed after 74.82s with status: succeeded
Stopping job with name resplendentai-nymph-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 75.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service resplendentai-nymph-8b-v3
Waiting for inference service resplendentai-nymph-8b-v3 to be ready
Inference service resplendentai-nymph-8b-v3 ready after 90.3714907169342s
Pipeline stage ISVCDeployer completed in 97.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0436851978302s
Received healthy response to inference request in 1.2863481044769287s
Received healthy response to inference request in 1.2839274406433105s
Received healthy response to inference request in 1.2695338726043701s
Received healthy response to inference request in 1.3054943084716797s
5 requests
0 failed requests
5th percentile: 1.2724125862121582
10th percentile: 1.2752912998199464
20th percentile: 1.2810487270355224
30th percentile: 1.284411573410034
40th percentile: 1.2853798389434814
50th percentile: 1.2863481044769287
60th percentile: 1.294006586074829
70th percentile: 1.3016650676727295
80th percentile: 1.4531324863433839
90th percentile: 1.748408842086792
95th percentile: 1.896047019958496
99th percentile: 2.014157562255859
mean time: 1.4377977848052979
Pipeline stage StressChecker completed in 8.16s
resplendentai-nymph-8b_v3 status is now deployed due to DeploymentManager action
resplendentai-nymph-8b_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of resplendentai-nymph-8b_v3
Running pipeline stage ISVCDeleter
Checking if service resplendentai-nymph-8b-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.97s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key resplendentai-nymph-8b-v3/config.json from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key resplendentai-nymph-8b-v3_reward/config.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
resplendentai-nymph-8b_v3 status is now torndown due to DeploymentManager action