submission_id: resplendentai-nymph-8b_v1
developer_uid: Azazelle
best_of: 16
celo_rating: 1192.31
display_name: resplendentai-nymph-8b_v1
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_v1
model_num_parameters: 8030261248.0
model_repo: ResplendentAI/Nymph_8B
model_size: 8B
num_battles: 31161
num_wins: 15988
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: 2024-07-05T23:55:06+00:00
us_pacific_date: 2024-07-05
win_ratio: 0.5130772439908861
Resubmit model
Running pipeline stage MKMLizer
Starting job with name resplendentai-nymph-8b-v1-mkmlizer
Waiting for job on resplendentai-nymph-8b-v1-mkmlizer to finish
resplendentai-nymph-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
resplendentai-nymph-8b-v1-mkmlizer: ║ _____ __ __ ║
resplendentai-nymph-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
resplendentai-nymph-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
resplendentai-nymph-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
resplendentai-nymph-8b-v1-mkmlizer: ║ /___/ ║
resplendentai-nymph-8b-v1-mkmlizer: ║ ║
resplendentai-nymph-8b-v1-mkmlizer: ║ Version: 0.8.14 ║
resplendentai-nymph-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
resplendentai-nymph-8b-v1-mkmlizer: ║ https://mk1.ai ║
resplendentai-nymph-8b-v1-mkmlizer: ║ ║
resplendentai-nymph-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
resplendentai-nymph-8b-v1-mkmlizer: ║ belonging to: ║
resplendentai-nymph-8b-v1-mkmlizer: ║ ║
resplendentai-nymph-8b-v1-mkmlizer: ║ Chai Research Corp. ║
resplendentai-nymph-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
resplendentai-nymph-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
resplendentai-nymph-8b-v1-mkmlizer: ║ ║
resplendentai-nymph-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
resplendentai-nymph-8b-v1-mkmlizer: Downloaded to shared memory in 33.888s
resplendentai-nymph-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
resplendentai-nymph-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
resplendentai-nymph-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:16, 2.34s/it] Loading 0: 4%|▍ | 13/291 [00:04<01:16, 3.66it/s] Loading 0: 8%|▊ | 23/291 [00:04<00:35, 7.54it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:20, 12.57it/s] Loading 0: 17%|█▋ | 49/291 [00:05<00:10, 22.92it/s] Loading 0: 21%|██ | 60/291 [00:05<00:09, 23.90it/s] Loading 0: 25%|██▌ | 73/291 [00:05<00:06, 33.70it/s] Loading 0: 29%|██▉ | 85/291 [00:05<00:04, 43.27it/s] Loading 0: 33%|███▎ | 95/291 [00:05<00:03, 50.94it/s] Loading 0: 36%|███▌ | 105/291 [00:05<00:03, 58.35it/s] Loading 0: 42%|████▏ | 121/291 [00:06<00:02, 76.05it/s] Loading 0: 46%|████▌ | 133/291 [00:06<00:01, 82.33it/s] Loading 0: 50%|████▉ | 145/291 [00:06<00:01, 90.58it/s] Loading 0: 54%|█████▍ | 157/291 [00:06<00:01, 96.00it/s] Loading 0: 58%|█████▊ | 169/291 [00:06<00:02, 58.14it/s] Loading 0: 62%|██████▏ | 181/291 [00:06<00:01, 68.71it/s] Loading 0: 66%|██████▋ | 193/291 [00:07<00:01, 78.09it/s] Loading 0: 70%|███████ | 204/291 [00:07<00:01, 80.02it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 94.09it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:00, 91.87it/s] Loading 0: 85%|████████▍ | 247/291 [00:07<00:00, 105.33it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 102.61it/s] Loading 0: 93%|█████████▎| 270/291 [00:07<00:00, 65.45it/s] Loading 0: 97%|█████████▋| 283/291 [00:08<00:00, 76.66it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
resplendentai-nymph-8b-v1-mkmlizer: quantized model in 24.767s
resplendentai-nymph-8b-v1-mkmlizer: Processed model ResplendentAI/Nymph_8B in 58.656s
resplendentai-nymph-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
resplendentai-nymph-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
resplendentai-nymph-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/resplendentai-nymph-8b-v1
resplendentai-nymph-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/resplendentai-nymph-8b-v1/tokenizer.json
resplendentai-nymph-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/resplendentai-nymph-8b-v1/config.json
resplendentai-nymph-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/resplendentai-nymph-8b-v1/tokenizer_config.json
resplendentai-nymph-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/resplendentai-nymph-8b-v1/special_tokens_map.json
resplendentai-nymph-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/resplendentai-nymph-8b-v1/flywheel_model.0.safetensors
resplendentai-nymph-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
resplendentai-nymph-8b-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.
resplendentai-nymph-8b-v1-mkmlizer: warnings.warn(
resplendentai-nymph-8b-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`.
resplendentai-nymph-8b-v1-mkmlizer: warnings.warn(
resplendentai-nymph-8b-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.
resplendentai-nymph-8b-v1-mkmlizer: warnings.warn(
resplendentai-nymph-8b-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.
resplendentai-nymph-8b-v1-mkmlizer: warnings.warn(
resplendentai-nymph-8b-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()
resplendentai-nymph-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
resplendentai-nymph-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
resplendentai-nymph-8b-v1-mkmlizer: Saving duration: 0.385s
resplendentai-nymph-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.370s
resplendentai-nymph-8b-v1-mkmlizer: creating bucket guanaco-reward-models
resplendentai-nymph-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
resplendentai-nymph-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/config.json
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/tokenizer_config.json
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/merges.txt
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/special_tokens_map.json
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/vocab.json
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/tokenizer.json
resplendentai-nymph-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/resplendentai-nymph-8b-v1_reward/reward.tensors
Job resplendentai-nymph-8b-v1-mkmlizer completed after 93.77s with status: succeeded
Stopping job with name resplendentai-nymph-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service resplendentai-nymph-8b-v1
Waiting for inference service resplendentai-nymph-8b-v1 to be ready
Inference service resplendentai-nymph-8b-v1 ready after 40.31824254989624s
Pipeline stage ISVCDeployer completed in 47.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0471787452697754s
Received healthy response to inference request in 1.3035364151000977s
Received healthy response to inference request in 1.2886216640472412s
Received healthy response to inference request in 1.219871997833252s
Received healthy response to inference request in 1.2996337413787842s
5 requests
0 failed requests
5th percentile: 1.23362193107605
10th percentile: 1.2473718643188476
20th percentile: 1.2748717308044433
30th percentile: 1.2908240795135497
40th percentile: 1.295228910446167
50th percentile: 1.2996337413787842
60th percentile: 1.3011948108673095
70th percentile: 1.302755880355835
80th percentile: 1.4522648811340333
90th percentile: 1.7497218132019043
95th percentile: 1.8984502792358398
99th percentile: 2.017433052062988
mean time: 1.4317685127258302
Pipeline stage StressChecker completed in 7.87s
resplendentai-nymph-8b_v1 status is now deployed due to DeploymentManager action
resplendentai-nymph-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of resplendentai-nymph-8b_v1
Running pipeline stage ISVCDeleter
Checking if service resplendentai-nymph-8b-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.30s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key resplendentai-nymph-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key resplendentai-nymph-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key resplendentai-nymph-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key resplendentai-nymph-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.51s
resplendentai-nymph-8b_v1 status is now torndown due to DeploymentManager action