developer_uid: clover0103
submission_id: deverdever-test-v1_v1
model_name: deverdever-test-v1_v1
model_group: DeverDever/test-v1
status: torndown
timestamp: 2024-06-05T13:18:48+00:00
num_battles: 25248
num_wins: 13294
celo_rating: 1190.24
family_friendly_score: 0.0
submission_type: basic
model_repo: DeverDever/test-v1
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: deverdever-test-v1_v1
is_internal_developer: False
language_model: DeverDever/test-v1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-05
win_ratio: 0.5265367553865653
generation_params: {'temperature': 1.0, '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}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name deverdever-test-v1-v1-mkmlizer
Waiting for job on deverdever-test-v1-v1-mkmlizer to finish
deverdever-test-v1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deverdever-test-v1-v1-mkmlizer: ║ _____ __ __ ║
deverdever-test-v1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
deverdever-test-v1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
deverdever-test-v1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
deverdever-test-v1-v1-mkmlizer: ║ /___/ ║
deverdever-test-v1-v1-mkmlizer: ║ ║
deverdever-test-v1-v1-mkmlizer: ║ Version: 0.8.14 ║
deverdever-test-v1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
deverdever-test-v1-v1-mkmlizer: ║ https://mk1.ai ║
deverdever-test-v1-v1-mkmlizer: ║ ║
deverdever-test-v1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
deverdever-test-v1-v1-mkmlizer: ║ belonging to: ║
deverdever-test-v1-v1-mkmlizer: ║ ║
deverdever-test-v1-v1-mkmlizer: ║ Chai Research Corp. ║
deverdever-test-v1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
deverdever-test-v1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
deverdever-test-v1-v1-mkmlizer: ║ ║
deverdever-test-v1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deverdever-test-v1-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.
deverdever-test-v1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
deverdever-test-v1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:01, 197.46it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 189.30it/s] Loading 0: 21%|██ | 61/291 [00:00<00:01, 186.18it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 180.49it/s] Loading 0: 34%|███▍ | 99/291 [00:00<00:02, 80.87it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 88.73it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 102.31it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 107.84it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 113.64it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 121.35it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 74.13it/s] Loading 0: 68%|██████▊ | 198/291 [00:01<00:01, 79.98it/s] Loading 0: 73%|███████▎ | 212/291 [00:02<00:00, 90.24it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 104.47it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 115.16it/s] Loading 0: 89%|████████▉ | 259/291 [00:02<00:00, 116.96it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 120.79it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 8.43it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
deverdever-test-v1-v1-mkmlizer: quantized model in 22.746s
deverdever-test-v1-v1-mkmlizer: Processed model DeverDever/test-v1 in 117.424s
deverdever-test-v1-v1-mkmlizer: creating bucket guanaco-mkml-models
deverdever-test-v1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deverdever-test-v1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deverdever-test-v1-v1
deverdever-test-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deverdever-test-v1-v1/tokenizer_config.json
deverdever-test-v1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deverdever-test-v1-v1/special_tokens_map.json
deverdever-test-v1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deverdever-test-v1-v1/config.json
deverdever-test-v1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deverdever-test-v1-v1/tokenizer.json
deverdever-test-v1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deverdever-test-v1-v1/flywheel_model.0.safetensors
deverdever-test-v1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
deverdever-test-v1-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.
deverdever-test-v1-v1-mkmlizer: warnings.warn(
deverdever-test-v1-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.
deverdever-test-v1-v1-mkmlizer: warnings.warn(
deverdever-test-v1-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.
deverdever-test-v1-v1-mkmlizer: warnings.warn(
deverdever-test-v1-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()
deverdever-test-v1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
deverdever-test-v1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
deverdever-test-v1-v1-mkmlizer: Saving duration: 0.217s
deverdever-test-v1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.375s
deverdever-test-v1-v1-mkmlizer: creating bucket guanaco-reward-models
deverdever-test-v1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
deverdever-test-v1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/deverdever-test-v1-v1_reward
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/deverdever-test-v1-v1_reward/special_tokens_map.json
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/deverdever-test-v1-v1_reward/config.json
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/deverdever-test-v1-v1_reward/tokenizer_config.json
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/deverdever-test-v1-v1_reward/merges.txt
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/deverdever-test-v1-v1_reward/vocab.json
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/deverdever-test-v1-v1_reward/tokenizer.json
deverdever-test-v1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/deverdever-test-v1-v1_reward/reward.tensors
Job deverdever-test-v1-v1-mkmlizer completed after 146.74s with status: succeeded
Stopping job with name deverdever-test-v1-v1-mkmlizer
Pipeline stage MKMLizer completed in 151.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service deverdever-test-v1-v1
Waiting for inference service deverdever-test-v1-v1 to be ready
Inference service deverdever-test-v1-v1 ready after 30.179500102996826s
Pipeline stage ISVCDeployer completed in 38.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.041545867919922s
Received healthy response to inference request in 0.9312646389007568s
Received healthy response to inference request in 1.2135207653045654s
Received healthy response to inference request in 1.2384822368621826s
Received healthy response to inference request in 1.2187268733978271s
5 requests
0 failed requests
5th percentile: 0.9877158641815186
10th percentile: 1.0441670894622803
20th percentile: 1.1570695400238038
30th percentile: 1.2145619869232178
40th percentile: 1.2166444301605224
50th percentile: 1.2187268733978271
60th percentile: 1.2266290187835693
70th percentile: 1.2345311641693115
80th percentile: 1.3990949630737306
90th percentile: 1.7203204154968263
95th percentile: 1.880933141708374
99th percentile: 2.009423322677612
mean time: 1.3287080764770507
Pipeline stage StressChecker completed in 7.38s
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
deverdever-test-v1_v1 status is now deployed due to DeploymentManager action
deverdever-test-v1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of deverdever-test-v1_v1
Running pipeline stage ISVCDeleter
Checking if service deverdever-test-v1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key deverdever-test-v1-v1/config.json from bucket guanaco-mkml-models
Deleting key deverdever-test-v1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key deverdever-test-v1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key deverdever-test-v1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key deverdever-test-v1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key deverdever-test-v1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key deverdever-test-v1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key deverdever-test-v1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key deverdever-test-v1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key deverdever-test-v1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key deverdever-test-v1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key deverdever-test-v1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.61s
deverdever-test-v1_v1 status is now torndown due to DeploymentManager action