submission_id: chaoticneutrals-puppy-pu_2579_v1
developer_uid: jeiku
status: torndown
model_repo: ChaoticNeutrals/Puppy_Purpose_0.69
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.2, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|im_end|>'], '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': False}
reward_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': False}
timestamp: 2024-05-13T01:37:19+00:00
model_name: chaoticneutrals-puppy-pu_2579_v1
model_eval_status: success
model_group: ChaoticNeutrals/Puppy_Pu
num_battles: 22026
num_wins: 11320
celo_rating: 1177.59
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: chaoticneutrals-puppy-pu_2579_v1
ineligible_reason: propriety_total_count < 800
language_model: ChaoticNeutrals/Puppy_Purpose_0.69
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-12
win_ratio: 0.5139380731862344
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaoticneutrals-puppy-pu-2579-v1-mkmlizer
Waiting for job on chaoticneutrals-puppy-pu-2579-v1-mkmlizer to finish
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ _____ __ __ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ /___/ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ Version: 0.8.10 ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ belonging to: ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ Chai Research Corp. ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ║ ║
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaoticneutrals-puppy-pu-2579-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.
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Downloaded to shared memory in 25.010s
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: quantizing model to /dev/shm/model_cache
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 49%|████▉ | 143/291 [00:00<00:01, 143.03it/s] Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 22.53it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: quantized model in 19.354s
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Processed model ChaoticNeutrals/Puppy_Purpose_0.69 in 45.597s
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: creating bucket guanaco-mkml-models
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaoticneutrals-puppy-pu-2579-v1
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaoticneutrals-puppy-pu-2579-v1/special_tokens_map.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaoticneutrals-puppy-pu-2579-v1/tokenizer_config.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaoticneutrals-puppy-pu-2579-v1/config.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaoticneutrals-puppy-pu-2579-v1/tokenizer.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaoticneutrals-puppy-pu-2579-v1/flywheel_model.0.safetensors
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaoticneutrals-puppy-pu-2579-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.
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: warnings.warn(
chaoticneutrals-puppy-pu-2579-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.
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: warnings.warn(
chaoticneutrals-puppy-pu-2579-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.
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: warnings.warn(
chaoticneutrals-puppy-pu-2579-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()
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: return self.fget.__get__(instance, owner)()
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Saving duration: 0.252s
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.091s
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: creating bucket guanaco-reward-models
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/config.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/special_tokens_map.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/tokenizer_config.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/merges.txt
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/vocab.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/tokenizer.json
chaoticneutrals-puppy-pu-2579-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaoticneutrals-puppy-pu-2579-v1_reward/reward.tensors
Job chaoticneutrals-puppy-pu-2579-v1-mkmlizer completed after 72.79s with status: succeeded
Stopping job with name chaoticneutrals-puppy-pu-2579-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaoticneutrals-puppy-pu-2579-v1
Waiting for inference service chaoticneutrals-puppy-pu-2579-v1 to be ready
Inference service chaoticneutrals-puppy-pu-2579-v1 ready after 30.17758274078369s
Pipeline stage ISVCDeployer completed in 37.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.071673631668091s
Received healthy response to inference request in 1.2545299530029297s
Received healthy response to inference request in 1.2408666610717773s
Received healthy response to inference request in 1.2336347103118896s
Received healthy response to inference request in 1.2460715770721436s
5 requests
0 failed requests
5th percentile: 1.235081100463867
10th percentile: 1.2365274906158448
20th percentile: 1.2394202709198
30th percentile: 1.2419076442718506
40th percentile: 1.243989610671997
50th percentile: 1.2460715770721436
60th percentile: 1.249454927444458
70th percentile: 1.2528382778167724
80th percentile: 1.417958688735962
90th percentile: 1.7448161602020265
95th percentile: 1.9082448959350584
99th percentile: 2.038987884521484
mean time: 1.4093553066253661
Pipeline stage StressChecker completed in 7.89s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
chaoticneutrals-puppy-pu_2579_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
chaoticneutrals-puppy-pu_2579_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaoticneutrals-puppy-pu_2579_v1
Running pipeline stage ISVCDeleter
Checking if service chaoticneutrals-puppy-pu-2579-v1 is running
Tearing down inference service chaoticneutrals-puppy-pu-2579-v1
Toredown service chaoticneutrals-puppy-pu-2579-v1
Pipeline stage ISVCDeleter completed in 3.29s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaoticneutrals-puppy-pu-2579-v1/config.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-puppy-pu-2579-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaoticneutrals-puppy-pu-2579-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-puppy-pu-2579-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-puppy-pu-2579-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-puppy-pu-2579-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.91s
chaoticneutrals-puppy-pu_2579_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics