submission_id: yuyuclimb-yxyllama2-v2-1_v1
developer_uid: yuyuclimb
status: torndown
model_repo: yuyuclimb/yxyllama2-v2.1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': 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: 2024-05-13T02:27:18+00:00
model_name: yxyllama2-v2-1
model_eval_status: success
model_group: yuyuclimb/yxyllama2-v2.1
num_battles: 21617
num_wins: 9610
celo_rating: 1132.79
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: yxyllama2-v2-1
ineligible_reason: propriety_total_count < 800
language_model: yuyuclimb/yxyllama2-v2.1
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-12
win_ratio: 0.44455752417079153
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name yuyuclimb-yxyllama2-v2-1-v1-mkmlizer
Waiting for job on yuyuclimb-yxyllama2-v2-1-v1-mkmlizer to finish
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ _____ __ __ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ /___/ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ Version: 0.8.10 ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ belonging to: ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ Chai Research Corp. ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yuyuclimb-yxyllama2-v2-1-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.
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Downloaded to shared memory in 21.177s
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:02, 92.30it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 90.40it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: quantized model in 10.351s
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Processed model yuyuclimb/yxyllama2-v2.1 in 32.433s
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: creating bucket guanaco-mkml-models
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1/special_tokens_map.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1/config.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1/tokenizer.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1/tokenizer.model
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1/tokenizer_config.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v2-1-v1/flywheel_model.0.safetensors
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
yuyuclimb-yxyllama2-v2-1-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.
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-v2-1-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.
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-v2-1-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()
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Saving duration: 0.245s
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.620s
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: creating bucket guanaco-reward-models
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/config.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/tokenizer_config.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/special_tokens_map.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/vocab.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/merges.txt
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/tokenizer.json
yuyuclimb-yxyllama2-v2-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/yuyuclimb-yxyllama2-v2-1-v1_reward/reward.tensors
Job yuyuclimb-yxyllama2-v2-1-v1-mkmlizer completed after 52.53s with status: succeeded
Stopping job with name yuyuclimb-yxyllama2-v2-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 56.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service yuyuclimb-yxyllama2-v2-1-v1
Waiting for inference service yuyuclimb-yxyllama2-v2-1-v1 to be ready
Inference service yuyuclimb-yxyllama2-v2-1-v1 ready after 40.235507011413574s
Pipeline stage ISVCDeployer completed in 47.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.019160747528076s
Received healthy response to inference request in 1.15785813331604s
Received healthy response to inference request in 1.3241207599639893s
Received healthy response to inference request in 1.1218326091766357s
Received healthy response to inference request in 1.2230794429779053s
5 requests
0 failed requests
5th percentile: 1.1290377140045167
10th percentile: 1.1362428188323974
20th percentile: 1.150653028488159
30th percentile: 1.170902395248413
40th percentile: 1.1969909191131591
50th percentile: 1.2230794429779053
60th percentile: 1.263495969772339
70th percentile: 1.3039124965667725
80th percentile: 1.4631287574768068
90th percentile: 1.7411447525024415
95th percentile: 1.8801527500152586
99th percentile: 1.9913591480255126
mean time: 1.3692103385925294
Pipeline stage StressChecker completed in 8.38s
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
yuyuclimb-yxyllama2-v2-1_v1 status is now deployed due to DeploymentManager action
yuyuclimb-yxyllama2-v2-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of yuyuclimb-yxyllama2-v2-1_v1
Running pipeline stage ISVCDeleter
Checking if service yuyuclimb-yxyllama2-v2-1-v1 is running
Tearing down inference service yuyuclimb-yxyllama2-v2-1-v1
Toredown service yuyuclimb-yxyllama2-v2-1-v1
Pipeline stage ISVCDeleter completed in 3.65s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key yuyuclimb-yxyllama2-v2-1-v1/config.json from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v2-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.83s
yuyuclimb-yxyllama2-v2-1_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics