submission_id: yuyuclimb-yxyllama2-v1-3_v2
developer_uid: yuyuclimb
status: torndown
model_repo: yuyuclimb/yxyllama2-v1.3
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: 2024-05-11T03:28:44+00:00
model_name: yxyllama2-v1-3
model_eval_status: success
model_group: yuyuclimb/yxyllama2-v1.3
num_battles: 12193
num_wins: 5550
celo_rating: 1135.18
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-v1-3
ineligible_reason: propriety_total_count < 800
language_model: yuyuclimb/yxyllama2-v1.3
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-10
win_ratio: 0.4551792011810055
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name yuyuclimb-yxyllama2-v1-3-v2-mkmlizer
Waiting for job on yuyuclimb-yxyllama2-v1-3-v2-mkmlizer to finish
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ _____ __ __ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ /___/ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ Version: 0.8.10 ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ belonging to: ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ Chai Research Corp. ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ║ ║
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yuyuclimb-yxyllama2-v1-3-v2-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-v1-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Downloaded to shared memory in 15.218s
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:01, 95.27it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 94.52it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: quantized model in 10.891s
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Processed model yuyuclimb/yxyllama2-v1.3 in 27.110s
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1-3-v2/tokenizer.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1-3-v2/tokenizer_config.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1-3-v2/config.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yuyuclimb-yxyllama2-v1-3-v2/flywheel_model.0.safetensors
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
yuyuclimb-yxyllama2-v1-3-v2-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-v1-3-v2-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-v1-3-v2-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-v1-3-v2-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-v1-3-v2-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.
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: warnings.warn(
yuyuclimb-yxyllama2-v1-3-v2-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-v1-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Saving duration: 0.231s
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.619s
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: creating bucket guanaco-reward-models
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/special_tokens_map.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/config.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/vocab.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/tokenizer_config.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/merges.txt
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/tokenizer.json
yuyuclimb-yxyllama2-v1-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/yuyuclimb-yxyllama2-v1-3-v2_reward/reward.tensors
Job yuyuclimb-yxyllama2-v1-3-v2-mkmlizer completed after 52.97s with status: succeeded
Stopping job with name yuyuclimb-yxyllama2-v1-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 57.47s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service yuyuclimb-yxyllama2-v1-3-v2
Waiting for inference service yuyuclimb-yxyllama2-v1-3-v2 to be ready
Inference service yuyuclimb-yxyllama2-v1-3-v2 ready after 30.207173109054565s
Pipeline stage ISVCDeployer completed in 38.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7141072750091553s
Received healthy response to inference request in 1.1436495780944824s
Received healthy response to inference request in 1.1473939418792725s
Received healthy response to inference request in 1.1551361083984375s
Received healthy response to inference request in 1.1320216655731201s
5 requests
0 failed requests
5th percentile: 1.1343472480773926
10th percentile: 1.1366728305816651
20th percentile: 1.14132399559021
30th percentile: 1.1443984508514404
40th percentile: 1.1458961963653564
50th percentile: 1.1473939418792725
60th percentile: 1.1504908084869385
70th percentile: 1.1535876750946046
80th percentile: 1.266930341720581
90th percentile: 1.4905188083648682
95th percentile: 1.6023130416870117
99th percentile: 1.6917484283447266
mean time: 1.2584617137908936
Pipeline stage StressChecker completed in 6.95s
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
yuyuclimb-yxyllama2-v1-3_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
yuyuclimb-yxyllama2-v1-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of yuyuclimb-yxyllama2-v1-3_v2
Running pipeline stage ISVCDeleter
Checking if service yuyuclimb-yxyllama2-v1-3-v2 is running
Tearing down inference service yuyuclimb-yxyllama2-v1-3-v2
Toredown service yuyuclimb-yxyllama2-v1-3-v2
Pipeline stage ISVCDeleter completed in 3.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key yuyuclimb-yxyllama2-v1-3-v2/config.json from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key yuyuclimb-yxyllama2-v1-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.84s
yuyuclimb-yxyllama2-v1-3_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics