trace2333-pippa-llama2-v0

developer_uid: Trace2333

submission_id: trace2333-pippa-llama2-v0_v3

model_name: trace2333-pippa-llama2-v0_v1

model_group: Trace2333/pippa_llama2_v

status: torndown

timestamp: 2024-06-12T08:44:57+00:00

num_battles: 15926

num_wins: 5802

celo_rating: 1088.76

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/pippa_llama2_v0

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 6738415616.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

display_name: trace2333-pippa-llama2-v0_v1

is_internal_developer: False

language_model: Trace2333/pippa_llama2_v0

model_size: 7B

ranking_group: single

us_pacific_date: 2024-06-12

win_ratio: 0.36430993344217005

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}", '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: {'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 trace2333-pippa-llama2-v0-v3-mkmlizer
Waiting for job on trace2333-pippa-llama2-v0-v3-mkmlizer to finish
trace2333-pippa-llama2-v0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-llama2-v0-v3-mkmlizer: ║     _____            __           __                                ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║       /___/                                                         ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  belonging to:                                                      ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ║                                                                     ║
trace2333-pippa-llama2-v0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-llama2-v0-v3-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.
trace2333-pippa-llama2-v0-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
trace2333-pippa-llama2-v0-v3-mkmlizer: Downloaded to shared memory in 33.537s
trace2333-pippa-llama2-v0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-llama2-v0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-llama2-v0-v3-mkmlizer: Processed model Trace2333/pippa_llama2_v0 in 47.879s
trace2333-pippa-llama2-v0-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-llama2-v0-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-llama2-v0-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3/config.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3/special_tokens_map.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3/tokenizer_config.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3/tokenizer.model
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3/tokenizer.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v3/flywheel_model.0.safetensors
trace2333-pippa-llama2-v0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-pippa-llama2-v0-v3-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.
trace2333-pippa-llama2-v0-v3-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-v3-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.
trace2333-pippa-llama2-v0-v3-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-v3-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.
trace2333-pippa-llama2-v0-v3-mkmlizer:   warnings.warn(
trace2333-pippa-llama2-v0-v3-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()
trace2333-pippa-llama2-v0-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-pippa-llama2-v0-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-llama2-v0-v3-mkmlizer: Saving duration: 0.311s
trace2333-pippa-llama2-v0-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.331s
trace2333-pippa-llama2-v0-v3-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-llama2-v0-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-llama2-v0-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/config.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/special_tokens_map.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/tokenizer_config.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/merges.txt
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/vocab.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/tokenizer.json
trace2333-pippa-llama2-v0-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v3_reward/reward.tensors
Job trace2333-pippa-llama2-v0-v3-mkmlizer completed after 76.31s with status: succeeded
Stopping job with name trace2333-pippa-llama2-v0-v3-mkmlizer
Pipeline stage MKMLizer completed in 76.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-llama2-v0-v3
Waiting for inference service trace2333-pippa-llama2-v0-v3 to be ready
Inference service trace2333-pippa-llama2-v0-v3 ready after 120.60854077339172s
Pipeline stage ISVCDeployer completed in 126.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.990891695022583s
Received healthy response to inference request in 1.08241868019104s
Received healthy response to inference request in 1.0759217739105225s
Received healthy response to inference request in 1.1137614250183105s
Received healthy response to inference request in 1.0995392799377441s
5 requests
0 failed requests
5th percentile: 1.077221155166626
10th percentile: 1.0785205364227295
20th percentile: 1.0811192989349365
30th percentile: 1.0858428001403808
40th percentile: 1.0926910400390626
50th percentile: 1.0995392799377441
60th percentile: 1.1052281379699707
70th percentile: 1.1109169960021972
80th percentile: 1.2891874790191653
90th percentile: 1.6400395870208742
95th percentile: 1.8154656410217282
99th percentile: 1.955806484222412
mean time: 1.2725065708160401
Pipeline stage StressChecker completed in 8.02s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
trace2333-pippa-llama2-v0_v3 status is now deployed due to DeploymentManager action
trace2333-pippa-llama2-v0_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-pippa-llama2-v0_v3
Running pipeline stage ISVCDeleter
Checking if service trace2333-pippa-llama2-v0-v3 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 trace2333-pippa-llama2-v0-v3/config.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v3/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-pippa-llama2-v0-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-pippa-llama2-v0-v3_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-pippa-llama2-v0-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.55s
trace2333-pippa-llama2-v0_v3 status is now torndown due to DeploymentManager action