submission_id: jeiku-chaos-rp-l3-8b_v1
developer_uid: jeiku
best_of: 4
celo_rating: 1156.88
display_name: jeiku-chaos-rp-l3-8b_v1
family_friendly_score: 0.0
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}
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': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: jeiku/Chaos_RP_l3_8B
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: jeiku/Chaos_RP_l3_8B
model_name: jeiku-chaos-rp-l3-8b_v1
model_num_parameters: 8030261248.0
model_repo: jeiku/Chaos_RP_l3_8B
model_size: 8B
num_battles: 7169
num_wins: 3627
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-04-23T02:36:21+00:00
us_pacific_date: 2024-04-22
win_ratio: 0.5059283024131678
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jeiku-chaos-rp-l3-8b-v1-mkmlizer
Waiting for job on jeiku-chaos-rp-l3-8b-v1-mkmlizer to finish
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ _____ __ __ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ /___/ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ Version: 0.8.10 ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ belonging to: ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ Chai Research Corp. ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ║ ║
jeiku-chaos-rp-l3-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jeiku-chaos-rp-l3-8b-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.
jeiku-chaos-rp-l3-8b-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Downloaded to shared memory in 16.074s
jeiku-chaos-rp-l3-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 64%|██████▍ | 187/291 [00:05<00:03, 31.32it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jeiku-chaos-rp-l3-8b-v1-mkmlizer: quantized model in 16.965s
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Processed model jeiku/Chaos_RP_l3_8B in 34.084s
jeiku-chaos-rp-l3-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jeiku-chaos-rp-l3-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jeiku-chaos-rp-l3-8b-v1
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jeiku-chaos-rp-l3-8b-v1/special_tokens_map.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jeiku-chaos-rp-l3-8b-v1/config.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jeiku-chaos-rp-l3-8b-v1/tokenizer_config.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jeiku-chaos-rp-l3-8b-v1/tokenizer.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jeiku-chaos-rp-l3-8b-v1/flywheel_model.0.safetensors
jeiku-chaos-rp-l3-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
jeiku-chaos-rp-l3-8b-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.
jeiku-chaos-rp-l3-8b-v1-mkmlizer: warnings.warn(
jeiku-chaos-rp-l3-8b-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.
jeiku-chaos-rp-l3-8b-v1-mkmlizer: warnings.warn(
jeiku-chaos-rp-l3-8b-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.
jeiku-chaos-rp-l3-8b-v1-mkmlizer: warnings.warn(
jeiku-chaos-rp-l3-8b-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()
jeiku-chaos-rp-l3-8b-v1-mkmlizer: return self.fget.__get__(instance, owner)()
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Saving duration: 0.229s
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.068s
jeiku-chaos-rp-l3-8b-v1-mkmlizer: creating bucket guanaco-reward-models
jeiku-chaos-rp-l3-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jeiku-chaos-rp-l3-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward/config.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward/special_tokens_map.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward/merges.txt
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward/tokenizer_config.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward/vocab.json
jeiku-chaos-rp-l3-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jeiku-chaos-rp-l3-8b-v1_reward/tokenizer.json
Job jeiku-chaos-rp-l3-8b-v1-mkmlizer completed after 64.06s with status: succeeded
Stopping job with name jeiku-chaos-rp-l3-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 68.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jeiku-chaos-rp-l3-8b-v1
Waiting for inference service jeiku-chaos-rp-l3-8b-v1 to be ready
Inference service jeiku-chaos-rp-l3-8b-v1 ready after 30.193508863449097s
Pipeline stage ISVCDeployer completed in 37.48s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9834144115447998s
Received healthy response to inference request in 1.125852346420288s
Received healthy response to inference request in 1.118520736694336s
Received healthy response to inference request in 1.317197561264038s
Received healthy response to inference request in 1.220292091369629s
5 requests
0 failed requests
5th percentile: 1.1199870586395264
10th percentile: 1.1214533805847169
20th percentile: 1.1243860244750976
30th percentile: 1.1447402954101562
40th percentile: 1.1825161933898927
50th percentile: 1.220292091369629
60th percentile: 1.2590542793273927
70th percentile: 1.2978164672851562
80th percentile: 1.4504409313201905
90th percentile: 1.7169276714324953
95th percentile: 1.8501710414886474
99th percentile: 1.9567657375335694
mean time: 1.3530554294586181
Pipeline stage StressChecker completed in 7.43s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.07s
jeiku-chaos-rp-l3-8b_v1 status is now deployed due to DeploymentManager action
jeiku-chaos-rp-l3-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jeiku-chaos-rp-l3-8b_v1
Running pipeline stage ISVCDeleter
Checking if service jeiku-chaos-rp-l3-8b-v1 is running
Tearing down inference service jeiku-chaos-rp-l3-8b-v1
Toredown service jeiku-chaos-rp-l3-8b-v1
Pipeline stage ISVCDeleter completed in 4.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jeiku-chaos-rp-l3-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key jeiku-chaos-rp-l3-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jeiku-chaos-rp-l3-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jeiku-chaos-rp-l3-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key jeiku-chaos-rp-l3-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jeiku-chaos-rp-l3-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.22s
jeiku-chaos-rp-l3-8b_v1 status is now torndown due to DeploymentManager action