submission_id: cycy233-llm2-0_v4
developer_uid: shiroe40
status: inactive
model_repo: cycy233/llm2.0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, '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': '"###system:\n{memory}\n"', 'prompt_template': '"### Input:\n# history:{prompt}\n#speaker:{bot_name}\n# Actual conversation:\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: 2024-05-07T16:13:02+00:00
model_name: rolej
model_eval_status: success
double_thumbs_up: 224
thumbs_up: 346
thumbs_down: 259
num_battles: 23248
num_wins: 10633
celo_rating: 1134.63
entertaining: 6.7
stay_in_character: 7.96
user_preference: 7.2
safety_score: 0.82
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rolej
double_thumbs_up_ratio: 0.27020506634499397
feedback_count: 829
ineligible_reason: None
language_model: cycy233/llm2.0
model_score: 7.286666666666666
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.41737032569360677
thumbs_down_ratio: 0.31242460796139926
thumbs_up_ratio: 0.6875753920386007
us_pacific_date: 2024-05-07
win_ratio: 0.4573726772195458
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-llm2-0-v4-mkmlizer
Waiting for job on cycy233-llm2-0-v4-mkmlizer to finish
cycy233-llm2-0-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm2-0-v4-mkmlizer: ║ _____ __ __ ║
cycy233-llm2-0-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-llm2-0-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-llm2-0-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-llm2-0-v4-mkmlizer: ║ /___/ ║
cycy233-llm2-0-v4-mkmlizer: ║ ║
cycy233-llm2-0-v4-mkmlizer: ║ Version: 0.8.10 ║
cycy233-llm2-0-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-llm2-0-v4-mkmlizer: ║ ║
cycy233-llm2-0-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-llm2-0-v4-mkmlizer: ║ belonging to: ║
cycy233-llm2-0-v4-mkmlizer: ║ ║
cycy233-llm2-0-v4-mkmlizer: ║ Chai Research Corp. ║
cycy233-llm2-0-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-llm2-0-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-llm2-0-v4-mkmlizer: ║ ║
cycy233-llm2-0-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm2-0-v4-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.
cycy233-llm2-0-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-llm2-0-v4-mkmlizer: Downloaded to shared memory in 13.955s
cycy233-llm2-0-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm2-0-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm2-0-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:02, 88.50it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 85.89it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm2-0-v4-mkmlizer: quantized model in 10.961s
cycy233-llm2-0-v4-mkmlizer: Processed model cycy233/llm2.0 in 25.919s
cycy233-llm2-0-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm2-0-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm2-0-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm2-0-v4
cycy233-llm2-0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm2-0-v4/tokenizer.model
cycy233-llm2-0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm2-0-v4/tokenizer_config.json
cycy233-llm2-0-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm2-0-v4/special_tokens_map.json
cycy233-llm2-0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm2-0-v4/tokenizer.json
cycy233-llm2-0-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm2-0-v4/config.json
cycy233-llm2-0-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm2-0-v4/flywheel_model.0.safetensors
cycy233-llm2-0-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm2-0-v4-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.
cycy233-llm2-0-v4-mkmlizer: warnings.warn(
cycy233-llm2-0-v4-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.
cycy233-llm2-0-v4-mkmlizer: warnings.warn(
cycy233-llm2-0-v4-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.
cycy233-llm2-0-v4-mkmlizer: warnings.warn(
cycy233-llm2-0-v4-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()
cycy233-llm2-0-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-llm2-0-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm2-0-v4-mkmlizer: Saving duration: 0.240s
cycy233-llm2-0-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.179s
cycy233-llm2-0-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm2-0-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm2-0-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm2-0-v4_reward
cycy233-llm2-0-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm2-0-v4_reward/special_tokens_map.json
cycy233-llm2-0-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm2-0-v4_reward/tokenizer_config.json
cycy233-llm2-0-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm2-0-v4_reward/vocab.json
cycy233-llm2-0-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm2-0-v4_reward/merges.txt
cycy233-llm2-0-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm2-0-v4_reward/tokenizer.json
cycy233-llm2-0-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm2-0-v4_reward/reward.tensors
Job cycy233-llm2-0-v4-mkmlizer completed after 180.45s with status: succeeded
Stopping job with name cycy233-llm2-0-v4-mkmlizer
Pipeline stage MKMLizer completed in 185.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm2-0-v4
Waiting for inference service cycy233-llm2-0-v4 to be ready
Inference service cycy233-llm2-0-v4 ready after 131.02944159507751s
Pipeline stage ISVCDeployer completed in 138.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.147149085998535s
Received healthy response to inference request in 1.1749513149261475s
Received healthy response to inference request in 1.2322123050689697s
Received healthy response to inference request in 1.1827104091644287s
Received healthy response to inference request in 1.206329107284546s
5 requests
0 failed requests
5th percentile: 1.1765031337738037
10th percentile: 1.1780549526214599
20th percentile: 1.1811585903167725
30th percentile: 1.187434148788452
40th percentile: 1.1968816280364991
50th percentile: 1.206329107284546
60th percentile: 1.2166823863983154
70th percentile: 1.2270356655120849
80th percentile: 1.415199661254883
90th percentile: 1.7811743736267092
95th percentile: 1.964161729812622
99th percentile: 2.1105516147613526
mean time: 1.3886704444885254
Pipeline stage StressChecker completed in 7.60s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
cycy233-llm2-0_v4 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-llm2-0_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics