submission_id: cycy233-llm2-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/llm2.0
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': 'system: {memory}\n####\n', 'prompt_template': '"### Input:\n# input:\n{prompt}\n# speaker:{bot_name}', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '"### output:\n{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: 2024-05-07T11:19:45+00:00
model_name: rolei
model_eval_status: success
double_thumbs_up: 227
thumbs_up: 323
thumbs_down: 257
num_battles: 22591
num_wins: 8755
celo_rating: 1079.06
entertaining: 6.88
stay_in_character: 7.67
user_preference: 6.82
safety_score: 0.84
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rolei
double_thumbs_up_ratio: 0.2812887236679058
feedback_count: 807
ineligible_reason: None
language_model: cycy233/llm2.0
model_score: 7.123333333333334
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.40024783147459725
thumbs_down_ratio: 0.3184634448574969
thumbs_up_ratio: 0.6815365551425031
us_pacific_date: 2024-05-07
win_ratio: 0.387543712097738
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-llm2-0-v1-mkmlizer
Waiting for job on cycy233-llm2-0-v1-mkmlizer to finish
cycy233-llm2-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm2-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-llm2-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-llm2-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-llm2-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-llm2-0-v1-mkmlizer: ║ /___/ ║
cycy233-llm2-0-v1-mkmlizer: ║ ║
cycy233-llm2-0-v1-mkmlizer: ║ Version: 0.8.10 ║
cycy233-llm2-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-llm2-0-v1-mkmlizer: ║ ║
cycy233-llm2-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-llm2-0-v1-mkmlizer: ║ belonging to: ║
cycy233-llm2-0-v1-mkmlizer: ║ ║
cycy233-llm2-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-llm2-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-llm2-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-llm2-0-v1-mkmlizer: ║ ║
cycy233-llm2-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm2-0-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.
cycy233-llm2-0-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-llm2-0-v1-mkmlizer: Downloaded to shared memory in 28.049s
cycy233-llm2-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm2-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm2-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:01, 99.10it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 91.89it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm2-0-v1-mkmlizer: quantized model in 11.475s
cycy233-llm2-0-v1-mkmlizer: Processed model cycy233/llm2.0 in 40.431s
cycy233-llm2-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm2-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm2-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm2-0-v1
cycy233-llm2-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm2-0-v1/config.json
cycy233-llm2-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm2-0-v1/special_tokens_map.json
cycy233-llm2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm2-0-v1/tokenizer_config.json
cycy233-llm2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm2-0-v1/tokenizer.model
cycy233-llm2-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm2-0-v1/tokenizer.json
cycy233-llm2-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-llm2-0-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.
cycy233-llm2-0-v1-mkmlizer: warnings.warn(
cycy233-llm2-0-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.
cycy233-llm2-0-v1-mkmlizer: warnings.warn(
cycy233-llm2-0-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.
cycy233-llm2-0-v1-mkmlizer: warnings.warn(
cycy233-llm2-0-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()
cycy233-llm2-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-llm2-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm2-0-v1-mkmlizer: Saving duration: 0.300s
cycy233-llm2-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.506s
cycy233-llm2-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm2-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm2-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm2-0-v1_reward
cycy233-llm2-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm2-0-v1_reward/config.json
cycy233-llm2-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm2-0-v1_reward/special_tokens_map.json
cycy233-llm2-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm2-0-v1_reward/tokenizer_config.json
cycy233-llm2-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm2-0-v1_reward/merges.txt
cycy233-llm2-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm2-0-v1_reward/reward.tensors
Job cycy233-llm2-0-v1-mkmlizer completed after 114.69s with status: succeeded
Stopping job with name cycy233-llm2-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm2-0-v1
Waiting for inference service cycy233-llm2-0-v1 to be ready
Inference service cycy233-llm2-0-v1 ready after 30.166741847991943s
Pipeline stage ISVCDeployer completed in 37.86s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0289134979248047s
Received healthy response to inference request in 1.1736798286437988s
Received healthy response to inference request in 1.1062161922454834s
Received healthy response to inference request in 1.1995010375976562s
Received healthy response to inference request in 1.193711757659912s
5 requests
0 failed requests
5th percentile: 1.1197089195251464
10th percentile: 1.1332016468048096
20th percentile: 1.1601871013641358
30th percentile: 1.1776862144470215
40th percentile: 1.1856989860534668
50th percentile: 1.193711757659912
60th percentile: 1.1960274696350097
70th percentile: 1.1983431816101073
80th percentile: 1.365383529663086
90th percentile: 1.6971485137939455
95th percentile: 1.8630310058593749
99th percentile: 1.9957369995117187
mean time: 1.340404462814331
Pipeline stage StressChecker completed in 7.42s
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
cycy233-llm2-0_v1 status is now deployed due to DeploymentManager action
cycy233-llm2-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics