submission_id: cycy233-llm3-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/llm3.0
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': 'prompt:{memory}\n####\n', 'prompt_template': 'input:{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: 2024-05-09T04:00:35+00:00
model_name: rolee
model_eval_status: success
double_thumbs_up: 295
thumbs_up: 545
thumbs_down: 342
num_battles: 24364
num_wins: 10964
celo_rating: 1131.38
entertaining: 6.74
stay_in_character: 8.08
user_preference: 6.68
safety_score: 0.65
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rolee
double_thumbs_up_ratio: 0.24957698815566837
feedback_count: 1182
ineligible_reason: None
language_model: cycy233/llm3.0
model_score: 7.166666666666667
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.461082910321489
thumbs_down_ratio: 0.2893401015228426
thumbs_up_ratio: 0.7106598984771574
us_pacific_date: 2024-05-08
win_ratio: 0.450008208832704
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-llm3-0-v1-mkmlizer
Waiting for job on cycy233-llm3-0-v1-mkmlizer to finish
cycy233-llm3-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-llm3-0-v1-mkmlizer: ║ _____ __ __ ║
cycy233-llm3-0-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-llm3-0-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-llm3-0-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-llm3-0-v1-mkmlizer: ║ /___/ ║
cycy233-llm3-0-v1-mkmlizer: ║ ║
cycy233-llm3-0-v1-mkmlizer: ║ Version: 0.8.10 ║
cycy233-llm3-0-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-llm3-0-v1-mkmlizer: ║ ║
cycy233-llm3-0-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-llm3-0-v1-mkmlizer: ║ belonging to: ║
cycy233-llm3-0-v1-mkmlizer: ║ ║
cycy233-llm3-0-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-llm3-0-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-llm3-0-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-llm3-0-v1-mkmlizer: ║ ║
cycy233-llm3-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-llm3-0-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-llm3-0-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-llm3-0-v1-mkmlizer: Downloaded to shared memory in 22.388s
cycy233-llm3-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-llm3-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-llm3-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 36%|███▋ | 106/291 [00:01<00:02, 73.67it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 79.15it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-llm3-0-v1-mkmlizer: quantized model in 11.485s
cycy233-llm3-0-v1-mkmlizer: Processed model cycy233/llm3.0 in 34.780s
cycy233-llm3-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-llm3-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-llm3-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-llm3-0-v1
cycy233-llm3-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-llm3-0-v1/special_tokens_map.json
cycy233-llm3-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-llm3-0-v1/config.json
cycy233-llm3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-llm3-0-v1/tokenizer.model
cycy233-llm3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-llm3-0-v1/tokenizer.json
cycy233-llm3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-llm3-0-v1/tokenizer_config.json
cycy233-llm3-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-llm3-0-v1/flywheel_model.0.safetensors
cycy233-llm3-0-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-llm3-0-v1-mkmlizer: warnings.warn(
cycy233-llm3-0-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-llm3-0-v1-mkmlizer: warnings.warn(
cycy233-llm3-0-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-llm3-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-llm3-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-llm3-0-v1-mkmlizer: Saving duration: 0.270s
cycy233-llm3-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.774s
cycy233-llm3-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-llm3-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-llm3-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-llm3-0-v1_reward
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/config.json
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/merges.txt
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/tokenizer_config.json
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/special_tokens_map.json
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/vocab.json
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/tokenizer.json
cycy233-llm3-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-llm3-0-v1_reward/reward.tensors
Job cycy233-llm3-0-v1-mkmlizer completed after 64.83s with status: succeeded
Stopping job with name cycy233-llm3-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 70.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-llm3-0-v1
Waiting for inference service cycy233-llm3-0-v1 to be ready
Inference service cycy233-llm3-0-v1 ready after 40.597437620162964s
Pipeline stage ISVCDeployer completed in 47.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0365333557128906s
Received healthy response to inference request in 1.1466877460479736s
Received healthy response to inference request in 1.17337965965271s
Received healthy response to inference request in 1.2028062343597412s
Received healthy response to inference request in 1.192474126815796s
5 requests
0 failed requests
5th percentile: 1.1520261287689209
10th percentile: 1.157364511489868
20th percentile: 1.1680412769317627
30th percentile: 1.177198553085327
40th percentile: 1.1848363399505615
50th percentile: 1.192474126815796
60th percentile: 1.1966069698333741
70th percentile: 1.200739812850952
80th percentile: 1.3695516586303713
90th percentile: 1.7030425071716309
95th percentile: 1.8697879314422605
99th percentile: 2.003184270858765
mean time: 1.3503762245178224
Pipeline stage StressChecker completed in 7.38s
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-llm3-0_v1 status is now deployed due to DeploymentManager action
cycy233-llm3-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics