submission_id: cycy233-misllm-v6-9-2-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.9.2.5
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': "{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': True}
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': True}
timestamp: 2024-06-13T02:16:48+00:00
model_name: base
model_eval_status: success
model_group: cycy233/misllm_v6.9.2.5
num_battles: 31892
num_wins: 15411
celo_rating: 1169.64
propriety_score: 0.6868884540117417
propriety_total_count: 13797.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
ineligible_reason: None
language_model: cycy233/misllm_v6.9.2.5
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.48322463313683683
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-9-2-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v6-9-2-5-v1-mkmlizer to finish
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ║ ║
cycy233-misllm-v6-9-2-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-9-2-5-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-misllm-v6-9-2-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Downloaded to shared memory in 44.200s
cycy233-misllm-v6-9-2-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 89.57it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 100.30it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 82.16it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-9-2-5-v1-mkmlizer: quantized model in 15.818s
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Processed model cycy233/misllm_v6.9.2.5 in 62.491s
cycy233-misllm-v6-9-2-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-2-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1/config.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1/tokenizer_config.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1/tokenizer.model
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1/tokenizer.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1/special_tokens_map.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-2-5-v1/flywheel_model.0.safetensors
cycy233-misllm-v6-9-2-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-2-5-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-misllm-v6-9-2-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-2-5-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-misllm-v6-9-2-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-2-5-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-misllm-v6-9-2-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-2-5-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-misllm-v6-9-2-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Saving duration: 0.449s
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.405s
cycy233-misllm-v6-9-2-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-9-2-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-9-2-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/special_tokens_map.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/tokenizer_config.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/vocab.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/config.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/merges.txt
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/tokenizer.json
cycy233-misllm-v6-9-2-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-9-2-5-v1_reward/reward.tensors
Job cycy233-misllm-v6-9-2-5-v1-mkmlizer completed after 93.37s with status: succeeded
Stopping job with name cycy233-misllm-v6-9-2-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.79s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-9-2-5-v1
Waiting for inference service cycy233-misllm-v6-9-2-5-v1 to be ready
Inference service cycy233-misllm-v6-9-2-5-v1 ready after 30.22633695602417s
Pipeline stage ISVCDeployer completed in 37.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 12.32758903503418s
Received healthy response to inference request in 0.9777030944824219s
Received healthy response to inference request in 1.057856559753418s
Received healthy response to inference request in 1.1406712532043457s
Received healthy response to inference request in 0.9881680011749268s
5 requests
0 failed requests
5th percentile: 0.9797960758209229
10th percentile: 0.9818890571594239
20th percentile: 0.9860750198364258
30th percentile: 1.002105712890625
40th percentile: 1.0299811363220215
50th percentile: 1.057856559753418
60th percentile: 1.090982437133789
70th percentile: 1.1241083145141602
80th percentile: 3.3780548095703145
90th percentile: 7.8528219223022475
95th percentile: 10.09020547866821
99th percentile: 11.880112323760986
mean time: 3.298397588729858
Pipeline stage StressChecker completed in 17.12s
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-misllm-v6-9-2-5_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-9-2-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics