submission_id: cycy233-misllm-v6-0-5_v9
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.0.5
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 70, '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': 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: 2024-06-05T02:50:01+00:00
model_name: base_f
model_eval_status: success
model_group: cycy233/misllm_v6.0.5
num_battles: 7154
num_wins: 3686
celo_rating: 1194.72
safety_score: 0.97
propriety_score: 0.6848739495798319
propriety_total_count: 238.0
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_f
ineligible_reason: propriety_total_count < 5000
language_model: cycy233/misllm_v6.0.5
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-04
win_ratio: 0.515236231478893
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-0-5-v9-mkmlizer
Waiting for job on cycy233-misllm-v6-0-5-v9-mkmlizer to finish
cycy233-misllm-v6-0-5-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ║ ║
cycy233-misllm-v6-0-5-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-0-5-v9-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-v6-0-5-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-0-5-v9-mkmlizer: Downloaded to shared memory in 13.383s
cycy233-misllm-v6-0-5-v9-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-0-5-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-0-5-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 82.47it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 93.55it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 83.14it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-0-5-v9-mkmlizer: quantized model in 11.080s
cycy233-misllm-v6-0-5-v9-mkmlizer: Processed model cycy233/misllm_v6.0.5 in 25.608s
cycy233-misllm-v6-0-5-v9-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-0-5-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-0-5-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9/special_tokens_map.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9/tokenizer_config.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9/config.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9/tokenizer.model
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9/tokenizer.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-0-5-v9/flywheel_model.0.safetensors
cycy233-misllm-v6-0-5-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-0-5-v9-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-v6-0-5-v9-mkmlizer: warnings.warn(
cycy233-misllm-v6-0-5-v9-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-v6-0-5-v9-mkmlizer: warnings.warn(
cycy233-misllm-v6-0-5-v9-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-v6-0-5-v9-mkmlizer: warnings.warn(
cycy233-misllm-v6-0-5-v9-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-v6-0-5-v9-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-0-5-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-0-5-v9-mkmlizer: Saving duration: 0.225s
cycy233-misllm-v6-0-5-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.021s
cycy233-misllm-v6-0-5-v9-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-0-5-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-0-5-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/config.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/tokenizer_config.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/special_tokens_map.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/merges.txt
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/vocab.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/tokenizer.json
cycy233-misllm-v6-0-5-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-0-5-v9_reward/reward.tensors
Job cycy233-misllm-v6-0-5-v9-mkmlizer completed after 52.59s with status: succeeded
Stopping job with name cycy233-misllm-v6-0-5-v9-mkmlizer
Pipeline stage MKMLizer completed in 57.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-0-5-v9
Waiting for inference service cycy233-misllm-v6-0-5-v9 to be ready
Inference service cycy233-misllm-v6-0-5-v9 ready after 40.2542986869812s
Pipeline stage ISVCDeployer completed in 48.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.087907075881958s
Received healthy response to inference request in 0.9196150302886963s
Received healthy response to inference request in 1.166736364364624s
Received healthy response to inference request in 1.1726949214935303s
Received healthy response to inference request in 1.162069320678711s
5 requests
0 failed requests
5th percentile: 0.9681058883666992
10th percentile: 1.016596746444702
20th percentile: 1.113578462600708
30th percentile: 1.1630027294158936
40th percentile: 1.1648695468902588
50th percentile: 1.166736364364624
60th percentile: 1.1691197872161865
70th percentile: 1.171503210067749
80th percentile: 1.355737352371216
90th percentile: 1.721822214126587
95th percentile: 1.9048646450042723
99th percentile: 2.0512985897064206
mean time: 1.301804542541504
Pipeline stage StressChecker completed in 7.20s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v6-0-5_v9 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-0-5_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics