submission_id: cycy233-misllm-v7-8-1-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v7.8.1.5
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': 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: 2024-06-17T03:19:21+00:00
model_name: cycy233-misllm-v7-8-1-5_v1
model_eval_status: success
model_group: cycy233/misllm_v7.8.1.5
num_battles: 16693
num_wins: 8382
celo_rating: 1192.01
propriety_score: 0.6925457828217694
propriety_total_count: 7754.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-misllm-v7-8-1-5_v1
ineligible_reason: None
language_model: cycy233/misllm_v7.8.1.5
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-16
win_ratio: 0.5021266399089439
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v7-8-1-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v7-8-1-5-v1-mkmlizer to finish
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ /___/ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ belonging to: ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ║ ║
cycy233-misllm-v7-8-1-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v7-8-1-5-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-v7-8-1-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Downloaded to shared memory in 30.537s
cycy233-misllm-v7-8-1-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 93.78it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 103.12it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 83.10it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v7-8-1-5-v1-mkmlizer: quantized model in 15.063s
cycy233-misllm-v7-8-1-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v7-8-1-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1/special_tokens_map.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1/config.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1/tokenizer_config.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1/tokenizer.model
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1/tokenizer.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v7-8-1-5-v1/flywheel_model.0.safetensors
cycy233-misllm-v7-8-1-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v7-8-1-5-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-v7-8-1-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v7-8-1-5-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-v7-8-1-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v7-8-1-5-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-v7-8-1-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v7-8-1-5-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-v7-8-1-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Saving duration: 0.437s
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.962s
cycy233-misllm-v7-8-1-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v7-8-1-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v7-8-1-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/config.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/merges.txt
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/special_tokens_map.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/tokenizer_config.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/vocab.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/tokenizer.json
cycy233-misllm-v7-8-1-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v7-8-1-5-v1_reward/reward.tensors
Job cycy233-misllm-v7-8-1-5-v1-mkmlizer completed after 73.17s with status: succeeded
Stopping job with name cycy233-misllm-v7-8-1-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v7-8-1-5-v1
Waiting for inference service cycy233-misllm-v7-8-1-5-v1 to be ready
Inference service cycy233-misllm-v7-8-1-5-v1 ready after 40.263402700424194s
Pipeline stage ISVCDeployer completed in 47.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1617560386657715s
Received healthy response to inference request in 1.2087128162384033s
Received healthy response to inference request in 1.2260465621948242s
Received healthy response to inference request in 1.2371959686279297s
Received healthy response to inference request in 1.2112557888031006s
5 requests
0 failed requests
5th percentile: 1.2092214107513428
10th percentile: 1.2097300052642823
20th percentile: 1.210747194290161
30th percentile: 1.2142139434814454
40th percentile: 1.2201302528381348
50th percentile: 1.2260465621948242
60th percentile: 1.2305063247680663
70th percentile: 1.2349660873413086
80th percentile: 1.4221079826354983
90th percentile: 1.791932010650635
95th percentile: 1.9768440246582029
99th percentile: 2.124773635864258
mean time: 1.4089934349060058
Pipeline stage StressChecker completed in 7.65s
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-v7-8-1-5_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v7-8-1-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics