submission_id: cycy233-misllm-v6-4-3_v4
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.4.3
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': 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: 2024-06-04T01:08:14+00:00
model_name: infer_test
model_eval_status: success
model_group: cycy233/misllm_v6.4.3
num_battles: 7540
num_wins: 3915
celo_rating: 1197.33
safety_score: 0.95
propriety_score: 0.6923076923076923
propriety_total_count: 208.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: infer_test
ineligible_reason: propriety_total_count < 5000
language_model: cycy233/misllm_v6.4.3
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-03
win_ratio: 0.5192307692307693
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-4-3-v4-mkmlizer
Waiting for job on cycy233-misllm-v6-4-3-v4-mkmlizer to finish
cycy233-misllm-v6-4-3-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ║ ║
cycy233-misllm-v6-4-3-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-4-3-v4-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-v6-4-3-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-4-3-v4-mkmlizer: Downloaded to shared memory in 15.820s
cycy233-misllm-v6-4-3-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-4-3-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-4-3-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 96.26it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 104.50it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 84.84it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-4-3-v4-mkmlizer: quantized model in 14.751s
cycy233-misllm-v6-4-3-v4-mkmlizer: Processed model cycy233/misllm_v6.4.3 in 32.849s
cycy233-misllm-v6-4-3-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-4-3-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-4-3-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-4-3-v4
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-4-3-v4/config.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-4-3-v4/special_tokens_map.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-4-3-v4/tokenizer_config.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-4-3-v4/tokenizer.model
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-4-3-v4/tokenizer.json
cycy233-misllm-v6-4-3-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-4-3-v4-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-v6-4-3-v4-mkmlizer: warnings.warn(
cycy233-misllm-v6-4-3-v4-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-v6-4-3-v4-mkmlizer: warnings.warn(
cycy233-misllm-v6-4-3-v4-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-v6-4-3-v4-mkmlizer: warnings.warn(
cycy233-misllm-v6-4-3-v4-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-v6-4-3-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-4-3-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-4-3-v4-mkmlizer: Saving duration: 0.392s
cycy233-misllm-v6-4-3-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.397s
cycy233-misllm-v6-4-3-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-4-3-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-4-3-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/config.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/special_tokens_map.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/tokenizer_config.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/merges.txt
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/vocab.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/tokenizer.json
cycy233-misllm-v6-4-3-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-4-3-v4_reward/reward.tensors
Job cycy233-misllm-v6-4-3-v4-mkmlizer completed after 53.0s with status: succeeded
Stopping job with name cycy233-misllm-v6-4-3-v4-mkmlizer
Pipeline stage MKMLizer completed in 56.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-4-3-v4
Waiting for inference service cycy233-misllm-v6-4-3-v4 to be ready
Inference service cycy233-misllm-v6-4-3-v4 ready after 30.207966566085815s
Pipeline stage ISVCDeployer completed in 37.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.020904541015625s
Received healthy response to inference request in 0.9614498615264893s
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Received healthy response to inference request in 1.0983152389526367s
Received healthy response to inference request in 2.210557460784912s
Received healthy response to inference request in 1.1585140228271484s
Received healthy response to inference request in 1.3114173412322998s
Received healthy response to inference request in 1.1441564559936523s
5 requests
0 failed requests
5th percentile: 1.10748348236084
10th percentile: 1.116651725769043
20th percentile: 1.1349882125854491
30th percentile: 1.1470279693603516
40th percentile: 1.15277099609375
50th percentile: 1.1585140228271484
60th percentile: 1.219675350189209
70th percentile: 1.2808366775512694
80th percentile: 1.4912453651428224
90th percentile: 1.8509014129638672
95th percentile: 2.0307294368743896
99th percentile: 2.1745918560028077
mean time: 1.38459210395813
Pipeline stage StressChecker completed in 20.89s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cycy233-misllm-v6-4-3_v4 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cycy233-misllm-v6-4-3_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics