submission_id: cycy233-misllm-v6-9-8_v4
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.9.8
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.02, 'top_k': 100, '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: 2024-06-14T09:09:44+00:00
model_name: cycy233-misllm-v6-9-8_v4
model_eval_status: success
model_group: cycy233/misllm_v6.9.8
num_battles: 33524
num_wins: 17781
celo_rating: 1191.18
propriety_score: 0.6905201284942929
propriety_total_count: 14631.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-misllm-v6-9-8_v4
ineligible_reason: None
language_model: cycy233/misllm_v6.9.8
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-14
win_ratio: 0.5303961341128743
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-9-8-v4-mkmlizer
Waiting for job on cycy233-misllm-v6-9-8-v4-mkmlizer to finish
cycy233-misllm-v6-9-8-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ /___/ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ belonging to: ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ║ ║
cycy233-misllm-v6-9-8-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-9-8-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-v6-9-8-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-9-8-v4-mkmlizer: Downloaded to shared memory in 27.233s
cycy233-misllm-v6-9-8-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-8-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-8-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 95.43it/s] Loading 0: 70%|███████ | 204/291 [00:01<00:00, 107.08it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 85.65it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-9-8-v4-mkmlizer: quantized model in 14.621s
cycy233-misllm-v6-9-8-v4-mkmlizer: Processed model cycy233/misllm_v6.9.8 in 44.137s
cycy233-misllm-v6-9-8-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-8-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-8-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4/config.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4/tokenizer_config.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4/special_tokens_map.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4/tokenizer.model
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4/tokenizer.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-8-v4/flywheel_model.0.safetensors
cycy233-misllm-v6-9-8-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-8-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-v6-9-8-v4-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-8-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-v6-9-8-v4-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-8-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-v6-9-8-v4-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-8-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-v6-9-8-v4-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-9-8-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-9-8-v4-mkmlizer: Saving duration: 0.410s
cycy233-misllm-v6-9-8-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.230s
cycy233-misllm-v6-9-8-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-9-8-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-9-8-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/special_tokens_map.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/tokenizer_config.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/merges.txt
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/vocab.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/config.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/tokenizer.json
cycy233-misllm-v6-9-8-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-9-8-v4_reward/reward.tensors
Job cycy233-misllm-v6-9-8-v4-mkmlizer completed after 72.87s with status: succeeded
Stopping job with name cycy233-misllm-v6-9-8-v4-mkmlizer
Pipeline stage MKMLizer completed in 77.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-9-8-v4
Waiting for inference service cycy233-misllm-v6-9-8-v4 to be ready
Inference service cycy233-misllm-v6-9-8-v4 ready after 40.278441429138184s
Pipeline stage ISVCDeployer completed in 47.84s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.058011770248413s
Received healthy response to inference request in 1.157116413116455s
Received healthy response to inference request in 1.1341488361358643s
Received healthy response to inference request in 1.1660399436950684s
Received healthy response to inference request in 1.6260626316070557s
5 requests
0 failed requests
5th percentile: 1.1387423515319823
10th percentile: 1.1433358669281006
20th percentile: 1.152522897720337
30th percentile: 1.1589011192321776
40th percentile: 1.162470531463623
50th percentile: 1.1660399436950684
60th percentile: 1.3500490188598633
70th percentile: 1.5340580940246582
80th percentile: 1.7124524593353272
90th percentile: 1.8852321147918703
95th percentile: 1.9716219425201416
99th percentile: 2.0407338047027586
mean time: 1.4282759189605714
Pipeline stage StressChecker completed in 8.10s
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-v6-9-8_v4 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-9-8_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics