submission_id: cycy233-misllm-v7-5-2_v3
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v7.5.2
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: 2024-06-13T06:38:15+00:00
model_name: cycy233-misllm-v7-5-2_v3
model_eval_status: success
model_group: cycy233/misllm_v7.5.2
num_battles: 17074
num_wins: 8601
celo_rating: 1183.87
propriety_score: 0.676284693597142
propriety_total_count: 7278.0
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-v7-5-2_v3
ineligible_reason: None
language_model: cycy233/misllm_v7.5.2
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.5037483893639452
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v7-5-2-v3-mkmlizer
Waiting for job on cycy233-misllm-v7-5-2-v3-mkmlizer to finish
cycy233-misllm-v7-5-2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ _____ __ __ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ /___/ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ belonging to: ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ║ ║
cycy233-misllm-v7-5-2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v7-5-2-v3-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-v7-5-2-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v7-5-2-v3-mkmlizer: Downloaded to shared memory in 16.253s
cycy233-misllm-v7-5-2-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v7-5-2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v7-5-2-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 86.96it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 102.24it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 82.67it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v7-5-2-v3-mkmlizer: quantized model in 14.939s
cycy233-misllm-v7-5-2-v3-mkmlizer: Processed model cycy233/misllm_v7.5.2 in 33.550s
cycy233-misllm-v7-5-2-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v7-5-2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v7-5-2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3/config.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3/tokenizer.model
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3/tokenizer_config.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3/special_tokens_map.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3/tokenizer.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v7-5-2-v3/flywheel_model.0.safetensors
cycy233-misllm-v7-5-2-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v7-5-2-v3-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-v7-5-2-v3-mkmlizer: warnings.warn(
cycy233-misllm-v7-5-2-v3-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-v7-5-2-v3-mkmlizer: warnings.warn(
cycy233-misllm-v7-5-2-v3-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-v7-5-2-v3-mkmlizer: warnings.warn(
cycy233-misllm-v7-5-2-v3-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-v7-5-2-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v7-5-2-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v7-5-2-v3-mkmlizer: Saving duration: 0.396s
cycy233-misllm-v7-5-2-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.946s
cycy233-misllm-v7-5-2-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v7-5-2-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v7-5-2-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/config.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/special_tokens_map.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/vocab.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/tokenizer_config.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/merges.txt
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/tokenizer.json
cycy233-misllm-v7-5-2-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v7-5-2-v3_reward/reward.tensors
Job cycy233-misllm-v7-5-2-v3-mkmlizer completed after 84.11s with status: succeeded
Stopping job with name cycy233-misllm-v7-5-2-v3-mkmlizer
Pipeline stage MKMLizer completed in 84.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v7-5-2-v3
Waiting for inference service cycy233-misllm-v7-5-2-v3 to be ready
Inference service cycy233-misllm-v7-5-2-v3 ready after 50.66207838058472s
Pipeline stage ISVCDeployer completed in 56.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.115767002105713s
Received healthy response to inference request in 1.2434585094451904s
Received healthy response to inference request in 1.224303960800171s
Received healthy response to inference request in 1.2166907787322998s
Received healthy response to inference request in 1.18727707862854s
5 requests
0 failed requests
5th percentile: 1.193159818649292
10th percentile: 1.199042558670044
20th percentile: 1.2108080387115479
30th percentile: 1.2182134151458741
40th percentile: 1.2212586879730225
50th percentile: 1.224303960800171
60th percentile: 1.2319657802581787
70th percentile: 1.2396275997161865
80th percentile: 1.417920207977295
90th percentile: 1.766843605041504
95th percentile: 1.9413053035736083
99th percentile: 2.080874662399292
mean time: 1.3974994659423827
Pipeline stage StressChecker completed in 7.55s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
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-v7-5-2_v3 status is now deployed due to DeploymentManager action
cycy233-misllm-v7-5-2_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics