submission_id: cycy233-l3-base-v4-e2-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base-v4-e2.5
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}
timestamp: 2024-06-22T15:08:30+00:00
model_name: auto
model_group: cycy233/L3-base-v4-e2.5
num_battles: 30540
num_wins: 16296
celo_rating: 1205.86
propriety_score: 0.7050448353754535
propriety_total_count: 14609.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
ineligible_reason: None
language_model: cycy233/L3-base-v4-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.5335952848722986
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v4-e2-5-v1-mkmlizer
Waiting for job on cycy233-l3-base-v4-e2-5-v1-mkmlizer to finish
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-base-v4-e2-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-base-v4-e2-5-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-l3-base-v4-e2-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Downloaded to shared memory in 37.316s
cycy233-l3-base-v4-e2-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 67.60it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 40.28it/s] Loading 0: 99%|█████████▊| 287/291 [00:04<00:00, 65.87it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v4-e2-5-v1-mkmlizer: quantized model in 26.079s
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Processed model cycy233/L3-base-v4-e2.5 in 65.854s
cycy233-l3-base-v4-e2-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v4-e2-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v4-e2-5-v1
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v4-e2-5-v1/special_tokens_map.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v4-e2-5-v1/config.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v4-e2-5-v1/tokenizer_config.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v4-e2-5-v1/tokenizer.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-base-v4-e2-5-v1/flywheel_model.0.safetensors
cycy233-l3-base-v4-e2-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v4-e2-5-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-l3-base-v4-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v4-e2-5-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-l3-base-v4-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v4-e2-5-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-l3-base-v4-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-base-v4-e2-5-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-l3-base-v4-e2-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Saving duration: 0.383s
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.569s
cycy233-l3-base-v4-e2-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v4-e2-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v4-e2-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/vocab.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/special_tokens_map.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/tokenizer.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/tokenizer_config.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/merges.txt
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/config.json
cycy233-l3-base-v4-e2-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v4-e2-5-v1_reward/reward.tensors
Job cycy233-l3-base-v4-e2-5-v1-mkmlizer completed after 93.36s with status: succeeded
Stopping job with name cycy233-l3-base-v4-e2-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 93.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v4-e2-5-v1
Waiting for inference service cycy233-l3-base-v4-e2-5-v1 to be ready
Tearing down inference service cycy233-l3-base-v4-e2-5-v1
%s, retrying in %s seconds...
Creating inference service cycy233-l3-base-v4-e2-5-v1
Waiting for inference service cycy233-l3-base-v4-e2-5-v1 to be ready
Inference service cycy233-l3-base-v4-e2-5-v1 ready after 40.2880744934082s
Pipeline stage ISVCDeployer completed in 61.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.087393283843994s
Received healthy response to inference request in 1.192479133605957s
Received healthy response to inference request in 1.2119910717010498s
Received healthy response to inference request in 1.1923043727874756s
Received healthy response to inference request in 1.2208023071289062s
5 requests
0 failed requests
5th percentile: 1.1923393249511718
10th percentile: 1.1923742771148682
20th percentile: 1.1924441814422608
30th percentile: 1.1963815212249755
40th percentile: 1.2041862964630128
50th percentile: 1.2119910717010498
60th percentile: 1.2155155658721923
70th percentile: 1.2190400600433349
80th percentile: 1.394120502471924
90th percentile: 1.7407568931579591
95th percentile: 1.9140750885009763
99th percentile: 2.0527296447753907
mean time: 1.3809940338134765
Pipeline stage StressChecker completed in 7.58s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
cycy233-l3-base-v4-e2-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-base-v4-e2-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics