submission_id: cycy233-l3i-base-v2-e2-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3i-base-v2-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: 2024-06-26T02:20:22+00:00
model_name: auto
model_group: cycy233/L3i-base-v2-e2.5
num_battles: 18941
num_wins: 10092
celo_rating: 1199.36
propriety_score: 0.7012010326635986
propriety_total_count: 8909.0
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/L3i-base-v2-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-25
win_ratio: 0.5328124175069954
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3i-base-v2-e2-5-v1-mkmlizer
Waiting for job on cycy233-l3i-base-v2-e2-5-v1-mkmlizer to finish
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ║ ║
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3i-base-v2-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-l3i-base-v2-e2-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Downloaded to shared memory in 43.360s
Retrying (%r) after connection broken by '%r': %s
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 76.92it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 90.58it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 132.89it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: quantized model in 19.381s
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Processed model cycy233/L3i-base-v2-e2.5 in 63.801s
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3i-base-v2-e2-5-v1
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e2-5-v1/config.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e2-5-v1/special_tokens_map.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e2-5-v1/tokenizer_config.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3i-base-v2-e2-5-v1/tokenizer.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3i-base-v2-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-l3i-base-v2-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3i-base-v2-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-l3i-base-v2-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3i-base-v2-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-l3i-base-v2-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3i-base-v2-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-l3i-base-v2-e2-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Saving duration: 0.318s
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 14.442s
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/config.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/special_tokens_map.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/tokenizer_config.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/merges.txt
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/vocab.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/tokenizer.json
cycy233-l3i-base-v2-e2-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3i-base-v2-e2-5-v1_reward/reward.tensors
Job cycy233-l3i-base-v2-e2-5-v1-mkmlizer completed after 96.45s with status: succeeded
Stopping job with name cycy233-l3i-base-v2-e2-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3i-base-v2-e2-5-v1
Waiting for inference service cycy233-l3i-base-v2-e2-5-v1 to be ready
Inference service cycy233-l3i-base-v2-e2-5-v1 ready after 40.295626401901245s
Pipeline stage ISVCDeployer completed in 46.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1435699462890625s
Received healthy response to inference request in 1.2059247493743896s
Received healthy response to inference request in 1.1862928867340088s
Received healthy response to inference request in 1.2217810153961182s
Received healthy response to inference request in 1.180427074432373s
5 requests
0 failed requests
5th percentile: 1.1816002368927
10th percentile: 1.1827733993530274
20th percentile: 1.1851197242736817
30th percentile: 1.190219259262085
40th percentile: 1.1980720043182373
50th percentile: 1.2059247493743896
60th percentile: 1.2122672557830811
70th percentile: 1.2186097621917724
80th percentile: 1.4061388015747072
90th percentile: 1.774854373931885
95th percentile: 1.9592121601104735
99th percentile: 2.106698389053345
mean time: 1.3875991344451903
Pipeline stage StressChecker completed in 7.85s
cycy233-l3i-base-v2-e2-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3i-base-v2-e2-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics