submission_id: cycy233-l3-klee-v1-e2-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-klee-v1-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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{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: 2024-07-01T03:01:53+00:00
model_name: auto
model_group: cycy233/L3-klee-v1-e2.5
num_battles: 15849
num_wins: 8008
celo_rating: 1189.03
propriety_score: 0.7127534336167429
propriety_total_count: 7645.0
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-klee-v1-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-30
win_ratio: 0.505268471196921
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-klee-v1-e2-5-v1-mkmlizer
Waiting for job on cycy233-l3-klee-v1-e2-5-v1-mkmlizer to finish
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ /___/ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ║ ║
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-klee-v1-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-klee-v1-e2-5-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51214->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Downloaded to shared memory in 32.029s
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 60.51it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 68.73it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 99.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: quantized model in 25.177s
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Processed model cycy233/L3-klee-v1-e2.5 in 59.834s
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-klee-v1-e2-5-v1
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e2-5-v1/config.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e2-5-v1/special_tokens_map.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e2-5-v1/tokenizer_config.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-klee-v1-e2-5-v1/tokenizer.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-klee-v1-e2-5-v1/flywheel_model.0.safetensors
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-klee-v1-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-klee-v1-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v1-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-klee-v1-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v1-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-klee-v1-e2-5-v1-mkmlizer: warnings.warn(
cycy233-l3-klee-v1-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-klee-v1-e2-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Saving duration: 0.431s
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.486s
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/special_tokens_map.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/config.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/vocab.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/tokenizer_config.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/merges.txt
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/tokenizer.json
cycy233-l3-klee-v1-e2-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-klee-v1-e2-5-v1_reward/reward.tensors
Job cycy233-l3-klee-v1-e2-5-v1-mkmlizer completed after 93.34s with status: succeeded
Stopping job with name cycy233-l3-klee-v1-e2-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-klee-v1-e2-5-v1
Waiting for inference service cycy233-l3-klee-v1-e2-5-v1 to be ready
Inference service cycy233-l3-klee-v1-e2-5-v1 ready after 40.202765703201294s
Pipeline stage ISVCDeployer completed in 46.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.186147689819336s
Received healthy response to inference request in 1.340867519378662s
Received healthy response to inference request in 1.3146464824676514s
Received healthy response to inference request in 1.2969927787780762s
Received healthy response to inference request in 1.370893955230713s
5 requests
0 failed requests
5th percentile: 1.3005235195159912
10th percentile: 1.3040542602539062
20th percentile: 1.3111157417297363
30th percentile: 1.3198906898498535
40th percentile: 1.330379104614258
50th percentile: 1.340867519378662
60th percentile: 1.3528780937194824
70th percentile: 1.3648886680603027
80th percentile: 1.5339447021484376
90th percentile: 1.8600461959838868
95th percentile: 2.0230969429016112
99th percentile: 2.153537540435791
mean time: 1.5019096851348877
Pipeline stage StressChecker completed in 8.19s
cycy233-l3-klee-v1-e2-5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-klee-v1-e2-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics