submission_id: cycy233-l3-brw-v0-c4_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-brw-v0-c4
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: 2024-07-03T16:31:21+00:00
model_name: auto
model_group: cycy233/L3-brw-v0-c4
num_battles: 11617
num_wins: 5713
celo_rating: 1175.53
propriety_score: 0.7387307760296977
propriety_total_count: 5657.0
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-brw-v0-c4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.4917792889730567
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-brw-v0-c4-v1-mkmlizer
Waiting for job on cycy233-l3-brw-v0-c4-v1-mkmlizer to finish
cycy233-l3-brw-v0-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ║ ║
cycy233-l3-brw-v0-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-brw-v0-c4-v1-mkmlizer: Downloaded to shared memory in 40.999s
cycy233-l3-brw-v0-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-brw-v0-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-brw-v0-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 57.71it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 65.45it/s] Loading 0: 99%|█████████▊| 287/291 [00:03<00:00, 97.95it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-brw-v0-c4-v1-mkmlizer: quantized model in 29.881s
cycy233-l3-brw-v0-c4-v1-mkmlizer: Processed model cycy233/L3-brw-v0-c4 in 70.880s
cycy233-l3-brw-v0-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-brw-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-brw-v0-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-brw-v0-c4-v1
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c4-v1/config.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c4-v1/special_tokens_map.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c4-v1/tokenizer_config.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c4-v1/tokenizer.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-brw-v0-c4-v1/flywheel_model.0.safetensors
cycy233-l3-brw-v0-c4-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-brw-v0-c4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-brw-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cycy233-l3-brw-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c4-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-brw-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c4-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-brw-v0-c4-v1-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c4-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-brw-v0-c4-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-brw-v0-c4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-brw-v0-c4-v1-mkmlizer: Saving duration: 0.515s
cycy233-l3-brw-v0-c4-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.427s
cycy233-l3-brw-v0-c4-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-brw-v0-c4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-brw-v0-c4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/config.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/vocab.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/merges.txt
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/tokenizer_config.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/special_tokens_map.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/tokenizer.json
cycy233-l3-brw-v0-c4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-brw-v0-c4-v1_reward/reward.tensors
Job cycy233-l3-brw-v0-c4-v1-mkmlizer completed after 103.86s with status: succeeded
Stopping job with name cycy233-l3-brw-v0-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-brw-v0-c4-v1
Waiting for inference service cycy233-l3-brw-v0-c4-v1 to be ready
Inference service cycy233-l3-brw-v0-c4-v1 ready after 40.19757127761841s
Pipeline stage ISVCDeployer completed in 46.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.042557954788208s
Received healthy response to inference request in 1.2493798732757568s
Received healthy response to inference request in 1.2697694301605225s
Received healthy response to inference request in 1.2557659149169922s
Received healthy response to inference request in 1.2441761493682861s
5 requests
0 failed requests
5th percentile: 1.2452168941497803
10th percentile: 1.2462576389312745
20th percentile: 1.2483391284942627
30th percentile: 1.250657081604004
40th percentile: 1.253211498260498
50th percentile: 1.2557659149169922
60th percentile: 1.2613673210144043
70th percentile: 1.2669687271118164
80th percentile: 1.4243271350860598
90th percentile: 1.7334425449371338
95th percentile: 1.8880002498626707
99th percentile: 2.0116464138031005
mean time: 1.412329864501953
Pipeline stage StressChecker completed in 7.73s
cycy233-l3-brw-v0-c4_v1 status is now deployed due to DeploymentManager action
cycy233-l3-brw-v0-c4_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics