submission_id: cycy233-l3-brw-v0-c3_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-brw-v0-c3
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: 2024-07-03T23:57:28+00:00
model_name: cycy233-l3-brw-v0-c3_v2
model_group: cycy233/L3-brw-v0-c3
num_battles: 15105
num_wins: 7481
celo_rating: 1183.88
propriety_score: 0.7215658362989323
propriety_total_count: 7025.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cycy233-l3-brw-v0-c3_v2
ineligible_reason: None
language_model: cycy233/L3-brw-v0-c3
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.4952664680569348
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-brw-v0-c3-v2-mkmlizer
Waiting for job on cycy233-l3-brw-v0-c3-v2-mkmlizer to finish
cycy233-l3-brw-v0-c3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ /___/ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ║ ║
cycy233-l3-brw-v0-c3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-brw-v0-c3-v2-mkmlizer: Downloaded to shared memory in 21.272s
cycy233-l3-brw-v0-c3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-brw-v0-c3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-brw-v0-c3-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 84.49it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 102.42it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 144.80it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-brw-v0-c3-v2-mkmlizer: quantized model in 19.001s
cycy233-l3-brw-v0-c3-v2-mkmlizer: Processed model cycy233/L3-brw-v0-c3 in 40.274s
cycy233-l3-brw-v0-c3-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-brw-v0-c3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-brw-v0-c3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v2
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v2/config.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v2/tokenizer_config.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v2/special_tokens_map.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v2/tokenizer.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-brw-v0-c3-v2/flywheel_model.0.safetensors
cycy233-l3-brw-v0-c3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-brw-v0-c3-v2-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-c3-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v2-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-c3-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v2-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-c3-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v2-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-c3-v2-mkmlizer: warnings.warn(
cycy233-l3-brw-v0-c3-v2-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-c3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-brw-v0-c3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-brw-v0-c3-v2-mkmlizer: Saving duration: 0.256s
cycy233-l3-brw-v0-c3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.665s
cycy233-l3-brw-v0-c3-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-brw-v0-c3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-brw-v0-c3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/tokenizer_config.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/special_tokens_map.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/config.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/merges.txt
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/tokenizer.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/vocab.json
cycy233-l3-brw-v0-c3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-brw-v0-c3-v2_reward/reward.tensors
Job cycy233-l3-brw-v0-c3-v2-mkmlizer completed after 73.22s with status: succeeded
Stopping job with name cycy233-l3-brw-v0-c3-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-brw-v0-c3-v2
Waiting for inference service cycy233-l3-brw-v0-c3-v2 to be ready
Inference service cycy233-l3-brw-v0-c3-v2 ready after 90.51735806465149s
Pipeline stage ISVCDeployer completed in 97.73s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0258097648620605s
Received healthy response to inference request in 1.2558951377868652s
Received healthy response to inference request in 1.2581510543823242s
Received healthy response to inference request in 1.2743163108825684s
Received healthy response to inference request in 1.2648320198059082s
5 requests
0 failed requests
5th percentile: 1.2563463211059571
10th percentile: 1.2567975044250488
20th percentile: 1.2576998710632323
30th percentile: 1.259487247467041
40th percentile: 1.2621596336364747
50th percentile: 1.2648320198059082
60th percentile: 1.2686257362365723
70th percentile: 1.2724194526672363
80th percentile: 1.4246150016784669
90th percentile: 1.7252123832702637
95th percentile: 1.875511074066162
99th percentile: 1.995750026702881
mean time: 1.4158008575439454
Pipeline stage StressChecker completed in 7.80s
cycy233-l3-brw-v0-c3_v2 status is now deployed due to DeploymentManager action
cycy233-l3-brw-v0-c3_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics