submission_id: cycy233-l3-bcm-v0-c2_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bcm-v0-c2
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: 2024-07-08T02:08:17+00:00
model_name: cycy233-l3-bcm-v0-c2_v2
model_group: cycy233/L3-bcm-v0-c2
num_battles: 30997
num_wins: 15379
celo_rating: 1191.02
propriety_score: 0.7157379518072289
propriety_total_count: 5312.0
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-bcm-v0-c2_v2
ineligible_reason: None
language_model: cycy233/L3-bcm-v0-c2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.4961447882053102
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bcm-v0-c2-v2-mkmlizer
Waiting for job on cycy233-l3-bcm-v0-c2-v2-mkmlizer to finish
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ /___/ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Downloaded to shared memory in 24.386s
cycy233-l3-bcm-v0-c2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cycy233-l3-bcm-v0-c2-v2-mkmlizer: quantized model in 29.688s
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Processed model cycy233/L3-bcm-v0-c2 in 54.075s
cycy233-l3-bcm-v0-c2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bcm-v0-c2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c2-v2
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c2-v2/config.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c2-v2/special_tokens_map.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c2-v2/tokenizer_config.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c2-v2/tokenizer.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c2-v2/flywheel_model.0.safetensors
cycy233-l3-bcm-v0-c2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bcm-v0-c2-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-bcm-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c2-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-bcm-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c2-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-bcm-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c2-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-bcm-v0-c2-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c2-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-bcm-v0-c2-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Saving duration: 0.523s
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.352s
cycy233-l3-bcm-v0-c2-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bcm-v0-c2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bcm-v0-c2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/config.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/tokenizer_config.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/special_tokens_map.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/vocab.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/merges.txt
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/tokenizer.json
cycy233-l3-bcm-v0-c2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bcm-v0-c2-v2_reward/reward.tensors
Job cycy233-l3-bcm-v0-c2-v2-mkmlizer completed after 83.72s with status: succeeded
Stopping job with name cycy233-l3-bcm-v0-c2-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bcm-v0-c2-v2
Waiting for inference service cycy233-l3-bcm-v0-c2-v2 to be ready
Inference service cycy233-l3-bcm-v0-c2-v2 ready after 40.365681648254395s
Pipeline stage ISVCDeployer completed in 46.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1027283668518066s
Received healthy response to inference request in 1.2993791103363037s
Received healthy response to inference request in 1.2747981548309326s
Received healthy response to inference request in 1.2906970977783203s
Received healthy response to inference request in 1.2896161079406738s
5 requests
0 failed requests
5th percentile: 1.277761745452881
10th percentile: 1.2807253360748292
20th percentile: 1.2866525173187255
30th percentile: 1.289832305908203
40th percentile: 1.2902647018432618
50th percentile: 1.2906970977783203
60th percentile: 1.2941699028015137
70th percentile: 1.297642707824707
80th percentile: 1.4600489616394046
90th percentile: 1.7813886642456056
95th percentile: 1.9420585155487058
99th percentile: 2.0705943965911864
mean time: 1.4514437675476075
Pipeline stage StressChecker completed in 8.02s
cycy233-l3-bcm-v0-c2_v2 status is now deployed due to DeploymentManager action
cycy233-l3-bcm-v0-c2_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics