submission_id: cycy233-l3-bcm-v0-c4_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bcm-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: 2024-07-08T02:05:52+00:00
model_name: cycy233-l3-bcm-v0-c4_v2
model_group: cycy233/L3-bcm-v0-c4
num_battles: 31517
num_wins: 15620
celo_rating: 1190.58
alignment_score: None
alignment_samples: 0
propriety_score: 0.7047673750717978
propriety_total_count: 5223.0
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-c4_v2
ineligible_reason: None
language_model: cycy233/L3-bcm-v0-c4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.4956055462131548
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bcm-v0-c4-v2-mkmlizer
Waiting for job on cycy233-l3-bcm-v0-c4-v2-mkmlizer to finish
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ /___/ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ║ ║
cycy233-l3-bcm-v0-c4-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Downloaded to shared memory in 43.495s
cycy233-l3-bcm-v0-c4-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:03, 64.02it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 78.14it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 114.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bcm-v0-c4-v2-mkmlizer: quantized model in 24.332s
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Processed model cycy233/L3-bcm-v0-c4 in 67.828s
cycy233-l3-bcm-v0-c4-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bcm-v0-c4-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v2
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v2/config.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v2/tokenizer_config.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v2/special_tokens_map.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v2/tokenizer.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bcm-v0-c4-v2/flywheel_model.0.safetensors
cycy233-l3-bcm-v0-c4-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bcm-v0-c4-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-c4-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-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-c4-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-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-c4-v2-mkmlizer: warnings.warn(
cycy233-l3-bcm-v0-c4-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-c4-v2-mkmlizer: warnings.warn(
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v61: ('http://mistralai-mixtral-8x7b-3473-v61-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')
cycy233-l3-bcm-v0-c4-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-c4-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Saving duration: 0.398s
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 148.801s
cycy233-l3-bcm-v0-c4-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bcm-v0-c4-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bcm-v0-c4-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/config.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/vocab.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/merges.txt
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/special_tokens_map.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/tokenizer_config.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/tokenizer.json
cycy233-l3-bcm-v0-c4-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bcm-v0-c4-v2_reward/reward.tensors
Job cycy233-l3-bcm-v0-c4-v2-mkmlizer completed after 259.13s with status: succeeded
Stopping job with name cycy233-l3-bcm-v0-c4-v2-mkmlizer
Pipeline stage MKMLizer completed in 259.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bcm-v0-c4-v2
Waiting for inference service cycy233-l3-bcm-v0-c4-v2 to be ready
Inference service cycy233-l3-bcm-v0-c4-v2 ready after 40.221274614334106s
Pipeline stage ISVCDeployer completed in 46.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.033484697341919s
Received healthy response to inference request in 1.2661290168762207s
Received healthy response to inference request in 1.2724685668945312s
Received healthy response to inference request in 1.2680597305297852s
Received healthy response to inference request in 1.2676618099212646s
5 requests
0 failed requests
5th percentile: 1.2664355754852294
10th percentile: 1.2667421340942382
20th percentile: 1.267355251312256
30th percentile: 1.2677413940429687
40th percentile: 1.267900562286377
50th percentile: 1.2680597305297852
60th percentile: 1.2698232650756835
70th percentile: 1.271586799621582
80th percentile: 1.424671792984009
90th percentile: 1.729078245162964
95th percentile: 1.8812814712524413
99th percentile: 2.0030440521240234
mean time: 1.4215607643127441
Pipeline stage StressChecker completed in 7.94s
cycy233-l3-bcm-v0-c4_v2 status is now deployed due to DeploymentManager action
cycy233-l3-bcm-v0-c4_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics