submission_id: cycy233-l3-bdpo-v5-c1_v3
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-bdpo-v5-c1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.6, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], '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: 2024-07-12T16:09:57+00:00
model_name: auto
model_group: cycy233/L3-bdpo-v5-c1
num_battles: 11624
num_wins: 4926
celo_rating: 1127.18
propriety_score: 0.7909950946040645
propriety_total_count: 5708.0
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-bdpo-v5-c1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-12
win_ratio: 0.4237783895388851
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bdpo-v5-c1-v3-mkmlizer
Waiting for job on cycy233-l3-bdpo-v5-c1-v3-mkmlizer to finish
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ /___/ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ Version: 0.8.14 ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ║ ║
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Downloaded to shared memory in 32.042s
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 112.36it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 106.38it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 119.03it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 112.05it/s] Loading 0: 22%|██▏ | 63/291 [00:00<00:02, 108.75it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 112.12it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:03, 53.35it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 68.04it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:02, 74.10it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 89.72it/s] Loading 0: 48%|████▊ | 141/291 [00:01<00:01, 92.80it/s] Loading 0: 54%|█████▎ | 156/291 [00:01<00:01, 103.87it/s] Loading 0: 58%|█████▊ | 168/291 [00:01<00:01, 103.84it/s] Loading 0: 62%|██████▏ | 181/291 [00:01<00:01, 107.67it/s] Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 65.29it/s] Loading 0: 71%|███████ | 206/291 [00:02<00:01, 76.50it/s] Loading 0: 75%|███████▌ | 219/291 [00:02<00:00, 86.77it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 89.48it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 103.42it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 104.73it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 114.33it/s] Loading 0: 98%|█████████▊| 286/291 [00:03<00:00, 116.39it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: quantized model in 29.094s
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Processed model cycy233/L3-bdpo-v5-c1 in 61.136s
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v3
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v3/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v3/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v3/config.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v3/tokenizer.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v3/flywheel_model.0.safetensors
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-bdpo-v5-c1-v3-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-bdpo-v5-c1-v3-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v3-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-bdpo-v5-c1-v3-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v3-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-bdpo-v5-c1-v3-mkmlizer: warnings.warn(
cycy233-l3-bdpo-v5-c1-v3-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-bdpo-v5-c1-v3-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Saving duration: 2.334s
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.280s
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/config.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/vocab.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/merges.txt
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/tokenizer.json
cycy233-l3-bdpo-v5-c1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v3_reward/reward.tensors
Job cycy233-l3-bdpo-v5-c1-v3-mkmlizer completed after 143.81s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v5-c1-v3-mkmlizer
Pipeline stage MKMLizer completed in 144.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v5-c1-v3
Waiting for inference service cycy233-l3-bdpo-v5-c1-v3 to be ready
Failed to get response for submission blend_pefis_2024-07-04: ('http://neversleep-noromaid-v0-8068-v116-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:45214->127.0.0.1:8080: read: connection reset by peer\n')
Inference service cycy233-l3-bdpo-v5-c1-v3 ready after 50.2767219543457s
Pipeline stage ISVCDeployer completed in 56.96s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0844693183898926s
Received healthy response to inference request in 1.3606045246124268s
Received healthy response to inference request in 1.3260924816131592s
Received healthy response to inference request in 1.2987229824066162s
Received healthy response to inference request in 1.3326129913330078s
5 requests
0 failed requests
5th percentile: 1.3041968822479248
10th percentile: 1.3096707820892335
20th percentile: 1.3206185817718505
30th percentile: 1.3273965835571289
40th percentile: 1.3300047874450684
50th percentile: 1.3326129913330078
60th percentile: 1.3438096046447754
70th percentile: 1.355006217956543
80th percentile: 1.50537748336792
90th percentile: 1.7949234008789063
95th percentile: 1.9396963596343992
99th percentile: 2.055514726638794
mean time: 1.4805004596710205
Pipeline stage StressChecker completed in 8.08s
cycy233-l3-bdpo-v5-c1_v3 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v5-c1_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics