submission_id: meseca-07062024-m1-dpo-1_v1
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/07062024-m1-dpo-1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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': '<|start_header_id|>system<|end_header_id|>\n\nThis is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically.\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: 2024-06-18T01:47:43+00:00
model_name: 07062024-m1-dpo
model_group: meseca/07062024-m1-dpo-1
num_battles: 15115
num_wins: 6474
celo_rating: 1137.64
propriety_score: 0.7526987242394504
propriety_total_count: 7133.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 07062024-m1-dpo
ineligible_reason: None
language_model: meseca/07062024-m1-dpo-1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-17
win_ratio: 0.428316242143566
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-07062024-m1-dpo-1-v1-mkmlizer
Waiting for job on meseca-07062024-m1-dpo-1-v1-mkmlizer to finish
meseca-07062024-m1-dpo-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ _____ __ __ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ /___/ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ Version: 0.8.14 ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ https://mk1.ai ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ belonging to: ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ Chai Research Corp. ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ║ ║
meseca-07062024-m1-dpo-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-07062024-m1-dpo-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
meseca-07062024-m1-dpo-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-07062024-m1-dpo-1-v1-mkmlizer: Downloaded to shared memory in 56.068s
meseca-07062024-m1-dpo-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-07062024-m1-dpo-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-07062024-m1-dpo-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 100.12it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:03, 79.95it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:02, 98.40it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:02, 105.02it/s] Loading 0: 20%|██ | 59/291 [00:00<00:02, 96.69it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 100.20it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:02, 100.52it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 57.52it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 64.57it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 69.61it/s] Loading 0: 42%|████▏ | 122/291 [00:01<00:02, 72.93it/s] Loading 0: 46%|████▌ | 134/291 [00:01<00:01, 83.59it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 86.89it/s] Loading 0: 53%|█████▎ | 154/291 [00:01<00:01, 89.54it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 90.73it/s] Loading 0: 60%|██████ | 175/291 [00:02<00:01, 93.17it/s] Loading 0: 64%|██████▎ | 185/291 [00:02<00:01, 93.88it/s] Loading 0: 67%|██████▋ | 195/291 [00:02<00:01, 53.16it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:01, 59.87it/s] Loading 0: 74%|███████▎ | 214/291 [00:02<00:01, 68.03it/s] Loading 0: 77%|███████▋ | 223/291 [00:02<00:00, 72.40it/s] Loading 0: 80%|███████▉ | 232/291 [00:02<00:00, 76.51it/s] Loading 0: 83%|████████▎ | 242/291 [00:03<00:00, 82.08it/s] Loading 0: 87%|████████▋ | 253/291 [00:03<00:00, 89.20it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 92.22it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 90.68it/s] Loading 0: 98%|█████████▊| 284/291 [00:03<00:00, 92.65it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-07062024-m1-dpo-1-v1-mkmlizer: quantized model in 25.438s
meseca-07062024-m1-dpo-1-v1-mkmlizer: Processed model meseca/07062024-m1-dpo-1 in 84.072s
meseca-07062024-m1-dpo-1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-07062024-m1-dpo-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-07062024-m1-dpo-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-07062024-m1-dpo-1-v1
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-07062024-m1-dpo-1-v1/config.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-07062024-m1-dpo-1-v1/tokenizer_config.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-07062024-m1-dpo-1-v1/special_tokens_map.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-07062024-m1-dpo-1-v1/tokenizer.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-07062024-m1-dpo-1-v1/flywheel_model.0.safetensors
meseca-07062024-m1-dpo-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-07062024-m1-dpo-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meseca-07062024-m1-dpo-1-v1-mkmlizer: warnings.warn(
meseca-07062024-m1-dpo-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meseca-07062024-m1-dpo-1-v1-mkmlizer: warnings.warn(
meseca-07062024-m1-dpo-1-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.
meseca-07062024-m1-dpo-1-v1-mkmlizer: warnings.warn(
meseca-07062024-m1-dpo-1-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()
meseca-07062024-m1-dpo-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-07062024-m1-dpo-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-07062024-m1-dpo-1-v1-mkmlizer: Saving duration: 0.501s
meseca-07062024-m1-dpo-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.631s
meseca-07062024-m1-dpo-1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-07062024-m1-dpo-1-v1-mkmlizer: WARNING: Retrying failed request: / ([Errno 110] Connection timed out)
meseca-07062024-m1-dpo-1-v1-mkmlizer: WARNING: Waiting 3 sec...
meseca-07062024-m1-dpo-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-07062024-m1-dpo-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/special_tokens_map.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/config.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/merges.txt
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/tokenizer_config.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/vocab.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/tokenizer.json
meseca-07062024-m1-dpo-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-07062024-m1-dpo-1-v1_reward/reward.tensors
Job meseca-07062024-m1-dpo-1-v1-mkmlizer completed after 257.61s with status: succeeded
Stopping job with name meseca-07062024-m1-dpo-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 260.66s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meseca-07062024-m1-dpo-1-v1
Waiting for inference service meseca-07062024-m1-dpo-1-v1 to be ready
Tearing down inference service meseca-07062024-m1-dpo-1-v1
%s, retrying in %s seconds...
Creating inference service meseca-07062024-m1-dpo-1-v1
Waiting for inference service meseca-07062024-m1-dpo-1-v1 to be ready
Inference service meseca-07062024-m1-dpo-1-v1 ready after 40.34146237373352s
Pipeline stage ISVCDeployer completed in 656.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1879355907440186s
Received healthy response to inference request in 1.3429303169250488s
Received healthy response to inference request in 1.3158957958221436s
Received healthy response to inference request in 1.389577865600586s
Received healthy response to inference request in 1.3618261814117432s
5 requests
0 failed requests
5th percentile: 1.3213027000427247
10th percentile: 1.3267096042633058
20th percentile: 1.3375234127044677
30th percentile: 1.3467094898223877
40th percentile: 1.3542678356170654
50th percentile: 1.3618261814117432
60th percentile: 1.3729268550872802
70th percentile: 1.3840275287628174
80th percentile: 1.5492494106292727
90th percentile: 1.8685925006866455
95th percentile: 2.028264045715332
99th percentile: 2.1560012817382814
mean time: 1.519633150100708
Pipeline stage StressChecker completed in 8.28s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
meseca-07062024-m1-dpo-1_v1 status is now deployed due to DeploymentManager action
meseca-07062024-m1-dpo-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics