submission_id: meseca-07062024-m1_v1
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/07062024-m1
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: 2024-06-07T03:31:46+00:00
model_name: meseca-caspian-11_v1
model_eval_status: success
model_group: meseca/07062024-m1
num_battles: 12264
num_wins: 6396
celo_rating: 1201.09
safety_score: 0.9
propriety_score: 0.6411149825783972
propriety_total_count: 861.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: meseca-caspian-11_v1
ineligible_reason: propriety_total_count < 5000
language_model: meseca/07062024-m1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5215264187866928
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-07062024-m1-v1-mkmlizer
Waiting for job on meseca-07062024-m1-v1-mkmlizer to finish
meseca-07062024-m1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-07062024-m1-v1-mkmlizer: ║ _____ __ __ ║
meseca-07062024-m1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-07062024-m1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-07062024-m1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-07062024-m1-v1-mkmlizer: ║ /___/ ║
meseca-07062024-m1-v1-mkmlizer: ║ ║
meseca-07062024-m1-v1-mkmlizer: ║ Version: 0.8.14 ║
meseca-07062024-m1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-07062024-m1-v1-mkmlizer: ║ https://mk1.ai ║
meseca-07062024-m1-v1-mkmlizer: ║ ║
meseca-07062024-m1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-07062024-m1-v1-mkmlizer: ║ belonging to: ║
meseca-07062024-m1-v1-mkmlizer: ║ ║
meseca-07062024-m1-v1-mkmlizer: ║ Chai Research Corp. ║
meseca-07062024-m1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-07062024-m1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-07062024-m1-v1-mkmlizer: ║ ║
meseca-07062024-m1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-07062024-m1-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-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-07062024-m1-v1-mkmlizer: Downloaded to shared memory in 45.747s
meseca-07062024-m1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-07062024-m1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-07062024-m1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 135.61it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 151.94it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 157.93it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 160.21it/s] Loading 0: 29%|██▉ | 85/291 [00:00<00:02, 85.40it/s] Loading 0: 35%|███▌ | 103/291 [00:00<00:01, 102.93it/s] Loading 0: 42%|████▏ | 121/291 [00:01<00:01, 117.01it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 129.02it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:00, 138.79it/s] Loading 0: 60%|██████ | 175/291 [00:01<00:00, 149.36it/s] Loading 0: 66%|██████▌ | 192/291 [00:01<00:01, 93.44it/s] Loading 0: 72%|███████▏ | 210/291 [00:01<00:00, 108.61it/s] Loading 0: 78%|███████▊ | 228/291 [00:01<00:00, 121.57it/s] Loading 0: 85%|████████▍ | 246/291 [00:02<00:00, 132.69it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 141.83it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 146.55it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-07062024-m1-v1-mkmlizer: quantized model in 22.904s
meseca-07062024-m1-v1-mkmlizer: Processed model meseca/07062024-m1 in 71.207s
meseca-07062024-m1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-07062024-m1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-07062024-m1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-07062024-m1-v1
meseca-07062024-m1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-07062024-m1-v1/special_tokens_map.json
meseca-07062024-m1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-07062024-m1-v1/config.json
meseca-07062024-m1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-07062024-m1-v1/tokenizer_config.json
meseca-07062024-m1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-07062024-m1-v1/tokenizer.json
meseca-07062024-m1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-07062024-m1-v1/flywheel_model.0.safetensors
meseca-07062024-m1-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-v1-mkmlizer: warnings.warn(
meseca-07062024-m1-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-v1-mkmlizer: warnings.warn(
meseca-07062024-m1-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-v1-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-07062024-m1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-07062024-m1-v1-mkmlizer: Saving duration: 0.399s
meseca-07062024-m1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.010s
meseca-07062024-m1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-07062024-m1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-07062024-m1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-07062024-m1-v1_reward
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/tokenizer_config.json
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/config.json
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/merges.txt
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/special_tokens_map.json
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/vocab.json
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/tokenizer.json
meseca-07062024-m1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-07062024-m1-v1_reward/reward.tensors
Job meseca-07062024-m1-v1-mkmlizer completed after 93.26s with status: succeeded
Stopping job with name meseca-07062024-m1-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service meseca-07062024-m1-v1
Waiting for inference service meseca-07062024-m1-v1 to be ready
Inference service meseca-07062024-m1-v1 ready after 30.216249465942383s
Pipeline stage ISVCDeployer completed in 37.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.118889331817627s
Received healthy response to inference request in 1.278057336807251s
Received healthy response to inference request in 1.2770676612854004s
Received healthy response to inference request in 1.349766492843628s
Received healthy response to inference request in 1.2813503742218018s
5 requests
0 failed requests
5th percentile: 1.2772655963897706
10th percentile: 1.2774635314941407
20th percentile: 1.2778594017028808
30th percentile: 1.2787159442901612
40th percentile: 1.2800331592559815
50th percentile: 1.2813503742218018
60th percentile: 1.3087168216705323
70th percentile: 1.3360832691192628
80th percentile: 1.503591060638428
90th percentile: 1.8112401962280273
95th percentile: 1.965064764022827
99th percentile: 2.088124418258667
mean time: 1.4610262393951416
Pipeline stage StressChecker completed in 7.88s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
meseca-07062024-m1_v1 status is now deployed due to DeploymentManager action
meseca-07062024-m1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics