meseca-05062024-v1

developer_uid: nguyenzzz

submission_id: meseca-05062024-v1_v3

model_name: meseca-05062024-v1_v1

model_group: meseca/05062024-v1

status: torndown

timestamp: 2024-06-16T05:58:29+00:00

num_battles: 11340

num_wins: 5671

celo_rating: 1174.18

family_friendly_score: 0.0

submission_type: basic

model_repo: meseca/05062024-v1

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: meseca-05062024-v1_v1

is_internal_developer: False

language_model: meseca/05062024-v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-15

win_ratio: 0.5000881834215167

generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, '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\nYou're {bot_name} in this fictional never-ending roleplay with {user_name}.\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}

model_eval_status: success

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name meseca-05062024-v1-v3-mkmlizer
Waiting for job on meseca-05062024-v1-v3-mkmlizer to finish
meseca-05062024-v1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-05062024-v1-v3-mkmlizer: ║     _____            __           __                                ║
meseca-05062024-v1-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-05062024-v1-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-05062024-v1-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-05062024-v1-v3-mkmlizer: ║       /___/                                                         ║
meseca-05062024-v1-v3-mkmlizer: ║                                                                     ║
meseca-05062024-v1-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-05062024-v1-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-05062024-v1-v3-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-05062024-v1-v3-mkmlizer: ║                                                                     ║
meseca-05062024-v1-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-05062024-v1-v3-mkmlizer: ║  belonging to:                                                      ║
meseca-05062024-v1-v3-mkmlizer: ║                                                                     ║
meseca-05062024-v1-v3-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-05062024-v1-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-05062024-v1-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-05062024-v1-v3-mkmlizer: ║                                                                     ║
meseca-05062024-v1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-05062024-v1-v3-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-05062024-v1-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-05062024-v1-v3-mkmlizer: Downloaded to shared memory in 37.828s
meseca-05062024-v1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-05062024-v1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-05062024-v1-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 9/291 [00:00<00:03, 89.36it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:02, 95.40it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:02, 94.99it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 86.09it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:02, 85.75it/s]
Loading 0:  20%|█▉        | 57/291 [00:00<00:02, 85.37it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:02, 85.13it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:02, 86.32it/s]
Loading 0:  29%|██▉       | 84/291 [00:01<00:04, 47.15it/s]
Loading 0:  32%|███▏      | 93/291 [00:01<00:03, 54.80it/s]
Loading 0:  35%|███▌      | 102/291 [00:01<00:03, 61.95it/s]
Loading 0:  38%|███▊      | 111/291 [00:01<00:02, 68.07it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:02, 72.99it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:02, 76.46it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 77.70it/s]
Loading 0:  51%|█████     | 149/291 [00:02<00:01, 78.76it/s]
Loading 0:  55%|█████▌    | 161/291 [00:02<00:01, 88.70it/s]
Loading 0:  59%|█████▉    | 172/291 [00:02<00:01, 94.36it/s]
Loading 0:  63%|██████▎   | 182/291 [00:02<00:01, 92.23it/s]
Loading 0:  66%|██████▌   | 192/291 [00:02<00:01, 55.13it/s]
Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 63.39it/s]
Loading 0:  73%|███████▎  | 212/291 [00:02<00:01, 70.77it/s]
Loading 0:  78%|███████▊  | 228/291 [00:03<00:00, 86.11it/s]
Loading 0:  82%|████████▏ | 238/291 [00:03<00:00, 82.87it/s]
Loading 0:  85%|████████▌ | 248/291 [00:03<00:00, 80.15it/s]
Loading 0:  91%|█████████ | 264/291 [00:03<00:00, 95.26it/s]
Loading 0:  95%|█████████▍| 275/291 [00:03<00:00, 86.60it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00,  6.54it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-05062024-v1-v3-mkmlizer: quantized model in 24.890s
meseca-05062024-v1-v3-mkmlizer: Processed model meseca/05062024-v1 in 65.308s
meseca-05062024-v1-v3-mkmlizer: creating bucket guanaco-mkml-models
meseca-05062024-v1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-05062024-v1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-05062024-v1-v3
meseca-05062024-v1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-05062024-v1-v3/config.json
meseca-05062024-v1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-05062024-v1-v3/tokenizer_config.json
meseca-05062024-v1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-05062024-v1-v3/special_tokens_map.json
meseca-05062024-v1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-05062024-v1-v3/tokenizer.json
meseca-05062024-v1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-05062024-v1-v3/flywheel_model.0.safetensors
meseca-05062024-v1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-05062024-v1-v3-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-05062024-v1-v3-mkmlizer:   warnings.warn(
meseca-05062024-v1-v3-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-05062024-v1-v3-mkmlizer:   warnings.warn(
meseca-05062024-v1-v3-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-05062024-v1-v3-mkmlizer:   warnings.warn(
meseca-05062024-v1-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()
meseca-05062024-v1-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-05062024-v1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-05062024-v1-v3-mkmlizer: Saving duration: 0.453s
meseca-05062024-v1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.298s
meseca-05062024-v1-v3-mkmlizer: creating bucket guanaco-reward-models
meseca-05062024-v1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-05062024-v1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-05062024-v1-v3_reward
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/config.json
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/tokenizer_config.json
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/vocab.json
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/merges.txt
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/special_tokens_map.json
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/tokenizer.json
meseca-05062024-v1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-05062024-v1-v3_reward/reward.tensors
Job meseca-05062024-v1-v3-mkmlizer completed after 113.62s with status: succeeded
Stopping job with name meseca-05062024-v1-v3-mkmlizer
Pipeline stage MKMLizer completed in 116.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service meseca-05062024-v1-v3
Waiting for inference service meseca-05062024-v1-v3 to be ready
Inference service meseca-05062024-v1-v3 ready after 50.40684986114502s
Pipeline stage ISVCDeployer completed in 57.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.09037709236145s
Received healthy response to inference request in 1.1513140201568604s
Received healthy response to inference request in 1.2994310855865479s
Received healthy response to inference request in 1.2552757263183594s
Received healthy response to inference request in 1.314093828201294s
5 requests
0 failed requests
5th percentile: 1.1721063613891602
10th percentile: 1.19289870262146
20th percentile: 1.2344833850860595
30th percentile: 1.2641067981719971
40th percentile: 1.2817689418792724
50th percentile: 1.2994310855865479
60th percentile: 1.3052961826324463
70th percentile: 1.3111612796783447
80th percentile: 1.4693504810333253
90th percentile: 1.7798637866973879
95th percentile: 1.9351204395294188
99th percentile: 2.059325761795044
mean time: 1.4220983505249023
Pipeline stage StressChecker completed in 7.71s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
meseca-05062024-v1_v3 status is now deployed due to DeploymentManager action
meseca-05062024-v1_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-05062024-v1_v3
Running pipeline stage ISVCDeleter
Checking if service meseca-05062024-v1-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-05062024-v1-v3/config.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-05062024-v1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.16s
meseca-05062024-v1_v3 status is now torndown due to DeploymentManager action