meseca-02072024-v1

developer_uid: nguyenzzz

submission_id: meseca-02072024-v1_v2

model_name: meseca-02072024-v1_v2

model_group: meseca/02072024-v1

status: torndown

timestamp: 2024-07-03T02:39:20+00:00

num_battles: 11025

num_wins: 5755

celo_rating: 1197.52

family_friendly_score: 0.0

submission_type: basic

model_repo: meseca/02072024-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-02072024-v1_v2

is_internal_developer: False

language_model: meseca/02072024-v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-02

win_ratio: 0.5219954648526077

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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\nCurrently, your role is {bot_name}, described in detail below. As {bot_name}, continue the narrative exchange 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}

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-02072024-v1-v2-mkmlizer
Waiting for job on meseca-02072024-v1-v2-mkmlizer to finish
meseca-02072024-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-02072024-v1-v2-mkmlizer: ║     _____            __           __                                ║
meseca-02072024-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-02072024-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-02072024-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-02072024-v1-v2-mkmlizer: ║       /___/                                                         ║
meseca-02072024-v1-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-02072024-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-02072024-v1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-02072024-v1-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-02072024-v1-v2-mkmlizer: ║  belonging to:                                                      ║
meseca-02072024-v1-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-02072024-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-02072024-v1-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-02072024-v1-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-02072024-v1-v2-mkmlizer: Downloaded to shared memory in 20.126s
meseca-02072024-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-02072024-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-02072024-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 116.92it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 128.33it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 124.51it/s]
Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 129.53it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 126.58it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 130.55it/s]
Loading 0:  33%|███▎      | 95/291 [00:01<00:02, 66.19it/s] 
Loading 0:  38%|███▊      | 111/291 [00:01<00:02, 83.15it/s]
Loading 0:  42%|████▏     | 123/291 [00:01<00:01, 89.55it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 102.98it/s]
Loading 0:  52%|█████▏    | 151/291 [00:01<00:01, 107.34it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 113.31it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 120.15it/s]
Loading 0:  66%|██████▋   | 193/291 [00:02<00:01, 73.45it/s] 
Loading 0:  71%|███████   | 207/291 [00:02<00:00, 85.29it/s]
Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 93.18it/s]
Loading 0:  81%|████████  | 235/291 [00:02<00:00, 105.91it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 105.94it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 118.76it/s]
Loading 0:  96%|█████████▌| 278/291 [00:02<00:00, 119.18it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00,  8.06it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-02072024-v1-v2-mkmlizer: quantized model in 23.704s
meseca-02072024-v1-v2-mkmlizer: Processed model meseca/02072024-v1 in 43.831s
meseca-02072024-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-02072024-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-02072024-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-02072024-v1-v2
meseca-02072024-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-02072024-v1-v2/special_tokens_map.json
meseca-02072024-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-02072024-v1-v2/tokenizer_config.json
meseca-02072024-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-02072024-v1-v2/config.json
meseca-02072024-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-02072024-v1-v2/tokenizer.json
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
meseca-02072024-v1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-02072024-v1-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.
meseca-02072024-v1-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-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`.
meseca-02072024-v1-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-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.
meseca-02072024-v1-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-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.
meseca-02072024-v1-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-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()
meseca-02072024-v1-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-02072024-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-02072024-v1-v2-mkmlizer: Saving duration: 0.405s
meseca-02072024-v1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.323s
meseca-02072024-v1-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-02072024-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-02072024-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-02072024-v1-v2_reward
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/config.json
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/tokenizer_config.json
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/special_tokens_map.json
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/merges.txt
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/vocab.json
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/tokenizer.json
meseca-02072024-v1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-02072024-v1-v2_reward/reward.tensors
Job meseca-02072024-v1-v2-mkmlizer completed after 73.16s with status: succeeded
Stopping job with name meseca-02072024-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meseca-02072024-v1-v2
Waiting for inference service meseca-02072024-v1-v2 to be ready
Inference service meseca-02072024-v1-v2 ready after 30.192718267440796s
Pipeline stage ISVCDeployer completed in 37.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1344308853149414s
Received healthy response to inference request in 1.3001539707183838s
Received healthy response to inference request in 1.2550873756408691s
Received healthy response to inference request in 1.348780632019043s
Received healthy response to inference request in 1.3025476932525635s
5 requests
0 failed requests
5th percentile: 1.264100694656372
10th percentile: 1.273114013671875
20th percentile: 1.291140651702881
30th percentile: 1.3006327152252197
40th percentile: 1.3015902042388916
50th percentile: 1.3025476932525635
60th percentile: 1.3210408687591553
70th percentile: 1.339534044265747
80th percentile: 1.5059106826782227
90th percentile: 1.8201707839965822
95th percentile: 1.9773008346557617
99th percentile: 2.1030048751831054
mean time: 1.46820011138916
Pipeline stage StressChecker completed in 8.08s
meseca-02072024-v1_v2 status is now deployed due to DeploymentManager action
meseca-02072024-v1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-02072024-v1_v2
Running pipeline stage ISVCDeleter
Checking if service meseca-02072024-v1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.76s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-02072024-v1-v2/config.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-02072024-v1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.41s
meseca-02072024-v1_v2 status is now torndown due to DeploymentManager action