developer_uid: nguyenzzz
submission_id: meseca-02072024-v1-2e_v1
model_name: meseca-02072024-v1-2e_v1
model_group: meseca/02072024-v1-2e
status: torndown
timestamp: 2024-07-03T02:21:18+00:00
num_battles: 12702
num_wins: 6482
celo_rating: 1189.99
family_friendly_score: 0.0
submission_type: basic
model_repo: meseca/02072024-v1-2e
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: meseca-02072024-v1-2e_v1
is_internal_developer: False
language_model: meseca/02072024-v1-2e
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-02
win_ratio: 0.5103133364824437
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, '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-v1-2e-v1-mkmlizer
Waiting for job on meseca-02072024-v1-2e-v1-mkmlizer to finish
meseca-02072024-v1-2e-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-02072024-v1-2e-v1-mkmlizer: ║     _____            __           __                                ║
meseca-02072024-v1-2e-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-02072024-v1-2e-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-02072024-v1-2e-v1-mkmlizer: ║       /___/                                                         ║
meseca-02072024-v1-2e-v1-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-02072024-v1-2e-v1-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-02072024-v1-2e-v1-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-02072024-v1-2e-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-02072024-v1-2e-v1-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-02072024-v1-2e-v1-mkmlizer: Downloaded to shared memory in 38.566s
meseca-02072024-v1-2e-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-02072024-v1-2e-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-02072024-v1-2e-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 106.27it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:02, 91.00it/s] 
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 110.04it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:02, 107.58it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 113.90it/s]
Loading 0:  27%|██▋       | 78/291 [00:00<00:02, 106.15it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:03, 64.17it/s] 
Loading 0:  35%|███▌      | 102/291 [00:01<00:02, 74.79it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:02, 75.79it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:02, 78.44it/s]
Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 92.64it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 94.95it/s]
Loading 0:  54%|█████▍    | 158/291 [00:01<00:01, 90.82it/s]
Loading 0:  58%|█████▊    | 170/291 [00:01<00:01, 96.99it/s]
Loading 0:  62%|██████▏   | 181/291 [00:02<00:01, 88.79it/s]
Loading 0:  66%|██████▌   | 191/291 [00:02<00:01, 61.05it/s]
Loading 0:  69%|██████▉   | 201/291 [00:02<00:01, 68.34it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 74.78it/s]
Loading 0:  77%|███████▋  | 224/291 [00:02<00:00, 86.74it/s]
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 96.01it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 94.64it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 106.64it/s]
Loading 0:  95%|█████████▍| 276/291 [00:03<00:00, 103.07it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00,  6.10it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-02072024-v1-2e-v1-mkmlizer: quantized model in 23.061s
meseca-02072024-v1-2e-v1-mkmlizer: Processed model meseca/02072024-v1-2e in 61.628s
meseca-02072024-v1-2e-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-02072024-v1-2e-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-02072024-v1-2e-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-02072024-v1-2e-v1
meseca-02072024-v1-2e-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v1/config.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v1/special_tokens_map.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v1/tokenizer.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v1/tokenizer_config.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-02072024-v1-2e-v1/flywheel_model.0.safetensors
meseca-02072024-v1-2e-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-02072024-v1-2e-v1-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-v1-2e-v1-mkmlizer:   warnings.warn(
meseca-02072024-v1-2e-v1-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-v1-2e-v1-mkmlizer:   warnings.warn(
meseca-02072024-v1-2e-v1-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-v1-2e-v1-mkmlizer:   warnings.warn(
meseca-02072024-v1-2e-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-02072024-v1-2e-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-02072024-v1-2e-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-02072024-v1-2e-v1-mkmlizer: Saving duration: 0.256s
meseca-02072024-v1-2e-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.402s
meseca-02072024-v1-2e-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-02072024-v1-2e-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-02072024-v1-2e-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/tokenizer_config.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/special_tokens_map.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/merges.txt
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/config.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/vocab.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/tokenizer.json
meseca-02072024-v1-2e-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-02072024-v1-2e-v1_reward/reward.tensors
Job meseca-02072024-v1-2e-v1-mkmlizer completed after 93.93s with status: succeeded
Stopping job with name meseca-02072024-v1-2e-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meseca-02072024-v1-2e-v1
Waiting for inference service meseca-02072024-v1-2e-v1 to be ready
Inference service meseca-02072024-v1-2e-v1 ready after 40.23903727531433s
Pipeline stage ISVCDeployer completed in 47.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.045980215072632s
Received healthy response to inference request in 1.2049996852874756s
Received healthy response to inference request in 1.2167000770568848s
Received healthy response to inference request in 1.2379908561706543s
Received healthy response to inference request in 1.2618117332458496s
5 requests
0 failed requests
5th percentile: 1.2073397636413574
10th percentile: 1.2096798419952393
20th percentile: 1.214359998703003
30th percentile: 1.2209582328796387
40th percentile: 1.2294745445251465
50th percentile: 1.2379908561706543
60th percentile: 1.2475192070007324
70th percentile: 1.2570475578308105
80th percentile: 1.418645429611206
90th percentile: 1.732312822341919
95th percentile: 1.8891465187072753
99th percentile: 2.0146134757995604
mean time: 1.3934965133666992
Pipeline stage StressChecker completed in 7.65s
meseca-02072024-v1-2e_v1 status is now deployed due to DeploymentManager action
meseca-02072024-v1-2e_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-02072024-v1-2e_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-02072024-v1-2e-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-02072024-v1-2e-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-02072024-v1-2e-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
meseca-02072024-v1-2e_v1 status is now torndown due to DeploymentManager action