meseca-02072024-v1-2e

developer_uid: nguyenzzz

submission_id: meseca-02072024-v1-2e_v2

model_name: meseca-02072024-v1-2e_v2

model_group: meseca/02072024-v1-2e

status: torndown

timestamp: 2024-07-03T03:11:56+00:00

num_battles: 12747

num_wins: 6583

celo_rating: 1191.84

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: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: meseca-02072024-v1-2e_v2

is_internal_developer: False

language_model: meseca/02072024-v1-2e

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-02

win_ratio: 0.5164352396642348

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-v1-2e-v2-mkmlizer
Waiting for job on meseca-02072024-v1-2e-v2-mkmlizer to finish
meseca-02072024-v1-2e-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-02072024-v1-2e-v2-mkmlizer: ║     _____            __           __                                ║
meseca-02072024-v1-2e-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-02072024-v1-2e-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-02072024-v1-2e-v2-mkmlizer: ║       /___/                                                         ║
meseca-02072024-v1-2e-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-02072024-v1-2e-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  belonging to:                                                      ║
meseca-02072024-v1-2e-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-02072024-v1-2e-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-02072024-v1-2e-v2-mkmlizer: ║                                                                     ║
meseca-02072024-v1-2e-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-02072024-v1-2e-v2-mkmlizer: Downloaded to shared memory in 21.485s
meseca-02072024-v1-2e-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-02072024-v1-2e-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
meseca-02072024-v1-2e-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 115.89it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 105.69it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:02, 113.90it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:02, 104.23it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:02, 112.00it/s]
Loading 0:  27%|██▋       | 78/291 [00:00<00:02, 104.80it/s]
Loading 0:  31%|███       | 89/291 [00:01<00:02, 71.26it/s] 
Loading 0:  35%|███▌      | 102/291 [00:01<00:02, 81.27it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:02, 84.38it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:01, 87.88it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 101.22it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 96.53it/s] 
Loading 0:  57%|█████▋    | 165/291 [00:01<00:01, 108.10it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:01, 111.43it/s]
Loading 0:  66%|██████▌   | 191/291 [00:02<00:01, 79.57it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 82.65it/s]
Loading 0:  74%|███████▎  | 214/291 [00:02<00:00, 90.91it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 99.12it/s]
Loading 0:  82%|████████▏ | 239/291 [00:02<00:00, 95.70it/s]
Loading 0:  87%|████████▋ | 252/291 [00:02<00:00, 103.92it/s]
Loading 0:  91%|█████████ | 264/291 [00:02<00:00, 107.11it/s]
Loading 0:  95%|█████████▍| 276/291 [00:02<00:00, 102.81it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00,  6.67it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-02072024-v1-2e-v2-mkmlizer: quantized model in 21.072s
meseca-02072024-v1-2e-v2-mkmlizer: Processed model meseca/02072024-v1-2e in 42.557s
meseca-02072024-v1-2e-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-02072024-v1-2e-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-02072024-v1-2e-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-02072024-v1-2e-v2
meseca-02072024-v1-2e-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v2/special_tokens_map.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v2/config.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v2/tokenizer_config.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-02072024-v1-2e-v2/tokenizer.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-02072024-v1-2e-v2/flywheel_model.0.safetensors
meseca-02072024-v1-2e-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-02072024-v1-2e-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-v1-2e-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-2e-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-v1-2e-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-2e-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-v1-2e-v2-mkmlizer:   warnings.warn(
meseca-02072024-v1-2e-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-v1-2e-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-02072024-v1-2e-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-02072024-v1-2e-v2-mkmlizer: Saving duration: 0.251s
meseca-02072024-v1-2e-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.101s
meseca-02072024-v1-2e-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-02072024-v1-2e-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-02072024-v1-2e-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/config.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/tokenizer_config.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/vocab.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/special_tokens_map.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/tokenizer.json
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/merges.txt
meseca-02072024-v1-2e-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-02072024-v1-2e-v2_reward/reward.tensors
Job meseca-02072024-v1-2e-v2-mkmlizer completed after 83.86s with status: succeeded
Stopping job with name meseca-02072024-v1-2e-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service meseca-02072024-v1-2e-v2
Waiting for inference service meseca-02072024-v1-2e-v2 to be ready
Inference service meseca-02072024-v1-2e-v2 ready after 201.232834815979s
Pipeline stage ISVCDeployer completed in 208.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.139230728149414s
Received healthy response to inference request in 1.2740166187286377s
Received healthy response to inference request in 1.2726762294769287s
Received healthy response to inference request in 1.343090295791626s
Received healthy response to inference request in 1.2814526557922363s
5 requests
0 failed requests
5th percentile: 1.2729443073272706
10th percentile: 1.2732123851776123
20th percentile: 1.2737485408782958
30th percentile: 1.2755038261413574
40th percentile: 1.278478240966797
50th percentile: 1.2814526557922363
60th percentile: 1.3061077117919921
70th percentile: 1.330762767791748
80th percentile: 1.5023183822631838
90th percentile: 1.8207745552062988
95th percentile: 1.9800026416778562
99th percentile: 2.1073851108551027
mean time: 1.4620933055877685
Pipeline stage StressChecker completed in 7.99s
meseca-02072024-v1-2e_v2 status is now deployed due to DeploymentManager action
meseca-02072024-v1-2e_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-02072024-v1-2e_v2
Running pipeline stage ISVCDeleter
Checking if service meseca-02072024-v1-2e-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-02072024-v1-2e-v2/config.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-02072024-v1-2e-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-02072024-v1-2e-v2_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-02072024-v1-2e-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.60s
meseca-02072024-v1-2e_v2 status is now torndown due to DeploymentManager action