submission_id: meseca-05062024-v2-2e_v1
developer_uid: nguyenzzz
best_of: 16
celo_rating: 1183.7
display_name: meseca-05062024-v2-2e_v1
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.13, '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}
is_internal_developer: False
language_model: meseca/05062024-v2-2e
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: meseca/05062024-v2-2e
model_name: meseca-05062024-v2-2e_v1
model_num_parameters: 8030261248.0
model_repo: meseca/05062024-v2-2e
model_size: 8B
num_battles: 32003
num_wins: 16490
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-06T17:03:16+00:00
us_pacific_date: 2024-06-06
win_ratio: 0.5152641939818142
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-05062024-v2-2e-v1-mkmlizer
Waiting for job on meseca-05062024-v2-2e-v1-mkmlizer to finish
Stopping job with name meseca-05062024-v2-2e-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name meseca-05062024-v2-2e-v1-mkmlizer
Waiting for job on meseca-05062024-v2-2e-v1-mkmlizer to finish
meseca-05062024-v2-2e-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-05062024-v2-2e-v1-mkmlizer: ║     _____            __           __                                ║
meseca-05062024-v2-2e-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-05062024-v2-2e-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-05062024-v2-2e-v1-mkmlizer: ║       /___/                                                         ║
meseca-05062024-v2-2e-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-05062024-v2-2e-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-05062024-v2-2e-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-05062024-v2-2e-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-05062024-v2-2e-v1-mkmlizer: ║                                                                     ║
meseca-05062024-v2-2e-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-05062024-v2-2e-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-05062024-v2-2e-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-05062024-v2-2e-v1-mkmlizer: Downloaded to shared memory in 47.907s
meseca-05062024-v2-2e-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-05062024-v2-2e-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-05062024-v2-2e-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 135.86it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 152.84it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 160.52it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 162.88it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:02, 87.09it/s] 
Loading 0:  35%|███▌      | 103/291 [00:00<00:01, 103.93it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 118.08it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 128.53it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:00, 137.72it/s]
Loading 0:  60%|█████▉    | 174/291 [00:01<00:00, 145.74it/s]
Loading 0:  65%|██████▌   | 190/291 [00:01<00:01, 93.54it/s] 
Loading 0:  71%|███████   | 206/291 [00:01<00:00, 105.88it/s]
Loading 0:  77%|███████▋  | 223/291 [00:01<00:00, 119.41it/s]
Loading 0:  82%|████████▏ | 239/291 [00:01<00:00, 126.78it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 137.67it/s]
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 145.57it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 10.08it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-05062024-v2-2e-v1-mkmlizer: quantized model in 22.402s
meseca-05062024-v2-2e-v1-mkmlizer: Processed model meseca/05062024-v2-2e in 72.773s
meseca-05062024-v2-2e-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-05062024-v2-2e-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-05062024-v2-2e-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-05062024-v2-2e-v1
meseca-05062024-v2-2e-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-05062024-v2-2e-v1/config.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-05062024-v2-2e-v1/tokenizer_config.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-05062024-v2-2e-v1/special_tokens_map.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-05062024-v2-2e-v1/tokenizer.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-05062024-v2-2e-v1/flywheel_model.0.safetensors
meseca-05062024-v2-2e-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-05062024-v2-2e-v1-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-v2-2e-v1-mkmlizer:   warnings.warn(
meseca-05062024-v2-2e-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-05062024-v2-2e-v1-mkmlizer:   warnings.warn(
meseca-05062024-v2-2e-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-05062024-v2-2e-v1-mkmlizer:   warnings.warn(
meseca-05062024-v2-2e-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-05062024-v2-2e-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-05062024-v2-2e-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-05062024-v2-2e-v1-mkmlizer: Saving duration: 0.416s
meseca-05062024-v2-2e-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.998s
meseca-05062024-v2-2e-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-05062024-v2-2e-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-05062024-v2-2e-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/config.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/tokenizer_config.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/merges.txt
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/special_tokens_map.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/vocab.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/tokenizer.json
meseca-05062024-v2-2e-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-05062024-v2-2e-v1_reward/reward.tensors
Job meseca-05062024-v2-2e-v1-mkmlizer completed after 104.21s with status: succeeded
Stopping job with name meseca-05062024-v2-2e-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-05062024-v2-2e-v1
Waiting for inference service meseca-05062024-v2-2e-v1 to be ready
Inference service meseca-05062024-v2-2e-v1 ready after 30.19501566886902s
Pipeline stage ISVCDeployer completed in 36.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3029847145080566s
Received healthy response to inference request in 1.3456900119781494s
Received healthy response to inference request in 1.298945665359497s
Received healthy response to inference request in 1.2432358264923096s
Received healthy response to inference request in 1.3477709293365479s
5 requests
0 failed requests
5th percentile: 1.254377794265747
10th percentile: 1.2655197620391845
20th percentile: 1.2878036975860596
30th percentile: 1.3082945346832275
40th percentile: 1.3269922733306885
50th percentile: 1.3456900119781494
60th percentile: 1.3465223789215088
70th percentile: 1.3473547458648683
80th percentile: 1.5388136863708497
90th percentile: 1.9208992004394532
95th percentile: 2.111941957473755
99th percentile: 2.2647761631011964
mean time: 1.507725429534912
Pipeline stage StressChecker completed in 8.22s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
meseca-05062024-v2-2e_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
meseca-05062024-v2-2e_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-05062024-v2-2e_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-05062024-v2-2e-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.31s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-05062024-v2-2e-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v2-2e-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-05062024-v2-2e-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v2-2e-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-05062024-v2-2e-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-05062024-v2-2e-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v2-2e-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-05062024-v2-2e-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-05062024-v2-2e-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v2-2e-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v2-2e-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-05062024-v2-2e-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.51s
meseca-05062024-v2-2e_v1 status is now torndown due to DeploymentManager action