meseca-07062024-c1

submission_id: meseca-07062024-c1_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1208.33

display_name: test_meseca_07062024-c1

family_friendly_score: 0.0

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

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 60, '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/07062024-c1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: meseca/07062024-c1

model_name: test_meseca_07062024-c1

model_num_parameters: 8030261248.0

model_repo: meseca/07062024-c1

model_size: 8B

num_battles: 17492

num_wins: 9347

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: 2024-07-01T03:23:23+00:00

us_pacific_date: 2024-06-30

win_ratio: 0.5343585639149325

Resubmit model

Running pipeline stage MKMLizer
Starting job with name meseca-07062024-c1-v1-mkmlizer
Waiting for job on meseca-07062024-c1-v1-mkmlizer to finish
meseca-07062024-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-07062024-c1-v1-mkmlizer: ║     _____            __           __                                ║
meseca-07062024-c1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-07062024-c1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-07062024-c1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-07062024-c1-v1-mkmlizer: ║       /___/                                                         ║
meseca-07062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-07062024-c1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-07062024-c1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-07062024-c1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-07062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-07062024-c1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-07062024-c1-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-07062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-07062024-c1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-07062024-c1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-07062024-c1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-07062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-07062024-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-07062024-c1-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-07062024-c1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-07062024-c1-v1-mkmlizer: Downloaded to shared memory in 70.561s
meseca-07062024-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-07062024-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-07062024-c1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:11,  2.32s/it]
Loading 0:   1%|          | 3/291 [00:04<06:44,  1.40s/it]
Loading 0:   5%|▌         | 15/291 [00:04<00:49,  5.54it/s]
Loading 0:   8%|▊         | 23/291 [00:04<00:28,  9.48it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:11, 21.62it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:08, 27.44it/s]
Loading 0:  22%|██▏       | 63/291 [00:05<00:06, 35.66it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:04, 50.39it/s]
Loading 0:  31%|███       | 89/291 [00:05<00:03, 56.09it/s]
Loading 0:  36%|███▌      | 104/291 [00:05<00:02, 63.31it/s]
Loading 0:  42%|████▏     | 122/291 [00:05<00:02, 83.01it/s]
Loading 0:  46%|████▌     | 134/291 [00:06<00:01, 80.83it/s]
Loading 0:  50%|████▉     | 145/291 [00:06<00:01, 79.11it/s]
Loading 0:  56%|█████▌    | 162/291 [00:06<00:01, 98.06it/s]
Loading 0:  60%|█████▉    | 174/291 [00:06<00:01, 93.19it/s]
Loading 0:  64%|██████▎   | 185/291 [00:06<00:01, 83.89it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:00, 104.08it/s]
Loading 0:  74%|███████▍  | 215/291 [00:06<00:00, 94.62it/s] 
Loading 0:  78%|███████▊  | 226/291 [00:07<00:00, 86.64it/s]
Loading 0:  82%|████████▏ | 240/291 [00:07<00:00, 96.87it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 88.56it/s]
Loading 0:  91%|█████████▏| 266/291 [00:07<00:00, 86.59it/s]
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 105.92it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-07062024-c1-v1-mkmlizer: quantized model in 23.641s
meseca-07062024-c1-v1-mkmlizer: Processed model meseca/07062024-c1 in 96.666s
meseca-07062024-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-07062024-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-07062024-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-07062024-c1-v1
meseca-07062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-07062024-c1-v1/config.json
meseca-07062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-07062024-c1-v1/tokenizer_config.json
meseca-07062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-07062024-c1-v1/special_tokens_map.json
meseca-07062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-07062024-c1-v1/tokenizer.json
meseca-07062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-07062024-c1-v1/flywheel_model.0.safetensors
meseca-07062024-c1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-07062024-c1-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-07062024-c1-v1-mkmlizer:   warnings.warn(
meseca-07062024-c1-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-07062024-c1-v1-mkmlizer:   warnings.warn(
meseca-07062024-c1-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-07062024-c1-v1-mkmlizer:   warnings.warn(
meseca-07062024-c1-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-07062024-c1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-07062024-c1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-07062024-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-07062024-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-07062024-c1-v1_reward
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/config.json
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/special_tokens_map.json
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/tokenizer_config.json
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/merges.txt
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/vocab.json
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/tokenizer.json
meseca-07062024-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-07062024-c1-v1_reward/reward.tensors
Job meseca-07062024-c1-v1-mkmlizer completed after 124.53s with status: succeeded
Stopping job with name meseca-07062024-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.24s
Running pipeline stage ISVCDeployer
Creating inference service meseca-07062024-c1-v1
Waiting for inference service meseca-07062024-c1-v1 to be ready
Connection pool is full, discarding connection: %s
Inference service meseca-07062024-c1-v1 ready after 110.65663576126099s
Pipeline stage ISVCDeployer completed in 117.76s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2122628688812256s
Received healthy response to inference request in 1.28303861618042s
Received healthy response to inference request in 1.2493746280670166s
Received healthy response to inference request in 1.2601838111877441s
Received healthy response to inference request in 1.278806209564209s
5 requests
0 failed requests
5th percentile: 1.2515364646911622
10th percentile: 1.2536983013153076
20th percentile: 1.2580219745635985
30th percentile: 1.263908290863037
40th percentile: 1.271357250213623
50th percentile: 1.278806209564209
60th percentile: 1.2804991722106933
70th percentile: 1.2821921348571776
80th percentile: 1.4688834667205812
90th percentile: 1.8405731678009034
95th percentile: 2.0264180183410643
99th percentile: 2.175093898773193
mean time: 1.456733226776123
Pipeline stage StressChecker completed in 8.01s
meseca-07062024-c1_v1 status is now deployed due to DeploymentManager action
meseca-07062024-c1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-07062024-c1_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-07062024-c1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-07062024-c1-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-07062024-c1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-07062024-c1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-07062024-c1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-07062024-c1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-07062024-c1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-07062024-c1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-07062024-c1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-07062024-c1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-07062024-c1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-07062024-c1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-07062024-c1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.30s
meseca-07062024-c1_v1 status is now torndown due to DeploymentManager action