meseca-20062024-c1

developer_uid: nguyenzzz

submission_id: meseca-20062024-c1_v1

model_name: meseca-20062024-c1_v1

model_group: meseca/20062024-c1

status: torndown

timestamp: 2024-06-27T15:33:33+00:00

num_battles: 19727

num_wins: 11042

celo_rating: 1214.57

family_friendly_score: 0.0

submission_type: basic

model_repo: meseca/20062024-c1

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-20062024-c1_v1

is_internal_developer: False

language_model: meseca/20062024-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-27

win_ratio: 0.5597404572413444

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', '<|eot_id|>'], '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\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-20062024-c1-v1-mkmlizer
Waiting for job on meseca-20062024-c1-v1-mkmlizer to finish
meseca-20062024-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-20062024-c1-v1-mkmlizer: ║     _____            __           __                                ║
meseca-20062024-c1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-20062024-c1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-20062024-c1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-20062024-c1-v1-mkmlizer: ║       /___/                                                         ║
meseca-20062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-20062024-c1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-20062024-c1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-20062024-c1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-20062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-20062024-c1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-20062024-c1-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-20062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-20062024-c1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-20062024-c1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-20062024-c1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-20062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-20062024-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-20062024-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-20062024-c1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-20062024-c1-v1-mkmlizer: Downloaded to shared memory in 33.979s
meseca-20062024-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-20062024-c1-v1-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
meseca-20062024-c1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:02, 111.00it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:02, 112.22it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:01, 127.64it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:01, 125.11it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 127.65it/s]
Loading 0:  27%|██▋       | 80/291 [00:00<00:01, 123.57it/s]
Loading 0:  32%|███▏      | 93/291 [00:01<00:02, 67.15it/s] 
Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 75.19it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 92.06it/s]
Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 104.88it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 105.45it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 117.27it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 122.90it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 73.29it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 88.83it/s]
Loading 0:  76%|███████▋  | 222/291 [00:02<00:00, 94.30it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 105.21it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 116.50it/s]
Loading 0:  92%|█████████▏| 269/291 [00:02<00:00, 119.73it/s]
Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 120.43it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-20062024-c1-v1-mkmlizer: quantized model in 23.336s
meseca-20062024-c1-v1-mkmlizer: Processed model meseca/20062024-c1 in 59.948s
meseca-20062024-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-20062024-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-20062024-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-20062024-c1-v1
meseca-20062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-20062024-c1-v1/special_tokens_map.json
meseca-20062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-20062024-c1-v1/tokenizer_config.json
meseca-20062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-20062024-c1-v1/config.json
meseca-20062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-20062024-c1-v1/tokenizer.json
meseca-20062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-20062024-c1-v1/flywheel_model.0.safetensors
meseca-20062024-c1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-20062024-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-20062024-c1-v1-mkmlizer:   warnings.warn(
meseca-20062024-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-20062024-c1-v1-mkmlizer:   warnings.warn(
meseca-20062024-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-20062024-c1-v1-mkmlizer:   warnings.warn(
meseca-20062024-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-20062024-c1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-20062024-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-20062024-c1-v1-mkmlizer: Saving duration: 0.428s
meseca-20062024-c1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.203s
meseca-20062024-c1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-20062024-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-20062024-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-20062024-c1-v1_reward
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/config.json
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/special_tokens_map.json
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/tokenizer_config.json
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/merges.txt
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/vocab.json
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/tokenizer.json
meseca-20062024-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-20062024-c1-v1_reward/reward.tensors
Job meseca-20062024-c1-v1-mkmlizer completed after 95.16s with status: succeeded
Stopping job with name meseca-20062024-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service meseca-20062024-c1-v1
Waiting for inference service meseca-20062024-c1-v1 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service meseca-20062024-c1-v1 ready after 40.268052101135254s
Pipeline stage ISVCDeployer completed in 47.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.180490016937256s
Received healthy response to inference request in 1.3386657238006592s
Received healthy response to inference request in 1.5650362968444824s
Received healthy response to inference request in 1.2897157669067383s
Received healthy response to inference request in 1.3908226490020752s
5 requests
0 failed requests
5th percentile: 1.2995057582855225
10th percentile: 1.3092957496643067
20th percentile: 1.328875732421875
30th percentile: 1.3490971088409425
40th percentile: 1.3699598789215088
50th percentile: 1.3908226490020752
60th percentile: 1.460508108139038
70th percentile: 1.530193567276001
80th percentile: 1.688127040863037
90th percentile: 1.9343085289001465
95th percentile: 2.057399272918701
99th percentile: 2.155871868133545
mean time: 1.5529460906982422
Pipeline stage StressChecker completed in 8.56s
meseca-20062024-c1_v1 status is now deployed due to DeploymentManager action
meseca-20062024-c1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-20062024-c1_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-20062024-c1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-20062024-c1-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-20062024-c1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-20062024-c1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-20062024-c1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-20062024-c1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-20062024-c1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-20062024-c1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-20062024-c1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-20062024-c1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-20062024-c1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-20062024-c1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-20062024-c1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.36s
meseca-20062024-c1_v1 status is now torndown due to DeploymentManager action