submission_id: alsebay-smaid-v0-1_v3
developer_uid: Alsebay
best_of: 4
celo_rating: 1193.94
display_name: alsebay-smaid-v0-1_v2
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': 1.15, 'top_p': 0.5, 'min_p': 0.075, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Alsebay/SMaid-v0.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Alsebay/SMaid-v0.1
model_name: alsebay-smaid-v0-1_v2
model_num_parameters: 8030261248.0
model_repo: Alsebay/SMaid-v0.1
model_size: 8B
num_battles: 17555
num_wins: 8990
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: 2024-06-22T22:32:26+00:00
us_pacific_date: 2024-06-22
win_ratio: 0.5121048134434634
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alsebay-smaid-v0-1-v3-mkmlizer
Waiting for job on alsebay-smaid-v0-1-v3-mkmlizer to finish
alsebay-smaid-v0-1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alsebay-smaid-v0-1-v3-mkmlizer: ║     _____            __           __                                ║
alsebay-smaid-v0-1-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alsebay-smaid-v0-1-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alsebay-smaid-v0-1-v3-mkmlizer: ║       /___/                                                         ║
alsebay-smaid-v0-1-v3-mkmlizer: ║                                                                     ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  https://mk1.ai                                                     ║
alsebay-smaid-v0-1-v3-mkmlizer: ║                                                                     ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  belonging to:                                                      ║
alsebay-smaid-v0-1-v3-mkmlizer: ║                                                                     ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  Chai Research Corp.                                                ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alsebay-smaid-v0-1-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
alsebay-smaid-v0-1-v3-mkmlizer: ║                                                                     ║
alsebay-smaid-v0-1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alsebay-smaid-v0-1-v3-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.
alsebay-smaid-v0-1-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
alsebay-smaid-v0-1-v3-mkmlizer: Downloaded to shared memory in 25.991s
alsebay-smaid-v0-1-v3-mkmlizer: quantizing model to /dev/shm/model_cache
alsebay-smaid-v0-1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alsebay-smaid-v0-1-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<12:26,  2.58s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:16,  3.60it/s]
Loading 0:   8%|▊         | 22/291 [00:05<00:43,  6.13it/s]
Loading 0:  13%|█▎        | 37/291 [00:05<00:19, 13.01it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:11, 21.01it/s]
Loading 0:  21%|██▏       | 62/291 [00:05<00:09, 25.36it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:05, 37.72it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:03, 53.23it/s]
Loading 0:  37%|███▋      | 108/291 [00:06<00:03, 51.45it/s]
Loading 0:  42%|████▏     | 123/291 [00:06<00:02, 64.26it/s]
Loading 0:  48%|████▊     | 140/291 [00:06<00:01, 81.41it/s]
Loading 0:  53%|█████▎    | 153/291 [00:06<00:01, 70.09it/s]
Loading 0:  58%|█████▊    | 168/291 [00:07<00:01, 82.65it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 74.22it/s]
Loading 0:  68%|██████▊   | 199/291 [00:07<00:01, 87.17it/s]
Loading 0:  73%|███████▎  | 213/291 [00:07<00:00, 96.70it/s]
Loading 0:  77%|███████▋  | 225/291 [00:07<00:00, 79.17it/s]
Loading 0:  82%|████████▏ | 240/291 [00:07<00:00, 90.14it/s]
Loading 0:  88%|████████▊ | 256/291 [00:07<00:00, 104.59it/s]
Loading 0:  92%|█████████▏| 269/291 [00:08<00:00, 80.07it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:08<00:00, 92.59it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alsebay-smaid-v0-1-v3-mkmlizer: quantized model in 20.671s
alsebay-smaid-v0-1-v3-mkmlizer: Processed model Alsebay/SMaid-v0.1 in 47.787s
alsebay-smaid-v0-1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alsebay-smaid-v0-1-v3/flywheel_model.0.safetensors
alsebay-smaid-v0-1-v3-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.
alsebay-smaid-v0-1-v3-mkmlizer:   warnings.warn(
alsebay-smaid-v0-1-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
alsebay-smaid-v0-1-v3-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.
alsebay-smaid-v0-1-v3-mkmlizer:   warnings.warn(
alsebay-smaid-v0-1-v3-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.
alsebay-smaid-v0-1-v3-mkmlizer:   warnings.warn(
alsebay-smaid-v0-1-v3-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()
alsebay-smaid-v0-1-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
alsebay-smaid-v0-1-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alsebay-smaid-v0-1-v3-mkmlizer: Saving duration: 0.239s
alsebay-smaid-v0-1-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.403s
alsebay-smaid-v0-1-v3-mkmlizer: creating bucket guanaco-reward-models
alsebay-smaid-v0-1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
alsebay-smaid-v0-1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/config.json
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/special_tokens_map.json
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/tokenizer_config.json
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/vocab.json
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/merges.txt
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/tokenizer.json
alsebay-smaid-v0-1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/alsebay-smaid-v0-1-v3_reward/reward.tensors
Job alsebay-smaid-v0-1-v3-mkmlizer completed after 74.26s with status: succeeded
Stopping job with name alsebay-smaid-v0-1-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service alsebay-smaid-v0-1-v3
Waiting for inference service alsebay-smaid-v0-1-v3 to be ready
Connection pool is full, discarding connection: %s
Inference service alsebay-smaid-v0-1-v3 ready after 40.19167876243591s
Pipeline stage ISVCDeployer completed in 45.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0752179622650146s
Received healthy response to inference request in 1.129040002822876s
Received healthy response to inference request in 1.1480977535247803s
Received healthy response to inference request in 1.1388754844665527s
Received healthy response to inference request in 1.127410888671875s
5 requests
0 failed requests
5th percentile: 1.127736711502075
10th percentile: 1.1280625343322754
20th percentile: 1.1287141799926759
30th percentile: 1.1310070991516112
40th percentile: 1.134941291809082
50th percentile: 1.1388754844665527
60th percentile: 1.1425643920898438
70th percentile: 1.1462532997131347
80th percentile: 1.3335217952728273
90th percentile: 1.704369878768921
95th percentile: 1.8897939205169676
99th percentile: 2.038133153915405
mean time: 1.3237284183502198
Pipeline stage StressChecker completed in 7.38s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
alsebay-smaid-v0-1_v3 status is now deployed due to DeploymentManager action
alsebay-smaid-v0-1_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of alsebay-smaid-v0-1_v3
Running pipeline stage ISVCDeleter
Checking if service alsebay-smaid-v0-1-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 1.81s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key alsebay-smaid-v0-1-v3/config.json from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key alsebay-smaid-v0-1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key alsebay-smaid-v0-1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key alsebay-smaid-v0-1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.38s
alsebay-smaid-v0-1_v3 status is now torndown due to DeploymentManager action