developer_uid: v000000
submission_id: v000000-l3-8b-serpent-test001_v1
model_name: v000000-l3-8b-serpent-test001_v1
model_group: v000000/L3-8B-Serpent-te
status: torndown
timestamp: 2024-06-12T18:56:11+00:00
num_battles: 34220
num_wins: 18130
celo_rating: 1204.23
family_friendly_score: 0.0
submission_type: basic
model_repo: v000000/L3-8B-Serpent-test001
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: v000000-l3-8b-serpent-test001_v1
is_internal_developer: False
language_model: v000000/L3-8B-Serpent-test001
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-12
win_ratio: 0.5298071303331385
generation_params: {'temperature': 1.22, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_of_text|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
model_eval_status: success
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 v000000-l3-8b-serpent-test001-v1-mkmlizer
Waiting for job on v000000-l3-8b-serpent-test001-v1-mkmlizer to finish
Stopping job with name v000000-l3-8b-serpent-test001-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name v000000-l3-8b-serpent-test001-v1-mkmlizer
Waiting for job on v000000-l3-8b-serpent-test001-v1-mkmlizer to finish
v000000-l3-8b-serpent-test001-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test001-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-serpent-test001-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.
v000000-l3-8b-serpent-test001-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-serpent-test001-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:52,  2.47s/it]
Loading 0:   5%|▌         | 15/291 [00:05<01:08,  4.05it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:23, 10.82it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:12, 19.55it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:09, 23.85it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 32.11it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 46.25it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 61.77it/s]
Loading 0:  45%|████▌     | 132/291 [00:06<00:02, 78.03it/s]
Loading 0:  52%|█████▏    | 150/291 [00:06<00:01, 93.31it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 70.67it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 86.00it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 101.26it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 115.23it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 126.65it/s]
Loading 0:  88%|████████▊ | 256/291 [00:07<00:00, 136.80it/s]
Loading 0:  93%|█████████▎| 272/291 [00:07<00:00, 90.09it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00, 102.34it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-serpent-test001-v1-mkmlizer: quantized model in 23.844s
v000000-l3-8b-serpent-test001-v1-mkmlizer: Processed model v000000/L3-8B-Serpent-test001 in 60.452s
v000000-l3-8b-serpent-test001-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-serpent-test001-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-serpent-test001-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-serpent-test001-v1
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test001-v1/tokenizer_config.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test001-v1/special_tokens_map.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test001-v1/config.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test001-v1/tokenizer.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-serpent-test001-v1/flywheel_model.0.safetensors
v000000-l3-8b-serpent-test001-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-serpent-test001-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.
v000000-l3-8b-serpent-test001-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpent-test001-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.
v000000-l3-8b-serpent-test001-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpent-test001-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.
v000000-l3-8b-serpent-test001-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpent-test001-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()
v000000-l3-8b-serpent-test001-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-serpent-test001-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-serpent-test001-v1-mkmlizer: Saving duration: 0.446s
v000000-l3-8b-serpent-test001-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.576s
v000000-l3-8b-serpent-test001-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-serpent-test001-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-serpent-test001-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/config.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/tokenizer_config.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/merges.txt
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/special_tokens_map.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/vocab.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/tokenizer.json
v000000-l3-8b-serpent-test001-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-serpent-test001-v1_reward/reward.tensors
Job v000000-l3-8b-serpent-test001-v1-mkmlizer completed after 93.62s with status: succeeded
Stopping job with name v000000-l3-8b-serpent-test001-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-serpent-test001-v1
Waiting for inference service v000000-l3-8b-serpent-test001-v1 to be ready
Inference service v000000-l3-8b-serpent-test001-v1 ready after 100.62726855278015s
Pipeline stage ISVCDeployer completed in 108.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.182260274887085s
Received healthy response to inference request in 1.252941370010376s
Received healthy response to inference request in 1.247380018234253s
Received healthy response to inference request in 1.252345085144043s
Received healthy response to inference request in 1.2514269351959229s
5 requests
0 failed requests
5th percentile: 1.2481894016265869
10th percentile: 1.2489987850189208
20th percentile: 1.250617551803589
30th percentile: 1.251610565185547
40th percentile: 1.2519778251647948
50th percentile: 1.252345085144043
60th percentile: 1.2525835990905763
70th percentile: 1.2528221130371093
80th percentile: 1.438805150985718
90th percentile: 1.8105327129364015
95th percentile: 1.996396493911743
99th percentile: 2.1450875186920166
mean time: 1.437270736694336
Pipeline stage StressChecker completed in 7.86s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
v000000-l3-8b-serpent-test001_v1 status is now deployed due to DeploymentManager action
v000000-l3-8b-serpent-test001_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-serpent-test001_v1
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-serpent-test001-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-serpent-test001-v1/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test001-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test001-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test001-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test001-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-serpent-test001-v1_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test001-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test001-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test001-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test001-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test001-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test001-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.24s
v000000-l3-8b-serpent-test001_v1 status is now torndown due to DeploymentManager action