v000000-l3-8b-serpent-test002

developer_uid: v000000

submission_id: v000000-l3-8b-serpent-test002_v1

model_name: v000000-l3-8b-serpent-test002_v1

model_group: v000000/L3-8B-Serpent-te

status: torndown

timestamp: 2024-06-12T18:56:41+00:00

num_battles: 6759

num_wins: 3377

celo_rating: 1195.24

family_friendly_score: 0.0

submission_type: basic

model_repo: v000000/L3-8B-Serpent-test002

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-test002_v1

is_internal_developer: False

language_model: v000000/L3-8B-Serpent-test002

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-12

win_ratio: 0.49963012279923064

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-test002-v1-mkmlizer
Waiting for job on v000000-l3-8b-serpent-test002-v1-mkmlizer to finish
v000000-l3-8b-serpent-test002-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║     _____            __           __                                ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║       /___/                                                         ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  belonging to:                                                      ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ║                                                                     ║
v000000-l3-8b-serpent-test002-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
v000000-l3-8b-serpent-test002-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-test002-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
v000000-l3-8b-serpent-test002-v1-mkmlizer: Downloaded to shared memory in 19.111s
v000000-l3-8b-serpent-test002-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-l3-8b-serpent-test002-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-l3-8b-serpent-test002-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:55,  2.27s/it]
Loading 0:   5%|▌         | 16/291 [00:04<00:58,  4.70it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.56it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 20.89it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.49it/s]
Loading 0:  28%|██▊       | 81/291 [00:05<00:05, 36.54it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.32it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.35it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 80.85it/s]
Loading 0:  51%|█████     | 148/291 [00:05<00:01, 93.06it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 68.01it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 83.43it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 98.24it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 111.70it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 124.40it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 135.11it/s]
Loading 0:  93%|█████████▎| 272/291 [00:07<00:00, 89.17it/s] 
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 96.26it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-l3-8b-serpent-test002-v1-mkmlizer: quantized model in 24.220s
v000000-l3-8b-serpent-test002-v1-mkmlizer: Processed model v000000/L3-8B-Serpent-test002 in 46.010s
v000000-l3-8b-serpent-test002-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-l3-8b-serpent-test002-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-l3-8b-serpent-test002-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-l3-8b-serpent-test002-v1
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test002-v1/special_tokens_map.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test002-v1/tokenizer_config.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test002-v1/config.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-l3-8b-serpent-test002-v1/tokenizer.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-l3-8b-serpent-test002-v1/flywheel_model.0.safetensors
v000000-l3-8b-serpent-test002-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-l3-8b-serpent-test002-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-test002-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpent-test002-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-test002-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpent-test002-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-test002-v1-mkmlizer:   warnings.warn(
v000000-l3-8b-serpent-test002-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-test002-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-l3-8b-serpent-test002-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-l3-8b-serpent-test002-v1-mkmlizer: Saving duration: 0.403s
v000000-l3-8b-serpent-test002-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.038s
v000000-l3-8b-serpent-test002-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-l3-8b-serpent-test002-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-l3-8b-serpent-test002-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/config.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/tokenizer_config.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/vocab.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/merges.txt
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/special_tokens_map.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/tokenizer.json
v000000-l3-8b-serpent-test002-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/v000000-l3-8b-serpent-test002-v1_reward/reward.tensors
Job v000000-l3-8b-serpent-test002-v1-mkmlizer completed after 73.5s with status: succeeded
Stopping job with name v000000-l3-8b-serpent-test002-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service v000000-l3-8b-serpent-test002-v1
Waiting for inference service v000000-l3-8b-serpent-test002-v1 to be ready
Inference service v000000-l3-8b-serpent-test002-v1 ready after 70.44239401817322s
Pipeline stage ISVCDeployer completed in 76.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.198667526245117s
Received healthy response to inference request in 1.2643318176269531s
Received healthy response to inference request in 1.237196683883667s
Received healthy response to inference request in 1.2324302196502686s
Received healthy response to inference request in 1.2365641593933105s
5 requests
0 failed requests
5th percentile: 1.233257007598877
10th percentile: 1.2340837955474853
20th percentile: 1.2357373714447022
30th percentile: 1.2366906642913817
40th percentile: 1.2369436740875244
50th percentile: 1.237196683883667
60th percentile: 1.2480507373809815
70th percentile: 1.258904790878296
80th percentile: 1.451198959350586
90th percentile: 1.8249332427978517
95th percentile: 2.011800384521484
99th percentile: 2.1612940979003907
mean time: 1.4338380813598632
Pipeline stage StressChecker completed in 7.74s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
v000000-l3-8b-serpent-test002_v1 status is now deployed due to DeploymentManager action
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
v000000-l3-8b-serpent-test002_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-l3-8b-serpent-test002_v1
Running pipeline stage ISVCDeleter
Checking if service v000000-l3-8b-serpent-test002-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.54s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-l3-8b-serpent-test002-v1/config.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test002-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test002-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test002-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-l3-8b-serpent-test002-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-l3-8b-serpent-test002-v1_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test002-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test002-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test002-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test002-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test002-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-l3-8b-serpent-test002-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.27s
v000000-l3-8b-serpent-test002_v1 status is now torndown due to DeploymentManager action