hastagaras-sciemet-8b-l3_4340

developer_uid: Hastagaras

submission_id: hastagaras-sciemet-8b-l3_4340_v2

model_name: t

model_group: Hastagaras/Sciemet-8B-L3

status: torndown

timestamp: 2024-06-16T19:22:47+00:00

num_battles: 25733

num_wins: 14031

celo_rating: 1215.4

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Sciemet-8B-L3-MK.II

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: t

is_internal_developer: False

language_model: Hastagaras/Sciemet-8B-L3-MK.II

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-16

win_ratio: 0.5452531768546225

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 45, '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'}

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-sciemet-8b-l3-4340-v2-mkmlizer
Waiting for job on hastagaras-sciemet-8b-l3-4340-v2-mkmlizer to finish
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sciemet-8b-l3-4340-v2-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.
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Downloaded to shared memory in 44.340s
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 8/291 [00:00<00:03, 78.69it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:02, 91.09it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:02, 96.48it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 94.26it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:02, 94.74it/s]
Loading 0:  22%|██▏       | 63/291 [00:00<00:02, 104.39it/s]
Loading 0:  26%|██▌       | 75/291 [00:00<00:02, 104.08it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:03, 54.05it/s] 
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 65.38it/s]
Loading 0:  37%|███▋      | 108/291 [00:01<00:02, 72.31it/s]
Loading 0:  41%|████      | 120/291 [00:01<00:02, 79.28it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 82.87it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 87.06it/s]
Loading 0:  53%|█████▎    | 154/291 [00:01<00:01, 100.49it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:01, 99.61it/s] 
Loading 0:  62%|██████▏   | 179/291 [00:02<00:01, 106.37it/s]
Loading 0:  66%|██████▌   | 191/291 [00:02<00:01, 64.92it/s] 
Loading 0:  69%|██████▉   | 201/291 [00:02<00:01, 69.22it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 72.53it/s]
Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 76.56it/s]
Loading 0:  81%|████████  | 235/291 [00:02<00:00, 91.39it/s]
Loading 0:  85%|████████▍ | 246/291 [00:02<00:00, 92.10it/s]
Loading 0:  88%|████████▊ | 257/291 [00:03<00:00, 87.31it/s]
Loading 0:  92%|█████████▏| 269/291 [00:03<00:00, 94.92it/s]
Loading 0:  96%|█████████▌| 280/291 [00:03<00:00, 98.70it/s]
Loading 0: 100%|██████████| 291/291 [00:09<00:00,  6.02it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: quantized model in 25.329s
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Processed model Hastagaras/Sciemet-8B-L3-MK.II in 72.572s
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v2
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v2/config.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v2/special_tokens_map.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v2/tokenizer_config.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v2/tokenizer.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v2/flywheel_model.0.safetensors
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sciemet-8b-l3-4340-v2-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.
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-4340-v2-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.
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-4340-v2-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.
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-4340-v2-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()
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Saving duration: 0.444s
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.182s
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/config.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/special_tokens_map.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/tokenizer_config.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/merges.txt
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/vocab.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/tokenizer.json
hastagaras-sciemet-8b-l3-4340-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v2_reward/reward.tensors
Job hastagaras-sciemet-8b-l3-4340-v2-mkmlizer completed after 113.47s with status: succeeded
Stopping job with name hastagaras-sciemet-8b-l3-4340-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sciemet-8b-l3-4340-v2
Waiting for inference service hastagaras-sciemet-8b-l3-4340-v2 to be ready
Inference service hastagaras-sciemet-8b-l3-4340-v2 ready after 30.243956804275513s
Pipeline stage ISVCDeployer completed in 37.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1241984367370605s
Received healthy response to inference request in 1.3697819709777832s
Received healthy response to inference request in 1.3326866626739502s
Received healthy response to inference request in 1.2728145122528076s
Received healthy response to inference request in 1.3608341217041016s
5 requests
0 failed requests
5th percentile: 1.2847889423370362
10th percentile: 1.2967633724212646
20th percentile: 1.3207122325897216
30th percentile: 1.3383161544799804
40th percentile: 1.349575138092041
50th percentile: 1.3608341217041016
60th percentile: 1.3644132614135742
70th percentile: 1.3679924011230469
80th percentile: 1.5206652641296388
90th percentile: 1.8224318504333497
95th percentile: 1.973315143585205
99th percentile: 2.0940217781066894
mean time: 1.4920631408691407
Pipeline stage StressChecker completed in 8.10s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-sciemet-8b-l3_4340_v2 status is now deployed due to DeploymentManager action
hastagaras-sciemet-8b-l3_4340_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sciemet-8b-l3_4340_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sciemet-8b-l3-4340-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.18s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-4340-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.34s
hastagaras-sciemet-8b-l3_4340_v2 status is now torndown due to DeploymentManager action