hastagaras-sycho-8b-l3-rp

developer_uid: Hastagaras

submission_id: hastagaras-sycho-8b-l3-rp_v2

model_name: tst

model_group: Hastagaras/Sycho-8B-L3-R

status: torndown

timestamp: 2024-06-17T08:50:42+00:00

num_battles: 24979

num_wins: 13722

celo_rating: 1215.09

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/Sycho-8B-L3-RP

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: tst

is_internal_developer: False

language_model: Hastagaras/Sycho-8B-L3-RP

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-17

win_ratio: 0.5493414468153248

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}

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 hastagaras-sycho-8b-l3-rp-v2-mkmlizer
Waiting for job on hastagaras-sycho-8b-l3-rp-v2-mkmlizer to finish
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sycho-8b-l3-rp-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-sycho-8b-l3-rp-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Downloaded to shared memory in 47.207s
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 8/291 [00:00<00:03, 74.37it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 77.35it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:03, 77.03it/s]
Loading 0:  12%|█▏        | 36/291 [00:00<00:02, 91.53it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:02, 94.41it/s]
Loading 0:  19%|█▉        | 56/291 [00:00<00:02, 95.46it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:02, 91.60it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 84.86it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:04, 44.27it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:03, 51.56it/s]
Loading 0:  36%|███▌      | 104/291 [00:01<00:03, 60.29it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 65.89it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:02, 70.64it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:02, 74.29it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 87.46it/s]
Loading 0:  54%|█████▎    | 156/291 [00:02<00:01, 91.95it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 90.72it/s]
Loading 0:  62%|██████▏   | 180/291 [00:02<00:01, 98.81it/s]
Loading 0:  66%|██████▌   | 191/291 [00:02<00:01, 57.98it/s]
Loading 0:  68%|██████▊   | 199/291 [00:02<00:01, 61.05it/s]
Loading 0:  71%|███████   | 207/291 [00:02<00:01, 64.48it/s]
Loading 0:  74%|███████▍  | 216/291 [00:02<00:01, 69.32it/s]
Loading 0:  77%|███████▋  | 225/291 [00:03<00:00, 73.28it/s]
Loading 0:  80%|████████  | 234/291 [00:03<00:00, 77.12it/s]
Loading 0:  84%|████████▎ | 243/291 [00:03<00:00, 80.16it/s]
Loading 0:  87%|████████▋ | 252/291 [00:03<00:00, 81.86it/s]
Loading 0:  90%|████████▉ | 261/291 [00:03<00:00, 82.85it/s]
Loading 0:  93%|█████████▎| 271/291 [00:03<00:00, 87.64it/s]
Loading 0:  96%|█████████▌| 280/291 [00:03<00:00, 88.05it/s]
Loading 0:  99%|█████████▉| 289/291 [00:09<00:00,  4.75it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: quantized model in 26.132s
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Processed model Hastagaras/Sycho-8B-L3-RP in 76.263s
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v2
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v2/config.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v2/special_tokens_map.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v2/tokenizer_config.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v2/tokenizer.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sycho-8b-l3-rp-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-sycho-8b-l3-rp-v2-mkmlizer:   warnings.warn(
hastagaras-sycho-8b-l3-rp-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-sycho-8b-l3-rp-v2-mkmlizer:   warnings.warn(
hastagaras-sycho-8b-l3-rp-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-sycho-8b-l3-rp-v2-mkmlizer:   warnings.warn(
hastagaras-sycho-8b-l3-rp-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-sycho-8b-l3-rp-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Saving duration: 0.523s
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.401s
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/config.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/special_tokens_map.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/tokenizer_config.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/vocab.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/merges.txt
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/tokenizer.json
hastagaras-sycho-8b-l3-rp-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v2_reward/reward.tensors
Job hastagaras-sycho-8b-l3-rp-v2-mkmlizer completed after 113.35s with status: succeeded
Stopping job with name hastagaras-sycho-8b-l3-rp-v2-mkmlizer
Pipeline stage MKMLizer completed in 116.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sycho-8b-l3-rp-v2
Waiting for inference service hastagaras-sycho-8b-l3-rp-v2 to be ready
Inference service hastagaras-sycho-8b-l3-rp-v2 ready after 110.53812861442566s
Pipeline stage ISVCDeployer completed in 117.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1389849185943604s
Received healthy response to inference request in 1.3319344520568848s
Received healthy response to inference request in 1.323486328125s
Received healthy response to inference request in 1.2875709533691406s
Received healthy response to inference request in 1.3474571704864502s
5 requests
0 failed requests
5th percentile: 1.2947540283203125
10th percentile: 1.3019371032714844
20th percentile: 1.3163032531738281
30th percentile: 1.325175952911377
40th percentile: 1.328555202484131
50th percentile: 1.3319344520568848
60th percentile: 1.338143539428711
70th percentile: 1.344352626800537
80th percentile: 1.5057627201080324
90th percentile: 1.8223738193511965
95th percentile: 1.9806793689727782
99th percentile: 2.107323808670044
mean time: 1.4858867645263671
Pipeline stage StressChecker completed in 8.03s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-sycho-8b-l3-rp_v2 status is now deployed due to DeploymentManager action
hastagaras-sycho-8b-l3-rp_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sycho-8b-l3-rp_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sycho-8b-l3-rp-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sycho-8b-l3-rp-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.99s
hastagaras-sycho-8b-l3-rp_v2 status is now torndown due to DeploymentManager action