developer_uid: Hastagaras
submission_id: hastagaras-sycho-8b-l3-rp_v3
model_name: tst
model_group: Hastagaras/Sycho-8B-L3-R
status: torndown
timestamp: 2024-06-17T09:43:59+00:00
num_battles: 29189
num_wins: 15562
celo_rating: 1210.64
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: 0.5331460481688307
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.065, 'top_k': 35, '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-v3-mkmlizer
Waiting for job on hastagaras-sycho-8b-l3-rp-v3-mkmlizer to finish
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ║                                                                     ║
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sycho-8b-l3-rp-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.
hastagaras-sycho-8b-l3-rp-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Downloaded to shared memory in 51.326s
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 123.59it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 149.45it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 157.82it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 159.59it/s]
Loading 0:  29%|██▉       | 84/291 [00:00<00:02, 86.93it/s] 
Loading 0:  35%|███▌      | 102/291 [00:00<00:01, 104.54it/s]
Loading 0:  41%|████      | 120/291 [00:00<00:01, 119.96it/s]
Loading 0:  47%|████▋     | 138/291 [00:01<00:01, 133.17it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:00, 142.90it/s]
Loading 0:  59%|█████▉    | 173/291 [00:01<00:00, 145.48it/s]
Loading 0:  65%|██████▍   | 189/291 [00:01<00:01, 90.28it/s] 
Loading 0:  71%|███████   | 206/291 [00:01<00:00, 104.94it/s]
Loading 0:  77%|███████▋  | 223/291 [00:01<00:00, 118.48it/s]
Loading 0:  82%|████████▏ | 239/291 [00:01<00:00, 127.36it/s]
Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 137.28it/s]
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 146.32it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00,  9.81it/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-v3-mkmlizer: quantized model in 22.722s
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Processed model Hastagaras/Sycho-8B-L3-RP in 76.526s
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v3
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v3/special_tokens_map.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v3/config.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v3/tokenizer_config.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v3/tokenizer.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sycho-8b-l3-rp-v3/flywheel_model.0.safetensors
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sycho-8b-l3-rp-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.
hastagaras-sycho-8b-l3-rp-v3-mkmlizer:   warnings.warn(
hastagaras-sycho-8b-l3-rp-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.
hastagaras-sycho-8b-l3-rp-v3-mkmlizer:   warnings.warn(
hastagaras-sycho-8b-l3-rp-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.
hastagaras-sycho-8b-l3-rp-v3-mkmlizer:   warnings.warn(
hastagaras-sycho-8b-l3-rp-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()
hastagaras-sycho-8b-l3-rp-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Saving duration: 0.468s
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.331s
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward/config.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward/tokenizer_config.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward/vocab.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward/special_tokens_map.json
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward/merges.txt
hastagaras-sycho-8b-l3-rp-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sycho-8b-l3-rp-v3_reward/tokenizer.json
Job hastagaras-sycho-8b-l3-rp-v3-mkmlizer completed after 113.7s with status: succeeded
Stopping job with name hastagaras-sycho-8b-l3-rp-v3-mkmlizer
Pipeline stage MKMLizer completed in 116.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sycho-8b-l3-rp-v3
Waiting for inference service hastagaras-sycho-8b-l3-rp-v3 to be ready
Inference service hastagaras-sycho-8b-l3-rp-v3 ready after 30.166940689086914s
Pipeline stage ISVCDeployer completed in 36.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2973930835723877s
Received healthy response to inference request in 1.331583023071289s
Received healthy response to inference request in 1.2997994422912598s
Received healthy response to inference request in 1.2785871028900146s
Received healthy response to inference request in 1.3226814270019531s
5 requests
0 failed requests
5th percentile: 1.2828295707702637
10th percentile: 1.2870720386505128
20th percentile: 1.2955569744110107
30th percentile: 1.3043758392333984
40th percentile: 1.3135286331176759
50th percentile: 1.3226814270019531
60th percentile: 1.3262420654296876
70th percentile: 1.3298027038574218
80th percentile: 1.524745035171509
90th percentile: 1.9110690593719484
95th percentile: 2.1042310714721677
99th percentile: 2.2587606811523435
mean time: 1.5060088157653808
Pipeline stage StressChecker completed in 8.48s
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
hastagaras-sycho-8b-l3-rp_v3 status is now deployed due to DeploymentManager action
hastagaras-sycho-8b-l3-rp_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sycho-8b-l3-rp_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sycho-8b-l3-rp-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.27s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sycho-8b-l3-rp-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sycho-8b-l3-rp-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sycho-8b-l3-rp-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.20s
hastagaras-sycho-8b-l3-rp_v3 status is now torndown due to DeploymentManager action