hastagaras-bnsca8bl3

developer_uid: Hastagaras

submission_id: hastagaras-bnsca8bl3_v2

model_name: sssffttt

model_group: Hastagaras/bnsca8bl3

status: torndown

timestamp: 2024-06-13T08:28:29+00:00

num_battles: 12548

num_wins: 6550

celo_rating: 1196.97

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/bnsca8bl3

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: sssffttt

is_internal_developer: False

language_model: Hastagaras/bnsca8bl3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-13

win_ratio: 0.5219955371373924

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 8, '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", '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-bnsca8bl3-v2-mkmlizer
Waiting for job on hastagaras-bnsca8bl3-v2-mkmlizer to finish
hastagaras-bnsca8bl3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-bnsca8bl3-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║                                                                     ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║                                                                     ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║                                                                     ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-bnsca8bl3-v2-mkmlizer: ║                                                                     ║
hastagaras-bnsca8bl3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-bnsca8bl3-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-bnsca8bl3-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-bnsca8bl3-v2-mkmlizer: Downloaded to shared memory in 16.730s
hastagaras-bnsca8bl3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-bnsca8bl3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-bnsca8bl3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 120.23it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 146.38it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 154.64it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 157.91it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 81.76it/s] 
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 89.16it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 107.10it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 120.92it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 131.94it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 141.23it/s]
Loading 0:  64%|██████▍   | 187/291 [00:01<00:01, 93.26it/s] 
Loading 0:  69%|██████▉   | 202/291 [00:01<00:00, 101.48it/s]
Loading 0:  76%|███████▌  | 220/291 [00:01<00:00, 115.60it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 127.03it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 137.90it/s]
Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 146.58it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.00it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-bnsca8bl3-v2-mkmlizer: quantized model in 22.979s
hastagaras-bnsca8bl3-v2-mkmlizer: Processed model Hastagaras/bnsca8bl3 in 42.337s
hastagaras-bnsca8bl3-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-bnsca8bl3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-bnsca8bl3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v2
hastagaras-bnsca8bl3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v2/special_tokens_map.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v2/config.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v2/tokenizer_config.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v2/tokenizer.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-bnsca8bl3-v2/flywheel_model.0.safetensors
hastagaras-bnsca8bl3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-bnsca8bl3-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-bnsca8bl3-v2-mkmlizer:   warnings.warn(
hastagaras-bnsca8bl3-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-bnsca8bl3-v2-mkmlizer:   warnings.warn(
hastagaras-bnsca8bl3-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-bnsca8bl3-v2-mkmlizer:   warnings.warn(
hastagaras-bnsca8bl3-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-bnsca8bl3-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-bnsca8bl3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-bnsca8bl3-v2-mkmlizer: Saving duration: 0.420s
hastagaras-bnsca8bl3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.806s
hastagaras-bnsca8bl3-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-bnsca8bl3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-bnsca8bl3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/config.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/special_tokens_map.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/tokenizer_config.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/merges.txt
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/vocab.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/tokenizer.json
hastagaras-bnsca8bl3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-bnsca8bl3-v2_reward/reward.tensors
Job hastagaras-bnsca8bl3-v2-mkmlizer completed after 62.61s with status: succeeded
Stopping job with name hastagaras-bnsca8bl3-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-bnsca8bl3-v2
Waiting for inference service hastagaras-bnsca8bl3-v2 to be ready
Inference service hastagaras-bnsca8bl3-v2 ready after 30.20753788948059s
Pipeline stage ISVCDeployer completed in 38.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.035817861557007s
Received healthy response to inference request in 1.2113988399505615s
Received healthy response to inference request in 1.182387351989746s
Received healthy response to inference request in 1.1738080978393555s
Received healthy response to inference request in 1.1918985843658447s
5 requests
0 failed requests
5th percentile: 1.1755239486694335
10th percentile: 1.1772397994995116
20th percentile: 1.180671501159668
30th percentile: 1.1842895984649657
40th percentile: 1.1880940914154052
50th percentile: 1.1918985843658447
60th percentile: 1.1996986865997314
70th percentile: 1.2074987888336182
80th percentile: 1.3762826442718508
90th percentile: 1.7060502529144288
95th percentile: 1.8709340572357176
99th percentile: 2.002841100692749
mean time: 1.3590621471405029
Pipeline stage StressChecker completed in 7.46s
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-bnsca8bl3_v2 status is now deployed due to DeploymentManager action
hastagaras-bnsca8bl3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-bnsca8bl3_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-bnsca8bl3-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-bnsca8bl3-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-bnsca8bl3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-bnsca8bl3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-bnsca8bl3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-bnsca8bl3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-bnsca8bl3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-bnsca8bl3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-bnsca8bl3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-bnsca8bl3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-bnsca8bl3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-bnsca8bl3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-bnsca8bl3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.14s
hastagaras-bnsca8bl3_v2 status is now torndown due to DeploymentManager action