hastagaras-sciemet-8b-l3_4340

developer_uid: Hastagaras

submission_id: hastagaras-sciemet-8b-l3_4340_v1

model_name: t

model_group: Hastagaras/Sciemet-8B-L3

status: torndown

timestamp: 2024-06-16T19:21:58+00:00

num_battles: 25352

num_wins: 13791

celo_rating: 1214.67

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: 0.5439807510255601

generation_params: {'temperature': 1.15, 'top_p': 0.95, 'min_p': 0.08, 'top_k': 65, '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-sciemet-8b-l3-4340-v1-mkmlizer
Waiting for job on hastagaras-sciemet-8b-l3-4340-v1-mkmlizer to finish
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sciemet-8b-l3-4340-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.
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Downloaded to shared memory in 45.602s
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:05, 49.24it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:03, 87.78it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:02, 101.74it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 94.65it/s] 
Loading 0:  20%|█▉        | 57/291 [00:00<00:02, 108.98it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:02, 101.08it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:03, 54.54it/s] 
Loading 0:  32%|███▏      | 93/291 [00:01<00:03, 61.11it/s]
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 68.12it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 74.37it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 90.31it/s]
Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 89.56it/s]
Loading 0:  54%|█████▎    | 156/291 [00:01<00:01, 101.47it/s]
Loading 0:  57%|█████▋    | 167/291 [00:01<00:01, 96.73it/s] 
Loading 0:  62%|██████▏   | 180/291 [00:02<00:01, 104.48it/s]
Loading 0:  66%|██████▌   | 191/291 [00:02<00:01, 64.20it/s] 
Loading 0:  69%|██████▉   | 201/291 [00:02<00:01, 70.23it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:01, 75.45it/s]
Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 80.42it/s]
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 94.81it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 92.57it/s]
Loading 0:  90%|████████▉ | 261/291 [00:03<00:00, 101.29it/s]
Loading 0:  94%|█████████▍| 273/291 [00:03<00:00, 104.45it/s]
Loading 0:  98%|█████████▊| 284/291 [00:03<00:00, 102.51it/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-v1-mkmlizer: quantized model in 26.188s
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Processed model Hastagaras/Sciemet-8B-L3-MK.II in 74.437s
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v1
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v1/config.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v1/special_tokens_map.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v1/tokenizer_config.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-4340-v1/tokenizer.json
hastagaras-sciemet-8b-l3-4340-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()
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Saving duration: 0.472s
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.699s
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: WARNING: Retrying failed request: /?location ([Errno 110] Connection timed out)
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: WARNING: Waiting 3 sec...
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward/special_tokens_map.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward/tokenizer_config.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward/config.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward/merges.txt
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward/vocab.json
hastagaras-sciemet-8b-l3-4340-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-4340-v1_reward/tokenizer.json
Job hastagaras-sciemet-8b-l3-4340-v1-mkmlizer completed after 245.8s with status: succeeded
Stopping job with name hastagaras-sciemet-8b-l3-4340-v1-mkmlizer
Pipeline stage MKMLizer completed in 248.58s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sciemet-8b-l3-4340-v1
Waiting for inference service hastagaras-sciemet-8b-l3-4340-v1 to be ready
Inference service hastagaras-sciemet-8b-l3-4340-v1 ready after 40.311293840408325s
Pipeline stage ISVCDeployer completed in 47.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2120189666748047s
Received healthy response to inference request in 1.3511569499969482s
Received healthy response to inference request in 1.3127737045288086s
Received healthy response to inference request in 1.2642953395843506s
Received healthy response to inference request in 1.36568284034729s
5 requests
0 failed requests
5th percentile: 1.273991012573242
10th percentile: 1.2836866855621338
20th percentile: 1.303078031539917
30th percentile: 1.3204503536224366
40th percentile: 1.3358036518096923
50th percentile: 1.3511569499969482
60th percentile: 1.356967306137085
70th percentile: 1.3627776622772216
80th percentile: 1.5349500656127932
90th percentile: 1.873484516143799
95th percentile: 2.0427517414093015
99th percentile: 2.178165521621704
mean time: 1.5011855602264403
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-sciemet-8b-l3_4340_v1 status is now deployed due to DeploymentManager action
hastagaras-sciemet-8b-l3_4340_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sciemet-8b-l3_4340_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sciemet-8b-l3-4340-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.19s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-4340-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-4340-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.31s
hastagaras-sciemet-8b-l3_4340_v1 status is now torndown due to DeploymentManager action