hastagaras-sciemet-8b-l3-mk-i

developer_uid: Hastagaras

submission_id: hastagaras-sciemet-8b-l3-mk-i_v2

model_name: 2

model_group: Hastagaras/Sciemet-8B-L3

status: torndown

timestamp: 2024-06-15T04:48:19+00:00

num_battles: 16464

num_wins: 8949

celo_rating: 1212.44

family_friendly_score: 0.0

submission_type: basic

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

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: 2

is_internal_developer: False

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

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-14

win_ratio: 0.5435495626822158

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 80, '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-mk-i-v2-mkmlizer
Waiting for job on hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer to finish
Stopping job with name hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer
Waiting for job on hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer to finish
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ║                                                                     ║
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-sciemet-8b-l3-mk-i-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-mk-i-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Downloaded to shared memory in 17.365s
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 121.56it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:01, 147.48it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 156.67it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 159.46it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 83.02it/s] 
Loading 0:  33%|███▎      | 96/291 [00:00<00:02, 92.42it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 107.22it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 121.89it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 133.22it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:00, 141.90it/s]
Loading 0:  63%|██████▎   | 183/291 [00:01<00:00, 149.22it/s]
Loading 0:  68%|██████▊   | 199/291 [00:01<00:01, 87.87it/s] 
Loading 0:  74%|███████▍  | 215/291 [00:01<00:00, 100.55it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 110.62it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 124.66it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 136.67it/s]
Loading 0:  98%|█████████▊| 285/291 [00:02<00:00, 149.62it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: quantized model in 22.983s
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Processed model Hastagaras/Sciemet-8B-L3-MK.I in 42.935s
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v2
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v2/config.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v2/tokenizer_config.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v2/special_tokens_map.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v2/tokenizer.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-sciemet-8b-l3-mk-i-v2/flywheel_model.0.safetensors
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-sciemet-8b-l3-mk-i-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-mk-i-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-mk-i-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-mk-i-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-mk-i-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-mk-i-v2-mkmlizer:   warnings.warn(
hastagaras-sciemet-8b-l3-mk-i-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-mk-i-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Saving duration: 0.404s
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.369s
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/merges.txt
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/vocab.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/tokenizer_config.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/tokenizer.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/config.json
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/reward.tensors
hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-sciemet-8b-l3-mk-i-v2_reward/special_tokens_map.json
Job hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer completed after 113.6s with status: succeeded
Stopping job with name hastagaras-sciemet-8b-l3-mk-i-v2-mkmlizer
Pipeline stage MKMLizer completed in 117.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-sciemet-8b-l3-mk-i-v2
Waiting for inference service hastagaras-sciemet-8b-l3-mk-i-v2 to be ready
Inference service hastagaras-sciemet-8b-l3-mk-i-v2 ready after 201.00011134147644s
Pipeline stage ISVCDeployer completed in 208.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.178501605987549s
Received healthy response to inference request in 1.3707623481750488s
Received healthy response to inference request in 1.3198161125183105s
Received healthy response to inference request in 1.2907063961029053s
Received healthy response to inference request in 1.3617753982543945s
5 requests
0 failed requests
5th percentile: 1.2965283393859863
10th percentile: 1.3023502826690674
20th percentile: 1.3139941692352295
30th percentile: 1.3282079696655273
40th percentile: 1.344991683959961
50th percentile: 1.3617753982543945
60th percentile: 1.3653701782226562
70th percentile: 1.368964958190918
80th percentile: 1.532310199737549
90th percentile: 1.855405902862549
95th percentile: 2.0169537544250487
99th percentile: 2.146192035675049
mean time: 1.5043123722076417
Pipeline stage StressChecker completed in 8.26s
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-mk-i_v2 status is now deployed due to DeploymentManager action
hastagaras-sciemet-8b-l3-mk-i_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-sciemet-8b-l3-mk-i_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-sciemet-8b-l3-mk-i-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-sciemet-8b-l3-mk-i-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.21s
hastagaras-sciemet-8b-l3-mk-i_v2 status is now torndown due to DeploymentManager action