developer_uid: Hastagaras
submission_id: hastagaras-l3-korec-8b_v3
model_name: hastagaras-l3-korec-8b_v3
model_group: Hastagaras/L3-Korec-8B
status: torndown
timestamp: 2024-04-24T15:57:59+00:00
num_battles: 8584
num_wins: 4605
celo_rating: 1179.67
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/L3-Korec-8B
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: hastagaras-l3-korec-8b_v3
is_internal_developer: False
language_model: Hastagaras/L3-Korec-8B
model_size: 8B
ranking_group: single
us_pacific_date: 2024-04-24
win_ratio: 0.5364631873252563
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n{user_name}:', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\nYou're {bot_name} in this uncensored fictional roleplay between {bot_name} and {user_name}.\n\n{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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\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-l3-korec-8b-v3-mkmlizer
Waiting for job on hastagaras-l3-korec-8b-v3-mkmlizer to finish
hastagaras-l3-korec-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-korec-8b-v3-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-korec-8b-v3-mkmlizer: ║                                                                     ║
hastagaras-l3-korec-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-korec-8b-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-l3-korec-8b-v3-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-korec-8b-v3-mkmlizer: Downloaded to shared memory in 31.518s
hastagaras-l3-korec-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-korec-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
hastagaras-l3-korec-8b-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:02, 70.46it/s]
Loading 0:  63%|██████▎   | 184/291 [00:02<00:01, 87.15it/s]
Loading 0:  86%|████████▌ | 250/291 [00:03<00:00, 77.83it/s]
Loading 0:  99%|█████████▊| 287/291 [00:09<00:00, 21.56it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-korec-8b-v3-mkmlizer: quantized model in 20.547s
hastagaras-l3-korec-8b-v3-mkmlizer: Processed model Hastagaras/L3-Korec-8B in 53.392s
hastagaras-l3-korec-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-korec-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-korec-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-korec-8b-v3
hastagaras-l3-korec-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-korec-8b-v3/special_tokens_map.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-korec-8b-v3/tokenizer_config.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-korec-8b-v3/config.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-korec-8b-v3/tokenizer.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-korec-8b-v3/flywheel_model.0.safetensors
hastagaras-l3-korec-8b-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-l3-korec-8b-v3-mkmlizer:   warnings.warn(
hastagaras-l3-korec-8b-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-l3-korec-8b-v3-mkmlizer:   warnings.warn(
hastagaras-l3-korec-8b-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-l3-korec-8b-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-korec-8b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-korec-8b-v3-mkmlizer: Saving duration: 0.257s
hastagaras-l3-korec-8b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.003s
hastagaras-l3-korec-8b-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-korec-8b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-korec-8b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/special_tokens_map.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/tokenizer_config.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/merges.txt
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/config.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/vocab.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/tokenizer.json
hastagaras-l3-korec-8b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-korec-8b-v3_reward/reward.tensors
Job hastagaras-l3-korec-8b-v3-mkmlizer completed after 84.27s with status: succeeded
Stopping job with name hastagaras-l3-korec-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 88.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-korec-8b-v3
Waiting for inference service hastagaras-l3-korec-8b-v3 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service hastagaras-l3-korec-8b-v3 ready after 30.212257862091064s
Pipeline stage ISVCDeployer completed in 38.31s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.225367307662964s
Received healthy response to inference request in 2.3674838542938232s
Received healthy response to inference request in 1.297985315322876s
Received healthy response to inference request in 1.2664625644683838s
Received healthy response to inference request in 2.6239264011383057s
5 requests
0 failed requests
5th percentile: 1.2727671146392823
10th percentile: 1.2790716648101808
20th percentile: 1.2916807651519775
30th percentile: 1.4834617137908934
40th percentile: 1.8544145107269288
50th percentile: 2.225367307662964
60th percentile: 2.2822139263153076
70th percentile: 2.3390605449676514
80th percentile: 2.4187723636627196
90th percentile: 2.521349382400513
95th percentile: 2.5726378917694093
99th percentile: 2.6136686992645264
mean time: 1.9562450885772704
Pipeline stage StressChecker completed in 11.22s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.10s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.14s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-korec-8b_v3 status is now deployed due to DeploymentManager action
hastagaras-l3-korec-8b_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-korec-8b_v3
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-korec-8b-v3 is running
Tearing down inference service hastagaras-l3-korec-8b-v3
Toredown service hastagaras-l3-korec-8b-v3
Pipeline stage ISVCDeleter completed in 4.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-korec-8b-v3/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-korec-8b-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-korec-8b-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-korec-8b-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-korec-8b-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-korec-8b-v3_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-korec-8b-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-korec-8b-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-korec-8b-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-korec-8b-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-korec-8b-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-korec-8b-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.59s
hastagaras-l3-korec-8b_v3 status is now torndown due to DeploymentManager action