theskullery-llama-3-cat-_5642

submission_id: theskullery-llama-3-cat-_5642_v1
developer_uid: Steelskull
best_of: 4
celo_rating: 1145.65
display_name: theskullery-llama-3-cat-_5642_v1
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.1, 'top_k': 75, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: TheSkullery/llama-3-cat-8b-instruct-v1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: TheSkullery/llama-3-cat-
model_name: theskullery-llama-3-cat-_5642_v1
model_num_parameters: 8030261248.0
model_repo: TheSkullery/llama-3-cat-8b-instruct-v1
model_size: 8B
num_battles: 15778
num_wins: 7325
ranking_group: single
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'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-19T21:57:14+00:00
us_pacific_date: 2024-05-19
win_ratio: 0.46425402459120296
Resubmit model
Running pipeline stage MKMLizer
Starting job with name theskullery-llama-3-cat-5642-v1-mkmlizer
Waiting for job on theskullery-llama-3-cat-5642-v1-mkmlizer to finish
theskullery-llama-3-cat-5642-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
theskullery-llama-3-cat-5642-v1-mkmlizer: ║     _____            __           __                                ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║       /___/                                                         ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║                                                                     ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  https://mk1.ai                                                     ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║                                                                     ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  belonging to:                                                      ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║                                                                     ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  Chai Research Corp.                                                ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ║                                                                     ║
theskullery-llama-3-cat-5642-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
theskullery-llama-3-cat-5642-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.
theskullery-llama-3-cat-5642-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
theskullery-llama-3-cat-5642-v1-mkmlizer: Downloaded to shared memory in 30.015s
theskullery-llama-3-cat-5642-v1-mkmlizer: quantizing model to /dev/shm/model_cache
theskullery-llama-3-cat-5642-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
theskullery-llama-3-cat-5642-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:03,  2.29s/it]
Loading 0:   4%|▍         | 13/291 [00:04<01:14,  3.73it/s]
Loading 0:   8%|▊         | 24/291 [00:04<00:33,  8.09it/s]
Loading 0:  14%|█▎        | 40/291 [00:04<00:15, 16.37it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:10, 22.77it/s]
Loading 0:  21%|██        | 61/291 [00:05<00:10, 22.45it/s]
Loading 0:  25%|██▍       | 72/291 [00:05<00:07, 30.21it/s]
Loading 0:  28%|██▊       | 82/291 [00:05<00:05, 38.00it/s]
Loading 0:  32%|███▏      | 94/291 [00:05<00:04, 48.62it/s]
Loading 0:  36%|███▌      | 104/291 [00:05<00:03, 56.16it/s]
Loading 0:  40%|████      | 117/291 [00:06<00:02, 69.98it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:02, 80.34it/s]
Loading 0:  48%|████▊     | 141/291 [00:06<00:01, 81.00it/s]
Loading 0:  53%|█████▎    | 154/291 [00:06<00:01, 91.19it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:02, 53.64it/s]
Loading 0:  61%|██████    | 177/291 [00:06<00:01, 62.16it/s]
Loading 0:  66%|██████▋   | 193/291 [00:07<00:01, 80.19it/s]
Loading 0:  70%|███████   | 205/291 [00:07<00:00, 87.85it/s]
Loading 0:  75%|███████▍  | 217/291 [00:07<00:00, 94.04it/s]
Loading 0:  79%|███████▉  | 230/291 [00:07<00:00, 98.48it/s]
Loading 0:  84%|████████▍ | 244/291 [00:07<00:00, 108.77it/s]
Loading 0:  88%|████████▊ | 257/291 [00:07<00:00, 107.24it/s]
Loading 0:  92%|█████████▏| 269/291 [00:08<00:00, 59.63it/s] 
Loading 0:  97%|█████████▋| 283/291 [00:08<00:00, 71.23it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
theskullery-llama-3-cat-5642-v1-mkmlizer: quantized model in 20.620s
theskullery-llama-3-cat-5642-v1-mkmlizer: Processed model TheSkullery/llama-3-cat-8b-instruct-v1 in 51.871s
theskullery-llama-3-cat-5642-v1-mkmlizer: creating bucket guanaco-mkml-models
theskullery-llama-3-cat-5642-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
theskullery-llama-3-cat-5642-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/theskullery-llama-3-cat-5642-v1
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/theskullery-llama-3-cat-5642-v1/special_tokens_map.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/theskullery-llama-3-cat-5642-v1/config.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/theskullery-llama-3-cat-5642-v1/tokenizer_config.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/theskullery-llama-3-cat-5642-v1/tokenizer.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/theskullery-llama-3-cat-5642-v1/flywheel_model.0.safetensors
theskullery-llama-3-cat-5642-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
theskullery-llama-3-cat-5642-v1-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.
theskullery-llama-3-cat-5642-v1-mkmlizer:   warnings.warn(
theskullery-llama-3-cat-5642-v1-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.
theskullery-llama-3-cat-5642-v1-mkmlizer:   warnings.warn(
theskullery-llama-3-cat-5642-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()
theskullery-llama-3-cat-5642-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
theskullery-llama-3-cat-5642-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
theskullery-llama-3-cat-5642-v1-mkmlizer: Saving duration: 0.300s
theskullery-llama-3-cat-5642-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.479s
theskullery-llama-3-cat-5642-v1-mkmlizer: creating bucket guanaco-reward-models
theskullery-llama-3-cat-5642-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
theskullery-llama-3-cat-5642-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/config.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/special_tokens_map.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/merges.txt
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/tokenizer_config.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/vocab.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/tokenizer.json
theskullery-llama-3-cat-5642-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/theskullery-llama-3-cat-5642-v1_reward/reward.tensors
Job theskullery-llama-3-cat-5642-v1-mkmlizer completed after 73.38s with status: succeeded
Stopping job with name theskullery-llama-3-cat-5642-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service theskullery-llama-3-cat-5642-v1
Waiting for inference service theskullery-llama-3-cat-5642-v1 to be ready
Inference service theskullery-llama-3-cat-5642-v1 ready after 30.420190811157227s
Pipeline stage ISVCDeployer completed in 37.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.00997257232666s
Received healthy response to inference request in 1.1097073554992676s
Received healthy response to inference request in 1.1127686500549316s
Received healthy response to inference request in 1.0353243350982666s
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
Received healthy response to inference request in 0.9717934131622314s
5 requests
0 failed requests
5th percentile: 0.9844995975494385
10th percentile: 0.9972057819366456
20th percentile: 1.0226181507110597
30th percentile: 1.0502009391784668
40th percentile: 1.0799541473388672
50th percentile: 1.1097073554992676
60th percentile: 1.1109318733215332
70th percentile: 1.1121563911437988
80th percentile: 1.2922094345092776
90th percentile: 1.6510910034179689
95th percentile: 1.8305317878723142
99th percentile: 1.974084415435791
mean time: 1.2479132652282714
Pipeline stage StressChecker completed in 6.92s
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
theskullery-llama-3-cat-_5642_v1 status is now deployed due to DeploymentManager action
theskullery-llama-3-cat-_5642_v1 status is now inactive due to auto deactivation removed underperforming models
Toredown service nitral-ai-poppy-porpoise-7217-v4
admin requested tearing down of theskullery-llama-3-cat-_5642_v1
Running pipeline stage ISVCDeleter
Pipeline stage ISVCDeleter completed in 4.38s
Running pipeline stage MKMLModelDeleter
Checking if service theskullery-llama-3-cat-5642-v1 is running
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-poppy-porpoise-7217-v4/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-poppy-porpoise-7217-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-poppy-porpoise-7217-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-poppy-porpoise-7217-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-poppy-porpoise-7217-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Tearing down inference service theskullery-llama-3-cat-5642-v1
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/tokenizer.json from bucket guanaco-reward-models
Toredown service theskullery-llama-3-cat-5642-v1
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-poppy-porpoise-7217-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage ISVCDeleter completed in 3.98s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 4.14s
Cleaning model data from S3
nitral-ai-poppy-porpoise_7217_v4 status is now torndown due to DeploymentManager action
Cleaning model data from model cache
Deleting key theskullery-llama-3-cat-5642-v1/config.json from bucket guanaco-mkml-models
Deleting key theskullery-llama-3-cat-5642-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key theskullery-llama-3-cat-5642-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key theskullery-llama-3-cat-5642-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key theskullery-llama-3-cat-5642-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key theskullery-llama-3-cat-5642-v1_reward/config.json from bucket guanaco-reward-models
Deleting key theskullery-llama-3-cat-5642-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key theskullery-llama-3-cat-5642-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key theskullery-llama-3-cat-5642-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key theskullery-llama-3-cat-5642-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key theskullery-llama-3-cat-5642-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key theskullery-llama-3-cat-5642-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.30s
theskullery-llama-3-cat-_5642_v1 status is now torndown due to DeploymentManager action