azazelle-l3-hecate-8b-v1-0

developer_uid: Azazelle

submission_id: azazelle-l3-hecate-8b-v1-0_v6

model_name: Azazelle-L3-Hecate-8B-v1_0

model_group: Azazelle/L3-Hecate-8B-v1

status: torndown

timestamp: 2024-07-08T19:43:57+00:00

num_battles: 31274

num_wins: 16461

celo_rating: 1214.39

family_friendly_score: 0.0

submission_type: basic

model_repo: Azazelle/L3-Hecate-8B-v1.0

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: Azazelle-L3-Hecate-8B-v1_0

is_internal_developer: False

language_model: Azazelle/L3-Hecate-8B-v1.0

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-08

win_ratio: 0.5263477649165441

generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.03, 'top_k': 60, '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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name azazelle-l3-hecate-8b-v1-0-v6-mkmlizer
Waiting for job on azazelle-l3-hecate-8b-v1-0-v6-mkmlizer to finish
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║     _____            __           __                                ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║       /___/                                                         ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  https://mk1.ai                                                     ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  belonging to:                                                      ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  Chai Research Corp.                                                ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Downloaded to shared memory in 72.605s
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: quantizing model to /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:45,  2.86s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:37,  1.31it/s]
Loading 0:   3%|▎         | 10/291 [00:06<01:59,  2.35it/s]
Loading 0:   5%|▌         | 15/291 [00:06<01:04,  4.30it/s]
Loading 0:   8%|▊         | 23/291 [00:06<00:31,  8.50it/s]
Loading 0:  11%|█         | 31/291 [00:06<00:18, 13.74it/s]
Loading 0:  13%|█▎        | 38/291 [00:06<00:13, 19.07it/s]
Loading 0:  15%|█▌        | 45/291 [00:06<00:10, 24.44it/s]
Loading 0:  18%|█▊        | 51/291 [00:06<00:08, 28.52it/s]
Loading 0:  20%|██        | 59/291 [00:07<00:06, 36.83it/s]
Loading 0:  23%|██▎       | 66/291 [00:07<00:08, 26.40it/s]
Loading 0:  24%|██▍       | 71/291 [00:07<00:07, 29.15it/s]
Loading 0:  27%|██▋       | 78/291 [00:07<00:06, 33.97it/s]
Loading 0:  30%|██▉       | 86/291 [00:07<00:04, 42.26it/s]
Loading 0:  32%|███▏      | 94/291 [00:07<00:04, 46.00it/s]
Loading 0:  34%|███▍      | 100/291 [00:08<00:03, 48.59it/s]
Loading 0:  36%|███▋      | 106/291 [00:08<00:03, 48.82it/s]
Loading 0:  39%|███▉      | 113/291 [00:08<00:06, 28.25it/s]
Loading 0:  42%|████▏     | 121/291 [00:08<00:04, 36.00it/s]
Loading 0:  44%|████▍     | 128/291 [00:08<00:03, 42.00it/s]
Loading 0:  46%|████▌     | 134/291 [00:08<00:03, 44.06it/s]
Loading 0:  48%|████▊     | 141/291 [00:09<00:03, 46.56it/s]
Loading 0:  51%|█████     | 149/291 [00:09<00:02, 53.91it/s]
Loading 0:  54%|█████▍    | 157/291 [00:09<00:02, 59.88it/s]
Loading 0:  56%|█████▋    | 164/291 [00:09<00:02, 62.04it/s]
Loading 0:  59%|█████▉    | 171/291 [00:09<00:03, 31.45it/s]
Loading 0:  61%|██████    | 177/291 [00:10<00:03, 34.69it/s]
Loading 0:  64%|██████▎   | 185/291 [00:10<00:02, 42.62it/s]
Loading 0:  67%|██████▋   | 194/291 [00:10<00:01, 48.96it/s]
Loading 0:  69%|██████▉   | 202/291 [00:10<00:01, 55.38it/s]
Loading 0:  72%|███████▏  | 209/291 [00:10<00:01, 58.55it/s]
Loading 0:  74%|███████▍  | 216/291 [00:10<00:02, 31.16it/s]
Loading 0:  76%|███████▋  | 222/291 [00:11<00:02, 33.95it/s]
Loading 0:  79%|███████▉  | 230/291 [00:11<00:01, 41.31it/s]
Loading 0:  82%|████████▏ | 238/291 [00:11<00:01, 48.34it/s]
Loading 0:  84%|████████▍ | 245/291 [00:11<00:00, 52.39it/s]
Loading 0:  87%|████████▋ | 252/291 [00:11<00:00, 53.18it/s]
Loading 0:  89%|████████▉ | 259/291 [00:11<00:00, 53.80it/s]
Loading 0:  91%|█████████▏| 266/291 [00:12<00:00, 30.42it/s]
Loading 0:  94%|█████████▍| 274/291 [00:12<00:00, 38.08it/s]
Loading 0:  96%|█████████▌| 280/291 [00:12<00:00, 40.44it/s]
Loading 0:  98%|█████████▊| 286/291 [00:12<00:00, 43.30it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: quantized model in 32.695s
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Processed model Azazelle/L3-Hecate-8B-v1.0 in 105.301s
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: creating bucket guanaco-mkml-models
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v6
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v6/special_tokens_map.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v6/tokenizer_config.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v6/config.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v6/flywheel_model.0.safetensors
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v6-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.
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v6-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()
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer:   return self.fget.__get__(instance, owner)()
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Saving duration: 0.505s
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.180s
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: creating bucket guanaco-reward-models
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/config.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/tokenizer_config.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/special_tokens_map.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/merges.txt
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/vocab.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/tokenizer.json
azazelle-l3-hecate-8b-v1-0-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v6_reward/reward.tensors
Job azazelle-l3-hecate-8b-v1-0-v6-mkmlizer completed after 136.06s with status: succeeded
Stopping job with name azazelle-l3-hecate-8b-v1-0-v6-mkmlizer
Pipeline stage MKMLizer completed in 137.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-l3-hecate-8b-v1-0-v6
Waiting for inference service azazelle-l3-hecate-8b-v1-0-v6 to be ready
Inference service azazelle-l3-hecate-8b-v1-0-v6 ready after 40.257742166519165s
Pipeline stage ISVCDeployer completed in 47.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0532703399658203s
Received healthy response to inference request in 1.471266746520996s
Received healthy response to inference request in 1.3254790306091309s
Received healthy response to inference request in 1.2900371551513672s
Received healthy response to inference request in 1.369746208190918s
5 requests
0 failed requests
5th percentile: 1.2971255302429199
10th percentile: 1.3042139053344726
20th percentile: 1.3183906555175782
30th percentile: 1.3343324661254883
40th percentile: 1.3520393371582031
50th percentile: 1.369746208190918
60th percentile: 1.4103544235229493
70th percentile: 1.4509626388549806
80th percentile: 1.587667465209961
90th percentile: 1.8204689025878906
95th percentile: 1.9368696212768555
99th percentile: 2.0299901962280273
mean time: 1.5019598960876466
Pipeline stage StressChecker completed in 8.27s
azazelle-l3-hecate-8b-v1-0_v6 status is now deployed due to DeploymentManager action
azazelle-l3-hecate-8b-v1-0_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-l3-hecate-8b-v1-0_v6
Running pipeline stage ISVCDeleter
Checking if service azazelle-l3-hecate-8b-v1-0-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 7.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-0-v6/config.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.75s
azazelle-l3-hecate-8b-v1-0_v6 status is now torndown due to DeploymentManager action