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

developer_uid: Azazelle

submission_id: azazelle-l3-hecate-8b-v1-0_v2

model_name: azazelle-l3-hecate-8b-v1-0_v1

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

status: torndown

timestamp: 2024-07-05T18:24:04+00:00

num_battles: 31599

num_wins: 17627

celo_rating: 1217.59

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_v1

is_internal_developer: False

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

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-05

win_ratio: 0.5578341086743251

generation_params: {'temperature': 0.96, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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-v2-mkmlizer
Waiting for job on azazelle-l3-hecate-8b-v1-0-v2-mkmlizer to finish
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║     _____            __           __                                ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║       /___/                                                         ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  https://mk1.ai                                                     ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  belonging to:                                                      ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  Chai Research Corp.                                                ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Downloaded to shared memory in 42.560s
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: quantizing model to /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:14<35:25,  7.35s/it]
Loading 0:   2%|▏         | 6/291 [00:14<09:09,  1.93s/it]
Loading 0:   3%|▎         | 10/291 [00:15<04:34,  1.02it/s]
Loading 0:   5%|▌         | 15/291 [00:15<02:23,  1.92it/s]
Loading 0:   8%|▊         | 23/291 [00:15<01:08,  3.91it/s]
Loading 0:  11%|█         | 31/291 [00:15<00:39,  6.57it/s]
Loading 0:  13%|█▎        | 37/291 [00:15<00:27,  9.10it/s]
Loading 0:  15%|█▍        | 43/291 [00:15<00:20, 12.18it/s]
Loading 0:  17%|█▋        | 50/291 [00:15<00:14, 16.85it/s]
Loading 0:  20%|█▉        | 58/291 [00:15<00:10, 23.25it/s]
Loading 0:  22%|██▏       | 65/291 [00:16<00:10, 21.87it/s]
Loading 0:  24%|██▍       | 70/291 [00:16<00:08, 24.75it/s]
Loading 0:  26%|██▋       | 77/291 [00:16<00:06, 30.92it/s]
Loading 0:  29%|██▉       | 85/291 [00:16<00:05, 38.71it/s]
Loading 0:  31%|███▏      | 91/291 [00:16<00:04, 42.33it/s]
Loading 0:  33%|███▎      | 97/291 [00:16<00:04, 44.06it/s]
Loading 0:  36%|███▌      | 104/291 [00:16<00:03, 49.08it/s]
Loading 0:  38%|███▊      | 112/291 [00:17<00:03, 55.60it/s]
Loading 0:  41%|████      | 119/291 [00:17<00:04, 35.61it/s]
Loading 0:  43%|████▎     | 125/291 [00:17<00:04, 38.42it/s]
Loading 0:  45%|████▌     | 131/291 [00:17<00:03, 42.43it/s]
Loading 0:  48%|████▊     | 139/291 [00:17<00:03, 50.04it/s]
Loading 0:  50%|████▉     | 145/291 [00:17<00:02, 51.96it/s]
Loading 0:  52%|█████▏    | 151/291 [00:17<00:02, 51.24it/s]
Loading 0:  54%|█████▍    | 158/291 [00:18<00:02, 55.50it/s]
Loading 0:  57%|█████▋    | 166/291 [00:18<00:03, 36.70it/s]
Loading 0:  60%|██████    | 175/291 [00:18<00:02, 43.84it/s]
Loading 0:  63%|██████▎   | 184/291 [00:18<00:02, 50.66it/s]
Loading 0:  66%|██████▋   | 193/291 [00:18<00:01, 56.71it/s]
Loading 0:  69%|██████▉   | 202/291 [00:18<00:01, 61.54it/s]
Loading 0:  72%|███████▏  | 210/291 [00:19<00:01, 65.88it/s]
Loading 0:  75%|███████▍  | 218/291 [00:19<00:01, 42.43it/s]
Loading 0:  77%|███████▋  | 224/291 [00:19<00:01, 45.33it/s]
Loading 0:  79%|███████▉  | 231/291 [00:19<00:01, 48.50it/s]
Loading 0:  82%|████████▏ | 240/291 [00:19<00:00, 54.66it/s]
Loading 0:  86%|████████▌ | 249/291 [00:19<00:00, 59.42it/s]
Loading 0:  89%|████████▊ | 258/291 [00:19<00:00, 63.55it/s]
Loading 0:  91%|█████████▏| 266/291 [00:20<00:00, 43.50it/s]
Loading 0:  95%|█████████▍| 275/291 [00:20<00:00, 50.02it/s]
Loading 0:  98%|█████████▊| 284/291 [00:20<00:00, 55.63it/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-v2-mkmlizer: quantized model in 110.142s
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Processed model Azazelle/L3-Hecate-8B-v1.0 in 152.703s
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: creating bucket guanaco-mkml-models
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v2
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v2/tokenizer_config.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v2/config.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v2/special_tokens_map.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v2/tokenizer.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v2/flywheel_model.0.safetensors
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-l3-hecate-8b-v1-0-v2-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-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v2-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-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v2-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-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-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.
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-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()
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Saving duration: 0.401s
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.589s
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: creating bucket guanaco-reward-models
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/special_tokens_map.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/tokenizer_config.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/config.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/vocab.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/merges.txt
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/tokenizer.json
azazelle-l3-hecate-8b-v1-0-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-0-v2_reward/reward.tensors
Job azazelle-l3-hecate-8b-v1-0-v2-mkmlizer completed after 176.44s with status: succeeded
Stopping job with name azazelle-l3-hecate-8b-v1-0-v2-mkmlizer
Pipeline stage MKMLizer completed in 177.41s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-l3-hecate-8b-v1-0-v2
Waiting for inference service azazelle-l3-hecate-8b-v1-0-v2 to be ready
Connection pool is full, discarding connection: %s
Inference service azazelle-l3-hecate-8b-v1-0-v2 ready after 40.28287100791931s
Pipeline stage ISVCDeployer completed in 46.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0165915489196777s
Received healthy response to inference request in 1.3346400260925293s
Received healthy response to inference request in 1.3422915935516357s
Received healthy response to inference request in 1.29091215133667s
Received healthy response to inference request in 1.3472874164581299s
5 requests
0 failed requests
5th percentile: 1.2996577262878417
10th percentile: 1.3084033012390137
20th percentile: 1.3258944511413575
30th percentile: 1.3361703395843505
40th percentile: 1.3392309665679931
50th percentile: 1.3422915935516357
60th percentile: 1.3442899227142333
70th percentile: 1.346288251876831
80th percentile: 1.4811482429504395
90th percentile: 1.7488698959350586
95th percentile: 1.8827307224273682
99th percentile: 1.989819383621216
mean time: 1.4663445472717285
Pipeline stage StressChecker completed in 8.04s
azazelle-l3-hecate-8b-v1-0_v2 status is now deployed due to DeploymentManager action
azazelle-l3-hecate-8b-v1-0_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-l3-hecate-8b-v1-0_v2
Running pipeline stage ISVCDeleter
Checking if service azazelle-l3-hecate-8b-v1-0-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 7.16s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-0-v2/config.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.32s
azazelle-l3-hecate-8b-v1-0_v2 status is now torndown due to DeploymentManager action