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

developer_uid: Azazelle

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

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

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

status: torndown

timestamp: 2024-07-05T18:14:18+00:00

num_battles: 33203

num_wins: 17535

celo_rating: 1198.97

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: 4

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: 0.5281149293738517

generation_params: {'temperature': 1.0, 'top_p': 0.5, 'min_p': 0.0, 'top_k': 1000, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}

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}

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-v1-mkmlizer
Waiting for job on azazelle-l3-hecate-8b-v1-0-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║     _____            __           __                                ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║       /___/                                                         ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  https://mk1.ai                                                     ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  belonging to:                                                      ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  Chai Research Corp.                                                ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: Downloaded to shared memory in 60.971s
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:28,  2.38s/it]
Loading 0:   1%|▏         | 4/291 [00:04<04:55,  1.03s/it]
Loading 0:   3%|▎         | 8/291 [00:05<01:53,  2.48it/s]
Loading 0:   3%|▎         | 10/291 [00:05<01:33,  2.99it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:00,  4.63it/s]
Loading 0:   5%|▌         | 15/291 [00:05<00:51,  5.39it/s]
Loading 0:   8%|▊         | 22/291 [00:05<00:24, 11.11it/s]
Loading 0:   9%|▊         | 25/291 [00:06<00:20, 12.88it/s]
Loading 0:  11%|█         | 31/291 [00:06<00:13, 18.58it/s]
Loading 0:  12%|█▏        | 35/291 [00:06<00:12, 20.37it/s]
Loading 0:  14%|█▎        | 40/291 [00:06<00:12, 19.45it/s]
Loading 0:  15%|█▍        | 43/291 [00:07<00:20, 11.83it/s]
Loading 0:  16%|█▌        | 46/291 [00:07<00:18, 13.18it/s]
Loading 0:  17%|█▋        | 49/291 [00:07<00:15, 15.22it/s]
Loading 0:  18%|█▊        | 52/291 [00:07<00:18, 12.58it/s]
Loading 0:  20%|█▉        | 58/291 [00:07<00:13, 17.36it/s]
Loading 0:  21%|██        | 61/291 [00:08<00:18, 12.58it/s]
Loading 0:  22%|██▏       | 64/291 [00:08<00:16, 13.90it/s]
Loading 0:  23%|██▎       | 67/291 [00:08<00:17, 12.94it/s]
Loading 0:  24%|██▎       | 69/291 [00:09<00:23,  9.53it/s]
Loading 0:  26%|██▋       | 77/291 [00:09<00:14, 14.63it/s]
Loading 0:  27%|██▋       | 79/291 [00:09<00:17, 12.28it/s]
Loading 0:  29%|██▊       | 83/291 [00:09<00:13, 15.51it/s]
Loading 0:  30%|██▉       | 86/291 [00:10<00:14, 13.90it/s]
Loading 0:  30%|███       | 88/291 [00:10<00:15, 13.32it/s]
Loading 0:  31%|███▏      | 91/291 [00:10<00:13, 14.33it/s]
Loading 0:  32%|███▏      | 94/291 [00:11<00:17, 11.03it/s]
Loading 0:  33%|███▎      | 96/291 [00:11<00:24,  8.04it/s]
Loading 0:  35%|███▌      | 103/291 [00:11<00:12, 14.84it/s]
Loading 0:  38%|███▊      | 112/291 [00:11<00:07, 23.95it/s]
Loading 0:  40%|███▉      | 116/291 [00:11<00:08, 21.15it/s]
Loading 0:  42%|████▏     | 123/291 [00:12<00:06, 27.94it/s]
Loading 0:  45%|████▌     | 132/291 [00:12<00:04, 38.06it/s]
Loading 0:  48%|████▊     | 141/291 [00:12<00:03, 46.98it/s]
Loading 0:  52%|█████▏    | 150/291 [00:12<00:02, 55.11it/s]
Loading 0:  55%|█████▍    | 159/291 [00:12<00:02, 61.91it/s]
Loading 0:  57%|█████▋    | 167/291 [00:12<00:02, 46.96it/s]
Loading 0:  60%|██████    | 176/291 [00:12<00:02, 53.79it/s]
Loading 0:  64%|██████▎   | 185/291 [00:13<00:01, 59.85it/s]
Loading 0:  67%|██████▋   | 194/291 [00:13<00:01, 64.66it/s]
Loading 0:  70%|██████▉   | 203/291 [00:13<00:01, 69.57it/s]
Loading 0:  73%|███████▎  | 212/291 [00:13<00:01, 73.34it/s]
Loading 0:  76%|███████▌  | 220/291 [00:13<00:01, 52.06it/s]
Loading 0:  79%|███████▊  | 229/291 [00:13<00:01, 57.61it/s]
Loading 0:  82%|████████▏ | 238/291 [00:13<00:00, 62.34it/s]
Loading 0:  85%|████████▍ | 247/291 [00:14<00:00, 66.77it/s]
Loading 0:  88%|████████▊ | 256/291 [00:14<00:00, 69.40it/s]
Loading 0:  91%|█████████ | 265/291 [00:14<00:00, 72.12it/s]
Loading 0:  94%|█████████▍| 273/291 [00:14<00:00, 51.89it/s]
Loading 0:  96%|█████████▌| 280/291 [00:14<00:00, 54.20it/s]
Loading 0:  99%|█████████▉| 288/291 [00:14<00:00, 58.98it/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-v1-mkmlizer: quantized model in 54.947s
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: Processed model Azazelle/L3-Hecate-8B-v1.0 in 115.919s
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: creating bucket guanaco-mkml-models
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v1
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v1/config.json
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v1/tokenizer_config.json
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v1/special_tokens_map.json
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v1/tokenizer.json
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-0-v1/flywheel_model.0.safetensors
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-l3-hecate-8b-v1-0-v1-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-v1-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v1-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-v1-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v1-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-v1-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-v1-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-v1-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-0-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()
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
azazelle-l3-hecate-8b-v1-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Job azazelle-l3-hecate-8b-v1-0-v1-mkmlizer completed after 347.19s with status: succeeded
Stopping job with name azazelle-l3-hecate-8b-v1-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 348.21s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-l3-hecate-8b-v1-0-v1
Waiting for inference service azazelle-l3-hecate-8b-v1-0-v1 to be ready
Inference service azazelle-l3-hecate-8b-v1-0-v1 ready after 40.294445753097534s
Pipeline stage ISVCDeployer completed in 47.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.011955738067627s
Received healthy response to inference request in 1.1288738250732422s
Received healthy response to inference request in 1.1592543125152588s
Received healthy response to inference request in 1.1246306896209717s
Received healthy response to inference request in 1.1300489902496338s
5 requests
0 failed requests
5th percentile: 1.1254793167114259
10th percentile: 1.1263279438018798
20th percentile: 1.128025197982788
30th percentile: 1.1291088581085205
40th percentile: 1.1295789241790772
50th percentile: 1.1300489902496338
60th percentile: 1.1417311191558839
70th percentile: 1.1534132480621337
80th percentile: 1.3297945976257326
90th percentile: 1.6708751678466798
95th percentile: 1.8414154529571531
99th percentile: 1.977847681045532
mean time: 1.3109527111053467
Pipeline stage StressChecker completed in 7.25s
azazelle-l3-hecate-8b-v1-0_v1 status is now deployed due to DeploymentManager action
azazelle-l3-hecate-8b-v1-0_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-l3-hecate-8b-v1-0_v1
Running pipeline stage ISVCDeleter
Checking if service azazelle-l3-hecate-8b-v1-0-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.19s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-0-v1/config.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-0-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.25s
azazelle-l3-hecate-8b-v1-0_v1 status is now torndown due to DeploymentManager action