azazelle-l3-hecate-8b-v1-2

developer_uid: Azazelle

submission_id: azazelle-l3-hecate-8b-v1-2_v2

model_name: Azazelle-L3-Hecate-8B-v1_2

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

status: torndown

timestamp: 2024-07-18T18:10:58+00:00

num_battles: 7709

num_wins: 4064

celo_rating: 1211.39

family_friendly_score: 0.0

submission_type: basic

model_repo: Azazelle/L3-Hecate-8B-v1.2

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_2

is_internal_developer: False

language_model: Azazelle/L3-Hecate-8B-v1.2

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-18

win_ratio: 0.5271760280191984

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.075, 'top_k': 80, '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-v1-2-v2-mkmlizer
Waiting for job on azazelle-l3-hecate-8b-v1-2-v2-mkmlizer to finish
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║     _____            __           __                                ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║       /___/                                                         ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  Version: 0.9.5.post3                                               ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  belonging to:                                                      ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ║                                                                     ║
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Downloaded to shared memory in 42.077s
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplbccp987, device:0
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:02,  2.29s/it]
Loading 0:   3%|▎         | 9/291 [00:04<01:51,  2.53it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:15,  3.67it/s]
Loading 0:   8%|▊         | 22/291 [00:05<00:33,  7.98it/s]
Loading 0:  11%|█         | 31/291 [00:05<00:19, 13.40it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:12, 19.93it/s]
Loading 0:  17%|█▋        | 49/291 [00:05<00:08, 27.41it/s]
Loading 0:  20%|█▉        | 58/291 [00:05<00:06, 35.57it/s]
Loading 0:  23%|██▎       | 66/291 [00:05<00:07, 29.95it/s]
Loading 0:  25%|██▌       | 73/291 [00:06<00:06, 35.02it/s]
Loading 0:  28%|██▊       | 81/291 [00:06<00:04, 42.12it/s]
Loading 0:  30%|███       | 88/291 [00:06<00:04, 45.66it/s]
Loading 0:  33%|███▎      | 96/291 [00:06<00:06, 30.04it/s]
Loading 0:  36%|███▌      | 105/291 [00:06<00:04, 37.83it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:05, 31.70it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:04, 39.36it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:03, 46.57it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 53.11it/s]
Loading 0:  51%|█████     | 149/291 [00:07<00:02, 59.31it/s]
Loading 0:  54%|█████▍    | 158/291 [00:07<00:02, 64.66it/s]
Loading 0:  57%|█████▋    | 166/291 [00:08<00:04, 28.56it/s]
Loading 0:  60%|██████    | 175/291 [00:08<00:03, 35.54it/s]
Loading 0:  63%|██████▎   | 184/291 [00:08<00:02, 42.79it/s]
Loading 0:  66%|██████▋   | 193/291 [00:08<00:01, 49.96it/s]
Loading 0:  69%|██████▉   | 202/291 [00:08<00:01, 55.92it/s]
Loading 0:  73%|███████▎  | 211/291 [00:09<00:01, 61.71it/s]
Loading 0:  75%|███████▌  | 219/291 [00:09<00:01, 41.29it/s]
Loading 0:  77%|███████▋  | 225/291 [00:10<00:02, 23.96it/s]
Loading 0:  80%|████████  | 233/291 [00:10<00:01, 30.38it/s]
Loading 0:  82%|████████▏ | 240/291 [00:10<00:01, 35.82it/s]
Loading 0:  86%|████████▌ | 249/291 [00:10<00:00, 44.57it/s]
Loading 0:  89%|████████▊ | 258/291 [00:10<00:00, 52.21it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 38.77it/s]
Loading 0:  95%|█████████▍| 275/291 [00:10<00:00, 46.07it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 53.54it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: quantized model in 27.944s
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Processed model Azazelle/L3-Hecate-8B-v1.2 in 70.021s
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: creating bucket guanaco-mkml-models
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-2-v2
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-2-v2/config.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-2-v2/special_tokens_map.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-2-v2/tokenizer_config.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-2-v2/tokenizer.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-l3-hecate-8b-v1-2-v2/flywheel_model.0.safetensors
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer:   warnings.warn(
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Saving duration: 0.400s
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.695s
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: creating bucket guanaco-reward-models
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/special_tokens_map.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/tokenizer_config.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/config.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/merges.txt
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/vocab.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/tokenizer.json
azazelle-l3-hecate-8b-v1-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/azazelle-l3-hecate-8b-v1-2-v2_reward/reward.tensors
Job azazelle-l3-hecate-8b-v1-2-v2-mkmlizer completed after 98.49s with status: succeeded
Stopping job with name azazelle-l3-hecate-8b-v1-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 100.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-l3-hecate-8b-v1-2-v2
Waiting for inference service azazelle-l3-hecate-8b-v1-2-v2 to be ready
Inference service azazelle-l3-hecate-8b-v1-2-v2 ready after 91.8020122051239s
Pipeline stage ISVCDeployer completed in 94.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.17897367477417s
Received healthy response to inference request in 1.3223998546600342s
Received healthy response to inference request in 1.2964205741882324s
Received healthy response to inference request in 1.2476074695587158s
Received healthy response to inference request in 1.2851378917694092s
5 requests
0 failed requests
5th percentile: 1.2551135540008544
10th percentile: 1.262619638442993
20th percentile: 1.2776318073272706
30th percentile: 1.2873944282531737
40th percentile: 1.291907501220703
50th percentile: 1.2964205741882324
60th percentile: 1.3068122863769531
70th percentile: 1.3172039985656738
80th percentile: 1.4937146186828616
90th percentile: 1.8363441467285158
95th percentile: 2.0076589107513425
99th percentile: 2.1447107219696044
mean time: 1.4661078929901123
Pipeline stage StressChecker completed in 7.97s
azazelle-l3-hecate-8b-v1-2_v2 status is now deployed due to DeploymentManager action
azazelle-l3-hecate-8b-v1-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-l3-hecate-8b-v1-2_v2
Running pipeline stage ISVCDeleter
Checking if service azazelle-l3-hecate-8b-v1-2-v2 is running
Tearing down inference service azazelle-l3-hecate-8b-v1-2-v2
Service azazelle-l3-hecate-8b-v1-2-v2 has been torndown
Pipeline stage ISVCDeleter completed in 5.66s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-2-v2/config.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-hecate-8b-v1-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.31s
azazelle-l3-hecate-8b-v1-2_v2 status is now torndown due to DeploymentManager action