azazelle-l3-tyche-8b-v1-0

developer_uid: notthesideeye

submission_id: azazelle-l3-tyche-8b-v1-0_v3

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

model_group: Azazelle/L3-Tyche-8B-v1.

status: torndown

timestamp: 2024-07-11T03:43:52+00:00

num_battles: 29217

num_wins: 15800

celo_rating: 1215.61

family_friendly_score: 0.0

submission_type: basic

model_repo: Azazelle/L3-Tyche-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-Tyche-8B-v1_0

is_internal_developer: False

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

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-10

win_ratio: 0.5407810521271862

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}<|eot_id|>\n\n", 'prompt_template': '{prompt}<|eot_id|>\n\n', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>\n\n', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>\n\n', '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-tyche-8b-v1-0-v3-mkmlizer
Waiting for job on azazelle-l3-tyche-8b-v1-0-v3-mkmlizer to finish
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║     _____            __           __                                ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║       /___/                                                         ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║                                                                     ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  https://mk1.ai                                                     ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║                                                                     ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  belonging to:                                                      ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║                                                                     ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  Chai Research Corp.                                                ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ║                                                                     ║
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Downloaded to shared memory in 46.052s
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: quantizing model to /dev/shm/model_cache
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:20,  2.77s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:30,  1.35it/s]
Loading 0:   3%|▎         | 10/291 [00:06<01:56,  2.41it/s]
Loading 0:   5%|▌         | 15/291 [00:06<01:02,  4.42it/s]
Loading 0:   8%|▊         | 24/291 [00:06<00:29,  9.13it/s]
Loading 0:  11%|█▏        | 33/291 [00:06<00:17, 14.78it/s]
Loading 0:  14%|█▍        | 42/291 [00:06<00:11, 21.20it/s]
Loading 0:  18%|█▊        | 51/291 [00:06<00:08, 28.08it/s]
Loading 0:  21%|██        | 60/291 [00:07<00:09, 24.26it/s]
Loading 0:  24%|██▎       | 69/291 [00:07<00:07, 30.60it/s]
Loading 0:  27%|██▋       | 78/291 [00:07<00:05, 36.98it/s]
Loading 0:  30%|██▉       | 87/291 [00:07<00:04, 42.82it/s]
Loading 0:  33%|███▎      | 96/291 [00:07<00:04, 48.23it/s]
Loading 0:  36%|███▌      | 105/291 [00:07<00:03, 52.79it/s]
Loading 0:  39%|███▉      | 113/291 [00:08<00:05, 34.54it/s]
Loading 0:  42%|████▏     | 122/291 [00:08<00:04, 40.78it/s]
Loading 0:  45%|████▌     | 131/291 [00:08<00:03, 46.34it/s]
Loading 0:  48%|████▊     | 139/291 [00:08<00:02, 52.43it/s]
Loading 0:  51%|█████     | 148/291 [00:08<00:02, 56.42it/s]
Loading 0:  54%|█████▍    | 157/291 [00:08<00:02, 59.51it/s]
Loading 0:  57%|█████▋    | 166/291 [00:09<00:03, 35.38it/s]
Loading 0:  60%|██████    | 175/291 [00:09<00:02, 41.40it/s]
Loading 0:  63%|██████▎   | 184/291 [00:09<00:02, 46.88it/s]
Loading 0:  66%|██████▋   | 193/291 [00:09<00:01, 51.74it/s]
Loading 0:  69%|██████▉   | 202/291 [00:09<00:01, 55.68it/s]
Loading 0:  73%|███████▎  | 211/291 [00:10<00:01, 58.47it/s]
Loading 0:  75%|███████▍  | 218/291 [00:10<00:02, 34.78it/s]
Loading 0:  77%|███████▋  | 223/291 [00:10<00:01, 36.73it/s]
Loading 0:  79%|███████▉  | 230/291 [00:10<00:01, 42.55it/s]
Loading 0:  82%|████████▏ | 239/291 [00:10<00:01, 48.78it/s]
Loading 0:  85%|████████▌ | 248/291 [00:11<00:00, 53.97it/s]
Loading 0:  88%|████████▊ | 257/291 [00:11<00:00, 57.86it/s]
Loading 0:  91%|█████████▏| 266/291 [00:11<00:00, 35.06it/s]
Loading 0:  95%|█████████▍| 275/291 [00:11<00:00, 41.23it/s]
Loading 0:  97%|█████████▋| 283/291 [00:11<00:00, 47.74it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: quantized model in 31.978s
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Processed model Azazelle/L3-Tyche-8B-v1.0 in 78.031s
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: creating bucket guanaco-mkml-models
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/azazelle-l3-tyche-8b-v1-0-v3
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/azazelle-l3-tyche-8b-v1-0-v3/config.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/azazelle-l3-tyche-8b-v1-0-v3/tokenizer_config.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/azazelle-l3-tyche-8b-v1-0-v3/special_tokens_map.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/azazelle-l3-tyche-8b-v1-0-v3/tokenizer.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/azazelle-l3-tyche-8b-v1-0-v3/flywheel_model.0.safetensors
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
azazelle-l3-tyche-8b-v1-0-v3-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-tyche-8b-v1-0-v3-mkmlizer:   warnings.warn(
azazelle-l3-tyche-8b-v1-0-v3-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-tyche-8b-v1-0-v3-mkmlizer:   warnings.warn(
azazelle-l3-tyche-8b-v1-0-v3-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-tyche-8b-v1-0-v3-mkmlizer:   warnings.warn(
azazelle-l3-tyche-8b-v1-0-v3-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-tyche-8b-v1-0-v3-mkmlizer:   warnings.warn(
azazelle-l3-tyche-8b-v1-0-v3-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-tyche-8b-v1-0-v3-mkmlizer:   return self.fget.__get__(instance, owner)()
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Saving duration: 0.525s
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.111s
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: creating bucket guanaco-reward-models
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/config.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/tokenizer_config.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/merges.txt
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/special_tokens_map.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/vocab.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/tokenizer.json
azazelle-l3-tyche-8b-v1-0-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/azazelle-l3-tyche-8b-v1-0-v3_reward/reward.tensors
Job azazelle-l3-tyche-8b-v1-0-v3-mkmlizer completed after 104.4s with status: succeeded
Stopping job with name azazelle-l3-tyche-8b-v1-0-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.38s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service azazelle-l3-tyche-8b-v1-0-v3
Waiting for inference service azazelle-l3-tyche-8b-v1-0-v3 to be ready
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
Inference service azazelle-l3-tyche-8b-v1-0-v3 ready after 40.38745450973511s
Pipeline stage ISVCDeployer completed in 47.55s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.158722162246704s
Received healthy response to inference request in 1.3620755672454834s
Received healthy response to inference request in 1.2934730052947998s
Received healthy response to inference request in 1.2704739570617676s
Received healthy response to inference request in 1.2548902034759521s
5 requests
0 failed requests
5th percentile: 1.2580069541931151
10th percentile: 1.2611237049102784
20th percentile: 1.2673572063446046
30th percentile: 1.275073766708374
40th percentile: 1.284273386001587
50th percentile: 1.2934730052947998
60th percentile: 1.3209140300750732
70th percentile: 1.3483550548553467
80th percentile: 1.5214048862457277
90th percentile: 1.840063524246216
95th percentile: 1.9993928432464598
99th percentile: 2.126856298446655
mean time: 1.4679269790649414
Pipeline stage StressChecker completed in 8.05s
azazelle-l3-tyche-8b-v1-0_v3 status is now deployed due to DeploymentManager action
azazelle-l3-tyche-8b-v1-0_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of azazelle-l3-tyche-8b-v1-0_v3
Running pipeline stage ISVCDeleter
Checking if service azazelle-l3-tyche-8b-v1-0-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.83s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key azazelle-l3-tyche-8b-v1-0-v3/config.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key azazelle-l3-tyche-8b-v1-0-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
azazelle-l3-tyche-8b-v1-0_v3 status is now torndown due to DeploymentManager action