v000000-swallowmaid-8b-l_7904

submission_id: v000000-swallowmaid-8b-l_7904_v1

developer_uid: v000000

best_of: 16

celo_rating: 1190.51

display_name: SwallowMaid-8B-L3-SPPO-ablit-01

family_friendly_score: 0.0

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}

generation_params: {'temperature': 1.2, 'top_p': 0.73, 'min_p': 0.11, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: v000000/SwallowMaid-8B-L3-SPPO-abliterated

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: v000000/SwallowMaid-8B-L

model_name: SwallowMaid-8B-L3-SPPO-ablit-01

model_num_parameters: 8030261248.0

model_repo: v000000/SwallowMaid-8B-L3-SPPO-abliterated

model_size: 8B

num_battles: 32675

num_wins: 16415

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-09T20:47:27+00:00

us_pacific_date: 2024-07-09

win_ratio: 0.502371843917368

Resubmit model

Running pipeline stage MKMLizer
Starting job with name v000000-swallowmaid-8b-l-7904-v1-mkmlizer
Waiting for job on v000000-swallowmaid-8b-l-7904-v1-mkmlizer to finish
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║     _____            __           __                                ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║       /___/                                                         ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║                                                                     ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  https://mk1.ai                                                     ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║                                                                     ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  belonging to:                                                      ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║                                                                     ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  Chai Research Corp.                                                ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ║                                                                     ║
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Downloaded to shared memory in 69.024s
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: quantizing model to /dev/shm/model_cache
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:21,  2.77s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:30,  1.35it/s]
Loading 0:   3%|▎         | 10/291 [00:06<01:55,  2.43it/s]
Loading 0:   5%|▌         | 15/291 [00:06<01:01,  4.45it/s]
Loading 0:   8%|▊         | 24/291 [00:06<00:29,  9.21it/s]
Loading 0:  11%|█▏        | 33/291 [00:06<00:17, 14.90it/s]
Loading 0:  14%|█▍        | 42/291 [00:06<00:11, 21.36it/s]
Loading 0:  18%|█▊        | 51/291 [00:06<00:08, 28.28it/s]
Loading 0:  21%|██        | 60/291 [00:07<00:09, 24.26it/s]
Loading 0:  24%|██▎       | 69/291 [00:07<00:07, 30.58it/s]
Loading 0:  27%|██▋       | 78/291 [00:07<00:05, 37.04it/s]
Loading 0:  30%|██▉       | 87/291 [00:07<00:04, 43.27it/s]
Loading 0:  33%|███▎      | 96/291 [00:07<00:03, 48.80it/s]
Loading 0:  36%|███▌      | 105/291 [00:07<00:03, 53.53it/s]
Loading 0:  39%|███▉      | 113/291 [00:08<00:05, 33.86it/s]
Loading 0:  42%|████▏     | 122/291 [00:08<00:04, 40.18it/s]
Loading 0:  45%|████▌     | 131/291 [00:08<00:03, 46.10it/s]
Loading 0:  48%|████▊     | 140/291 [00:08<00:02, 51.20it/s]
Loading 0:  51%|█████     | 148/291 [00:08<00:02, 56.90it/s]
Loading 0:  54%|█████▍    | 157/291 [00:08<00:02, 59.90it/s]
Loading 0:  57%|█████▋    | 166/291 [00:09<00:03, 35.67it/s]
Loading 0:  60%|██████    | 175/291 [00:09<00:02, 41.60it/s]
Loading 0:  63%|██████▎   | 184/291 [00:09<00:02, 47.19it/s]
Loading 0:  66%|██████▋   | 193/291 [00:09<00:01, 52.30it/s]
Loading 0:  69%|██████▉   | 202/291 [00:09<00:01, 56.14it/s]
Loading 0:  73%|███████▎  | 211/291 [00:10<00:01, 59.31it/s]
Loading 0:  75%|███████▍  | 218/291 [00:10<00:02, 35.45it/s]
Loading 0:  77%|███████▋  | 224/291 [00:10<00:01, 38.28it/s]
Loading 0:  79%|███████▉  | 230/291 [00:10<00:01, 33.99it/s]
Loading 0:  82%|████████▏ | 238/291 [00:10<00:01, 41.73it/s]
Loading 0:  85%|████████▍ | 247/291 [00:11<00:00, 47.98it/s]
Loading 0:  88%|████████▊ | 256/291 [00:11<00:00, 53.48it/s]
Loading 0:  91%|█████████ | 265/291 [00:11<00:00, 57.78it/s]
Loading 0:  93%|█████████▎| 272/291 [00:11<00:00, 33.78it/s]
Loading 0:  95%|█████████▌| 277/291 [00:11<00:00, 35.99it/s]
Loading 0:  98%|█████████▊| 285/291 [00:12<00:00, 41.70it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: quantized model in 31.979s
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Processed model v000000/SwallowMaid-8B-L3-SPPO-abliterated in 101.003s
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: creating bucket guanaco-mkml-models
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/v000000-swallowmaid-8b-l-7904-v1
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/v000000-swallowmaid-8b-l-7904-v1/special_tokens_map.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/v000000-swallowmaid-8b-l-7904-v1/tokenizer_config.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/v000000-swallowmaid-8b-l-7904-v1/config.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/v000000-swallowmaid-8b-l-7904-v1/tokenizer.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/v000000-swallowmaid-8b-l-7904-v1/flywheel_model.0.safetensors
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
v000000-swallowmaid-8b-l-7904-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.
v000000-swallowmaid-8b-l-7904-v1-mkmlizer:   warnings.warn(
v000000-swallowmaid-8b-l-7904-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`.
v000000-swallowmaid-8b-l-7904-v1-mkmlizer:   warnings.warn(
v000000-swallowmaid-8b-l-7904-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.
v000000-swallowmaid-8b-l-7904-v1-mkmlizer:   warnings.warn(
v000000-swallowmaid-8b-l-7904-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.
v000000-swallowmaid-8b-l-7904-v1-mkmlizer:   warnings.warn(
v000000-swallowmaid-8b-l-7904-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()
v000000-swallowmaid-8b-l-7904-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Saving duration: 0.509s
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.339s
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: creating bucket guanaco-reward-models
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward/tokenizer_config.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward/special_tokens_map.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward/config.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward/vocab.json
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward/merges.txt
v000000-swallowmaid-8b-l-7904-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/v000000-swallowmaid-8b-l-7904-v1_reward/tokenizer.json
Job v000000-swallowmaid-8b-l-7904-v1-mkmlizer completed after 135.59s with status: succeeded
Stopping job with name v000000-swallowmaid-8b-l-7904-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service v000000-swallowmaid-8b-l-7904-v1
Waiting for inference service v000000-swallowmaid-8b-l-7904-v1 to be ready
Inference service v000000-swallowmaid-8b-l-7904-v1 ready after 40.18811583518982s
Pipeline stage ISVCDeployer completed in 47.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0753140449523926s
Received healthy response to inference request in 1.3671941757202148s
Received healthy response to inference request in 1.326047658920288s
Received healthy response to inference request in 1.301027536392212s
Received healthy response to inference request in 1.3782267570495605s
5 requests
0 failed requests
5th percentile: 1.3060315608978272
10th percentile: 1.3110355854034423
20th percentile: 1.3210436344146728
30th percentile: 1.3342769622802735
40th percentile: 1.350735569000244
50th percentile: 1.3671941757202148
60th percentile: 1.371607208251953
70th percentile: 1.3760202407836915
80th percentile: 1.517644214630127
90th percentile: 1.79647912979126
95th percentile: 1.9358965873718261
99th percentile: 2.0474305534362793
mean time: 1.4895620346069336
Pipeline stage StressChecker completed in 8.10s
v000000-swallowmaid-8b-l_7904_v1 status is now deployed due to DeploymentManager action
v000000-swallowmaid-8b-l_7904_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of v000000-swallowmaid-8b-l_7904_v1
Running pipeline stage ISVCDeleter
Checking if service v000000-swallowmaid-8b-l-7904-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key v000000-swallowmaid-8b-l-7904-v1/config.json from bucket guanaco-mkml-models
Deleting key v000000-swallowmaid-8b-l-7904-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key v000000-swallowmaid-8b-l-7904-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key v000000-swallowmaid-8b-l-7904-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key v000000-swallowmaid-8b-l-7904-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/config.json from bucket guanaco-reward-models
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key v000000-swallowmaid-8b-l-7904-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.62s
v000000-swallowmaid-8b-l_7904_v1 status is now torndown due to DeploymentManager action