bbchicago-test-sfw-8b-l3-v0-1

submission_id: bbchicago-test-sfw-8b-l3-v0-1_v1

developer_uid: Bbbrun0

best_of: 16

celo_rating: 1189.11

display_name: bbchicago-test-sfw-8b-l3-v0-1_v1

family_friendly_score: 0.0

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}

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 80, '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: BBChicago/Test-sfw-8B-L3_v0.1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: BBChicago/Test-sfw-8B-L3

model_name: bbchicago-test-sfw-8b-l3-v0-1_v1

model_num_parameters: 8030261248.0

model_repo: BBChicago/Test-sfw-8B-L3_v0.1

model_size: 8B

num_battles: 24077

num_wins: 12264

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: 2024-06-28T14:28:12+00:00

us_pacific_date: 2024-06-28

win_ratio: 0.5093657847738505

Resubmit model

Running pipeline stage MKMLizer
Starting job with name bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer
Waiting for job on bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer to finish
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║                                                                     ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║                                                                     ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║                                                                     ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ║                                                                     ║
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Downloaded to shared memory in 35.131s
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 137.76it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 155.25it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 159.87it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 161.76it/s]
Loading 0:  29%|██▉       | 85/291 [00:00<00:02, 87.36it/s] 
Loading 0:  35%|███▌      | 103/291 [00:00<00:01, 104.49it/s]
Loading 0:  42%|████▏     | 121/291 [00:00<00:01, 120.03it/s]
Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 132.71it/s]
Loading 0:  54%|█████▍    | 157/291 [00:01<00:00, 141.70it/s]
Loading 0:  60%|██████    | 176/291 [00:01<00:00, 153.32it/s]
Loading 0:  66%|██████▋   | 193/291 [00:01<00:01, 94.65it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:01<00:00, 104.24it/s]
Loading 0:  77%|███████▋  | 224/291 [00:01<00:00, 99.87it/s] 
Loading 0:  81%|████████▏ | 237/291 [00:02<00:00, 101.68it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 117.39it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 131.37it/s]
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00,  9.57it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: quantized model in 22.649s
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Processed model BBChicago/Test-sfw-8B-L3_v0.1 in 60.297s
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-test-sfw-8b-l3-v0-1-v1
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-test-sfw-8b-l3-v0-1-v1/tokenizer_config.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-test-sfw-8b-l3-v0-1-v1/config.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-test-sfw-8b-l3-v0-1-v1/special_tokens_map.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-test-sfw-8b-l3-v0-1-v1/tokenizer.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-test-sfw-8b-l3-v0-1-v1/flywheel_model.0.safetensors
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer:   warnings.warn(
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer:   warnings.warn(
bbchicago-test-sfw-8b-l3-v0-1-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.
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer:   warnings.warn(
bbchicago-test-sfw-8b-l3-v0-1-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()
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Saving duration: 0.404s
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.393s
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/config.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/special_tokens_map.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/tokenizer_config.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/merges.txt
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/vocab.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/tokenizer.json
bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-test-sfw-8b-l3-v0-1-v1_reward/reward.tensors
Job bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer completed after 93.72s with status: succeeded
Stopping job with name bbchicago-test-sfw-8b-l3-v0-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-test-sfw-8b-l3-v0-1-v1
Waiting for inference service bbchicago-test-sfw-8b-l3-v0-1-v1 to be ready
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42886->127.0.0.1:8080: read: connection reset by peer\n')
Inference service bbchicago-test-sfw-8b-l3-v0-1-v1 ready after 160.81539630889893s
Pipeline stage ISVCDeployer completed in 167.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1662228107452393s
Received healthy response to inference request in 1.2227442264556885s
Received healthy response to inference request in 1.257718563079834s
Received healthy response to inference request in 2.2899527549743652s
Received healthy response to inference request in 1.433847188949585s
5 requests
0 failed requests
5th percentile: 1.2297390937805175
10th percentile: 1.2367339611053467
20th percentile: 1.250723695755005
30th percentile: 1.2929442882537843
40th percentile: 1.3633957386016846
50th percentile: 1.433847188949585
60th percentile: 1.7267974376678465
70th percentile: 2.019747686386108
80th percentile: 2.1909687995910643
90th percentile: 2.2404607772827148
95th percentile: 2.26520676612854
99th percentile: 2.2850035572052003
mean time: 1.6740971088409424
Pipeline stage StressChecker completed in 9.15s
bbchicago-test-sfw-8b-l3-v0-1_v1 status is now deployed due to DeploymentManager action
bbchicago-test-sfw-8b-l3-v0-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-test-sfw-8b-l3-v0-1_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-test-sfw-8b-l3-v0-1-v1 is running
admin requested tearing down of blend_buham_2024-06-29
blend_buham_2024-06-29 status is now torndown due to DeploymentManager action
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 9.91s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-test-sfw-8b-l3-v0-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.43s
bbchicago-test-sfw-8b-l3-v0-1_v1 status is now torndown due to DeploymentManager action
admin requested tearing down of bbchicago-test-sfw-8b-l3-v0-1_v1
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 0.45s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLModelDeleter completed in 0.36s
bbchicago-test-sfw-8b-l3-v0-1_v1 status is now torndown due to DeploymentManager action