sao10k-l3-rp-v5-5

developer_uid: sao10k

submission_id: sao10k-l3-rp-v5-5_v1

model_name: RP-v5-5-1

model_group: Sao10K/L3-RP-v5.5

status: torndown

timestamp: 2024-07-11T10:57:12+00:00

num_battles: 34405

num_wins: 18808

celo_rating: 1220.21

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/L3-RP-v5.5

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: RP-v5-5-1

is_internal_developer: False

language_model: Sao10K/L3-RP-v5.5

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-11

win_ratio: 0.5466647289638134

generation_params: {'temperature': 1.4, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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 sao10k-l3-rp-v5-5-v1-mkmlizer
Waiting for job on sao10k-l3-rp-v5-5-v1-mkmlizer to finish
sao10k-l3-rp-v5-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-5-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v5-5-v1-mkmlizer: Downloaded to shared memory in 35.998s
sao10k-l3-rp-v5-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-5-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:34,  2.82s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:23,  3.30it/s]
Loading 0:  10%|▉         | 28/291 [00:05<00:33,  7.94it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:18, 13.55it/s]
Loading 0:  19%|█▊        | 54/291 [00:06<00:11, 20.74it/s]
Loading 0:  23%|██▎       | 66/291 [00:06<00:10, 22.14it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:07, 29.01it/s]
Loading 0:  31%|███▏      | 91/291 [00:06<00:04, 40.45it/s]
Loading 0:  36%|███▌      | 104/291 [00:06<00:03, 51.23it/s]
Loading 0:  40%|████      | 117/291 [00:06<00:02, 63.06it/s]
Loading 0:  45%|████▍     | 130/291 [00:07<00:02, 74.09it/s]
Loading 0:  49%|████▉     | 142/291 [00:07<00:01, 80.88it/s]
Loading 0:  54%|█████▍    | 157/291 [00:07<00:01, 95.64it/s]
Loading 0:  58%|█████▊    | 170/291 [00:07<00:02, 55.69it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 68.33it/s]
Loading 0:  67%|██████▋   | 195/291 [00:07<00:01, 74.75it/s]
Loading 0:  73%|███████▎  | 211/291 [00:08<00:00, 91.05it/s]
Loading 0:  77%|███████▋  | 223/291 [00:08<00:00, 96.05it/s]
Loading 0:  82%|████████▏ | 238/291 [00:08<00:00, 108.29it/s]
Loading 0:  86%|████████▋ | 251/291 [00:08<00:00, 110.79it/s]
Loading 0:  91%|█████████ | 265/291 [00:08<00:00, 116.12it/s]
Loading 0:  96%|█████████▌| 278/291 [00:08<00:00, 61.38it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v5-5-v1-mkmlizer: quantized model in 29.418s
sao10k-l3-rp-v5-5-v1-mkmlizer: Processed model Sao10K/L3-RP-v5.5 in 65.417s
sao10k-l3-rp-v5-5-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-5-v1
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-5-v1/config.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-5-v1/special_tokens_map.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-5-v1/tokenizer.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-5-v1/tokenizer_config.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-5-v1/flywheel_model.0.safetensors
sao10k-l3-rp-v5-5-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.
sao10k-l3-rp-v5-5-v1-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-5-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()
sao10k-l3-rp-v5-5-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v5-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v5-5-v1-mkmlizer: Saving duration: 0.577s
sao10k-l3-rp-v5-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.586s
sao10k-l3-rp-v5-5-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v5-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v5-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/config.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/special_tokens_map.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/vocab.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/merges.txt
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/tokenizer_config.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/tokenizer.json
sao10k-l3-rp-v5-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v5-5-v1_reward/reward.tensors
Job sao10k-l3-rp-v5-5-v1-mkmlizer completed after 93.97s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.96s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-5-v1
Waiting for inference service sao10k-l3-rp-v5-5-v1 to be ready
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Inference service sao10k-l3-rp-v5-5-v1 ready after 40.32263517379761s
Pipeline stage ISVCDeployer completed in 47.40s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9589779376983643s
Received healthy response to inference request in 1.332371473312378s
Received healthy response to inference request in 1.2887887954711914s
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\'"}')
Received healthy response to inference request in 1.258971929550171s
Received healthy response to inference request in 1.3485522270202637s
5 requests
0 failed requests
5th percentile: 1.264935302734375
10th percentile: 1.2708986759185792
20th percentile: 1.2828254222869873
30th percentile: 1.2975053310394287
40th percentile: 1.3149384021759034
50th percentile: 1.332371473312378
60th percentile: 1.3388437747955322
70th percentile: 1.3453160762786864
80th percentile: 1.4706373691558838
90th percentile: 1.7148076534271242
95th percentile: 1.836892795562744
99th percentile: 1.9345609092712401
mean time: 1.4375324726104737
Pipeline stage StressChecker completed in 7.80s
sao10k-l3-rp-v5-5_v1 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-5_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-5_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-5-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.99s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-5-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-5-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-5-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-5-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-5-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-5-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-5-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-5-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-5-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.36s
sao10k-l3-rp-v5-5_v1 status is now torndown due to DeploymentManager action