sao10k-l3-rp-v5-2

developer_uid: sao10k

submission_id: sao10k-l3-rp-v5-2_v5

model_name: RP-v5-Expr22

model_group: Sao10K/L3-RP-v5.2

status: torndown

timestamp: 2024-07-09T15:39:24+00:00

num_battles: 29682

num_wins: 15802

celo_rating: 1216.94

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/L3-RP-v5.2

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: RP-v5-Expr22

is_internal_developer: False

language_model: Sao10K/L3-RP-v5.2

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-09

win_ratio: 0.5323765244929587

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-v5-2-v5-mkmlizer
Waiting for job on sao10k-l3-rp-v5-2-v5-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
sao10k-l3-rp-v5-2-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-2-v5-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v5-2-v5-mkmlizer: Downloaded to shared memory in 29.564s
sao10k-l3-rp-v5-2-v5-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-2-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-2-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:39,  2.42s/it]
Loading 0:   3%|▎         | 10/291 [00:04<01:44,  2.69it/s]
Loading 0:   6%|▌         | 18/291 [00:05<00:47,  5.72it/s]
Loading 0:  11%|█         | 31/291 [00:05<00:21, 12.20it/s]
Loading 0:  14%|█▎        | 40/291 [00:05<00:14, 17.62it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:09, 24.57it/s]
Loading 0:  21%|██        | 60/291 [00:05<00:09, 24.62it/s]
Loading 0:  24%|██▎       | 69/291 [00:05<00:07, 31.39it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:05, 38.57it/s]
Loading 0:  31%|███       | 89/291 [00:06<00:04, 49.57it/s]
Loading 0:  34%|███▎      | 98/291 [00:06<00:03, 56.65it/s]
Loading 0:  37%|███▋      | 107/291 [00:06<00:02, 62.78it/s]
Loading 0:  42%|████▏     | 121/291 [00:06<00:02, 77.21it/s]
Loading 0:  45%|████▌     | 131/291 [00:06<00:02, 79.67it/s]
Loading 0:  48%|████▊     | 141/291 [00:06<00:01, 82.49it/s]
Loading 0:  52%|█████▏    | 152/291 [00:06<00:01, 89.12it/s]
Loading 0:  56%|█████▌    | 162/291 [00:06<00:01, 90.26it/s]
Loading 0:  59%|█████▉    | 172/291 [00:07<00:01, 60.67it/s]
Loading 0:  63%|██████▎   | 184/291 [00:07<00:01, 71.27it/s]
Loading 0:  67%|██████▋   | 194/291 [00:07<00:01, 76.77it/s]
Loading 0:  70%|███████   | 205/291 [00:07<00:01, 84.62it/s]
Loading 0:  74%|███████▍  | 216/291 [00:07<00:00, 90.45it/s]
Loading 0:  79%|███████▊  | 229/291 [00:07<00:00, 98.03it/s]
Loading 0:  82%|████████▏ | 240/291 [00:07<00:00, 94.52it/s]
Loading 0:  87%|████████▋ | 253/291 [00:07<00:00, 103.59it/s]
Loading 0:  91%|█████████ | 265/291 [00:08<00:00, 106.47it/s]
Loading 0:  95%|█████████▍| 276/291 [00:08<00:00, 68.74it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
sao10k-l3-rp-v5-2-v5-mkmlizer: quantized model in 20.183s
sao10k-l3-rp-v5-2-v5-mkmlizer: Processed model Sao10K/L3-RP-v5.2 in 49.748s
sao10k-l3-rp-v5-2-v5-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-2-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-2-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v5
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v5/special_tokens_map.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v5/config.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v5/tokenizer_config.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v5/tokenizer.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v5/flywheel_model.0.safetensors
sao10k-l3-rp-v5-2-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v5-2-v5-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.
sao10k-l3-rp-v5-2-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v5-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`.
sao10k-l3-rp-v5-2-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v5-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.
sao10k-l3-rp-v5-2-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v5-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-v5-2-v5-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v5-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-v5-2-v5-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v5-2-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v5-2-v5-mkmlizer: Saving duration: 0.271s
sao10k-l3-rp-v5-2-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.991s
sao10k-l3-rp-v5-2-v5-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v5-2-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v5-2-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/special_tokens_map.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/merges.txt
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/config.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/tokenizer_config.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/vocab.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/tokenizer.json
sao10k-l3-rp-v5-2-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v5_reward/reward.tensors
Job sao10k-l3-rp-v5-2-v5-mkmlizer completed after 220.91s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-2-v5-mkmlizer
Pipeline stage MKMLizer completed in 222.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-2-v5
Waiting for inference service sao10k-l3-rp-v5-2-v5 to be ready
Inference service sao10k-l3-rp-v5-2-v5 ready after 40.30928111076355s
Pipeline stage ISVCDeployer completed in 47.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.033273458480835s
Received healthy response to inference request in 2.318967580795288s
Received healthy response to inference request in 1.3297011852264404s
Received healthy response to inference request in 4.3249335289001465s
Received healthy response to inference request in 1.3218286037445068s
5 requests
0 failed requests
5th percentile: 1.3234031200408936
10th percentile: 1.3249776363372803
20th percentile: 1.3281266689300537
30th percentile: 1.4704156398773194
40th percentile: 1.7518445491790773
50th percentile: 2.033273458480835
60th percentile: 2.147551107406616
70th percentile: 2.2618287563323975
80th percentile: 2.72016077041626
90th percentile: 3.5225471496582035
95th percentile: 3.9237403392791745
99th percentile: 4.244694890975952
mean time: 2.2657408714294434
Pipeline stage StressChecker completed in 12.00s
sao10k-l3-rp-v5-2_v5 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-2_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-2_v5
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-2-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.09s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-2-v5/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-2-v5_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.84s
sao10k-l3-rp-v5-2_v5 status is now torndown due to DeploymentManager action