submission_id: sao10k-l3-rp-v5-2_v2
developer_uid: sao10k
best_of: 4
celo_rating: 1201.23
display_name: expr22
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': 1.3, 'top_p': 0.8, 'min_p': 0.1, 'top_k': 50, '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': 4, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Sao10K/L3-RP-v5.2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/L3-RP-v5.2
model_name: expr22
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3-RP-v5.2
model_size: 8B
num_battles: 39137
num_wins: 20324
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: 2024-07-07T22:39:02+00:00
us_pacific_date: 2024-07-07
win_ratio: 0.519303983442778
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-rp-v5-2-v2-mkmlizer
Waiting for job on sao10k-l3-rp-v5-2-v2-mkmlizer to finish
sao10k-l3-rp-v5-2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-2-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
sao10k-l3-rp-v5-2-v2-mkmlizer: Downloaded to shared memory in 42.950s
sao10k-l3-rp-v5-2-v2-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-2-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:44,  2.23s/it]
Loading 0:   5%|▌         | 16/291 [00:04<00:57,  4.78it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:21, 11.77it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.29it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.92it/s]
Loading 0:  27%|██▋       | 80/291 [00:05<00:05, 36.36it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:03, 49.34it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 65.59it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 82.46it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 98.31it/s]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:01, 77.10it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 93.26it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 108.52it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 119.12it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 130.26it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 140.23it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:00, 91.05it/s] 
Loading 0:  99%|█████████▉| 288/291 [00:06<00:00, 103.13it/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-v2-mkmlizer: quantized model in 22.632s
sao10k-l3-rp-v5-2-v2-mkmlizer: Processed model Sao10K/L3-RP-v5.2 in 65.582s
sao10k-l3-rp-v5-2-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v2
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v2/config.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v2/special_tokens_map.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v2/tokenizer_config.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v2/tokenizer.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v2/flywheel_model.0.safetensors
sao10k-l3-rp-v5-2-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
sao10k-l3-rp-v5-2-v2-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-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v2-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-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v2-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-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v2-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-v2-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
sao10k-l3-rp-v5-2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-rp-v5-2-v2-mkmlizer: Saving duration: 0.386s
sao10k-l3-rp-v5-2-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.411s
sao10k-l3-rp-v5-2-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-rp-v5-2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-rp-v5-2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/special_tokens_map.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/tokenizer_config.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/merges.txt
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/config.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/vocab.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/tokenizer.json
sao10k-l3-rp-v5-2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v2_reward/reward.tensors
Job sao10k-l3-rp-v5-2-v2-mkmlizer completed after 114.16s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-2-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-2-v2
Waiting for inference service sao10k-l3-rp-v5-2-v2 to be ready
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v5: ('http://chaiml-sao10k-l3-rp-v3-3-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39548->127.0.0.1:8080: read: connection reset by peer\n')
Inference service sao10k-l3-rp-v5-2-v2 ready after 40.302955627441406s
Pipeline stage ISVCDeployer completed in 47.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9124469757080078s
Received healthy response to inference request in 1.1211402416229248s
Received healthy response to inference request in 1.130751132965088s
Received healthy response to inference request in 1.1044237613677979s
Received healthy response to inference request in 1.1206700801849365s
5 requests
0 failed requests
5th percentile: 1.1076730251312257
10th percentile: 1.1109222888946533
20th percentile: 1.1174208164215087
30th percentile: 1.1207641124725343
40th percentile: 1.1209521770477295
50th percentile: 1.1211402416229248
60th percentile: 1.1249845981597901
70th percentile: 1.1288289546966552
80th percentile: 1.287090301513672
90th percentile: 1.5997686386108398
95th percentile: 1.7561078071594236
99th percentile: 1.881179141998291
mean time: 1.277886438369751
Pipeline stage StressChecker completed in 6.99s
sao10k-l3-rp-v5-2_v2 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-2_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-2-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.01s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-2-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.65s
sao10k-l3-rp-v5-2_v2 status is now torndown due to DeploymentManager action