developer_uid: sao10k
submission_id: sao10k-l3-rp-v5-2_v3
model_name: 5-2-Align
model_group: Sao10K/L3-RP-v5.2
status: torndown
timestamp: 2024-07-09T11:04:46+00:00
num_battles: 31977
num_wins: 13829
celo_rating: 1150.99
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/L3-RP-v5.2
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/CHAI_alignment_reward_model
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 5-2-Align
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: 0.4324670857178597
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Starting job with name sao10k-l3-rp-v5-2-v3-mkmlizer
Waiting for job on sao10k-l3-rp-v5-2-v3-mkmlizer to finish
sao10k-l3-rp-v5-2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-rp-v5-2-v3-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║       /___/                                                         ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  Version: 0.8.14                                                    ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ║                                                                     ║
sao10k-l3-rp-v5-2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-rp-v5-2-v3-mkmlizer: Downloaded to shared memory in 21.421s
sao10k-l3-rp-v5-2-v3-mkmlizer: quantizing model to /dev/shm/model_cache
sao10k-l3-rp-v5-2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-rp-v5-2-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:14,  2.33s/it]
Loading 0:   5%|▍         | 14/291 [00:04<01:09,  3.96it/s]
Loading 0:   9%|▉         | 27/291 [00:04<00:29,  9.06it/s]
Loading 0:  14%|█▎        | 40/291 [00:04<00:16, 15.67it/s]
Loading 0:  18%|█▊        | 51/291 [00:05<00:10, 22.26it/s]
Loading 0:  21%|██▏       | 62/291 [00:05<00:09, 23.59it/s]
Loading 0:  26%|██▌       | 76/291 [00:05<00:06, 34.24it/s]
Loading 0:  30%|██▉       | 87/291 [00:05<00:04, 42.52it/s]
Loading 0:  35%|███▌      | 103/291 [00:05<00:03, 58.45it/s]
Loading 0:  40%|███▉      | 115/291 [00:05<00:02, 67.09it/s]
Loading 0:  45%|████▍     | 130/291 [00:06<00:01, 81.73it/s]
Loading 0:  49%|████▉     | 142/291 [00:06<00:01, 87.58it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 100.46it/s]
Loading 0:  58%|█████▊    | 170/291 [00:06<00:01, 64.93it/s] 
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 76.94it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 81.09it/s]
Loading 0:  73%|███████▎  | 211/291 [00:06<00:00, 95.45it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:00, 97.91it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:00, 108.78it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:00, 110.67it/s]
Loading 0:  91%|█████████ | 265/291 [00:07<00:00, 117.11it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 68.71it/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-v3-mkmlizer: quantized model in 24.315s
sao10k-l3-rp-v5-2-v3-mkmlizer: Processed model Sao10K/L3-RP-v5.2 in 45.737s
sao10k-l3-rp-v5-2-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-rp-v5-2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-rp-v5-2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v3
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v3/tokenizer_config.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v3/special_tokens_map.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v3/config.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v3/tokenizer.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-rp-v5-2-v3/flywheel_model.0.safetensors
sao10k-l3-rp-v5-2-v3-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
sao10k-l3-rp-v5-2-v3-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-v3-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v3-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-v3-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v3-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-v3-mkmlizer:   warnings.warn(
sao10k-l3-rp-v5-2-v3-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-v3-mkmlizer:   warnings.warn(
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/special_tokens_map.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/tokenizer_config.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/config.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/merges.txt
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/vocab.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/tokenizer.json
sao10k-l3-rp-v5-2-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-rp-v5-2-v3_reward/reward.tensors
Job sao10k-l3-rp-v5-2-v3-mkmlizer completed after 73.58s with status: succeeded
Stopping job with name sao10k-l3-rp-v5-2-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-rp-v5-2-v3
Waiting for inference service sao10k-l3-rp-v5-2-v3 to be ready
Inference service sao10k-l3-rp-v5-2-v3 ready after 40.49532151222229s
Pipeline stage ISVCDeployer completed in 47.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8864870071411133s
Received healthy response to inference request in 1.2689366340637207s
Received healthy response to inference request in 1.2464196681976318s
Received healthy response to inference request in 1.1962924003601074s
Received healthy response to inference request in 1.2782762050628662s
5 requests
0 failed requests
5th percentile: 1.2063178539276123
10th percentile: 1.216343307495117
20th percentile: 1.236394214630127
30th percentile: 1.2509230613708495
40th percentile: 1.2599298477172851
50th percentile: 1.2689366340637207
60th percentile: 1.272672462463379
70th percentile: 1.2764082908630372
80th percentile: 1.3999183654785157
90th percentile: 1.6432026863098146
95th percentile: 1.7648448467254638
99th percentile: 1.8621585750579834
mean time: 1.375282382965088
Pipeline stage StressChecker completed in 7.60s
sao10k-l3-rp-v5-2_v3 status is now deployed due to DeploymentManager action
sao10k-l3-rp-v5-2_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-rp-v5-2_v3
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-rp-v5-2-v3 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.04s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-2-v3/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-rp-v5-2-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-rp-v5-2-v3_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-rp-v5-2-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.48s
sao10k-l3-rp-v5-2_v3 status is now torndown due to DeploymentManager action