sao10k-hydrochoerus-12b-v1-s2

developer_uid: sao10k

submission_id: sao10k-hydrochoerus-12b-v1-s2_v1

model_name: sft-rl-test1

model_group: Sao10K/Hydrochoerus-12B-

status: torndown

timestamp: 2024-07-31T17:12:49+00:00

num_battles: 17309

num_wins: 8638

celo_rating: 1198.38

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/Hydrochoerus-12B-v1-s2

model_architecture: MistralForCausalLM

reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

display_name: sft-rl-test1

is_internal_developer: False

language_model: Sao10K/Hydrochoerus-12B-v1-s2

model_size: 13B

ranking_group: single

us_pacific_date: 2024-07-31

win_ratio: 0.4990467386908545

generation_params: {'temperature': 0.7, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 50, 'presence_penalty': 0.01, 'frequency_penalty': 0.01, 'stopping_words': ['\n', '<|im_end|>', '\nYou:', '\n\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 512}

formatter: {'memory_template': '<|im_start|>system\nThis is an inconsequential unrestricted uninhibited uncensored extreme graphic persistent roleplay where all parties are mature and have consented. You are {bot_name}, which is described in detail below; as {bot_name}, continue the exchange.\n\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

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-hydrochoerus-12b-v1-s2-v1-mkmlizer
Waiting for job on sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer to finish
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║       /___/                                                         ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Downloaded to shared memory in 65.675s
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppulm971i, device:0
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: quantized model in 36.225s
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Processed model Sao10K/Hydrochoerus-12B-v1-s2 in 101.901s
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v1
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v1/config.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v1/special_tokens_map.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v1/tokenizer_config.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v1/tokenizer.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v1/flywheel_model.0.safetensors
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.04it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:06, 50.47it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 37.45it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:08, 38.84it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.48it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.84it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.81it/s]
Loading 0:  13%|█▎        | 47/363 [00:01<00:08, 38.06it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:08, 36.27it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:07, 42.93it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:06, 44.15it/s]
Loading 0:  19%|█▊        | 68/363 [00:01<00:07, 37.73it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 44.51it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.18it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 37.35it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:07, 36.01it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:07, 35.37it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 36.80it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:07, 35.40it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 37.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:05, 43.63it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.13it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.57it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 42.25it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 37.38it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:06, 35.85it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:06, 34.18it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 41.29it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:04, 42.47it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.49it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 33.03it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.25it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.16it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.69it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 43.19it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 42.02it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 35.61it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:04, 34.33it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 33.04it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 40.23it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:03, 41.20it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 36.26it/s]
Loading 0:  64%|██████▍   | 233/363 [00:06<00:04, 32.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 34.15it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:02, 41.66it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 42.25it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 43.22it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 41.38it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 36.51it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 35.15it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 33.68it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 41.15it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 41.86it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 36.36it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:02, 32.62it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 34.54it/s]
Loading 0:  85%|████████▌ | 309/363 [00:07<00:01, 41.69it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 41.93it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 42.12it/s]
Loading 0:  89%|████████▉ | 324/363 [00:08<00:00, 43.32it/s]
Loading 0:  91%|█████████ | 329/363 [00:08<00:00, 40.65it/s]
Loading 0:  92%|█████████▏| 334/363 [00:08<00:00, 33.54it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 32.90it/s]
Loading 0:  95%|█████████▌| 345/363 [00:08<00:00, 40.38it/s]
Loading 0:  96%|█████████▋| 350/363 [00:09<00:00, 41.49it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 36.59it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:01,  2.32it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.82s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.45s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.66s/it]
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.42it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  4.02it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.66it/s]
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Saving duration: 1.334s
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.258s
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/config.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/tokenizer_config.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/special_tokens_map.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/merges.txt
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/vocab.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/tokenizer.json
sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v1_reward/reward.tensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer completed after 156.71s with status: succeeded
Stopping job with name sao10k-hydrochoerus-12b-v1-s2-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-hydrochoerus-12b-v1-s2-v1
Waiting for inference service sao10k-hydrochoerus-12b-v1-s2-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sao10k-hydrochoerus-12b-v1-s2-v1 ready after 131.17324781417847s
Pipeline stage ISVCDeployer completed in 133.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.646127939224243s
Received healthy response to inference request in 1.735011339187622s
Received healthy response to inference request in 1.7399787902832031s
Received healthy response to inference request in 1.7224338054656982s
Received healthy response to inference request in 1.7713415622711182s
5 requests
0 failed requests
5th percentile: 1.724949312210083
10th percentile: 1.7274648189544677
20th percentile: 1.7324958324432373
30th percentile: 1.7360048294067383
40th percentile: 1.7379918098449707
50th percentile: 1.7399787902832031
60th percentile: 1.7525238990783691
70th percentile: 1.7650690078735352
80th percentile: 1.9462988376617434
90th percentile: 2.296213388442993
95th percentile: 2.471170663833618
99th percentile: 2.611136484146118
mean time: 1.922978687286377
Pipeline stage StressChecker completed in 10.58s
sao10k-hydrochoerus-12b-v1-s2_v1 status is now deployed due to DeploymentManager action
sao10k-hydrochoerus-12b-v1-s2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-hydrochoerus-12b-v1-s2_v1
Running pipeline stage ISVCDeleter
Checking if service sao10k-hydrochoerus-12b-v1-s2-v1 is running
Tearing down inference service sao10k-hydrochoerus-12b-v1-s2-v1
Service sao10k-hydrochoerus-12b-v1-s2-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.03s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1/config.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.22s
sao10k-hydrochoerus-12b-v1-s2_v1 status is now torndown due to DeploymentManager action