sao10k-hydrochoerus-12b-v1-s2

developer_uid: sao10k

submission_id: sao10k-hydrochoerus-12b-v1-s2_v2

model_name: sft-rl-test1-minp

model_group: Sao10K/Hydrochoerus-12B-

status: torndown

timestamp: 2024-07-31T17:13:14+00:00

num_battles: 13684

num_wins: 6882

celo_rating: 1201.62

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-minp

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: 0.502923121894183

generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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-v2-mkmlizer
Waiting for job on sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer to finish
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║       /___/                                                         ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ║                                                                     ║
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: quantized model in 35.820s
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: Processed model Sao10K/Hydrochoerus-12B-v1-s2 in 81.999s
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v2
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v2/config.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v2/special_tokens_map.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v2/tokenizer_config.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v2/tokenizer.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hydrochoerus-12b-v1-s2-v2/flywheel_model.0.safetensors
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 32.90it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 48.37it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:10, 33.21it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.12it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.84it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.62it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:07, 43.25it/s]
Loading 0:  13%|█▎        | 47/363 [00:01<00:08, 37.20it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:08, 36.14it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:07, 42.90it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:07, 41.59it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:07, 41.81it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 45.67it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.79it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 38.55it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:07, 36.09it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:07, 35.55it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 37.24it/s]
Loading 0:  29%|██▉       | 107/363 [00:02<00:07, 36.14it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 37.53it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:05, 44.09it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.68it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.39it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.77it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 41.26it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:06, 33.39it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:06, 33.31it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 41.16it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:04, 41.46it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.80it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 32.59it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.00it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.32it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.51it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 42.65it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 41.04it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 36.37it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:04, 33.34it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 32.76it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 41.12it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:03, 42.42it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 37.60it/s]
Loading 0:  64%|██████▍   | 234/363 [00:06<00:03, 33.92it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 35.93it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:02, 43.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 43.17it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 43.90it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 41.89it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 36.61it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 35.80it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.62it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 42.98it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 43.80it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 37.85it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 33.90it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 36.03it/s]
Loading 0:  85%|████████▌ | 309/363 [00:07<00:01, 43.02it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 43.18it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 43.96it/s]
Loading 0:  89%|████████▉ | 324/363 [00:08<00:00, 45.47it/s]
Loading 0:  91%|█████████ | 329/363 [00:08<00:00, 42.38it/s]
Loading 0:  92%|█████████▏| 334/363 [00:08<00:00, 34.05it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 33.51it/s]
Loading 0:  95%|█████████▌| 345/363 [00:08<00:00, 41.08it/s]
Loading 0:  96%|█████████▋| 350/363 [00:08<00:00, 41.61it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 36.73it/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-v2-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: 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-v2-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s2-v2-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-v2-mkmlizer:   warnings.warn(
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:05<00:05,  5.38s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.17s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.35s/it]
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  2.40it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.99it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  3.63it/s]
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: Saving duration: 1.348s
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.649s
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/config.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/special_tokens_map.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/tokenizer_config.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/merges.txt
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/vocab.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/tokenizer.json
sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-hydrochoerus-12b-v1-s2-v2_reward/reward.tensors
Job sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer completed after 126.75s with status: succeeded
Stopping job with name sao10k-hydrochoerus-12b-v1-s2-v2-mkmlizer
Pipeline stage MKMLizer completed in 127.77s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-hydrochoerus-12b-v1-s2-v2
Waiting for inference service sao10k-hydrochoerus-12b-v1-s2-v2 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
Inference service sao10k-hydrochoerus-12b-v1-s2-v2 ready after 121.50404906272888s
Pipeline stage ISVCDeployer completed in 123.49s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.263371229171753s
Received healthy response to inference request in 1.7406806945800781s
Received healthy response to inference request in 1.716240644454956s
Received healthy response to inference request in 1.72615385055542s
Received healthy response to inference request in 1.4670512676239014s
5 requests
0 failed requests
5th percentile: 1.5168891429901123
10th percentile: 1.5667270183563233
20th percentile: 1.666402769088745
30th percentile: 1.7182232856750488
40th percentile: 1.7221885681152345
50th percentile: 1.72615385055542
60th percentile: 1.7319645881652832
70th percentile: 1.7377753257751465
80th percentile: 1.8452188014984132
90th percentile: 2.054295015335083
95th percentile: 2.158833122253418
99th percentile: 2.242463607788086
mean time: 1.7826995372772216
Pipeline stage StressChecker completed in 9.70s
sao10k-hydrochoerus-12b-v1-s2_v2 status is now deployed due to DeploymentManager action
sao10k-hydrochoerus-12b-v1-s2_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-hydrochoerus-12b-v1-s2_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-hydrochoerus-12b-v1-s2-v2 is running
Tearing down inference service sao10k-hydrochoerus-12b-v1-s2-v2
Service sao10k-hydrochoerus-12b-v1-s2-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.50s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-hydrochoerus-12b-v1-s2-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.50s
sao10k-hydrochoerus-12b-v1-s2_v2 status is now torndown due to DeploymentManager action