chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v89

model_name: chaiml-sao10k-l3-rp-v3-3_v89

model_group: ChaiML/sao10k-l3-rp-v3-3

status: torndown

timestamp: 2024-08-06T23:03:35+00:00

num_battles: 12871

num_wins: 6461

celo_rating: 1220.4

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/sao10k-l3-rp-v3-3

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

display_name: chaiml-sao10k-l3-rp-v3-3_v89

is_internal_developer: True

language_model: ChaiML/sao10k-l3-rp-v3-3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-06

win_ratio: 0.5019811980421102

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64, 'reward_max_token_input': 256}

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: {message}\n', 'memory_template': '', 'prompt_template': '', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  Version: 0.9.9                                                     ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Downloaded to shared memory in 22.765s
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa9svh81b, device:0
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: quantized model in 26.337s
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 49.102s
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v89
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v89/config.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v89/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v89/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v89/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v89/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:26,  2.37s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:02,  1.56it/s]
Loading 0:   4%|▍         | 13/291 [00:04<01:05,  4.27it/s]
Loading 0:   6%|▌         | 18/291 [00:05<00:40,  6.71it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:26,  9.96it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:16, 15.95it/s]
Loading 0:  13%|█▎        | 38/291 [00:05<00:12, 19.83it/s]
Loading 0:  15%|█▍        | 43/291 [00:05<00:10, 23.33it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 29.82it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 31.59it/s]
Loading 0:  21%|██        | 61/291 [00:06<00:08, 25.66it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:06, 32.13it/s]
Loading 0:  25%|██▌       | 73/291 [00:06<00:06, 35.41it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:06, 33.07it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 41.73it/s]
Loading 0:  32%|███▏      | 92/291 [00:06<00:05, 38.75it/s]
Loading 0:  33%|███▎      | 97/291 [00:07<00:05, 38.56it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:04, 44.17it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:04, 42.55it/s]
Loading 0:  40%|███▉      | 115/291 [00:07<00:04, 41.84it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 46.95it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 44.91it/s]
Loading 0:  46%|████▌     | 133/291 [00:07<00:03, 43.64it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:03, 48.13it/s]
Loading 0:  50%|████▉     | 145/291 [00:08<00:03, 48.35it/s]
Loading 0:  52%|█████▏    | 150/291 [00:08<00:03, 40.21it/s]
Loading 0:  54%|█████▍    | 157/291 [00:08<00:02, 46.04it/s]
Loading 0:  56%|█████▌    | 162/291 [00:08<00:02, 45.07it/s]
Loading 0:  57%|█████▋    | 167/291 [00:08<00:03, 31.83it/s]
Loading 0:  59%|█████▉    | 172/291 [00:08<00:03, 35.40it/s]
Loading 0:  61%|██████    | 177/291 [00:08<00:03, 33.11it/s]
Loading 0:  64%|██████▎   | 185/291 [00:09<00:02, 42.21it/s]
Loading 0:  66%|██████▌   | 191/291 [00:09<00:02, 41.30it/s]
Loading 0:  67%|██████▋   | 196/291 [00:09<00:02, 41.01it/s]
Loading 0:  70%|██████▉   | 203/291 [00:09<00:01, 46.32it/s]
Loading 0:  72%|███████▏  | 209/291 [00:09<00:01, 43.43it/s]
Loading 0:  74%|███████▎  | 214/291 [00:09<00:01, 42.55it/s]
Loading 0:  76%|███████▌  | 221/291 [00:09<00:01, 47.94it/s]
Loading 0:  78%|███████▊  | 227/291 [00:10<00:01, 45.63it/s]
Loading 0:  80%|███████▉  | 232/291 [00:10<00:01, 44.65it/s]
Loading 0:  82%|████████▏ | 239/291 [00:10<00:01, 50.37it/s]
Loading 0:  84%|████████▍ | 245/291 [00:10<00:00, 47.30it/s]
Loading 0:  86%|████████▌ | 250/291 [00:10<00:00, 45.80it/s]
Loading 0:  88%|████████▊ | 256/291 [00:10<00:00, 49.16it/s]
Loading 0:  90%|█████████ | 262/291 [00:10<00:00, 51.32it/s]
Loading 0:  92%|█████████▏| 268/291 [00:11<00:00, 32.70it/s]
Loading 0:  95%|█████████▍| 275/291 [00:11<00:00, 38.54it/s]
Loading 0:  97%|█████████▋| 281/291 [00:11<00:00, 39.36it/s]
Loading 0:  98%|█████████▊| 286/291 [00:11<00:00, 40.65it/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.
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v89-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.
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v89-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.
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Saving duration: 0.325s
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.544s
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v89_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer completed after 84.33s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v89-mkmlizer
Pipeline stage MKMLizer completed in 85.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v89
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v89 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v89 ready after 191.613440990448s
Pipeline stage ISVCDeployer completed in 193.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0511672496795654s
Received healthy response to inference request in 1.1615636348724365s
Received healthy response to inference request in 1.1994032859802246s
Received healthy response to inference request in 1.1945502758026123s
Received healthy response to inference request in 1.1744775772094727s
5 requests
0 failed requests
5th percentile: 1.1641464233398438
10th percentile: 1.166729211807251
20th percentile: 1.1718947887420654
30th percentile: 1.1784921169281006
40th percentile: 1.1865211963653564
50th percentile: 1.1945502758026123
60th percentile: 1.1964914798736572
70th percentile: 1.1984326839447021
80th percentile: 1.3697560787200929
90th percentile: 1.7104616641998291
95th percentile: 1.8808144569396972
99th percentile: 2.017096691131592
mean time: 1.3562324047088623
Pipeline stage StressChecker completed in 7.44s
chaiml-sao10k-l3-rp-v3-3_v89 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v89 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v89
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v89 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v89
Service chaiml-sao10k-l3-rp-v3-3-v89 has been torndown
Pipeline stage ISVCDeleter completed in 5.30s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v89/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v89_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.08s
chaiml-sao10k-l3-rp-v3-3_v89 status is now torndown due to DeploymentManager action