chaiml-sao10k-l3-rp-v3-3

developer_uid: robert_irvine

submission_id: chaiml-sao10k-l3-rp-v3-3_v88

model_name: chaiml-sao10k-l3-rp-v3-3_v88

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

status: torndown

timestamp: 2024-08-06T23:02:54+00:00

num_battles: 12963

num_wins: 6280

celo_rating: 1209.84

family_friendly_score: 0.0

submission_type: basic

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

model_architecture: LlamaForCausalLM

reward_repo: rirv938/reward_gpt2_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_v88

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: 0.4844557586978323

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-v88-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║     _____            __           __                                ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║       /___/                                                         ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  Version: 0.9.9                                                     ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  belonging to:                                                      ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ║                                                                     ║
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Downloaded to shared memory in 24.179s
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ttho1sj, device:0
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: quantized model in 25.458s
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Processed model ChaiML/sao10k-l3-rp-v3-3 in 49.637s
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v88
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v88/config.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v88/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v88/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v88/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v88/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: loading reward model from rirv938/reward_gpt2_preference_24m_e2
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:24,  2.37s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:02,  1.57it/s]
Loading 0:   5%|▍         | 14/291 [00:04<00:59,  4.66it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:36,  7.51it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:25, 10.45it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:16, 15.82it/s]
Loading 0:  14%|█▍        | 42/291 [00:05<00:11, 22.05it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 28.92it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 31.78it/s]
Loading 0:  21%|██▏       | 62/291 [00:06<00:08, 27.75it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:07, 31.07it/s]
Loading 0:  26%|██▋       | 77/291 [00:06<00:05, 38.55it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:05, 39.78it/s]
Loading 0:  30%|███       | 88/291 [00:06<00:04, 41.55it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 47.52it/s]
Loading 0:  35%|███▍      | 101/291 [00:06<00:04, 45.56it/s]
Loading 0:  37%|███▋      | 107/291 [00:06<00:03, 47.71it/s]
Loading 0:  39%|███▉      | 114/291 [00:07<00:03, 45.01it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 52.18it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 49.84it/s]
Loading 0:  46%|████▌     | 134/291 [00:07<00:03, 51.39it/s]
Loading 0:  48%|████▊     | 141/291 [00:07<00:03, 47.71it/s]
Loading 0:  52%|█████▏    | 150/291 [00:07<00:02, 49.56it/s]
Loading 0:  55%|█████▍    | 159/291 [00:08<00:02, 50.81it/s]
Loading 0:  57%|█████▋    | 166/291 [00:08<00:02, 42.24it/s]
Loading 0:  59%|█████▉    | 171/291 [00:08<00:02, 43.41it/s]
Loading 0:  61%|██████    | 177/291 [00:08<00:02, 41.76it/s]
Loading 0:  64%|██████▎   | 185/291 [00:08<00:02, 48.31it/s]
Loading 0:  66%|██████▌   | 191/291 [00:08<00:02, 47.66it/s]
Loading 0:  67%|██████▋   | 196/291 [00:08<00:02, 47.38it/s]
Loading 0:  70%|███████   | 204/291 [00:09<00:01, 47.50it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 54.77it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 52.05it/s]
Loading 0:  77%|███████▋  | 224/291 [00:09<00:01, 52.57it/s]
Loading 0:  79%|███████▉  | 231/291 [00:09<00:01, 48.55it/s]
Loading 0:  82%|████████▏ | 240/291 [00:09<00:01, 50.12it/s]
Loading 0:  86%|████████▌ | 249/291 [00:09<00:00, 50.88it/s]
Loading 0:  89%|████████▊ | 258/291 [00:10<00:00, 51.22it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 42.34it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 42.39it/s]
Loading 0:  95%|█████████▌| 277/291 [00:10<00:00, 43.41it/s]
Loading 0:  98%|█████████▊| 284/291 [00:10<00:00, 48.87it/s]
Loading 0: 100%|█████████▉| 290/291 [00:10<00:00, 46.77it/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-v88-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v88-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-v88-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v88-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-v88-mkmlizer:   warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Saving duration: 0.115s
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: Processed model rirv938/reward_gpt2_preference_24m_e2 in 5.778s
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v88_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v88_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v88_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v88_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v88_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v88_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer completed after 84.93s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v88-mkmlizer
Pipeline stage MKMLizer completed in 86.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v88
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v88 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v88 ready after 171.07814764976501s
Pipeline stage ISVCDeployer completed in 173.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2204172611236572s
Received healthy response to inference request in 1.1706504821777344s
Received healthy response to inference request in 1.1823415756225586s
Received healthy response to inference request in 1.1909935474395752s
Received healthy response to inference request in 1.1791846752166748s
5 requests
0 failed requests
5th percentile: 1.1723573207855225
10th percentile: 1.1740641593933105
20th percentile: 1.1774778366088867
30th percentile: 1.1798160552978516
40th percentile: 1.181078815460205
50th percentile: 1.1823415756225586
60th percentile: 1.1858023643493651
70th percentile: 1.189263153076172
80th percentile: 1.3968782901763919
90th percentile: 1.8086477756500245
95th percentile: 2.0145325183868406
99th percentile: 2.179240312576294
mean time: 1.3887175083160401
Pipeline stage StressChecker completed in 7.62s
chaiml-sao10k-l3-rp-v3-3_v88 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v88 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v88
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v88 is running
Tearing down inference service chaiml-sao10k-l3-rp-v3-3-v88
Service chaiml-sao10k-l3-rp-v3-3-v88 has been torndown
Pipeline stage ISVCDeleter completed in 4.70s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v88/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v88_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.32s
chaiml-sao10k-l3-rp-v3-3_v88 status is now torndown due to DeploymentManager action