submission_id: sao10k-l3-tamama-3-1_v1
developer_uid: sao10k
best_of: 16
celo_rating: 1218.6
display_name: Tamama1
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}', 'You:', '\n\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Sao10K/L3-Tamama-3.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/L3-Tamama-3.1
model_name: Tamama1
model_num_parameters: 8030261248.0
model_repo: Sao10K/L3-Tamama-3.1
model_size: 8B
num_battles: 13158
num_wins: 6512
ranking_group: single
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'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-03T08:49:53+00:00
us_pacific_date: 2024-08-03
win_ratio: 0.4949080407356741
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-l3-tamama-3-1-v1-mkmlizer
Waiting for job on sao10k-l3-tamama-3-1-v1-mkmlizer to finish
sao10k-l3-tamama-3-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-tamama-3-1-v1-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║       /___/                                                         ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ║                                                                     ║
sao10k-l3-tamama-3-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-tamama-3-1-v1-mkmlizer: Downloaded to shared memory in 29.413s
sao10k-l3-tamama-3-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgazl4m32, device:0
sao10k-l3-tamama-3-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-tamama-3-1-v1-mkmlizer: quantized model in 26.459s
sao10k-l3-tamama-3-1-v1-mkmlizer: Processed model Sao10K/L3-Tamama-3.1 in 55.872s
sao10k-l3-tamama-3-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-tamama-3-1-v1/config.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-tamama-3-1-v1/special_tokens_map.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-tamama-3-1-v1/tokenizer_config.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-tamama-3-1-v1/tokenizer.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-tamama-3-1-v1/flywheel_model.0.safetensors
sao10k-l3-tamama-3-1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-tamama-3-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:49,  2.46s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:08,  1.51it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:07,  4.13it/s]
Loading 0:   7%|▋         | 19/291 [00:05<00:38,  7.02it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:27,  9.58it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:16, 15.54it/s]
Loading 0:  13%|█▎        | 38/291 [00:05<00:13, 19.35it/s]
Loading 0:  15%|█▍        | 43/291 [00:05<00:10, 22.92it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:08, 30.02it/s]
Loading 0:  19%|█▉        | 56/291 [00:06<00:07, 32.79it/s]
Loading 0:  21%|██        | 61/291 [00:06<00:06, 35.36it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:05, 41.05it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:05, 41.03it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:05, 42.35it/s]
Loading 0:  29%|██▉       | 84/291 [00:06<00:06, 32.61it/s]
Loading 0:  30%|███       | 88/291 [00:06<00:06, 33.29it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 40.94it/s]
Loading 0:  35%|███▍      | 101/291 [00:07<00:04, 39.66it/s]
Loading 0:  36%|███▋      | 106/291 [00:07<00:04, 39.66it/s]
Loading 0:  39%|███▉      | 113/291 [00:07<00:03, 45.67it/s]
Loading 0:  41%|████      | 119/291 [00:07<00:03, 44.13it/s]
Loading 0:  43%|████▎     | 124/291 [00:07<00:03, 44.13it/s]
Loading 0:  45%|████▌     | 131/291 [00:07<00:03, 50.02it/s]
Loading 0:  47%|████▋     | 137/291 [00:07<00:03, 45.75it/s]
Loading 0:  49%|████▉     | 142/291 [00:08<00:03, 45.43it/s]
Loading 0:  51%|█████     | 149/291 [00:08<00:02, 51.29it/s]
Loading 0:  53%|█████▎    | 155/291 [00:08<00:02, 48.25it/s]
Loading 0:  55%|█████▍    | 160/291 [00:08<00:02, 47.12it/s]
Loading 0:  57%|█████▋    | 167/291 [00:08<00:02, 51.44it/s]
Loading 0:  59%|█████▉    | 173/291 [00:08<00:02, 47.23it/s]
Loading 0:  61%|██████    | 178/291 [00:08<00:02, 46.45it/s]
Loading 0:  64%|██████▎   | 185/291 [00:08<00:02, 51.39it/s]
Loading 0:  66%|██████▌   | 191/291 [00:09<00:02, 46.32it/s]
Loading 0:  67%|██████▋   | 196/291 [00:09<00:02, 45.18it/s]
Loading 0:  70%|██████▉   | 203/291 [00:09<00:01, 49.11it/s]
Loading 0:  72%|███████▏  | 209/291 [00:09<00:02, 31.07it/s]
Loading 0:  74%|███████▎  | 214/291 [00:09<00:02, 33.67it/s]
Loading 0:  76%|███████▌  | 221/291 [00:09<00:01, 39.75it/s]
Loading 0:  78%|███████▊  | 227/291 [00:10<00:01, 39.28it/s]
Loading 0:  80%|███████▉  | 232/291 [00:10<00:01, 40.12it/s]
Loading 0:  82%|████████▏ | 239/291 [00:10<00:01, 45.53it/s]
Loading 0:  84%|████████▍ | 245/291 [00:10<00:01, 43.39it/s]
Loading 0:  86%|████████▌ | 250/291 [00:10<00:00, 43.69it/s]
Loading 0:  88%|████████▊ | 257/291 [00:10<00:00, 48.36it/s]
Loading 0:  90%|█████████ | 263/291 [00:10<00:00, 45.41it/s]
Loading 0:  92%|█████████▏| 268/291 [00:10<00:00, 44.80it/s]
Loading 0:  95%|█████████▍| 275/291 [00:11<00:00, 49.12it/s]
Loading 0:  97%|█████████▋| 281/291 [00:11<00:00, 44.52it/s]
Loading 0:  98%|█████████▊| 286/291 [00:11<00:00, 44.16it/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-l3-tamama-3-1-v1-mkmlizer:   warnings.warn(
sao10k-l3-tamama-3-1-v1-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-l3-tamama-3-1-v1-mkmlizer:   warnings.warn(
sao10k-l3-tamama-3-1-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-l3-tamama-3-1-v1-mkmlizer:   warnings.warn(
sao10k-l3-tamama-3-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-tamama-3-1-v1-mkmlizer: Saving duration: 1.341s
sao10k-l3-tamama-3-1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.757s
sao10k-l3-tamama-3-1-v1-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-tamama-3-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-tamama-3-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/config.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/special_tokens_map.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/tokenizer_config.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/merges.txt
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/vocab.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/tokenizer.json
sao10k-l3-tamama-3-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-tamama-3-1-v1_reward/reward.tensors
Job sao10k-l3-tamama-3-1-v1-mkmlizer completed after 95.33s with status: succeeded
Stopping job with name sao10k-l3-tamama-3-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-tamama-3-1-v1
Waiting for inference service sao10k-l3-tamama-3-1-v1 to be ready
Inference service sao10k-l3-tamama-3-1-v1 ready after 151.58036971092224s
Pipeline stage ISVCDeployer completed in 153.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2996256351470947s
Received healthy response to inference request in 1.4365508556365967s
Received healthy response to inference request in 1.449204683303833s
Received healthy response to inference request in 1.410487174987793s
Received healthy response to inference request in 1.679736614227295s
5 requests
0 failed requests
5th percentile: 1.4156999111175537
10th percentile: 1.4209126472473144
20th percentile: 1.431338119506836
30th percentile: 1.439081621170044
40th percentile: 1.4441431522369386
50th percentile: 1.449204683303833
60th percentile: 1.5414174556732179
70th percentile: 1.6336302280426025
80th percentile: 1.803714418411255
90th percentile: 2.051670026779175
95th percentile: 2.175647830963135
99th percentile: 2.274830074310303
mean time: 1.6551209926605224
Pipeline stage StressChecker completed in 8.99s
sao10k-l3-tamama-3-1_v1 status is now deployed due to DeploymentManager action
sao10k-l3-tamama-3-1_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-tamama-3-1_v1 status is now torndown due to DeploymentManager action