sao10k-l3-8b-tamamo-v1

submission_id: sao10k-l3-8b-tamamo-v1_v2

developer_uid: sao10k

best_of: 16

celo_rating: 1255.84

display_name: tamamo2

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/L3-8B-Tamamo-v1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Sao10K/L3-8B-Tamamo-v1

model_name: tamamo2

model_num_parameters: 8030261248.0

model_repo: Sao10K/L3-8B-Tamamo-v1

model_size: 8B

num_battles: 12615

num_wins: 7165

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: 2024-07-27T00:25:33+00:00

us_pacific_date: 2024-07-26

win_ratio: 0.5679746333729687

Download Preference Data

Resubmit model

Running pipeline stage MKMLizer
Starting job with name sao10k-l3-8b-tamamo-v1-v2-mkmlizer
Waiting for job on sao10k-l3-8b-tamamo-v1-v2-mkmlizer to finish
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║       /___/                                                         ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ║                                                                     ║
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Downloaded to shared memory in 23.634s
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnhph7ymy, device:0
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: quantized model in 26.451s
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Processed model Sao10K/L3-8B-Tamamo-v1 in 50.086s
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v2
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v2/config.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v2/special_tokens_map.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v2/tokenizer_config.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v2/tokenizer.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-tamamo-v1-v2/flywheel_model.0.safetensors
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:39,  2.42s/it]
Loading 0:   2%|▏         | 6/291 [00:04<03:06,  1.53it/s]
Loading 0:   4%|▍         | 13/291 [00:05<01:06,  4.19it/s]
Loading 0:   6%|▌         | 18/291 [00:05<00:41,  6.58it/s]
Loading 0:   8%|▊         | 24/291 [00:05<00:27,  9.86it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:16, 15.96it/s]
Loading 0:  13%|█▎        | 38/291 [00:05<00:12, 20.02it/s]
Loading 0:  15%|█▌        | 44/291 [00:05<00:09, 24.87it/s]
Loading 0:  17%|█▋        | 50/291 [00:05<00:07, 30.33it/s]
Loading 0:  19%|█▉        | 56/291 [00:05<00:07, 33.37it/s]
Loading 0:  21%|██▏       | 62/291 [00:06<00:08, 27.09it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:06, 32.36it/s]
Loading 0:  25%|██▌       | 74/291 [00:06<00:06, 34.28it/s]
Loading 0:  27%|██▋       | 79/291 [00:06<00:05, 36.57it/s]
Loading 0:  30%|██▉       | 86/291 [00:06<00:04, 42.90it/s]
Loading 0:  32%|███▏      | 92/291 [00:06<00:04, 42.96it/s]
Loading 0:  33%|███▎      | 97/291 [00:06<00:04, 43.92it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:03, 49.33it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:03, 47.15it/s]
Loading 0:  40%|███▉      | 115/291 [00:07<00:03, 45.69it/s]
Loading 0:  42%|████▏     | 122/291 [00:07<00:03, 50.74it/s]
Loading 0:  44%|████▍     | 128/291 [00:07<00:03, 46.99it/s]
Loading 0:  46%|████▌     | 133/291 [00:07<00:03, 46.47it/s]
Loading 0:  48%|████▊     | 140/291 [00:07<00:02, 51.81it/s]
Loading 0:  50%|█████     | 146/291 [00:07<00:02, 48.61it/s]
Loading 0:  52%|█████▏    | 152/291 [00:08<00:02, 49.60it/s]
Loading 0:  54%|█████▍    | 158/291 [00:08<00:02, 52.11it/s]
Loading 0:  56%|█████▋    | 164/291 [00:08<00:02, 48.56it/s]
Loading 0:  58%|█████▊    | 169/291 [00:08<00:03, 32.30it/s]
Loading 0:  60%|██████    | 176/291 [00:08<00:02, 38.86it/s]
Loading 0:  63%|██████▎   | 182/291 [00:08<00:02, 39.00it/s]
Loading 0:  64%|██████▍   | 187/291 [00:09<00:02, 40.09it/s]
Loading 0:  67%|██████▋   | 194/291 [00:09<00:02, 46.43it/s]
Loading 0:  69%|██████▊   | 200/291 [00:09<00:02, 45.32it/s]
Loading 0:  70%|███████   | 205/291 [00:09<00:01, 44.18it/s]
Loading 0:  73%|███████▎  | 212/291 [00:09<00:01, 48.65it/s]
Loading 0:  75%|███████▍  | 218/291 [00:09<00:01, 45.42it/s]
Loading 0:  77%|███████▋  | 223/291 [00:09<00:01, 45.78it/s]
Loading 0:  79%|███████▉  | 230/291 [00:09<00:01, 51.29it/s]
Loading 0:  81%|████████  | 236/291 [00:09<00:01, 48.28it/s]
Loading 0:  83%|████████▎ | 241/291 [00:10<00:01, 47.47it/s]
Loading 0:  85%|████████▌ | 248/291 [00:10<00:00, 51.55it/s]
Loading 0:  87%|████████▋ | 254/291 [00:10<00:00, 48.17it/s]
Loading 0:  89%|████████▉ | 259/291 [00:10<00:00, 47.79it/s]
Loading 0:  91%|█████████▏| 266/291 [00:10<00:00, 35.88it/s]
Loading 0:  93%|█████████▎| 272/291 [00:10<00:00, 37.26it/s]
Loading 0:  95%|█████████▌| 277/291 [00:11<00:00, 39.31it/s]
Loading 0:  98%|█████████▊| 284/291 [00:11<00:00, 45.21it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 44.42it/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-l3-8b-tamamo-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-8b-tamamo-v1-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-l3-8b-tamamo-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-8b-tamamo-v1-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-l3-8b-tamamo-v1-v2-mkmlizer:   warnings.warn(
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Saving duration: 1.417s
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.510s
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: creating bucket guanaco-reward-models
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/config.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/tokenizer_config.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/special_tokens_map.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/merges.txt
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/vocab.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/tokenizer.json
sao10k-l3-8b-tamamo-v1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/sao10k-l3-8b-tamamo-v1-v2_reward/reward.tensors
Job sao10k-l3-8b-tamamo-v1-v2-mkmlizer completed after 95.41s with status: succeeded
Stopping job with name sao10k-l3-8b-tamamo-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-l3-8b-tamamo-v1-v2
Waiting for inference service sao10k-l3-8b-tamamo-v1-v2 to be ready
Inference service sao10k-l3-8b-tamamo-v1-v2 ready after 80.55754280090332s
Pipeline stage ISVCDeployer completed in 82.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.190216541290283s
Received healthy response to inference request in 1.4709570407867432s
Received healthy response to inference request in 1.4153730869293213s
Received healthy response to inference request in 1.3851196765899658s
Received healthy response to inference request in 1.4770290851593018s
5 requests
0 failed requests
5th percentile: 1.391170358657837
10th percentile: 1.397221040725708
20th percentile: 1.40932240486145
30th percentile: 1.4264898777008057
40th percentile: 1.4487234592437743
50th percentile: 1.4709570407867432
60th percentile: 1.4733858585357666
70th percentile: 1.4758146762847901
80th percentile: 1.6196665763854983
90th percentile: 1.9049415588378906
95th percentile: 2.047579050064087
99th percentile: 2.161689043045044
mean time: 1.5877390861511231
Pipeline stage StressChecker completed in 8.64s
sao10k-l3-8b-tamamo-v1_v2 status is now deployed due to DeploymentManager action
sao10k-l3-8b-tamamo-v1_v2 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-8b-tamamo-v1_v2 status is now deployed due to admin request
sao10k-l3-8b-tamamo-v1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of sao10k-l3-8b-tamamo-v1_v2
Running pipeline stage ISVCDeleter
Checking if service sao10k-l3-8b-tamamo-v1-v2 is running
Tearing down inference service sao10k-l3-8b-tamamo-v1-v2
Service sao10k-l3-8b-tamamo-v1-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key sao10k-l3-8b-tamamo-v1-v2/config.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key sao10k-l3-8b-tamamo-v1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key sao10k-l3-8b-tamamo-v1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.65s
sao10k-l3-8b-tamamo-v1_v2 status is now torndown due to DeploymentManager action