jellywibble-wibblewobble

developer_uid: Bbbrun0

submission_id: jellywibble-wibblewobble_v4

model_name: test

model_group: Jellywibble/WibbleWobble

status: torndown

timestamp: 2024-08-14T03:40:19+00:00

num_battles: 10327

num_wins: 5731

celo_rating: 1253.98

family_friendly_score: 0.0

submission_type: basic

model_repo: Jellywibble/WibbleWobble

model_architecture: LlamaForCausalLM

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: test

is_internal_developer: False

language_model: Jellywibble/WibbleWobble

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-13

win_ratio: 0.5549530357315774

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': 512, 'best_of': 16, '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_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 jellywibble-wibblewobble-v4-mkmlizer
Waiting for job on jellywibble-wibblewobble-v4-mkmlizer to finish
jellywibble-wibblewobble-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-wibblewobble-v4-mkmlizer: ║     _____            __           __                                ║
jellywibble-wibblewobble-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-wibblewobble-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-wibblewobble-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-wibblewobble-v4-mkmlizer: ║       /___/                                                         ║
jellywibble-wibblewobble-v4-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v4-mkmlizer: ║  Version: 0.9.9                                                     ║
jellywibble-wibblewobble-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-wibblewobble-v4-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-wibblewobble-v4-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-wibblewobble-v4-mkmlizer: ║  belonging to:                                                      ║
jellywibble-wibblewobble-v4-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v4-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-wibblewobble-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-wibblewobble-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-wibblewobble-v4-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-wibblewobble-v4-mkmlizer: Downloaded to shared memory in 61.947s
jellywibble-wibblewobble-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1mtp53tc, device:0
jellywibble-wibblewobble-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-wibblewobble-v4-mkmlizer: quantized model in 29.664s
jellywibble-wibblewobble-v4-mkmlizer: Processed model Jellywibble/WibbleWobble in 91.611s
jellywibble-wibblewobble-v4-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-wibblewobble-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-wibblewobble-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-wibblewobble-v4
jellywibble-wibblewobble-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-wibblewobble-v4/config.json
jellywibble-wibblewobble-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-wibblewobble-v4/tokenizer_config.json
jellywibble-wibblewobble-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-wibblewobble-v4/special_tokens_map.json
jellywibble-wibblewobble-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-wibblewobble-v4/flywheel_model.0.safetensors
jellywibble-wibblewobble-v4-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jellywibble-wibblewobble-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.91it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 34.21it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 31.99it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 34.96it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 33.01it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 36.84it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:10, 24.42it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:10, 23.83it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 23.76it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.47it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.93it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 33.45it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.53it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.08it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.21it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.47it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.63it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 23.07it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.37it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.58it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.88it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.40it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.50it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.19it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.12it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.28it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 36.81it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 34.80it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.65it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.81it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.75it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 31.92it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.28it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 33.93it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 32.92it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.51it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.95it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.44it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.80it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 37.43it/s]
Loading 0:  64%|██████▍   | 187/291 [00:06<00:03, 26.07it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 27.24it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:03, 26.51it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.58it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.16it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.76it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.06it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 35.39it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 33.79it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 33.55it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.90it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.83it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.40it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 31.53it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 30.84it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.27it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 31.92it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.33it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.38it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 34.05it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 32.46it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 32.83it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:02,  2.49it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.09it/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.
jellywibble-wibblewobble-v4-mkmlizer:   warnings.warn(
jellywibble-wibblewobble-v4-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.
jellywibble-wibblewobble-v4-mkmlizer:   warnings.warn(
jellywibble-wibblewobble-v4-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.
jellywibble-wibblewobble-v4-mkmlizer:   warnings.warn(
jellywibble-wibblewobble-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-wibblewobble-v4-mkmlizer: Saving duration: 1.381s
jellywibble-wibblewobble-v4-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.127s
jellywibble-wibblewobble-v4-mkmlizer: creating bucket guanaco-reward-models
jellywibble-wibblewobble-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-wibblewobble-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward
jellywibble-wibblewobble-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward/special_tokens_map.json
jellywibble-wibblewobble-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward/config.json
jellywibble-wibblewobble-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward/tokenizer_config.json
jellywibble-wibblewobble-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward/merges.txt
jellywibble-wibblewobble-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward/vocab.json
jellywibble-wibblewobble-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-wibblewobble-v4_reward/tokenizer.json
Job jellywibble-wibblewobble-v4-mkmlizer completed after 135.13s with status: succeeded
Stopping job with name jellywibble-wibblewobble-v4-mkmlizer
Pipeline stage MKMLizer completed in 136.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-wibblewobble-v4
Waiting for inference service jellywibble-wibblewobble-v4 to be ready
Inference service jellywibble-wibblewobble-v4 ready after 301.09867691993713s
Pipeline stage ISVCDeployer completed in 303.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3886990547180176s
Received healthy response to inference request in 1.6258137226104736s
Received healthy response to inference request in 1.529062032699585s
Received healthy response to inference request in 1.504410743713379s
Received healthy response to inference request in 1.5726680755615234s
5 requests
0 failed requests
5th percentile: 1.5093410015106201
10th percentile: 1.5142712593078613
20th percentile: 1.5241317749023438
30th percentile: 1.5377832412719727
40th percentile: 1.555225658416748
50th percentile: 1.5726680755615234
60th percentile: 1.5939263343811034
70th percentile: 1.6151845932006836
80th percentile: 1.7783907890319826
90th percentile: 2.083544921875
95th percentile: 2.2361219882965084
99th percentile: 2.358183641433716
mean time: 1.7241307258605958
Pipeline stage StressChecker completed in 9.33s
jellywibble-wibblewobble_v4 status is now deployed due to DeploymentManager action
jellywibble-wibblewobble_v4 status is now inactive due to auto deactivation removed underperforming models
jellywibble-wibblewobble_v4 status is now torndown due to DeploymentManager action