jellywibble-wibblewobble

developer_uid: Bbbrun0

submission_id: jellywibble-wibblewobble_v1

model_name: auto

model_group: Jellywibble/WibbleWobble

status: torndown

timestamp: 2024-08-05T03:38:01+00:00

num_battles: 13330

num_wins: 7592

celo_rating: 1255.92

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: auto

is_internal_developer: False

language_model: Jellywibble/WibbleWobble

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-04

win_ratio: 0.5695423855963991

generation_params: {'temperature': 1.0, 'top_p': 0.9, '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-v1-mkmlizer
Waiting for job on jellywibble-wibblewobble-v1-mkmlizer to finish
Stopping job with name jellywibble-wibblewobble-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jellywibble-wibblewobble-v1-mkmlizer
Waiting for job on jellywibble-wibblewobble-v1-mkmlizer to finish
Stopping job with name jellywibble-wibblewobble-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name jellywibble-wibblewobble-v1-mkmlizer
Waiting for job on jellywibble-wibblewobble-v1-mkmlizer to finish
jellywibble-wibblewobble-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-wibblewobble-v1-mkmlizer: ║     _____            __           __                                ║
jellywibble-wibblewobble-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-wibblewobble-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-wibblewobble-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-wibblewobble-v1-mkmlizer: ║       /___/                                                         ║
jellywibble-wibblewobble-v1-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
jellywibble-wibblewobble-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-wibblewobble-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-wibblewobble-v1-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-wibblewobble-v1-mkmlizer: ║  belonging to:                                                      ║
jellywibble-wibblewobble-v1-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-wibblewobble-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-wibblewobble-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-wibblewobble-v1-mkmlizer: ║                                                                     ║
jellywibble-wibblewobble-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-wibblewobble-v1-mkmlizer: Downloaded to shared memory in 44.400s
jellywibble-wibblewobble-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdg_89f1d, device:0
jellywibble-wibblewobble-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-wibblewobble-v1-mkmlizer: quantized model in 28.628s
jellywibble-wibblewobble-v1-mkmlizer: Processed model Jellywibble/WibbleWobble in 73.028s
jellywibble-wibblewobble-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-wibblewobble-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-wibblewobble-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-wibblewobble-v1
jellywibble-wibblewobble-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-wibblewobble-v1/special_tokens_map.json
jellywibble-wibblewobble-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-wibblewobble-v1/config.json
jellywibble-wibblewobble-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-wibblewobble-v1/tokenizer_config.json
jellywibble-wibblewobble-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-wibblewobble-v1/flywheel_model.0.safetensors
jellywibble-wibblewobble-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jellywibble-wibblewobble-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.99it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.62it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 34.01it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.32it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.53it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.87it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 23.23it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.96it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.65it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 31.52it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 33.71it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 32.98it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.57it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.37it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.45it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.42it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.42it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.21it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.69it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 29.21it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.69it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.22it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.36it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 34.17it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 34.35it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.77it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.70it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.42it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.79it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.30it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.40it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.74it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.06it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.93it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.74it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.14it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.12it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.95it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 40.86it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.28it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.11it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.72it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.40it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.63it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.72it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.25it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.87it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 34.90it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 34.69it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.60it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.39it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.14it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.67it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.73it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 34.40it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.04it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.53it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.65it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.83it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.33it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.23it/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-v1-mkmlizer:   warnings.warn(
jellywibble-wibblewobble-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.
jellywibble-wibblewobble-v1-mkmlizer:   warnings.warn(
jellywibble-wibblewobble-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-wibblewobble-v1-mkmlizer: Saving duration: 1.349s
jellywibble-wibblewobble-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 12.037s
jellywibble-wibblewobble-v1-mkmlizer: creating bucket guanaco-reward-models
jellywibble-wibblewobble-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-wibblewobble-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/config.json
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/special_tokens_map.json
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/tokenizer_config.json
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/merges.txt
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/vocab.json
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/tokenizer.json
jellywibble-wibblewobble-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-wibblewobble-v1_reward/reward.tensors
Job jellywibble-wibblewobble-v1-mkmlizer completed after 114.73s with status: succeeded
Stopping job with name jellywibble-wibblewobble-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-wibblewobble-v1
Waiting for inference service jellywibble-wibblewobble-v1 to be ready
Inference service jellywibble-wibblewobble-v1 ready after 181.12531423568726s
Pipeline stage ISVCDeployer completed in 182.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.236431121826172s
Received healthy response to inference request in 1.4696907997131348s
Received healthy response to inference request in 1.4308509826660156s
Received healthy response to inference request in 1.4109621047973633s
Received healthy response to inference request in 1.483405351638794s
5 requests
0 failed requests
5th percentile: 1.4149398803710938
10th percentile: 1.4189176559448242
20th percentile: 1.4268732070922852
30th percentile: 1.4386189460754395
40th percentile: 1.454154872894287
50th percentile: 1.4696907997131348
60th percentile: 1.4751766204833985
70th percentile: 1.4806624412536622
80th percentile: 1.6340105056762697
90th percentile: 1.9352208137512208
95th percentile: 2.085825967788696
99th percentile: 2.206310091018677
mean time: 1.6062680721282958
Pipeline stage StressChecker completed in 8.76s
jellywibble-wibblewobble_v1 status is now deployed due to DeploymentManager action
jellywibble-wibblewobble_v1 status is now inactive due to auto deactivation removed underperforming models
jellywibble-wibblewobble_v1 status is now deployed due to admin request
jellywibble-wibblewobble_v1 status is now inactive due to auto deactivation removed underperforming models
jellywibble-wibblewobble_v1 status is now torndown due to DeploymentManager action