cycy233-l3-e-v2-c1

submission_id: cycy233-l3-e-v2-c1_v24

developer_uid: shiroe40

best_of: 4

celo_rating: 1235.24

display_name: auto

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': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}

is_internal_developer: False

language_model: cycy233/L3-e-v2-c1

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-e-v2-c1

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-e-v2-c1

model_size: 8B

num_battles: 10317

num_wins: 5425

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: 2024-07-29T02:22:01+00:00

us_pacific_date: 2024-07-28

win_ratio: 0.5258311524668023

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-l3-e-v2-c1-v24-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v24-mkmlizer to finish
cycy233-l3-e-v2-c1-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v24-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v24-mkmlizer: Downloaded to shared memory in 22.586s
cycy233-l3-e-v2-c1-v24-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp0f0_m1z, device:0
cycy233-l3-e-v2-c1-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v24-mkmlizer: quantized model in 26.761s
cycy233-l3-e-v2-c1-v24-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 49.347s
cycy233-l3-e-v2-c1-v24-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v24
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v24/config.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v24/special_tokens_map.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v24/tokenizer_config.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v24/tokenizer.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v24/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v24-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c1-v24-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.52it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 58.05it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:04, 54.58it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:04, 53.98it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 46.47it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 49.08it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 56.39it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 51.36it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:04, 51.14it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 53.09it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.56it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 46.09it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.24it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:06, 32.48it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 39.68it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 40.71it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 42.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.79it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 45.39it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 45.08it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.44it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 45.19it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:04, 30.32it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:04, 35.70it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:03, 37.97it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:03, 40.42it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:03, 41.08it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 41.94it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 48.70it/s]
Loading 0:  62%|██████▏   | 181/291 [00:04<00:02, 43.01it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 33.77it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.46it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 34.22it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 40.10it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 41.77it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 42.26it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 40.44it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 40.32it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 44.04it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 43.83it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 44.28it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 40.92it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:01, 40.42it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 44.69it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 42.79it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 42.60it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 47.41it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 43.70it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 42.57it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  3.16it/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.
cycy233-l3-e-v2-c1-v24-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v24-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.
cycy233-l3-e-v2-c1-v24-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v24-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.
cycy233-l3-e-v2-c1-v24-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v24-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v24-mkmlizer: Saving duration: 1.394s
cycy233-l3-e-v2-c1-v24-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.868s
cycy233-l3-e-v2-c1-v24-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v24-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v24-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/config.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/merges.txt
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/vocab.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/tokenizer.json
cycy233-l3-e-v2-c1-v24-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v24_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v24-mkmlizer completed after 95.63s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v24-mkmlizer
Pipeline stage MKMLizer completed in 96.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v24
Waiting for inference service cycy233-l3-e-v2-c1-v24 to be ready
Inference service cycy233-l3-e-v2-c1-v24 ready after 101.07860040664673s
Pipeline stage ISVCDeployer completed in 102.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0972039699554443s
Received healthy response to inference request in 1.1468167304992676s
Received healthy response to inference request in 1.1282620429992676s
Received healthy response to inference request in 1.146989345550537s
Received healthy response to inference request in 1.1266355514526367s
5 requests
0 failed requests
5th percentile: 1.126960849761963
10th percentile: 1.127286148071289
20th percentile: 1.1279367446899413
30th percentile: 1.1319729804992675
40th percentile: 1.1393948554992677
50th percentile: 1.1468167304992676
60th percentile: 1.1468857765197753
70th percentile: 1.1469548225402832
80th percentile: 1.3370322704315187
90th percentile: 1.7171181201934815
95th percentile: 1.9071610450744627
99th percentile: 2.059195384979248
mean time: 1.3291815280914308
Pipeline stage StressChecker completed in 7.33s
cycy233-l3-e-v2-c1_v24 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v24 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v24
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v24 is running
Tearing down inference service cycy233-l3-e-v2-c1-v24
Service cycy233-l3-e-v2-c1-v24 has been torndown
Pipeline stage ISVCDeleter completed in 4.52s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v24/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v24/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v24/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v24/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v24/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v24_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v24_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v24_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v24_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v24_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v24_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v24_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.74s
cycy233-l3-e-v2-c1_v24 status is now torndown due to DeploymentManager action