cycy233-l3-e-v2-c1

submission_id: cycy233-l3-e-v2-c1_v26

developer_uid: shiroe40

best_of: 16

celo_rating: 1241.45

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': 16, '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: 9897

num_wins: 5292

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: rirv938/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-29T02:25:52+00:00

us_pacific_date: 2024-07-28

win_ratio: 0.5347074871173083

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-l3-e-v2-c1-v26-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v26-mkmlizer to finish
cycy233-l3-e-v2-c1-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v26-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v26-mkmlizer: Downloaded to shared memory in 21.773s
cycy233-l3-e-v2-c1-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5_bpy63m, device:0
cycy233-l3-e-v2-c1-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v26-mkmlizer: quantized model in 28.145s
cycy233-l3-e-v2-c1-v26-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 49.918s
cycy233-l3-e-v2-c1-v26-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v26
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v26/config.json
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v26/special_tokens_map.json
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v26/tokenizer_config.json
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v26/tokenizer.json
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v26/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v26-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cycy233-l3-e-v2-c1-v26-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.59it/s]
Loading 0:   4%|▍         | 11/291 [00:00<00:06, 45.03it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:06, 40.84it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:06, 41.34it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:06, 43.30it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 44.56it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:06, 42.02it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 42.33it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 48.59it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 46.50it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:04, 46.54it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 52.25it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.98it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 46.44it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:06, 30.90it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 30.15it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 35.71it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 34.87it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:05, 35.99it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 35.47it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:04, 37.84it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 36.30it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 37.88it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:04, 36.27it/s]
Loading 0:  44%|████▍     | 129/291 [00:03<00:04, 38.52it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 37.03it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 39.15it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:04, 36.69it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 38.61it/s]
Loading 0:  52%|█████▏    | 151/291 [00:03<00:03, 37.01it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:03, 39.15it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 37.44it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 39.41it/s]
Loading 0:  58%|█████▊    | 169/291 [00:04<00:03, 35.38it/s]
Loading 0:  59%|█████▉    | 173/291 [00:04<00:03, 34.82it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 39.41it/s]
Loading 0:  63%|██████▎   | 183/291 [00:04<00:02, 38.31it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 25.67it/s]
Loading 0:  66%|██████▌   | 191/291 [00:05<00:03, 28.26it/s]
Loading 0:  67%|██████▋   | 195/291 [00:05<00:03, 29.30it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 35.74it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 36.60it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:02, 39.98it/s]
Loading 0:  74%|███████▍  | 215/291 [00:05<00:01, 42.04it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 43.74it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 40.63it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 41.44it/s]
Loading 0:  81%|████████▏ | 237/291 [00:06<00:01, 45.47it/s]
Loading 0:  83%|████████▎ | 242/291 [00:06<00:01, 45.54it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:00, 44.81it/s]
Loading 0:  87%|████████▋ | 253/291 [00:06<00:00, 42.28it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 42.68it/s]
Loading 0:  91%|█████████ | 264/291 [00:06<00:00, 47.03it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 46.40it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 46.81it/s]
Loading 0:  96%|█████████▌| 279/291 [00:07<00:00, 47.17it/s]
Loading 0:  98%|█████████▊| 284/291 [00:07<00:00, 35.85it/s]
Loading 0:  99%|█████████▉| 289/291 [00:12<00:00,  2.87it/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-v26-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v26-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-v26-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v26-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-v26-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v26-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v26-mkmlizer: Saving duration: 0.331s
cycy233-l3-e-v2-c1-v26-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.169s
cycy233-l3-e-v2-c1-v26-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v26-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c1-v26-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v26_reward
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v26_reward/merges.txt
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v26_reward/vocab.json
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v26_reward/tokenizer.json
cycy233-l3-e-v2-c1-v26-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v26_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v26-mkmlizer completed after 94.92s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v26-mkmlizer
Pipeline stage MKMLizer completed in 95.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v26
Waiting for inference service cycy233-l3-e-v2-c1-v26 to be ready
Inference service cycy233-l3-e-v2-c1-v26 ready after 111.35122561454773s
Pipeline stage ISVCDeployer completed in 112.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3139536380767822s
Received healthy response to inference request in 1.2938110828399658s
Received healthy response to inference request in 1.2564198970794678s
Received healthy response to inference request in 1.235691785812378s
Received healthy response to inference request in 1.3052010536193848s
5 requests
0 failed requests
5th percentile: 1.239837408065796
10th percentile: 1.2439830303192139
20th percentile: 1.2522742748260498
30th percentile: 1.2638981342315674
40th percentile: 1.2788546085357666
50th percentile: 1.2938110828399658
60th percentile: 1.2983670711517334
70th percentile: 1.302923059463501
80th percentile: 1.5069515705108645
90th percentile: 1.9104526042938232
95th percentile: 2.1122031211853027
99th percentile: 2.2736035346984864
mean time: 1.4810154914855957
Pipeline stage StressChecker completed in 8.02s
cycy233-l3-e-v2-c1_v26 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v26 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v26
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v26 is running
Tearing down inference service cycy233-l3-e-v2-c1-v26
Service cycy233-l3-e-v2-c1-v26 has been torndown
Pipeline stage ISVCDeleter completed in 5.06s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v26/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v26/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v26/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v26/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v26/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v26_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v26_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v26_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v26_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v26_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v26_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v26_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.24s
cycy233-l3-e-v2-c1_v26 status is now torndown due to DeploymentManager action