cycy233-l3-e-v3-c9

developer_uid: shiroe40

submission_id: cycy233-l3-e-v3-c9_v1

model_name: auto

model_group: cycy233/L3-e-v3-c9

status: torndown

timestamp: 2024-07-31T02:31:54+00:00

num_battles: 10461

num_wins: 5795

celo_rating: 1259.31

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v3-c9

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: cycy233/L3-e-v3-c9

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-30

win_ratio: 0.5539623362967212

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|>'], '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 cycy233-l3-e-v3-c9-v1-mkmlizer
Waiting for job on cycy233-l3-e-v3-c9-v1-mkmlizer to finish
cycy233-l3-e-v3-c9-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v3-c9-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c9-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v3-c9-v1-mkmlizer: Downloaded to shared memory in 37.126s
cycy233-l3-e-v3-c9-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj3xzytor, device:0
cycy233-l3-e-v3-c9-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v3-c9-v1-mkmlizer: quantized model in 27.530s
cycy233-l3-e-v3-c9-v1-mkmlizer: Processed model cycy233/L3-e-v3-c9 in 64.656s
cycy233-l3-e-v3-c9-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v3-c9-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v3-c9-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v3-c9-v1
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c9-v1/config.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c9-v1/special_tokens_map.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c9-v1/tokenizer_config.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c9-v1/tokenizer.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v3-c9-v1/flywheel_model.0.safetensors
cycy233-l3-e-v3-c9-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v3-c9-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 32.13it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 49.22it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:05, 50.71it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 41.50it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 47.51it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 43.34it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 43.35it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 49.27it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 43.47it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 42.49it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 45.96it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 45.21it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 45.08it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 46.35it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:08, 25.03it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:06, 32.13it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 34.50it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 36.71it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 39.48it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:05, 33.74it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:04, 42.27it/s]
Loading 0:  43%|████▎     | 126/291 [00:03<00:03, 43.77it/s]
Loading 0:  45%|████▌     | 131/291 [00:03<00:04, 37.82it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 44.10it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:03, 43.28it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 43.37it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:03, 44.74it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:03, 36.93it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:02, 43.71it/s]
Loading 0:  58%|█████▊    | 170/291 [00:04<00:02, 43.80it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 42.89it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 42.88it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 41.10it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 29.39it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 29.36it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 34.81it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:02, 35.68it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:02, 38.76it/s]
Loading 0:  74%|███████▍  | 215/291 [00:05<00:01, 40.73it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 42.42it/s]
Loading 0:  77%|███████▋  | 225/291 [00:05<00:01, 43.28it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 36.12it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 44.13it/s]
Loading 0:  83%|████████▎ | 242/291 [00:06<00:01, 44.25it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:01, 43.82it/s]
Loading 0:  87%|████████▋ | 253/291 [00:06<00:00, 40.63it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 40.63it/s]
Loading 0:  91%|█████████ | 264/291 [00:06<00:00, 43.51it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 43.69it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 43.82it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 40.16it/s]
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 39.10it/s]
Loading 0:  99%|█████████▉| 289/291 [00:12<00:00,  2.82it/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-v3-c9-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c9-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.
cycy233-l3-e-v3-c9-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c9-v1-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-v3-c9-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c9-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v3-c9-v1-mkmlizer: Saving duration: 1.383s
cycy233-l3-e-v3-c9-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.069s
cycy233-l3-e-v3-c9-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v3-c9-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v3-c9-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/config.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/special_tokens_map.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/tokenizer_config.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/merges.txt
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/vocab.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/tokenizer.json
cycy233-l3-e-v3-c9-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v3-c9-v1_reward/reward.tensors
Job cycy233-l3-e-v3-c9-v1-mkmlizer completed after 115.12s with status: succeeded
Stopping job with name cycy233-l3-e-v3-c9-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v3-c9-v1
Waiting for inference service cycy233-l3-e-v3-c9-v1 to be ready
Inference service cycy233-l3-e-v3-c9-v1 ready after 120.86056065559387s
Pipeline stage ISVCDeployer completed in 122.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.218733549118042s
Received healthy response to inference request in 1.4745328426361084s
Received healthy response to inference request in 1.388636827468872s
Received healthy response to inference request in 1.4228732585906982s
Received healthy response to inference request in 1.4773616790771484s
5 requests
0 failed requests
5th percentile: 1.3954841136932372
10th percentile: 1.4023313999176026
20th percentile: 1.416025972366333
30th percentile: 1.4332051753997803
40th percentile: 1.4538690090179442
50th percentile: 1.4745328426361084
60th percentile: 1.4756643772125244
70th percentile: 1.4767959117889404
80th percentile: 1.6256360530853273
90th percentile: 1.9221848011016847
95th percentile: 2.070459175109863
99th percentile: 2.189078674316406
mean time: 1.5964276313781738
Pipeline stage StressChecker completed in 8.74s
cycy233-l3-e-v3-c9_v1 status is now deployed due to DeploymentManager action
cycy233-l3-e-v3-c9_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v3-c9_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v3-c9-v1 is running
Tearing down inference service cycy233-l3-e-v3-c9-v1
Service cycy233-l3-e-v3-c9-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.72s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v3-c9-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c9-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c9-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c9-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c9-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v3-c9-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c9-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c9-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c9-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c9-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c9-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c9-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.33s
cycy233-l3-e-v3-c9_v1 status is now torndown due to DeploymentManager action