cycy233-l3-e-v2-c4

submission_id: cycy233-l3-e-v2-c4_v6

developer_uid: shiroe40

best_of: 4

celo_rating: 1225.53

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-c4

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-e-v2-c4

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-e-v2-c4

model_size: 8B

num_battles: 9951

num_wins: 5126

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: 2024-07-29T02:06:29+00:00

us_pacific_date: 2024-07-28

win_ratio: 0.5151241081298362

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-l3-e-v2-c4-v6-mkmlizer
Waiting for job on cycy233-l3-e-v2-c4-v6-mkmlizer to finish
cycy233-l3-e-v2-c4-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c4-v6-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c4-v6-mkmlizer: Downloaded to shared memory in 33.937s
cycy233-l3-e-v2-c4-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoli5zbhq, device:0
cycy233-l3-e-v2-c4-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c4-v6-mkmlizer: quantized model in 25.809s
cycy233-l3-e-v2-c4-v6-mkmlizer: Processed model cycy233/L3-e-v2-c4 in 59.746s
cycy233-l3-e-v2-c4-v6-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c4-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c4-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v6
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v6/config.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v6/special_tokens_map.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v6/tokenizer_config.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v6/tokenizer.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v6/flywheel_model.0.safetensors
cycy233-l3-e-v2-c4-v6-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cycy233-l3-e-v2-c4-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.96it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 57.72it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:05, 53.93it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:04, 54.23it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 47.31it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 50.02it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 51.34it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 52.16it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 58.40it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 55.46it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:03, 53.58it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:06, 33.72it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:04, 41.53it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 41.13it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 42.18it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.45it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 46.28it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.96it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.52it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 46.38it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:03, 46.09it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 50.90it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 47.20it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 46.52it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 51.57it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 47.42it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 50.80it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 51.63it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 35.69it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.56it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 41.66it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 41.04it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.93it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 46.65it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 45.04it/s]
Loading 0:  79%|███████▉  | 231/291 [00:04<00:01, 44.82it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 50.38it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 47.63it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 45.78it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.17it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 46.82it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 46.24it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 49.73it/s]
Loading 0:  96%|█████████▌| 279/291 [00:05<00:00, 51.11it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 45.16it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  3.36it/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-c4-v6-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v6-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-c4-v6-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v6-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-c4-v6-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c4-v6-mkmlizer: Saving duration: 0.353s
cycy233-l3-e-v2-c4-v6-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.822s
cycy233-l3-e-v2-c4-v6-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c4-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c4-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/config.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/special_tokens_map.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/tokenizer_config.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/merges.txt
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/vocab.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/tokenizer.json
cycy233-l3-e-v2-c4-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v6_reward/reward.tensors
Job cycy233-l3-e-v2-c4-v6-mkmlizer completed after 95.4s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c4-v6-mkmlizer
Pipeline stage MKMLizer completed in 96.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c4-v6
Waiting for inference service cycy233-l3-e-v2-c4-v6 to be ready
Inference service cycy233-l3-e-v2-c4-v6 ready after 100.94827938079834s
Pipeline stage ISVCDeployer completed in 102.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.869194507598877s
Received healthy response to inference request in 1.2524523735046387s
Received healthy response to inference request in 1.085690975189209s
Received healthy response to inference request in 1.1237096786499023s
Received healthy response to inference request in 1.0719528198242188s
5 requests
0 failed requests
5th percentile: 1.0747004508972169
10th percentile: 1.0774480819702148
20th percentile: 1.0829433441162108
30th percentile: 1.0932947158813477
40th percentile: 1.108502197265625
50th percentile: 1.1237096786499023
60th percentile: 1.175206756591797
70th percentile: 1.2267038345336914
80th percentile: 1.3758008003234865
90th percentile: 1.6224976539611817
95th percentile: 1.7458460807800291
99th percentile: 1.8445248222351074
mean time: 1.2806000709533691
Pipeline stage StressChecker completed in 7.12s
cycy233-l3-e-v2-c4_v6 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c4_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c4_v6
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c4-v6 is running
Tearing down inference service cycy233-l3-e-v2-c4-v6
Service cycy233-l3-e-v2-c4-v6 has been torndown
Pipeline stage ISVCDeleter completed in 4.17s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v6/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v6_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.75s
cycy233-l3-e-v2-c4_v6 status is now torndown due to DeploymentManager action