cycy233-l3-e-v2-c4

developer_uid: shiroe40

submission_id: cycy233-l3-e-v2-c4_v8

model_name: auto

model_group: cycy233/L3-e-v2-c4

status: torndown

timestamp: 2024-07-29T02:24:40+00:00

num_battles: 12324

num_wins: 7144

celo_rating: 1273.78

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v2-c4

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-v2-c4

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-28

win_ratio: 0.5796819214540734

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}

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-v2-c4-v8-mkmlizer
Waiting for job on cycy233-l3-e-v2-c4-v8-mkmlizer to finish
cycy233-l3-e-v2-c4-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c4-v8-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c4-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c4-v8-mkmlizer: Downloaded to shared memory in 21.859s
cycy233-l3-e-v2-c4-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4amd68q_, device:0
cycy233-l3-e-v2-c4-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c4-v8-mkmlizer: quantized model in 26.956s
cycy233-l3-e-v2-c4-v8-mkmlizer: Processed model cycy233/L3-e-v2-c4 in 48.816s
cycy233-l3-e-v2-c4-v8-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c4-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c4-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v8
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v8/config.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v8/special_tokens_map.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v8/tokenizer_config.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v8/tokenizer.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c4-v8/flywheel_model.0.safetensors
cycy233-l3-e-v2-c4-v8-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v2-c4-v8-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 30.55it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 49.99it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 46.80it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 46.71it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 53.67it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 48.87it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 51.42it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 53.38it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 49.02it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:04, 50.43it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 45.55it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:04, 48.85it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 50.35it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 31.85it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 37.78it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 38.33it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:05, 35.54it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 41.77it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 42.46it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 43.14it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:03, 46.85it/s]
Loading 0:  46%|████▌     | 134/291 [00:03<00:03, 47.57it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:03, 43.92it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 52.47it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 48.73it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:02, 49.87it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 52.33it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 44.26it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 44.79it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 43.38it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 32.57it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.04it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 34.06it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 40.08it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 41.13it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 42.94it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 42.18it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 42.84it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 47.83it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 45.38it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 44.85it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 49.92it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 46.62it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 46.08it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 50.83it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 47.30it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 46.32it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 42.87it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.20it/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-v8-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v8-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-v8-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v8-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-v8-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c4-v8-mkmlizer: Saving duration: 1.644s
cycy233-l3-e-v2-c4-v8-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.530s
cycy233-l3-e-v2-c4-v8-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c4-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v2-c4-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/config.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/special_tokens_map.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/tokenizer_config.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/merges.txt
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/vocab.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/tokenizer.json
cycy233-l3-e-v2-c4-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c4-v8_reward/reward.tensors
Job cycy233-l3-e-v2-c4-v8-mkmlizer completed after 95.46s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c4-v8-mkmlizer
Pipeline stage MKMLizer completed in 96.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c4-v8
Waiting for inference service cycy233-l3-e-v2-c4-v8 to be ready
Inference service cycy233-l3-e-v2-c4-v8 ready after 100.67877101898193s
Pipeline stage ISVCDeployer completed in 102.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1978490352630615s
Received healthy response to inference request in 1.4722964763641357s
Received healthy response to inference request in 1.4585697650909424s
Received healthy response to inference request in 1.4275968074798584s
Received healthy response to inference request in 1.4970378875732422s
5 requests
0 failed requests
5th percentile: 1.4337913990020752
10th percentile: 1.439985990524292
20th percentile: 1.4523751735687256
30th percentile: 1.461315107345581
40th percentile: 1.4668057918548585
50th percentile: 1.4722964763641357
60th percentile: 1.4821930408477784
70th percentile: 1.492089605331421
80th percentile: 1.637200117111206
90th percentile: 1.9175245761871338
95th percentile: 2.0576868057250977
99th percentile: 2.169816589355469
mean time: 1.610669994354248
Pipeline stage StressChecker completed in 9.03s
cycy233-l3-e-v2-c4_v8 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c4_v8 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-e-v2-c4_v8 status is now deployed due to admin request
cycy233-l3-e-v2-c4_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c4_v8
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c4-v8 is running
Tearing down inference service cycy233-l3-e-v2-c4-v8
Service cycy233-l3-e-v2-c4-v8 has been torndown
Pipeline stage ISVCDeleter completed in 4.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v8/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c4-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c4-v8_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c4-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.63s
cycy233-l3-e-v2-c4_v8 status is now torndown due to DeploymentManager action