cycy233-l3-e-v3-c6

submission_id: cycy233-l3-e-v3-c6_v1

developer_uid: shiroe40

best_of: 16

celo_rating: 1262.27

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': 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}

is_internal_developer: False

language_model: cycy233/L3-e-v3-c6

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-e-v3-c6

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-e-v3-c6

model_size: 8B

num_battles: 10491

num_wins: 5862

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: 2024-07-31T02:31:09+00:00

us_pacific_date: 2024-07-30

win_ratio: 0.5587646554189305

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cycy233-l3-e-v3-c6-v1-mkmlizer
Waiting for job on cycy233-l3-e-v3-c6-v1-mkmlizer to finish
cycy233-l3-e-v3-c6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v3-c6-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v3-c6-v1-mkmlizer: Downloaded to shared memory in 38.663s
cycy233-l3-e-v3-c6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp63erl0br, device:0
cycy233-l3-e-v3-c6-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v3-c6-v1-mkmlizer: quantized model in 27.102s
cycy233-l3-e-v3-c6-v1-mkmlizer: Processed model cycy233/L3-e-v3-c6 in 65.765s
cycy233-l3-e-v3-c6-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c6-v1/config.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c6-v1/special_tokens_map.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c6-v1/tokenizer_config.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c6-v1/tokenizer.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v3-c6-v1/flywheel_model.0.safetensors
cycy233-l3-e-v3-c6-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v3-c6-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.63it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 53.27it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 45.94it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 44.68it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 50.94it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.53it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.64it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 51.52it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 48.57it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:04, 46.80it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.65it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 45.49it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 45.05it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.37it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 32.74it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 39.52it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 38.48it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.15it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:04, 42.70it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:04, 42.56it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 42.93it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 41.47it/s]
Loading 0:  45%|████▌     | 132/291 [00:03<00:03, 40.83it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 45.15it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:03, 45.18it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 46.33it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 43.56it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 43.38it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 46.86it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 46.53it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 49.53it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 41.66it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 30.85it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 33.25it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 33.33it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 38.36it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 38.47it/s]
Loading 0:  73%|███████▎  | 213/291 [00:05<00:01, 39.10it/s]
Loading 0:  75%|███████▌  | 219/291 [00:05<00:01, 43.65it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 44.31it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 45.21it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 42.47it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 41.75it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 45.95it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 46.28it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 46.19it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 44.34it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 44.35it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 50.56it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 47.70it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 47.63it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  3.18it/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-c6-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c6-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-c6-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c6-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v3-c6-v1-mkmlizer: Saving duration: 1.540s
cycy233-l3-e-v3-c6-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.330s
cycy233-l3-e-v3-c6-v1-mkmlizer: creating bucket guanaco-reward-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/tokenizer_config.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/special_tokens_map.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/config.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/merges.txt
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/vocab.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/tokenizer.json
cycy233-l3-e-v3-c6-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v3-c6-v1_reward/reward.tensors
Job cycy233-l3-e-v3-c6-v1-mkmlizer completed after 115.51s with status: succeeded
Stopping job with name cycy233-l3-e-v3-c6-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v3-c6-v1
Waiting for inference service cycy233-l3-e-v3-c6-v1 to be ready
Inference service cycy233-l3-e-v3-c6-v1 ready after 121.34190821647644s
Pipeline stage ISVCDeployer completed in 122.72s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.393728256225586s
Received healthy response to inference request in 1.4782443046569824s
Received healthy response to inference request in 1.4485936164855957s
Received healthy response to inference request in 1.4128849506378174s
Received healthy response to inference request in 1.4794921875s
5 requests
0 failed requests
5th percentile: 1.420026683807373
10th percentile: 1.4271684169769288
20th percentile: 1.4414518833160401
30th percentile: 1.454523754119873
40th percentile: 1.4663840293884278
50th percentile: 1.4782443046569824
60th percentile: 1.4787434577941894
70th percentile: 1.4792426109313965
80th percentile: 1.6623394012451174
90th percentile: 2.0280338287353517
95th percentile: 2.2108810424804686
99th percentile: 2.3571588134765626
mean time: 1.6425886631011963
Pipeline stage StressChecker completed in 8.98s
cycy233-l3-e-v3-c6_v1 status is now deployed due to DeploymentManager action
cycy233-l3-e-v3-c6_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v3-c6_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v3-c6-v1 is running
Tearing down inference service cycy233-l3-e-v3-c6-v1
Service cycy233-l3-e-v3-c6-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.82s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v3-c6-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c6-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c6-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c6-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c6-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v3-c6-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c6-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c6-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c6-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c6-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c6-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c6-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
cycy233-l3-e-v3-c6_v1 status is now torndown due to DeploymentManager action