cycy233-l3-e-v2-c1

developer_uid: shiroe40

submission_id: cycy233-l3-e-v2-c1_v31

model_name: auto

model_group: cycy233/L3-e-v2-c1

status: torndown

timestamp: 2024-08-08T02:08:46+00:00

num_battles: 11645

num_wins: 5510

celo_rating: 1193.8

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v2-c1

model_architecture: LlamaForCausalLM

reward_repo: cycy233/results

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: auto

is_internal_developer: False

language_model: cycy233/L3-e-v2-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-07

win_ratio: 0.47316444826105625

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 512}

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-c1-v31-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v31-mkmlizer to finish
cycy233-l3-e-v2-c1-v31-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v31-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  Version: 0.9.9                                                     ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v31-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v31-mkmlizer: Downloaded to shared memory in 23.400s
cycy233-l3-e-v2-c1-v31-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl8hvw40y, device:0
cycy233-l3-e-v2-c1-v31-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v31-mkmlizer: quantized model in 26.644s
cycy233-l3-e-v2-c1-v31-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 50.045s
cycy233-l3-e-v2-c1-v31-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v31-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v31-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v31
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v31/config.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v31/special_tokens_map.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v31/tokenizer_config.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v31/tokenizer.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v31/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v31-mkmlizer: loading reward model from cycy233/results
cycy233-l3-e-v2-c1-v31-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.18it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 53.59it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 44.97it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 43.72it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:05, 48.21it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:05, 46.79it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:05, 45.68it/s]
Loading 0:  15%|█▌        | 45/291 [00:00<00:05, 46.71it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:06, 37.42it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:05, 45.21it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:05, 44.44it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:05, 44.38it/s]
Loading 0:  25%|██▍       | 72/291 [00:01<00:04, 45.15it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:05, 36.80it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:07, 29.11it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 29.66it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 35.13it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:05, 34.21it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:05, 37.37it/s]
Loading 0:  37%|███▋      | 107/291 [00:02<00:04, 38.55it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.40it/s]
Loading 0:  40%|████      | 117/291 [00:02<00:04, 40.78it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 33.82it/s]
Loading 0:  44%|████▍     | 129/291 [00:03<00:04, 40.16it/s]
Loading 0:  46%|████▌     | 134/291 [00:03<00:03, 40.27it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 41.27it/s]
Loading 0:  49%|████▉     | 144/291 [00:03<00:03, 43.06it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 36.08it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:03, 43.34it/s]
Loading 0:  55%|█████▌    | 161/291 [00:04<00:03, 42.75it/s]
Loading 0:  57%|█████▋    | 166/291 [00:04<00:02, 42.24it/s]
Loading 0:  59%|█████▉    | 171/291 [00:04<00:02, 43.50it/s]
Loading 0:  60%|██████    | 176/291 [00:04<00:02, 43.44it/s]
Loading 0:  62%|██████▏   | 181/291 [00:04<00:03, 35.17it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 28.89it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 30.77it/s]
Loading 0:  67%|██████▋   | 195/291 [00:05<00:03, 31.44it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 37.44it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 39.57it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:01, 41.42it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 43.63it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:01, 36.61it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 44.07it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 44.78it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 44.29it/s]
Loading 0:  84%|████████▎ | 243/291 [00:06<00:01, 42.75it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 37.40it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 45.53it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 42.37it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 42.30it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 47.18it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 43.91it/s]
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 43.59it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  3.21it/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-v31-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v31-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-v31-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v31-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-v31-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v31-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v31-mkmlizer: Saving duration: 0.139s
cycy233-l3-e-v2-c1-v31-mkmlizer: Processed model cycy233/results in 6.020s
cycy233-l3-e-v2-c1-v31-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/config.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/merges.txt
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/vocab.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/tokenizer.json
cycy233-l3-e-v2-c1-v31-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v31_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v31-mkmlizer completed after 83.73s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v31-mkmlizer
Pipeline stage MKMLizer completed in 84.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v31
Waiting for inference service cycy233-l3-e-v2-c1-v31 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-e-v2-c1-v31 ready after 191.2283582687378s
Pipeline stage ISVCDeployer completed in 192.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.104867935180664s
Received healthy response to inference request in 1.1633100509643555s
Received healthy response to inference request in 1.188014268875122s
Received healthy response to inference request in 1.1448924541473389s
Received healthy response to inference request in 1.1763904094696045s
5 requests
0 failed requests
5th percentile: 1.1485759735107421
10th percentile: 1.1522594928741454
20th percentile: 1.1596265316009522
30th percentile: 1.1659261226654052
40th percentile: 1.1711582660675048
50th percentile: 1.1763904094696045
60th percentile: 1.1810399532318114
70th percentile: 1.1856894969940186
80th percentile: 1.3713850021362306
90th percentile: 1.7381264686584474
95th percentile: 1.9214972019195555
99th percentile: 2.0681937885284425
mean time: 1.355495023727417
Pipeline stage StressChecker completed in 7.77s
cycy233-l3-e-v2-c1_v31 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v31 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v31
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v31 is running
Tearing down inference service cycy233-l3-e-v2-c1-v31
Service cycy233-l3-e-v2-c1-v31 has been torndown
Pipeline stage ISVCDeleter completed in 4.91s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v31/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v31/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v31/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v31/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v31/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v31_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v31_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v31_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v31_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v31_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v31_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v31_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.81s
cycy233-l3-e-v2-c1_v31 status is now torndown due to DeploymentManager action