cycy233-l3-e-v3-c5

developer_uid: shiroe40

submission_id: cycy233-l3-e-v3-c5_v1

model_name: auto

model_group: cycy233/L3-e-v3-c5

status: torndown

timestamp: 2024-07-31T02:30:54+00:00

num_battles: 10057

num_wins: 5610

celo_rating: 1262.19

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v3-c5

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-c5

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-30

win_ratio: 0.5578204235855623

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-c5-v1-mkmlizer
Waiting for job on cycy233-l3-e-v3-c5-v1-mkmlizer to finish
cycy233-l3-e-v3-c5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v3-c5-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ║                                                                     ║
cycy233-l3-e-v3-c5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v3-c5-v1-mkmlizer: Downloaded to shared memory in 37.839s
cycy233-l3-e-v3-c5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp72old6yx, device:0
cycy233-l3-e-v3-c5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v3-c5-v1-mkmlizer: quantized model in 26.762s
cycy233-l3-e-v3-c5-v1-mkmlizer: Processed model cycy233/L3-e-v3-c5 in 64.601s
cycy233-l3-e-v3-c5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v3-c5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v3-c5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v3-c5-v1
cycy233-l3-e-v3-c5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c5-v1/config.json
cycy233-l3-e-v3-c5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c5-v1/special_tokens_map.json
cycy233-l3-e-v3-c5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c5-v1/tokenizer_config.json
cycy233-l3-e-v3-c5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v3-c5-v1/tokenizer.json
cycy233-l3-e-v3-c5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v3-c5-v1/flywheel_model.0.safetensors
cycy233-l3-e-v3-c5-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-e-v3-c5-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.00it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.44it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 47.85it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 49.00it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 51.01it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.89it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.08it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 51.37it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 47.25it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 45.24it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.20it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 45.96it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 44.62it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.23it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 32.43it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 39.16it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 38.61it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.37it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 44.72it/s]
Loading 0:  40%|████      | 117/291 [00:02<00:03, 45.59it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:04, 38.86it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 46.74it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 44.38it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 43.17it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 48.19it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 44.26it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 43.29it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 46.78it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 45.13it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 45.67it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 45.01it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 42.46it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 29.86it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 30.56it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 37.55it/s]
Loading 0:  71%|███████   | 207/291 [00:04<00:02, 40.06it/s]
Loading 0:  73%|███████▎  | 212/291 [00:05<00:02, 35.70it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 44.59it/s]
Loading 0:  78%|███████▊  | 226/291 [00:05<00:01, 42.04it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 41.60it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 46.33it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 46.83it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 39.33it/s]
Loading 0:  88%|████████▊ | 255/291 [00:05<00:00, 46.44it/s]
Loading 0:  90%|████████▉ | 261/291 [00:06<00:00, 47.20it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 40.43it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 45.42it/s]
Loading 0:  96%|█████████▌| 279/291 [00:06<00:00, 45.88it/s]
Loading 0:  98%|█████████▊| 284/291 [00:06<00:00, 40.05it/s]
Loading 0:  99%|█████████▉| 289/291 [00:12<00:00,  3.16it/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-c5-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c5-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-c5-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c5-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-c5-v1-mkmlizer:   warnings.warn(
cycy233-l3-e-v3-c5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v3-c5-v1-mkmlizer: Saving duration: 1.445s
cycy233-l3-e-v3-c5-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.315s
cycy233-l3-e-v3-c5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v3-c5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-e-v3-c5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-e-v3-c5-v1_reward
cycy233-l3-e-v3-c5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v3-c5-v1_reward/reward.tensors
Job cycy233-l3-e-v3-c5-v1-mkmlizer completed after 104.91s with status: succeeded
Stopping job with name cycy233-l3-e-v3-c5-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v3-c5-v1
Waiting for inference service cycy233-l3-e-v3-c5-v1 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
Inference service cycy233-l3-e-v3-c5-v1 ready after 120.97201561927795s
Pipeline stage ISVCDeployer completed in 122.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.38840389251709s
Received healthy response to inference request in 1.4643678665161133s
Received healthy response to inference request in 1.4481983184814453s
Received healthy response to inference request in 1.4290320873260498s
Received healthy response to inference request in 2.745722770690918s
5 requests
0 failed requests
5th percentile: 1.4328653335571289
10th percentile: 1.436698579788208
20th percentile: 1.4443650722503663
30th percentile: 1.451432228088379
40th percentile: 1.457900047302246
50th percentile: 1.4643678665161133
60th percentile: 1.8339822769165037
70th percentile: 2.203596687316894
80th percentile: 2.4598676681518556
90th percentile: 2.602795219421387
95th percentile: 2.674258995056152
99th percentile: 2.731430015563965
mean time: 1.8951449871063233
Pipeline stage StressChecker completed in 10.33s
cycy233-l3-e-v3-c5_v1 status is now deployed due to DeploymentManager action
cycy233-l3-e-v3-c5_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v3-c5_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v3-c5-v1 is running
Tearing down inference service cycy233-l3-e-v3-c5-v1
Service cycy233-l3-e-v3-c5-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v3-c5-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c5-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v3-c5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v3-c5-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c5-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c5-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c5-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c5-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c5-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v3-c5-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.48s
cycy233-l3-e-v3-c5_v1 status is now torndown due to DeploymentManager action